feat: bump version to 0.3.25 (#1300)

Co-authored-by: zxhlyh <jasonapring2015@outlook.com>

.devcontainer/Dockerfile

@@ -0,0 +1,8 @@
+FROM mcr.microsoft.com/devcontainers/python:3.10
+
+COPY . .
+
+
+# [Optional] Uncomment this section to install additional OS packages.
+# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+#     && apt-get -y install --no-install-recommends <your-package-list-here>

.devcontainer/README.md

@@ -0,0 +1,37 @@
+# Devlopment with devcontainer
+This project includes a devcontainer configuration that allows you to open the project in a container with a fully configured development environment.
+Both frontend and backend environments are initialized when the container is started.
+## GitHub Codespaces
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langgenius/dify)
+
+you can simply click the button above to open this project in GitHub Codespaces.
+
+For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
+
+
+## VS Code Dev Containers
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langgenius/dify)
+
+if you have VS Code installed, you can click the button above to open this project in VS Code Dev Containers.
+
+You can learn more in the [Dev Containers documentation](https://code.visualstudio.com/docs/devcontainers/containers).
+
+
+## Pros of Devcontainer
+Unified Development Environment: By using devcontainers, you can ensure that all developers are developing in the same environment, reducing the occurrence of "it works on my machine" type of issues.
+
+Quick Start: New developers can set up their development environment in a few simple steps, without spending a lot of time on environment configuration.
+
+Isolation: Devcontainers isolate your project from your host operating system, reducing the chance of OS updates or other application installations impacting the development environment.
+
+## Cons of Devcontainer
+Learning Curve: For developers unfamiliar with Docker and VS Code, using devcontainers may be somewhat complex.
+
+Performance Impact: While usually minimal, programs running inside a devcontainer may be slightly slower than those running directly on the host.
+
+## Troubleshooting
+if you see such error message when you open this project in codespaces:
+![Alt text](troubleshooting.png)
+
+a simple workaround is change `/signin` endpoint into another one, then login with github account and close the tab, then change it back to `/signin` endpoint. Then all things will be fine.
+The reason is `signin` endpoint is not allowed in codespaces, details can be found [here](https://github.com/orgs/community/discussions/5204)

.devcontainer/devcontainer.json

@@ -0,0 +1,52 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
+{
+	"name": "Python 3.10",
+	"build": { 
+		"context": "..",
+		"dockerfile": "Dockerfile"
+	},
+	"features": {
+		"ghcr.io/devcontainers/features/node:1": {
+			"nodeGypDependencies": true,
+			"version": "lts"
+		},
+		"ghcr.io/devcontainers-contrib/features/npm-package:1": {
+			"package": "typescript",
+			"version": "latest"
+		},
+		"ghcr.io/devcontainers/features/docker-in-docker:2": {
+			"moby": true,
+			"azureDnsAutoDetection": true,
+			"installDockerBuildx": true,
+			"version": "latest",
+			"dockerDashComposeVersion": "v2"
+		}
+	},
+	"customizations": {
+		"vscode": {
+			"extensions": [
+				"ms-python.pylint",
+				"GitHub.copilot",
+				"ms-python.python"
+			]
+		}
+	},
+	"postStartCommand": "cd api && pip install -r requirements.txt",
+	"postCreateCommand": "cd web && npm install"
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Use 'postCreateCommand' to run commands after the container is created.
+	// "postCreateCommand": "python --version",
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

.devcontainer/noop.txt

@@ -0,0 +1,3 @@
+This file copied into the container along with environment.yml* from the parent
+folder. This file is included to prevents the Dockerfile COPY instruction from 
+failing if no environment.yml is found.

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,49 @@
+name: "🕷️ Bug report"
+description: Report errors or unexpected behavior
+labels:
+- bug
+body:
+- type: markdown
+  attributes:
+    value: Please make sure to [search for existing issues](https://github.com/langgenius/dify/issues) before filing a new one!
+- type: input
+  attributes:
+    label: Dify version
+    placeholder: 0.3.21
+    description: See about section in Dify console
+  validations:
+    required: true
+
+- type: dropdown
+  attributes:
+    label: Cloud or Self Hosted
+    description: How / Where was Dify installed from?
+    multiple: true
+    options:
+      - Cloud
+      - Self Hosted
+      - Other (please specify in "Steps to Reproduce")
+  validations:
+    required: true
+
+- type: textarea
+  attributes:
+    label: Steps to reproduce
+    description: We highly suggest including screenshots and a bug report log.
+    placeholder: Having detailed steps helps us reproduce the bug. 
+  validations:
+    required: true
+
+- type: textarea
+  attributes:
+    label: ✔️ Expected Behavior
+    placeholder: What were you expecting?
+  validations:
+    required: false
+
+- type: textarea
+  attributes:
+    label: ❌ Actual Behavior
+    placeholder: What happened instead?
+  validations:
+    required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,8 @@
+blank_issues_enabled: false
+contact_links:
+  - name: "\U0001F4DA Dify user documentation"
+    url: https://docs.dify.ai/getting-started/readme
+    about: Documentation for users of Dify
+  - name: "\U0001F4DA Dify dev documentation"
+    url: https://docs.dify.ai/getting-started/install-self-hosted
+    about: Documentation for people interested in developing and contributing for Dify

.github/ISSUE_TEMPLATE/document_issue.yml

@@ -0,0 +1,11 @@
+name: "📚 Documentation Issue"
+description: Report issues in our documentation
+labels: 
+- ducumentation
+body:
+- type: textarea
+  attributes: 
+    label: Provide a description of requested docs changes
+    placeholder: Briefly describe which document needs to be corrected and why.
+  validations:
+    required: true

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,26 @@
+name: "⭐ Feature or enhancement request"
+description: Propose something new.
+labels:
+- enhancement
+body:
+- type: textarea
+  attributes: 
+    label: Description of the new feature / enhancement
+    placeholder: What is the expected behavior of the proposed feature?
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: Scenario when this would be used?
+    placeholder: What is the scenario this would be used? Why is this important to your workflow as a dify user?
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: Supporting information
+    placeholder: "Having additional evidence, data, tweets, blog posts, research, ... anything is extremely helpful. This information provides context to the scenario that may otherwise be lost."
+  validations:
+    required: false
+- type: markdown
+  attributes:
+    value: Please limit one request per issue.

.github/ISSUE_TEMPLATE/help_wanted.yml

@@ -0,0 +1,11 @@
+name: "🤝 Help Wanted"
+description: "Request help from the community"
+labels:
+- help-wanted
+body:
+- type: textarea
+  attributes:
+    label: Provide a description of the help you need
+    placeholder: Briefly describe what you need help with.
+  validations:
+    required: true

.github/ISSUE_TEMPLATE/translation_issue.yml

@@ -0,0 +1,46 @@
+name: "🌐 Localization/Translation issue"
+description: Report incorrect translations.
+labels:
+- translation
+body:
+- type: markdown
+  attributes:
+    value: Please make sure to [search for existing issues](https://github.com/langgenius/dify/issues) before filing a new one!
+- type: input
+  attributes:
+    label: Dify version
+    placeholder: 0.3.21
+    description: Hover over system tray icon or look at Settings
+  validations:
+    required: true
+- type: input
+  attributes:
+    label: Utility with translation issue
+    placeholder: Some area
+    description: Please input here the utility with the translation issue
+  validations:
+    required: true
+- type: input
+  attributes:
+    label: 🌐 Language affected
+    placeholder: "German"
+  validations:
+    required: true
+- type: textarea
+  attributes: 
+    label: ❌ Actual phrase(s)
+    placeholder: What is there? Please include a screenshot as that is extremely helpful.
+  validations:
+    required: true
+- type: textarea
+  attributes: 
+    label: ✔️ Expected phrase(s)
+    placeholder: What was expected?
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: ℹ Why is the current translation wrong
+    placeholder: Why do you feel this is incorrect?
+  validations:
+    required: true

.github/ISSUE_TEMPLATE/🐛-bug-report.md

@@ -1,32 +0,0 @@
----
-name: "\U0001F41B Bug report"
-about: Create a report to help us improve
-title: ''
-labels: bug
-assignees: ''
-
----
-
-<!--
-  Please provide a clear and concise description of what the bug is. Include
-  screenshots if needed. Please test using the latest version of the relevant
-  Dify packages to make sure your issue has not already been fixed.
--->
-
-Dify version: Cloud | Self Host
-
-## Steps To Reproduce
-<!--
-  Your bug will get fixed much faster if we can run your code and it doesn't
-  have dependencies other than Dify. Issues without reproduction steps or
-  code examples may be immediately closed as not actionable.
--->
-
-1.
-2.
-
-
-## The current behavior
-
-
-## The expected behavior

.github/ISSUE_TEMPLATE/🚀-feature-request.md

@@ -1,20 +0,0 @@
----
-name: "\U0001F680 Feature request"
-about: Suggest an idea for this project
-title: ''
-labels: enhancement
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/🤔-questions-and-help.md

@@ -1,10 +0,0 @@
----
-name: "\U0001F914 Questions and Help"
-about: Ask a usage or consultation question
-title: ''
-labels: ''
-assignees: ''
-
----
-
-

.github/workflows/api-unit-tests.yml

@@ -0,0 +1,38 @@
+name: Run Pytest
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - deploy/dev
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.10'
+
+    - name: Cache pip dependencies
+      uses: actions/cache@v2
+      with:
+        path: ~/.cache/pip
+        key: ${{ runner.os }}-pip-${{ hashFiles('api/requirements.txt') }}
+        restore-keys: ${{ runner.os }}-pip-
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pytest
+        pip install -r api/requirements.txt
+
+    - name: Run pytest
+      run: pytest api/tests/unit_tests

.github/workflows/build-api-image.yml

@@ -42,12 +42,14 @@ jobs:
       uses: docker/build-push-action@v4
       with:
         context: "{{defaultContext}}:api"
-        platforms: linux/amd64,linux/arm64
+        platforms: ${{ startsWith(github.ref, 'refs/tags/') && 'linux/amd64,linux/arm64' || 'linux/amd64' }}
         build-args: |
           COMMIT_SHA=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.revision'] }}
         push: true
         tags: ${{ steps.meta.outputs.tags }}
         labels: ${{ steps.meta.outputs.labels }}
+        cache-from: type=gha
+        cache-to: type=gha,mode=max
 
     - name: Deploy to server
       if: github.ref == 'refs/heads/deploy/dev'

.github/workflows/build-web-image.yml

@@ -42,12 +42,14 @@ jobs:
       uses: docker/build-push-action@v4
       with:
         context: "{{defaultContext}}:web"
-        platforms: linux/amd64,linux/arm64
+        platforms: ${{ startsWith(github.ref, 'refs/tags/') && 'linux/amd64,linux/arm64' || 'linux/amd64' }}
         build-args: |
           COMMIT_SHA=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.revision'] }}
         push: true
         tags: ${{ steps.meta.outputs.tags }}
         labels: ${{ steps.meta.outputs.labels }}
+        cache-from: type=gha
+        cache-to: type=gha,mode=max
 
     - name: Deploy to server
       if: github.ref == 'refs/heads/deploy/dev'

.github/workflows/check_no_chinese_comments.py

@@ -19,7 +19,9 @@ def check_file_for_chinese_comments(file_path):
 
 def main():
     has_chinese = False
-    excluded_files = ["model_template.py", 'stopwords.py', 'commands.py', 'indexing_runner.py']
+    excluded_files = ["model_template.py", 'stopwords.py', 'commands.py',
+                      'indexing_runner.py', 'web_reader_tool.py', 'spark_provider.py',
+                      'prompts.py']
 
     for root, _, files in os.walk("."):
         for file in files:

.github/workflows/stale.yml

@@ -0,0 +1,30 @@
+# This workflow warns and then closes issues and PRs that have had no activity for a specified amount of time.
+#
+# You can adjust the behavior by modifying this file.
+# For more information, see:
+# https://github.com/actions/stale
+name: Mark stale issues and pull requests
+
+on:
+  schedule:
+  - cron: '0 3 * * *'
+
+jobs:
+  stale:
+
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+
+    steps:
+    - uses: actions/stale@v5
+      with:
+        days-before-issue-stale: 30
+        days-before-issue-close: 3
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-issue-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
+        stale-pr-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
+        stale-issue-label: 'no-issue-activity'
+        stale-pr-label: 'no-pr-activity'
+        any-of-labels: 'duplicate,question,invalid,wontfix,no-issue-activity,no-pr-activity,enhancement'

.gitignore

@@ -109,6 +109,7 @@ venv/
 ENV/
 env.bak/
 venv.bak/
+.conda/
 
 # Spyder project settings
 .spyderproject
@@ -130,7 +131,7 @@ dmypy.json
 .idea/'
 
 .DS_Store
-.vscode
+web/.vscode/settings.json
 
 # Intellij IDEA Files
 .idea/
@@ -143,7 +144,11 @@ docker/volumes/app/storage/*
 docker/volumes/db/data/*
 docker/volumes/redis/data/*
 docker/volumes/weaviate/*
+docker/volumes/qdrant/*
 
 sdks/python-client/build
 sdks/python-client/dist
 sdks/python-client/dify_client.egg-info
+
+.vscode/*
+!.vscode/launch.json

.vscode/launch.json

@@ -0,0 +1,27 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Flask",
+            "type": "python",
+            "request": "launch",
+            "module": "flask",
+            "env": {
+                "FLASK_APP": "api/app.py",
+                "FLASK_DEBUG": "1",
+                "GEVENT_SUPPORT": "True"
+            },
+            "args": [
+                "run",
+                "--host=0.0.0.0",
+                "--port=5001",
+                "--debug"
+            ],
+            "jinja": true,
+            "justMyCode": true
+        }
+    ]
+}

CONTRIBUTING.md

@@ -53,4 +53,9 @@ Did you have an issue, like a merge conflict, or don't know how to open a pull r
 
 ## Community channels
 
-Stuck somewhere? Have any questions? Join the [Discord Community Server](https://discord.gg/AhzKf7dNgk). We are here to help!
+Stuck somewhere? Have any questions? Join the [Discord Community Server](https://discord.gg/j3XRWSPBf7). We are here to help!
+
+### i18n (Internationalization) Support
+
+We are looking for contributors to help with translations in other languages. If you are interested in helping, please join the [Discord Community Server](https://discord.gg/AhzKf7dNgk) and let us know.  
+Also check out the [Frontend i18n README]((web/i18n/README_EN.md)) for more information.

CONTRIBUTING_CN.md

@@ -16,15 +16,15 @@
 
 ## 本地开发
 
-要设置一个可工作的开发环境，只需 fork 项目的 git 存储库，并使用适当的软件包管理器安装后端和前端依赖项，然后创建并运行 docker-compose 堆栈。
+要设置一个可工作的开发环境，只需 fork 项目的 git 存储库，并使用适当的软件包管理器安装后端和前端依赖项，然后创建并运行 docker-compose。
 
 ### Fork存储库
 
-您需要 fork [存储库](https://github.com/langgenius/dify)。
+您需要 fork [Git 仓库](https://github.com/langgenius/dify)。
 
 ### 克隆存储库
 
-克隆您在 GitHub 上 fork 的存储库：
+克隆您在 GitHub 上 fork 的仓库：
 
 ```
 git clone git@github.com:<github_username>/dify.git
@@ -51,3 +51,7 @@ git clone git@github.com:<github_username>/dify.git
 ## 社区渠道
 
 遇到困难了吗？有任何问题吗? 加入 [Discord Community Server](https://discord.gg/AhzKf7dNgk)，我们将为您提供帮助。
+
+### 多语言支持
+
+需要参与贡献翻译内容，请参阅[前端多语言翻译 README](web/i18n/README_CN.md)。

CONTRIBUTING_JA.md

@@ -52,4 +52,4 @@ git clone git@github.com:<github_username>/dify.git
 
 ## コミュニティチャンネル
 
-お困りですか？何か質問がありますか？ [Discord Community サーバ](https://discord.gg/AhzKf7dNgk)に参加してください。私たちがお手伝いします！
+お困りですか？何か質問がありますか？ [Discord Community サーバ](https://discord.gg/j3XRWSPBf7) に参加してください。私たちがお手伝いします！

LICENSE

@@ -1,26 +1,26 @@
 # Dify Open Source License
 
-The Dify project uses a combination of the Apache License 2.0, MIT License, and an additional agreement to protect against direct competition with Dify Cloud services.
+The Dify project is licensed under the Apache License 2.0, with the following additional conditions:
 
-As a contributor, you should agree that your contributed code:
-a. Might be subject to a more permissive open source license in the future.
+1. Dify is permitted to be used for commercialization, such as using Dify as a "backend-as-a-service" for your other applications, or delivering it to enterprises as an application development platform. However, when the following conditions are met, you must contact the producer to obtain a commercial license:
+
+a. Multi-tenant SaaS service: Unless explicitly authorized by Dify in writing, you may not use the Dify.AI source code to operate a multi-tenant SaaS service that is similar to the Dify.AI service edition.
+b. LOGO and copyright information: In the process of using Dify, you may not remove or modify the LOGO or copyright information in the Dify console.
+
+Please contact business@dify.ai by email to inquire about licensing matters.
+
+2. As a contributor, you should agree that your contributed code:
+
+a. The producer can adjust the open-source agreement to be more strict or relaxed.
 b. Can be used for commercial purposes, such as Dify's cloud business.
 
-The following components are open source under the MIT license, allowing you to build and develop applications based on them:
-- WebApp elements, e.g., web/app/components/share
-- Derived WebApp Template projects
-
-The remaining parts of the project are open source under the Apache License 2.0.
-
-With the Apache License 2.0, MIT License, and this supplementary agreement, anyone can freely use, modify, and distribute Dify, provided that:
-
-- If you use Dify solely as a backend service for other applications, no authorization is needed for commercial or closed source purposes.
-- If you wish to use Dify for commercial and closed source SaaS services similar to Dify Cloud, please contact us for authorization.
+Apart from this, all other rights and restrictions follow the Apache License 2.0. If you need more detailed information, you can refer to the full version of Apache License 2.0.
 
 The interactive design of this product is protected by appearance patent.
 
 © 2023 LangGenius, Inc.
 
+
 ----------
 
 Licensed under the Apache License, Version 2.0 (the "License");
@@ -34,13 +34,3 @@ distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
-
-----------
-The MIT License
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -2,13 +2,11 @@
 <p align="center">
   <a href="./README.md">English</a> |
   <a href="./README_CN.md">简体中文</a> |
-  <a href="./README_JA.md">日本語</a>
+  <a href="./README_JA.md">日本語</a> |
+  <a href="./README_ES.md">Español</a>
 </p>
 
-[Website](https://dify.ai) • [Docs](https://docs.dify.ai) • [Twitter](https://twitter.com/dify_ai) • [Discord](https://discord.gg/FngNHpbcY7)
-
-Vote for us on Product Hunt ↓  
-<a href="https://www.producthunt.com/posts/dify-ai"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?sanitize=true&post_id=dify-ai&theme=light" alt="Product Hunt Badge" width="250" height="54"></a>
+#### [Website](https://dify.ai) • [Docs](https://docs.dify.ai) • [Deployment Docs](https://docs.dify.ai/getting-started/install-self-hosted) •  [FAQ](https://docs.dify.ai/getting-started/faq) • [Twitter](https://twitter.com/dify_ai) • [Discord](https://discord.gg/FngNHpbcY7)
 
 **Dify** is an easy-to-use LLMOps platform designed to empower more people to create sustainable, AI-native applications. With visual orchestration for various application types, Dify offers out-of-the-box, ready-to-use applications that can also serve as Backend-as-a-Service APIs. Unify your development process with one API for plugins and datasets integration, and streamline your operations using a single interface for prompt engineering, visual analytics, and continuous improvement.
 
@@ -17,11 +15,48 @@ Applications created with Dify include:
 Out-of-the-box web sites supporting form mode and chat conversation mode
 A single API encompassing plugin capabilities, context enhancement, and more, saving you backend coding effort
 Visual data analysis, log review, and annotation for applications
-Dify is compatible with Langchain, meaning we'll gradually support multiple LLMs, currently supported:
 
-- GPT 3 (text-davinci-003)
-- GPT 3.5 Turbo(ChatGPT)
-- GPT-4
+
+https://github.com/langgenius/dify/assets/100913391/f6e658d5-31b3-4c16-a0af-9e191da4d0f6
+
+
+## Highlighted Features
+**1. LLMs support:** Choose capabilities based on different models when building your Dify AI apps. Dify is compatible with Langchain, meaning it will support various LLMs. Currently supported:
+
+- [x] **OpenAI**: GPT4, GPT3.5-turbo, GPT3.5-turbo-16k, text-davinci-003 
+- [x] **Azure OpenAI Service**
+- [x] **Anthropic**: Claude2, Claude-instant
+- [x] **Replicate**
+- [x] **Hugging Face Hub**
+- [x] **ChatGLM**
+- [x] **Llama2**
+- [x] **MiniMax**
+- [x] **Spark**
+- [x] **Wenxin**
+- [x] **Tongyi**
+
+
+We provide the following free resources for registered Dify cloud users (sign up at [dify.ai](https://dify.ai)):
+* 600,000 free Claude model tokens to build Claude-powered apps
+* 200 free OpenAI queries to build OpenAI-based apps
+
+  
+**2. Visual orchestration:** Build an AI app in minutes by writing and debugging prompts visually.
+
+**3. Text embedding:** Fully automated text preprocessing embeds your data as context without complex concepts. Supports PDF, TXT, and syncing data from Notion, webpages, APIs.
+
+**4. API-based:**  Backend-as-a-service. Access web apps directly or integrate via APIs without complex backend setup.
+
+**5. Plugins:** Dify "Smart Chat" now supports first-party plugins like web browsing, Google search, Wikipedia to enable online lookup, analyzing web content, and explaining the AI's reasoning process conversationally.
+
+**6. Team workspaces:** Team members can join workspaces to collaboratively edit, manage, and use team AI apps.
+
+**7. Data labeling and improvement:**  Visually inspect AI app logs and improve data via labeling. Observe the AI's reasoning process to continuously enhance performance. (Coming soon)
+
+## Use cases
+* [Create an AI ChatBot with Business Data in Minutes.](https://docs.dify.ai/use-cases/create-an-ai-chatbot-with-business-data-in-minutes)
+* [How to Build an Notion AI Assistant Based on Your Own Notes?](https://docs.dify.ai/use-cases/build-an-notion-ai-assistant)
+* [Create a Midjoureny Prompt Bot Without Code in Just a Few Minutes.](https://docs.dify.ai/use-cases/create-a-midjoureny-prompt-bot-with-dify)
 
 ## Use Cloud Services
 
@@ -33,7 +68,7 @@ Visit [Dify.ai](https://dify.ai)
 
 Before installing Dify, make sure your machine meets the following minimum system requirements:
 
-- CPU >= 1 Core
+- CPU >= 2 Core
 - RAM >= 4GB
 
 ### Quick Start
@@ -42,11 +77,16 @@ The easiest way to start the Dify server is to run our [docker-compose.yml](dock
 
 ```bash
 cd docker
-docker-compose up -d
+docker compose up -d
 ```
 
 After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization installation process.
 
+### Helm Chart
+
+A big thanks to @BorisPolonsky for providing us with a [Helm Chart](https://helm.sh/) version, which allows Dify to be deployed on Kubernetes.
+You can go to https://github.com/BorisPolonsky/dify-helm for deployment information.
+
 ### Configuration
 
 If you need to customize the configuration, please refer to the comments in our [docker-compose.yml](docker/docker-compose.yaml) file and manually set the environment configuration. After making the changes, please run 'docker-compose up -d' again.
@@ -59,8 +99,6 @@ Features under development:
 We will support more datasets, including text, webpages, and even Notion content. Users can build AI applications based on their own data sources.
 - **Plugins**, introducing ChatGPT Plugin-standard plugins for applications, or using Dify-produced plugins
 We will release plugins complying with ChatGPT standard, or Dify's own plugins to enable more capabilities in applications. 
-- **Open-source models**, e.g. adopting Llama as a model provider or for further fine-tuning
-We will work with excellent open-source models like Llama, by providing them as model options in our platform, or using them for further fine-tuning.
 
 
 ## Q&A
@@ -85,6 +123,32 @@ A: English and Chinese are currently supported, and you can contribute language
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
+
+## Contributing 
+
+We welcome you to contribute to Dify to help make Dify better. We welcome contributions in various ways, submitting code, issues, new ideas, or sharing the interesting and useful AI applications you have created based on Dify. At the same time, we also welcome you to share Dify at different events, conferences, and social media.
+
+### Submit a Pull Request 
+
+To ensure proper review, all code contributions, including from contributors with direct commit access, must be submitted as PR requests and approved by core developers before merging branches. 
+We welcome PRs from everyone! If you're willing to help out, you can learn more about how to contribute code to the project in the [Contribution Guide](CONTRIBUTING.md).  
+
+### Submit issues or ideas  
+
+You can submit your issues or ideas by adding issues to the Dify repository. If you encounter issues, please describe the steps you took to encounter the issue as much as possible so we can better discover it. If you have any new ideas for our product, we also welcome your feedback. Please share your insights as much as possible so we can get more feedback and further discussion in the community.  
+
+### Share your applications
+
+We encourage all community members to share their AI applications built on Dify, which can be applied to different scenarios or different users. This will provide powerful inspiration for people who want to create AI capabilities! You can share your experience by [submitting an issue in the Dify-user-case repository](https://github.com/langgenius/dify-user-case/issues).  
+
+### Share Dify with others
+
+We encourage community contributors to actively demonstrate different aspects of using Dify. You can talk or share any feature of using Dify at  meetups and conferences, blogs or social media. We believe your unique sharing will be of great help to others!  Mention @Dify.AI on Twitter and/or communicate on [Discord](https://discord.gg/FngNHpbcY7) so we can give pointers and tips and help you spread the word by promoting your content on the different Dify communication channels.
+
+### Help others 
+You can also help people in need of help on Discord, GitHub issues or other social platforms, guide others to solve problems encountered during use and share usage experiences. This is also a great contribution! If you want to become a maintainer of the Dify community, please contact the official team via [Discord](https://discord.gg/FngNHpbcY7) or email us at support@dify.ai. 
+
+
 ## Contact Us
 
 If you have any questions, suggestions, or partnership inquiries, feel free to contact us through the following channels:
@@ -95,12 +159,6 @@ If you have any questions, suggestions, or partnership inquiries, feel free to c
 
 We're eager to assist you and together create more fun and useful AI applications!
 
-## Contributing
-
-To ensure proper review, all code contributions - including those from contributors with direct commit access - must be submitted via pull requests and approved by the core development team prior to being merged.
-
-We welcome all pull requests! If you'd like to help, check out the [Contribution Guide](CONTRIBUTING.md) for more information on how to get started.
-
 ## Security
 
 To protect your privacy, please avoid posting security issues on GitHub. Instead, send your questions to security@dify.ai and we will provide you with a more detailed answer.
@@ -110,7 +168,6 @@ To protect your privacy, please avoid posting security issues on GitHub. Instead
 This software uses the following open-source software:
 
 - Chase, H. (2022). LangChain [Computer software]. https://github.com/hwchase17/langchain
-- Liu, J. (2022). LlamaIndex [Computer software]. doi: 10.5281/zenodo.1234.
 
 For more information, please refer to the official website or license text of the respective software.
 

README_CN.md

@@ -2,16 +2,14 @@
 <p align="center">
   <a href="./README.md">English</a> |
   <a href="./README_CN.md">简体中文</a> |
-  <a href="./README_JA.md">日本語</a>
+  <a href="./README_JA.md">日本語</a> |
+  <a href="./README_ES.md">Español</a>
 </p>
 
 
-[官方网站](https://dify.ai) • [文档](https://docs.dify.ai/v/zh-hans) • [Twitter](https://twitter.com/dify_ai) •  [Discord](https://discord.gg/FngNHpbcY7)
+####  [官方网站](https://dify.ai) •  [使用文档](https://docs.dify.ai/v/zh-hans)  · [部署文档](https://docs.dify.ai/v/zh-hans/getting-started/install-self-hosted)  ·  [FAQ](https://docs.dify.ai/v/zh-hans/getting-started/faq) • [Twitter](https://twitter.com/dify_ai) •  [Discord](https://discord.gg/FngNHpbcY7)
 
-在 Product Hunt 上投我们一票吧 ↓  
-<a href="https://www.producthunt.com/posts/dify-ai"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?sanitize=true&post_id=dify-ai&theme=light" alt="Product Hunt Badge" width="250" height="54"></a>
-
-**Dify** 是一个易用的 LLMOps 平台，旨在让更多人可以创建可持续运营的原生 AI 应用。Dify 提供多种类型应用的可视化编排，应用可开箱即用，也能以“后端即服务”的 API 提供服务。
+**Dify** 是一个易用的 LLMOps 平台，基于不同的大型语言模型能力，让更多人可以简易地创建可持续运营的原生 AI 应用。Dify 提供多种类型应用的可视化编排，应用可开箱即用，也能以“后端即服务”的 API 提供服务。
 
 通过 Dify 创建的应用包含了：
 
@@ -19,15 +17,45 @@
 - 一套 API 即可包含插件、上下文增强等能力，替你省下了后端代码的编写工作
 - 可视化的对应用进行数据分析，查阅日志或进行标注
 
-Dify 兼容 Langchain，这意味着我们将逐步支持多种 LLMs ，目前已支持：
+https://github.com/langgenius/dify/assets/100913391/f6e658d5-31b3-4c16-a0af-9e191da4d0f6
+
+## 核心能力
+1. **模型支持：** 你可以在 Dify 上选择基于不同模型的能力来开发你的 AI 应用。Dify 兼容 Langchain，这意味着我们将逐步支持多种 LLMs ，目前支持的模型供应商：
+
+- [x] **OpenAI**：GPT4、GPT3.5-turbo、GPT3.5-turbo-16k、text-davinci-003 
+- [x] **Azure OpenAI Service**
+- [x] **Anthropic**：Claude2、Claude-instant
+- [x] **Replicate**
+- [x] **Hugging Face Hub**
+- [x] **ChatGLM**
+- [x] **Llama2**
+- [x] **MiniMax**
+- [x] **讯飞星火大模型**
+- [x] **文心一言**
+- [x] **通义千问**
+
+
+我们为所有注册云端版的用户免费提供以下资源（登录 [dify.ai](https://cloud.dify.ai) 即可使用）：
+* 60 万 Tokens Claude 模型的消息调用额度，用于创建基于 Claude 模型的 AI 应用
+* 200 次 OpenAI 模型的消息调用额度，用于创建基于 OpenAI 模型的 AI 应用
+* 300 万 讯飞星火大模型 Token 的调用额度，用于创建基于讯飞星火大模型的 AI 应用
+* 100 万 MiniMax Token 的调用额度，用于创建基于 MiniMax 模型的 AI 应用
+2. **可视化编排 Prompt：** 通过界面化编写 prompt 并调试，只需几分钟即可发布一个 AI 应用。
+3. **文本 Embedding 处理（数据集）**：全自动完成文本预处理，使用你的数据作为上下文，无需理解晦涩的概念和技术处理。支持 PDF、txt 等文件格式，支持从 Notion、网页、API 同步数据。
+4. **基于 API 开发：** 后端即服务。您可以直接访问网页应用，也可以接入 API 集成到您的应用中，无需关注复杂的后端架构和部署过程。
+5. **插件能力：** Dify 「智聊」平台已支持网页浏览、Google 搜索、Wikipedia 查询等第一方插件，可在对话中实现联网搜索、分析网页内容、展示 AI 的推理过程。
+6. **团队 Workspace：** 团队成员可加入 Workspace 编辑、管理和使用团队内的 AI 应用。
+6. **数据标注与改进：** 可视化查阅 AI 应用日志并对数据进行改进标注，观测 AI 的推理过程，不断提高其性能。（Coming soon）
+ -----------------------------
+ ## Use cases
+ * [几分钟创建一个带有业务数据的官网 AI 智能客服](https://docs.dify.ai/v/zh-hans/use-cases/create-an-ai-chatbot-with-business-data-in-minutes)
+ * [构建一个 Notion AI 助手](https://docs.dify.ai/v/zh-hans/use-cases/build-an-notion-ai-assistant)
+ * [创建 Midjoureny 提示词机器人](https://docs.dify.ai/v/zh-hans/use-cases/create-a-midjoureny-prompt-word-robot-with-zero-code)
 
-- GPT 3 (text-davinci-003)
-- GPT 3.5 Turbo(ChatGPT)
-- GPT-4
 
 ## 使用云服务
 
-访问 [Dify.ai](https://cloud.dify.ai)
+访问 [Dify.ai](https://cloud.dify.ai) 使用云端版。
 
 ## 安装社区版
 
@@ -35,7 +63,7 @@ Dify 兼容 Langchain，这意味着我们将逐步支持多种 LLMs ，目前
 
 在安装 Dify 之前，请确保您的机器满足以下最低系统要求：
 
-- CPU >= 1 Core
+- CPU >= 2 Core
 - RAM >= 4GB
 
 ### 快速启动
@@ -44,11 +72,16 @@ Dify 兼容 Langchain，这意味着我们将逐步支持多种 LLMs ，目前
 
 ```bash
 cd docker
-docker-compose up -d
+docker compose up -d
 ```
 
 运行后，可以在浏览器上访问 [http://localhost/install](http://localhost/install) 进入 Dify 控制台并开始初始化安装操作。
 
+### Helm Chart
+
+非常感谢 @BorisPolonsky 为我们提供了一个 [Helm Chart](https://helm.sh/) 版本，可以在 Kubernetes 上部署 Dify。
+您可以前往 https://github.com/BorisPolonsky/dify-helm 来获取部署信息。
+
 ### 配置
 
 需要自定义配置，请参考我们的 [docker-compose.yml](docker/docker-compose.yaml) 文件中的注释，并手动设置环境配置，修改完毕后，请再次执行 `docker-compose up -d`。
@@ -57,12 +90,8 @@ docker-compose up -d
 
 我们正在开发中的功能：
 
-- **数据集**，支持更多的数据集，例如同步 Notion 或网页的内容
-我们将支持更多的数据集，包括文本、网页，甚至 Notion 内容。用户可以根据自己的数据源构建 AI 应用程序。
-- **插件**，推出符合 ChatGPT 标准的插件，或使用 Dify 产生的插件
-我们将发布符合 ChatGPT 标准的插件，或者 Dify 自己的插件，以在应用程序中启用更多功能。
-- **开源模型**，例如采用 Llama 作为模型提供者，或进行进一步的微调
-我们将与优秀的开源模型如 Llama 合作，通过在我们的平台中提供它们作为模型选项，或使用它们进行进一步的微调。
+- **数据集**，支持更多的数据集，通过网页、API 同步内容。用户可以根据自己的数据源构建 AI 应用程序。
+- **插件**，我们将发布符合 ChatGPT 标准的插件，支持更多 Dify 自己的插件，支持用户自定义插件能力，以在应用程序中启用更多功能，例如以支持以目标为导向的分解推理任务。
 
 ## Q&A
 
@@ -76,16 +105,39 @@ A: 一个有价值的应用由 Prompt Engineering、上下文增强和 Fine-tune
 
 **Q: 如果要创建一个自己的应用，我需要准备什么？**
 
-A: 我们假定你已经有了 OpenAI API Key，如果没有请去注册一个。如果你已经有了一些内容可以作为训练上下文，就太好了。
+A: 我们假定你已经有了 OpenAI 或 Claude 等模型的 API Key，如果没有请去注册一个。如果你已经有了一些内容可以作为训练上下文，就太好了。
 
 **Q: 提供哪些界面语言？**
 
-A: 现已支持英文与中文，你可以为我们贡献语言包。
+A:  支持英文、中文，你可以为我们贡献语言包并提供维护支持。
 
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
+
+## 贡献
+
+我们欢迎你为 Dify 作出贡献帮助 Dify 变得更好。我们欢迎各种方式的贡献，提交代码、问题、新想法、或者分享你基于 Dify 创建出的各种有趣有用的 AI 应用。同时，我们也欢迎你在不同的活动、研讨会、社交媒体上分享 Dify。
+
+### 贡献代码
+为了确保正确审查，所有代码贡献 - 包括来自具有直接提交更改权限的贡献者 - 都必须提交 PR 请求并在合并分支之前得到核心开发人员的批准。
+
+我们欢迎所有人提交 PR！如果您愿意提供帮助，可以在 [贡献指南](CONTRIBUTING_CN.md) 中了解有关如何为项目做出代码贡献的更多信息。
+
+### 提交问题或想法
+你可以通过 Dify 代码仓库新增 issues 来提交你的问题或想法。如遇到问题，请尽可能描述你遇到问题的操作步骤，以便我们更好地发现它。如果你对我们的产品有任何新想法，也欢迎向我们反馈，请尽可能多地分享你的见解，以便我们在社区中获得更多反馈和进一步讨论。
+
+### 分享你的应用
+我们鼓励所有社区成员分享他们基于 Dify 创造出的 AI 应用，它们可以是应用于不同情景或不同用户，这将有助于为希望基于 AI 能力创造的人们提供强大灵感！你可以通过 [Dify-user-case 仓库项目提交 issue](https://github.com/langgenius/dify-user-case) 来分享你的应用案例。
+
+### 向别人分享 Dify
+我们鼓励社区贡献者们积极展示你使用 Dify 的不同角度。你可以通过线下研讨会、博客或社交媒体上谈论或分享你使用 Dify 的任意功能，相信你独特的使用分享会给别人带来非常大的帮助！如果你需要任何指导帮助，欢迎联系我们 support@dify.ai ,你也可以在 twitter @Dify.AI 或在 [Discord 社区](https://discord.gg/FngNHpbcY7)交流来帮助你传播信息。
+
+### 帮助别人
+你还可以在 Discord、GitHub issues或其他社交平台上帮助需要帮助的人，指导别人解决使用过程中遇到的问题和分享使用经验。这也是个非常了不起的贡献！如果你希望成为 Dify 社区的维护者，请通过[Discord 社区](https://discord.gg/FngNHpbcY7) 联系官方团队或邮件联系我们 support@dify.ai.
+
+
 ## 联系我们
 
 如果您有任何问题、建议或合作意向，欢迎通过以下方式联系我们：
@@ -94,12 +146,6 @@ A: 现已支持英文与中文，你可以为我们贡献语言包。
 - 在我们的 [Discord 社区](https://discord.gg/FngNHpbcY7) 上加入讨论
 - 发送邮件至 hello@dify.ai
 
-## 贡献代码
-
-为了确保正确审查，所有代码贡献 - 包括来自具有直接提交更改权限的贡献者 - 都必须提交 PR 请求并在合并分支之前得到核心开发人员的批准。
-
-我们欢迎所有人提交 PR！如果您愿意提供帮助，可以在 [贡献指南](CONTRIBUTING_CN.md) 中了解有关如何为项目做出贡献的更多信息。
-
 ## 安全
 
 为了保护您的隐私，请避免在 GitHub 上发布安全问题。发送问题至 security@dify.ai，我们将为您做更细致的解答。
@@ -109,7 +155,6 @@ A: 现已支持英文与中文，你可以为我们贡献语言包。
 本软件使用了以下开源软件：
 
 - Chase, H. (2022). LangChain [Computer software]. https://github.com/hwchase17/langchain
-- Liu, J. (2022). LlamaIndex [Computer software]. doi: 10.5281/zenodo.1234.
 
 更多信息，请参考相应软件的官方网站或许可证文本。
 

README_ES.md

@@ -0,0 +1,123 @@
+![](./images/describe-en.png)
+<p align="center">
+  <a href="./README.md">English</a> |
+  <a href="./README_CN.md">简体中文</a> |
+  <a href="./README_JA.md">日本語</a> |
+  <a href="./README_ES.md">Español</a>
+</p>
+
+[Sitio web](https://dify.ai) • [Documentación](https://docs.dify.ai) • [Twitter](https://twitter.com/dify_ai) • [Discord](https://discord.gg/FngNHpbcY7)
+
+**Dify** es una plataforma LLMOps fácil de usar diseñada para capacitar a más personas para que creen aplicaciones sostenibles basadas en IA. Con orquestación visual para varios tipos de aplicaciones, Dify ofrece aplicaciones listas para usar que también pueden funcionar como APIs de Backend-as-a-Service. Unifica tu proceso de desarrollo con una API para la integración de complementos y conjuntos de datos, y agiliza tus operaciones utilizando una interfaz única para la ingeniería de indicaciones, análisis visual y mejora continua.
+
+Las aplicaciones creadas con Dify incluyen:
+
+- Sitios web listos para usar que admiten el modo de formulario y el modo de conversación por chat.
+- Una API única que abarca capacidades de complementos, mejora de contexto y más, lo que te ahorra esfuerzo de programación en el backend.
+- Análisis visual de datos, revisión de registros y anotación para aplicaciones.
+
+Dify es compatible con Langchain, lo que significa que gradualmente admitiremos múltiples LLMs, actualmente compatibles con:
+
+- GPT 3 (text-davinci-003)
+- GPT 3.5 Turbo (ChatGPT)
+- GPT-4
+
+## Usar servicios en la nube
+
+Visita [Dify.ai](https://dify.ai)
+
+## Instalar la Edición Comunitaria
+
+### Requisitos del sistema
+
+Antes de instalar Dify, asegúrate de que tu máquina cumple con los siguientes requisitos mínimos del sistema:
+
+- CPU >= 2 Core
+- RAM >= 4GB
+
+### Inicio rápido
+
+La forma más sencilla de iniciar el servidor de Dify es ejecutar nuestro archivo [docker-compose.yml](docker/docker-compose.yaml). Antes de ejecutar el comando de instalación, asegúrate de que [Docker](https://docs.docker.com/get-docker/) y [Docker Compose](https://docs.docker.com/compose/install/) estén instalados en tu máquina:
+
+```bash
+cd docker
+docker compose up -d
+```
+
+Después de ejecutarlo, puedes acceder al panel de control de Dify en tu navegador desde [http://localhost/install](http://localhost/install) y comenzar el proceso de instalación de inicialización.
+
+### Helm Chart
+
+Un gran agradecimiento a @BorisPolonsky por proporcionarnos una versión de [Helm Chart](https://helm.sh/), que permite desplegar Dify en Kubernetes.
+Puede ir a https://github.com/BorisPolonsky/dify-helm para obtener información de despliegue.
+
+### Configuración
+
+Si necesitas personalizar la configuración, consulta los comentarios en nuestro archivo [docker-compose.yml](docker/docker-compose.yaml) y configura manualmente la configuración del entorno. Después de realizar los cambios, ejecuta nuevamente 'docker-compose up -d'.
+
+## Hoja de ruta
+
+Funciones en desarrollo:
+
+- **Conjuntos de datos**, admitiendo más conjuntos de datos, por ejemplo, sincronización de contenido desde Notion o páginas web.
+Admitiremos más conjuntos de datos, incluidos texto, páginas web e incluso contenido de Notion. Los usuarios pueden construir aplicaciones de IA basadas en sus propias fuentes de datos
+- **Complementos**, introduciendo complementos estándar de ChatGPT para aplicaciones, o utilizando complementos producidos por Dify.
+Lanzaremos complementos que cumplan con el estándar de ChatGPT, o nuestros propios complementos de Dify para habilitar más capacidades en las aplicaciones.
+- **Modelos de código abierto**, por ejemplo, adoptar Llama como proveedor de modelos o para un ajuste adicional.
+Trabajaremos con excelentes modelos de código abierto como Llama, proporcionándolos como opciones de modelos en nuestra plataforma o utilizándolos para un ajuste adicional.
+
+## Preguntas y respuestas
+
+**P: ¿Qué puedo hacer con Dify?**
+
+R: Dify es una herramienta de desarrollo y operaciones de LLM, simple pero poderosa. Puedes usarla para construir aplicaciones de calidad comercial y asistentes personales. Si deseas desarrollar tus propias aplicaciones, LangDifyGenius puede ahorrarte trabajo en el backend al integrar con OpenAI y ofrecer capacidades de operaciones visuales, lo que te permite mejorar y entrenar continuamente tu modelo GPT.
+
+**P: ¿Cómo uso Dify para "entrenar" mi propio modelo?**
+
+R: Una aplicación valiosa consta de Ingeniería de indicaciones, mejora de contexto y ajuste fino. Hemos creado un enfoque de programación híbrida que combina las indicaciones con lenguajes de programación (similar a un motor de plantillas), lo que facilita la incorporación de texto largo o la captura de subtítulos de un video de YouTube ingresado por el usuario, todo lo cual se enviará como contexto para que los LLM lo procesen. Damos gran importancia a la operabilidad de la aplicación, con los datos generados por los usuarios durante el uso de la aplicación disponibles para análisis, anotación y entrenamiento continuo. Sin las herramientas adecuadas, estos pasos pueden llevar mucho tiempo.
+
+**P: ¿Qué necesito preparar si quiero crear mi propia aplicación?**
+
+R: Suponemos que ya tienes una clave de API de OpenAI; si no la tienes, por favor regístrate. ¡Si ya tienes contenido que pueda servir como contexto de entrenamiento, eso es genial!
+
+**P: ¿Qué idiomas de interfaz están disponibles?**
+
+R: Actualmente se admiten inglés y chino, y puedes contribuir con paquetes de idiomas.
+
+## Historial de estrellas
+
+[![Gráfico de historial de estrellas](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+
+## Contáctanos
+
+Si tienes alguna pregunta, sugerencia o consulta sobre asociación, no dudes en contactarnos a través de los siguientes canales:
+
+- Presentar un problema o una solicitud de extracción en nuestro repositorio de GitHub.
+- Únete a la discusión en nuestra comunidad de [Discord](https://discord.gg/FngNHpbcY7).
+- Envía un correo electrónico a hello@dify.ai.
+
+¡Estamos ansiosos por ayudarte y crear juntos aplicaciones de IA más divertidas y útiles!
+
+## Contribuciones
+
+Para garantizar una revisión adecuada, todas las contribuciones de código, incluidas las de los colaboradores con acceso directo a los compromisos, deben enviarse mediante solicitudes de extracción y ser aprobadas por el equipo principal de
+
+ desarrollo antes de fusionarse.
+
+¡Agradecemos todas las solicitudes de extracción! Si deseas ayudar, consulta la [Guía de Contribución](CONTRIBUTING.md) para obtener más información sobre cómo comenzar.
+
+## Seguridad
+
+Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada.
+
+## Citación
+
+Este software utiliza el siguiente software de código abierto:
+
+- Chase, H. (2022). LangChain [Software de computadora]. https://github.com/hwchase17/langchain
+
+Para obtener más información, consulta el sitio web oficial o el texto de la licencia del software correspondiente.
+
+## Licencia
+
+Este repositorio está disponible bajo la [Licencia de código abierto de Dify](LICENSE).

README_JA.md

@@ -2,14 +2,12 @@
 <p align="center">
   <a href="./README.md">English</a> |
   <a href="./README_CN.md">简体中文</a> |
-  <a href="./README_JA.md">日本語</a>
+  <a href="./README_JA.md">日本語</a> |
+  <a href="./README_ES.md">Español</a>
 </p>
 
 [Web サイト](https://dify.ai) • [ドキュメント](https://docs.dify.ai) • [Twitter](https://twitter.com/dify_ai) • [Discord](https://discord.gg/FngNHpbcY7)
 
-Product Huntで私たちに投票してください ↓  
-<a href="https://www.producthunt.com/posts/dify-ai"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?sanitize=true&post_id=dify-ai&theme=light" alt="Product Hunt Badge" width="250" height="54"></a>
-
 
 **Dify** は、より多くの人々が持続可能な AI ネイティブアプリケーションを作成できるように設計された、使いやすい LLMOps プラットフォームです。様々なアプリケーションタイプに対応したビジュアルオーケストレーションにより Dify は Backend-as-a-Service API としても機能する、すぐに使えるアプリケーションを提供します。プラグインやデータセットを統合するための1つの API で開発プロセスを統一し、プロンプトエンジニアリング、ビジュアル分析、継続的な改善のための1つのインターフェイスを使って業務を合理化します。
 
@@ -43,11 +41,16 @@ Dify サーバーを起動する最も簡単な方法は、[docker-compose.yml](
 
 ```bash
 cd docker
-docker-compose up -d
+docker compose up -d
 ```
 
 実行後、ブラウザで [http://localhost/install](http://localhost/install) にアクセスし、初期化インストール作業を開始することができます。
 
+### Helm Chart
+
+@BorisPolonsky に大感謝します。彼は Dify を Kubernetes 上にデプロイするための [Helm Chart](https://helm.sh/) バージョンを提供してくれました。
+デプロイ情報については、https://github.com/BorisPolonsky/dify-helm をご覧ください。
+
 ### 構成
 
 カスタマイズが必要な場合は、[docker-compose.yml](docker/docker-compose.yaml) ファイルのコメントを参照し、手動で環境設定をお願いします。変更後、再度 'docker-compose up -d' を実行してください。
@@ -111,7 +114,6 @@ A: 現在、英語と中国語に対応しており、言語パックを寄贈
 本ソフトウェアは、以下のオープンソースソフトウェアを使用しています:
 
 - Chase, H. (2022). LangChain [Computer software]. https://github.com/hwchase17/langchain
-- Liu, J. (2022). LlamaIndex [Computer software]. doi: 10.5281/zenodo.1234.
 
 詳しくは、各ソフトウェアの公式サイトまたはライセンス文をご参照ください。
 

api/.dockerignore

@@ -1,2 +1,11 @@
 .env
-storage/privkeys/*
+*.env.*
+
+storage/privkeys/*
+
+# Logs
+logs
+*.log*
+
+# jetbrains
+.idea

api/.env.example

@@ -8,13 +8,15 @@ EDITION=SELF_HOSTED
 SECRET_KEY=
 
 # Console API base URL
-CONSOLE_URL=http://127.0.0.1:5001
+CONSOLE_API_URL=http://127.0.0.1:5001
+CONSOLE_WEB_URL=http://127.0.0.1:3000
 
 # Service API base URL
-API_URL=http://127.0.0.1:5001
+SERVICE_API_URL=http://127.0.0.1:5001
 
 # Web APP base URL
-APP_URL=http://127.0.0.1:3000
+APP_API_URL=http://127.0.0.1:5001
+APP_WEB_URL=http://127.0.0.1:3000
 
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
@@ -22,6 +24,7 @@ CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 # redis configuration
 REDIS_HOST=localhost
 REDIS_PORT=6379
+REDIS_USERNAME=
 REDIS_PASSWORD=difyai123456
 REDIS_DB=0
 
@@ -47,24 +50,6 @@ S3_REGION=your-region
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
-# Cookie configuration
-COOKIE_HTTPONLY=true
-COOKIE_SAMESITE=None
-COOKIE_SECURE=true
-
-# Session configuration
-SESSION_PERMANENT=true
-SESSION_USE_SIGNER=true
-
-## support redis, sqlalchemy
-SESSION_TYPE=redis
-
-# session redis configuration
-SESSION_REDIS_HOST=localhost
-SESSION_REDIS_PORT=6379
-SESSION_REDIS_PASSWORD=difyai123456
-SESSION_REDIS_DB=2
-
 # Vector database configuration, support: weaviate, qdrant
 VECTOR_STORE=weaviate
 
@@ -72,10 +57,16 @@ VECTOR_STORE=weaviate
 WEAVIATE_ENDPOINT=http://localhost:8080
 WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
 WEAVIATE_GRPC_ENABLED=false
+WEAVIATE_BATCH_SIZE=100
 
-# Qdrant configuration, use `path:` prefix for local mode or `https://your-qdrant-cluster-url.qdrant.io` for remote mode
-QDRANT_URL=path:storage/qdrant
-QDRANT_API_KEY=your-qdrant-api-key
+# Qdrant configuration, use `http://localhost:6333` for local mode or `https://your-qdrant-cluster-url.qdrant.io` for remote mode
+QDRANT_URL=http://localhost:6333
+QDRANT_API_KEY=difyai123456
+
+# Mail configuration, support: resend
+MAIL_TYPE=
+MAIL_DEFAULT_SEND_FROM=no-reply <no-reply@dify.ai>
+RESEND_API_KEY=
 
 # Sentry configuration
 SENTRY_DSN=
@@ -83,3 +74,37 @@ SENTRY_DSN=
 # DEBUG
 DEBUG=false
 SQLALCHEMY_ECHO=false
+
+# Notion import configuration, support public and internal
+NOTION_INTEGRATION_TYPE=public
+NOTION_CLIENT_SECRET=you-client-secret
+NOTION_CLIENT_ID=you-client-id
+NOTION_INTERNAL_SECRET=you-internal-secret
+
+# Hosted Model Credentials
+HOSTED_OPENAI_ENABLED=false
+HOSTED_OPENAI_API_KEY=
+HOSTED_OPENAI_API_BASE=
+HOSTED_OPENAI_API_ORGANIZATION=
+HOSTED_OPENAI_QUOTA_LIMIT=200
+HOSTED_OPENAI_PAID_ENABLED=false
+HOSTED_OPENAI_PAID_STRIPE_PRICE_ID=
+HOSTED_OPENAI_PAID_INCREASE_QUOTA=1
+
+HOSTED_AZURE_OPENAI_ENABLED=false
+HOSTED_AZURE_OPENAI_API_KEY=
+HOSTED_AZURE_OPENAI_API_BASE=
+HOSTED_AZURE_OPENAI_QUOTA_LIMIT=200
+
+HOSTED_ANTHROPIC_ENABLED=false
+HOSTED_ANTHROPIC_API_BASE=
+HOSTED_ANTHROPIC_API_KEY=
+HOSTED_ANTHROPIC_QUOTA_LIMIT=600000
+HOSTED_ANTHROPIC_PAID_ENABLED=false
+HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID=
+HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA=1000000
+HOSTED_ANTHROPIC_PAID_MIN_QUANTITY=20
+HOSTED_ANTHROPIC_PAID_MAX_QUANTITY=100
+
+STRIPE_API_KEY=
+STRIPE_WEBHOOK_SECRET=

api/Dockerfile

@@ -1,28 +1,46 @@
-FROM langgenius/base:1.0.0-bullseye-slim as langgenius-api
+# packages install stage
+FROM python:3.10-slim AS base
 
 LABEL maintainer="takatost@gmail.com"
 
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends gcc g++ python3-dev libc-dev libffi-dev
+
+COPY requirements.txt /requirements.txt
+
+RUN pip install --prefix=/pkg -r requirements.txt
+
+# build stage
+FROM python:3.10-slim AS builder
+
 ENV FLASK_APP app.py
 ENV EDITION SELF_HOSTED
 ENV DEPLOY_ENV PRODUCTION
-ENV CONSOLE_URL http://127.0.0.1:5001
-ENV API_URL http://127.0.0.1:5001
-ENV APP_URL http://127.0.0.1:5001
+ENV CONSOLE_API_URL http://127.0.0.1:5001
+ENV CONSOLE_WEB_URL http://127.0.0.1:3000
+ENV SERVICE_API_URL http://127.0.0.1:5001
+ENV APP_API_URL http://127.0.0.1:5001
+ENV APP_WEB_URL http://127.0.0.1:3000
 
 EXPOSE 5001
 
 WORKDIR /app/api
 
-COPY requirements.txt /app/api/requirements.txt
-
-RUN pip install -r requirements.txt
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends bash curl wget vim nodejs \
+    && apt-get autoremove \
+    && rm -rf /var/lib/apt/lists/*
 
+COPY --from=base /pkg /usr/local
 COPY . /app/api/
 
+RUN python -c "from transformers import GPT2TokenizerFast; GPT2TokenizerFast.from_pretrained('gpt2')"
+ENV TRANSFORMERS_OFFLINE true
+
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh
 
 ARG COMMIT_SHA
 ENV COMMIT_SHA ${COMMIT_SHA}
 
-ENTRYPOINT ["/entrypoint.sh"]
+ENTRYPOINT ["/bin/bash", "/entrypoint.sh"]

api/README.md

@@ -8,7 +8,7 @@
    
    ```bash
    cd ../docker
-   docker-compose -f docker-compose.middleware.yaml up -d
+   docker-compose -f docker-compose.middleware.yaml -p dify up -d
    cd ../api
    ```
 2. Copy `.env.example` to `.env`
@@ -17,6 +17,11 @@
    ```bash
    openssl rand -base64 42
    ```
+3.5 If you use annaconda, create a new environment and activate it
+   ```bash
+   conda create --name dify python=3.10
+   conda activate dify
+   ```
 4. Install dependencies
    ```bash
    pip install -r requirements.txt
@@ -28,9 +33,32 @@
    ```bash
    flask db upgrade
    ```
+
+   ⚠️ If you encounter problems with jieba, for example
+
+   ```
+   > flask db upgrade
+   Error: While importing 'app', an ImportError was raised:
+   ```
+
+   Please run the following command instead.
+
+   ```
+   pip install -r requirements.txt --upgrade --force-reinstall
+   ```
+   
 6. Start backend:
    ```bash
    flask run --host 0.0.0.0 --port=5001 --debug
    ```
 7. Setup your application by visiting http://localhost:5001/console/api/setup or other apis...
-8. If you need to debug local async processing, you can run `celery -A app.celery worker`, celery can do dataset importing and other async tasks.
+8. If you need to debug local async processing, you can run `celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail`, celery can do dataset importing and other async tasks.
+
+8. Start frontend
+
+   You can start the frontend by running `npm install && npm run dev` in web/ folder, or you can use docker to start the frontend, for example:
+
+   ```
+   docker run -it -d --platform linux/amd64 -p 3000:3000 -e EDITION=SELF_HOSTED -e CONSOLE_URL=http://127.0.0.1:5001 --name web-self-hosted langgenius/dify-web:latest
+   ```
+   This will start a dify frontend, now you are all set, happy coding!

api/app.py

@@ -1,5 +1,8 @@
 # -*- coding:utf-8 -*-
 import os
+
+from werkzeug.exceptions import Unauthorized
+
 if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
     from gevent import monkey
     monkey.patch_all()
@@ -8,25 +11,24 @@ import logging
 import json
 import threading
 
-from flask import Flask, request, Response, session
-import flask_login
+from flask import Flask, request, Response
 from flask_cors import CORS
 
-from extensions import ext_session, ext_celery, ext_sentry, ext_redis, ext_login, ext_vector_store, ext_migrate, \
-    ext_database, ext_storage
+from core.model_providers.providers import hosted
+from extensions import ext_celery, ext_sentry, ext_redis, ext_login, ext_migrate, \
+    ext_database, ext_storage, ext_mail, ext_stripe
 from extensions.ext_database import db
 from extensions.ext_login import login_manager
 
 # DO NOT REMOVE BELOW
-from models import model, account, dataset, web, task
+from models import model, account, dataset, web, task, source, tool
 from events import event_handlers
 # DO NOT REMOVE ABOVE
 
-import core
 from config import Config, CloudEditionConfig
 from commands import register_commands
-from models.account import TenantAccountJoin
-from models.model import Account, EndUser, App
+from services.account_service import AccountService
+from libs.passport import PassportService
 
 import warnings
 warnings.simplefilter("ignore", ResourceWarning)
@@ -66,7 +68,7 @@ def create_app(test_config=None) -> Flask:
     register_blueprints(app)
     register_commands(app)
 
-    core.init_app(app)
+    hosted.init_app(app)
 
     return app
 
@@ -77,59 +79,35 @@ def initialize_extensions(app):
     ext_database.init_app(app)
     ext_migrate.init(app, db)
     ext_redis.init_app(app)
-    ext_vector_store.init_app(app)
     ext_storage.init_app(app)
     ext_celery.init_app(app)
-    ext_session.init_app(app)
     ext_login.init_app(app)
+    ext_mail.init_app(app)
     ext_sentry.init_app(app)
+    ext_stripe.init_app(app)
 
 
 # Flask-Login configuration
-@login_manager.user_loader
-def load_user(user_id):
-    """Load user based on the user_id."""
+@login_manager.request_loader
+def load_user_from_request(request_from_flask_login):
+    """Load user based on the request."""
     if request.blueprint == 'console':
         # Check if the user_id contains a dot, indicating the old format
-        if '.' in user_id:
-            tenant_id, account_id = user_id.split('.')
-        else:
-            account_id = user_id
+        auth_header = request.headers.get('Authorization', '')
+        if ' ' not in auth_header:
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+        auth_scheme, auth_token = auth_header.split(None, 1)
+        auth_scheme = auth_scheme.lower()
+        if auth_scheme != 'bearer':
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+        
+        decoded = PassportService().verify(auth_token)
+        user_id = decoded.get('user_id')
 
-        account = db.session.query(Account).filter(Account.id == account_id).first()
-
-        if account:
-            workspace_id = session.get('workspace_id')
-            if workspace_id:
-                tenant_account_join = db.session.query(TenantAccountJoin).filter(
-                    TenantAccountJoin.account_id == account.id,
-                    TenantAccountJoin.tenant_id == workspace_id
-                ).first()
-
-                if not tenant_account_join:
-                    tenant_account_join = db.session.query(TenantAccountJoin).filter(
-                        TenantAccountJoin.account_id == account.id).first()
-
-                    if tenant_account_join:
-                        account.current_tenant_id = tenant_account_join.tenant_id
-                        session['workspace_id'] = account.current_tenant_id
-                else:
-                    account.current_tenant_id = workspace_id
-            else:
-                tenant_account_join = db.session.query(TenantAccountJoin).filter(
-                    TenantAccountJoin.account_id == account.id).first()
-                if tenant_account_join:
-                    account.current_tenant_id = tenant_account_join.tenant_id
-                    session['workspace_id'] = account.current_tenant_id
-
-            # Log in the user with the updated user_id
-            flask_login.login_user(account, remember=True)
-
-        return account
+        return AccountService.load_user(user_id)
     else:
         return None
 
-
 @login_manager.unauthorized_handler
 def unauthorized_handler():
     """Handle unauthorized requests."""
@@ -145,13 +123,17 @@ def register_blueprints(app):
     from controllers.web import bp as web_bp
     from controllers.console import bp as console_app_bp
 
+    CORS(service_api_bp,
+         allow_headers=['Content-Type', 'Authorization', 'X-App-Code'],
+         methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH']
+         )
     app.register_blueprint(service_api_bp)
 
     CORS(web_bp,
          resources={
              r"/*": {"origins": app.config['WEB_API_CORS_ALLOW_ORIGINS']}},
          supports_credentials=True,
-         allow_headers=['Content-Type', 'Authorization'],
+         allow_headers=['Content-Type', 'Authorization', 'X-App-Code'],
          methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'],
          expose_headers=['X-Version', 'X-Env']
          )
@@ -182,6 +164,7 @@ if app.config['TESTING']:
 @app.after_request
 def after_request(response):
     """Add Version headers to the response."""
+    response.set_cookie('remember_token', '', expires=0)
     response.headers.add('X-Version', app.config['CURRENT_VERSION'])
     response.headers.add('X-Env', app.config['DEPLOY_ENV'])
     return response
@@ -218,5 +201,18 @@ def threads():
     }
 
 
+@app.route('/db-pool-stat')
+def pool_stat():
+    engine = db.engine
+    return {
+        'pool_size': engine.pool.size(),
+        'checked_in_connections': engine.pool.checkedin(),
+        'checked_out_connections': engine.pool.checkedout(),
+        'overflow_connections': engine.pool.overflow(),
+        'connection_timeout': engine.pool.timeout(),
+        'recycle_time': db.engine.pool._recycle
+    }
+
+
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=5001)

api/commands.py

@@ -1,17 +1,37 @@
 import datetime
+import json
+import math
 import random
 import string
+import threading
+import time
+import uuid
 
 import click
+from tqdm import tqdm
+from flask import current_app, Flask
+from langchain.embeddings import OpenAIEmbeddings
+from werkzeug.exceptions import NotFound
 
+from core.embedding.cached_embedding import CacheEmbedding
+from core.index.index import IndexBuilder
+from core.model_providers.model_factory import ModelFactory
+from core.model_providers.models.embedding.openai_embedding import OpenAIEmbedding
+from core.model_providers.models.entity.model_params import ModelType
+from core.model_providers.providers.hosted import hosted_model_providers
+from core.model_providers.providers.openai_provider import OpenAIProvider
 from libs.password import password_pattern, valid_password, hash_password
 from libs.helper import email as email_validate
 from extensions.ext_database import db
-from models.account import InvitationCode
-from models.model import Account
+from libs.rsa import generate_key_pair
+from models.account import InvitationCode, Tenant, TenantAccountJoin
+from models.dataset import Dataset, DatasetQuery, Document, DatasetCollectionBinding
+from models.model import Account, AppModelConfig, App
 import secrets
 import base64
 
+from models.provider import Provider, ProviderType, ProviderQuotaType, ProviderModel
+
 
 @click.command('reset-password', help='Reset the account password.')
 @click.option('--email', prompt=True, help='The email address of the account whose password you need to reset')
@@ -73,6 +93,32 @@ def reset_email(email, new_email, email_confirm):
     click.echo(click.style('Congratulations!, email has been reset.', fg='green'))
 
 
+@click.command('reset-encrypt-key-pair', help='Reset the asymmetric key pair of workspace for encrypt LLM credentials. '
+                                              'After the reset, all LLM credentials will become invalid, '
+                                              'requiring re-entry.'
+                                              'Only support SELF_HOSTED mode.')
+@click.confirmation_option(prompt=click.style('Are you sure you want to reset encrypt key pair?'
+                                              ' this operation cannot be rolled back!', fg='red'))
+def reset_encrypt_key_pair():
+    if current_app.config['EDITION'] != 'SELF_HOSTED':
+        click.echo(click.style('Sorry, only support SELF_HOSTED mode.', fg='red'))
+        return
+
+    tenant = db.session.query(Tenant).first()
+    if not tenant:
+        click.echo(click.style('Sorry, no workspace found. Please enter /install to initialize.', fg='red'))
+        return
+
+    tenant.encrypt_public_key = generate_key_pair(tenant.id)
+
+    db.session.query(Provider).filter(Provider.provider_type == 'custom').delete()
+    db.session.query(ProviderModel).delete()
+    db.session.commit()
+
+    click.echo(click.style('Congratulations! '
+                           'the asymmetric key pair of workspace {} has been reset.'.format(tenant.id), fg='green'))
+
+
 @click.command('generate-invitation-codes', help='Generate invitation codes.')
 @click.option('--batch', help='The batch of invitation codes.')
 @click.option('--count', prompt=True, help='Invitation codes count.')
@@ -130,7 +176,558 @@ def generate_upper_string():
     return result
 
 
+@click.command('recreate-all-dataset-indexes', help='Recreate all dataset indexes.')
+def recreate_all_dataset_indexes():
+    click.echo(click.style('Start recreate all dataset indexes.', fg='green'))
+    recreate_count = 0
+
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
+        except NotFound:
+            break
+
+        page += 1
+        for dataset in datasets:
+            try:
+                click.echo('Recreating dataset index: {}'.format(dataset.id))
+                index = IndexBuilder.get_index(dataset, 'high_quality')
+                if index and index._is_origin():
+                    index.recreate_dataset(dataset)
+                    recreate_count += 1
+                else:
+                    click.echo('passed.')
+            except Exception as e:
+                click.echo(
+                    click.style('Recreate dataset index error: {} {}'.format(e.__class__.__name__, str(e)), fg='red'))
+                continue
+
+    click.echo(click.style('Congratulations! Recreate {} dataset indexes.'.format(recreate_count), fg='green'))
+
+
+@click.command('clean-unused-dataset-indexes', help='Clean unused dataset indexes.')
+def clean_unused_dataset_indexes():
+    click.echo(click.style('Start clean unused dataset indexes.', fg='green'))
+    clean_days = int(current_app.config.get('CLEAN_DAY_SETTING'))
+    start_at = time.perf_counter()
+    thirty_days_ago = datetime.datetime.now() - datetime.timedelta(days=clean_days)
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.created_at < thirty_days_ago) \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
+        except NotFound:
+            break
+        page += 1
+        for dataset in datasets:
+            dataset_query = db.session.query(DatasetQuery).filter(
+                DatasetQuery.created_at > thirty_days_ago,
+                DatasetQuery.dataset_id == dataset.id
+            ).all()
+            if not dataset_query or len(dataset_query) == 0:
+                documents = db.session.query(Document).filter(
+                    Document.dataset_id == dataset.id,
+                    Document.indexing_status == 'completed',
+                    Document.enabled == True,
+                    Document.archived == False,
+                    Document.updated_at > thirty_days_ago
+                ).all()
+                if not documents or len(documents) == 0:
+                    try:
+                        # remove index
+                        vector_index = IndexBuilder.get_index(dataset, 'high_quality')
+                        kw_index = IndexBuilder.get_index(dataset, 'economy')
+                        # delete from vector index
+                        if vector_index:
+                            if dataset.collection_binding_id:
+                                vector_index.delete_by_group_id(dataset.id)
+                            else:
+                                if dataset.collection_binding_id:
+                                    vector_index.delete_by_group_id(dataset.id)
+                                else:
+                                    vector_index.delete()
+                        kw_index.delete()
+                        # update document
+                        update_params = {
+                            Document.enabled: False
+                        }
+
+                        Document.query.filter_by(dataset_id=dataset.id).update(update_params)
+                        db.session.commit()
+                        click.echo(click.style('Cleaned unused dataset {} from db success!'.format(dataset.id),
+                                               fg='green'))
+                    except Exception as e:
+                        click.echo(
+                            click.style('clean dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                        fg='red'))
+    end_at = time.perf_counter()
+    click.echo(click.style('Cleaned unused dataset from db success latency: {}'.format(end_at - start_at), fg='green'))
+
+
+@click.command('sync-anthropic-hosted-providers', help='Sync anthropic hosted providers.')
+def sync_anthropic_hosted_providers():
+    if not hosted_model_providers.anthropic:
+        click.echo(click.style('Anthropic hosted provider is not configured.', fg='red'))
+        return
+
+    click.echo(click.style('Start sync anthropic hosted providers.', fg='green'))
+    count = 0
+
+    new_quota_limit = hosted_model_providers.anthropic.quota_limit
+
+    page = 1
+    while True:
+        try:
+            providers = db.session.query(Provider).filter(
+                Provider.provider_name == 'anthropic',
+                Provider.provider_type == ProviderType.SYSTEM.value,
+                Provider.quota_type == ProviderQuotaType.TRIAL.value,
+                Provider.quota_limit != new_quota_limit
+            ).order_by(Provider.created_at.desc()).paginate(page=page, per_page=100)
+        except NotFound:
+            break
+
+        page += 1
+        for provider in providers:
+            try:
+                click.echo('Syncing tenant anthropic hosted provider: {}, origin: limit {}, used {}'
+                           .format(provider.tenant_id, provider.quota_limit, provider.quota_used))
+                original_quota_limit = provider.quota_limit
+                division = math.ceil(new_quota_limit / 1000)
+
+                provider.quota_limit = new_quota_limit if original_quota_limit == 1000 \
+                    else original_quota_limit * division
+                provider.quota_used = division * provider.quota_used
+                db.session.commit()
+
+                count += 1
+            except Exception as e:
+                click.echo(click.style(
+                    'Sync tenant anthropic hosted provider error: {} {}'.format(e.__class__.__name__, str(e)),
+                    fg='red'))
+                continue
+
+    click.echo(click.style('Congratulations! Synced {} anthropic hosted providers.'.format(count), fg='green'))
+
+
+@click.command('create-qdrant-indexes', help='Create qdrant indexes.')
+def create_qdrant_indexes():
+    click.echo(click.style('Start create qdrant indexes.', fg='green'))
+    create_count = 0
+
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
+        except NotFound:
+            break
+
+        page += 1
+        for dataset in datasets:
+            if dataset.index_struct_dict:
+                if dataset.index_struct_dict['type'] != 'qdrant':
+                    try:
+                        click.echo('Create dataset qdrant index: {}'.format(dataset.id))
+                        try:
+                            embedding_model = ModelFactory.get_embedding_model(
+                                tenant_id=dataset.tenant_id,
+                                model_provider_name=dataset.embedding_model_provider,
+                                model_name=dataset.embedding_model
+                            )
+                        except Exception:
+                            try:
+                                embedding_model = ModelFactory.get_embedding_model(
+                                    tenant_id=dataset.tenant_id
+                                )
+                                dataset.embedding_model = embedding_model.name
+                                dataset.embedding_model_provider = embedding_model.model_provider.provider_name
+                            except Exception:
+                                provider = Provider(
+                                    id='provider_id',
+                                    tenant_id=dataset.tenant_id,
+                                    provider_name='openai',
+                                    provider_type=ProviderType.SYSTEM.value,
+                                    encrypted_config=json.dumps({'openai_api_key': 'TEST'}),
+                                    is_valid=True,
+                                )
+                                model_provider = OpenAIProvider(provider=provider)
+                                embedding_model = OpenAIEmbedding(name="text-embedding-ada-002",
+                                                                  model_provider=model_provider)
+                        embeddings = CacheEmbedding(embedding_model)
+
+                        from core.index.vector_index.qdrant_vector_index import QdrantVectorIndex, QdrantConfig
+
+                        index = QdrantVectorIndex(
+                            dataset=dataset,
+                            config=QdrantConfig(
+                                endpoint=current_app.config.get('QDRANT_URL'),
+                                api_key=current_app.config.get('QDRANT_API_KEY'),
+                                root_path=current_app.root_path
+                            ),
+                            embeddings=embeddings
+                        )
+                        if index:
+                            index.create_qdrant_dataset(dataset)
+                            index_struct = {
+                                "type": 'qdrant',
+                                "vector_store": {
+                                    "class_prefix": dataset.index_struct_dict['vector_store']['class_prefix']}
+                            }
+                            dataset.index_struct = json.dumps(index_struct)
+                            db.session.commit()
+                            create_count += 1
+                        else:
+                            click.echo('passed.')
+                    except Exception as e:
+                        click.echo(
+                            click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                        fg='red'))
+                        continue
+
+    click.echo(click.style('Congratulations! Create {} dataset indexes.'.format(create_count), fg='green'))
+
+
+@click.command('update-qdrant-indexes', help='Update qdrant indexes.')
+def update_qdrant_indexes():
+    click.echo(click.style('Start Update qdrant indexes.', fg='green'))
+    create_count = 0
+
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
+        except NotFound:
+            break
+
+        page += 1
+        for dataset in datasets:
+            if dataset.index_struct_dict:
+                if dataset.index_struct_dict['type'] != 'qdrant':
+                    try:
+                        click.echo('Update dataset qdrant index: {}'.format(dataset.id))
+                        try:
+                            embedding_model = ModelFactory.get_embedding_model(
+                                tenant_id=dataset.tenant_id,
+                                model_provider_name=dataset.embedding_model_provider,
+                                model_name=dataset.embedding_model
+                            )
+                        except Exception:
+                            provider = Provider(
+                                id='provider_id',
+                                tenant_id=dataset.tenant_id,
+                                provider_name='openai',
+                                provider_type=ProviderType.CUSTOM.value,
+                                encrypted_config=json.dumps({'openai_api_key': 'TEST'}),
+                                is_valid=True,
+                            )
+                            model_provider = OpenAIProvider(provider=provider)
+                            embedding_model = OpenAIEmbedding(name="text-embedding-ada-002",
+                                                              model_provider=model_provider)
+                        embeddings = CacheEmbedding(embedding_model)
+
+                        from core.index.vector_index.qdrant_vector_index import QdrantVectorIndex, QdrantConfig
+
+                        index = QdrantVectorIndex(
+                            dataset=dataset,
+                            config=QdrantConfig(
+                                endpoint=current_app.config.get('QDRANT_URL'),
+                                api_key=current_app.config.get('QDRANT_API_KEY'),
+                                root_path=current_app.root_path
+                            ),
+                            embeddings=embeddings
+                        )
+                        if index:
+                            index.update_qdrant_dataset(dataset)
+                            create_count += 1
+                        else:
+                            click.echo('passed.')
+                    except Exception as e:
+                        click.echo(
+                            click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                        fg='red'))
+                        continue
+
+    click.echo(click.style('Congratulations! Update {} dataset indexes.'.format(create_count), fg='green'))
+
+
+@click.command('normalization-collections', help='restore all collections in one')
+def normalization_collections():
+    click.echo(click.style('Start normalization collections.', fg='green'))
+    normalization_count = []
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=100)
+        except NotFound:
+            break
+        datasets_result = datasets.items
+        page += 1
+        for i in range(0, len(datasets_result), 5):
+            threads = []
+            sub_datasets = datasets_result[i:i + 5]
+            for dataset in sub_datasets:
+                document_format_thread = threading.Thread(target=deal_dataset_vector, kwargs={
+                    'flask_app': current_app._get_current_object(),
+                    'dataset': dataset,
+                    'normalization_count': normalization_count
+                })
+                threads.append(document_format_thread)
+                document_format_thread.start()
+            for thread in threads:
+                thread.join()
+
+    click.echo(click.style('Congratulations! restore {} dataset indexes.'.format(len(normalization_count)), fg='green'))
+
+
+def deal_dataset_vector(flask_app: Flask, dataset: Dataset, normalization_count: list):
+    with flask_app.app_context():
+        try:
+            click.echo('restore dataset index: {}'.format(dataset.id))
+            try:
+                embedding_model = ModelFactory.get_embedding_model(
+                    tenant_id=dataset.tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except Exception:
+                provider = Provider(
+                    id='provider_id',
+                    tenant_id=dataset.tenant_id,
+                    provider_name='openai',
+                    provider_type=ProviderType.CUSTOM.value,
+                    encrypted_config=json.dumps({'openai_api_key': 'TEST'}),
+                    is_valid=True,
+                )
+                model_provider = OpenAIProvider(provider=provider)
+                embedding_model = OpenAIEmbedding(name="text-embedding-ada-002",
+                                                  model_provider=model_provider)
+            embeddings = CacheEmbedding(embedding_model)
+            dataset_collection_binding = db.session.query(DatasetCollectionBinding). \
+                filter(DatasetCollectionBinding.provider_name == embedding_model.model_provider.provider_name,
+                       DatasetCollectionBinding.model_name == embedding_model.name). \
+                order_by(DatasetCollectionBinding.created_at). \
+                first()
+
+            if not dataset_collection_binding:
+                dataset_collection_binding = DatasetCollectionBinding(
+                    provider_name=embedding_model.model_provider.provider_name,
+                    model_name=embedding_model.name,
+                    collection_name="Vector_index_" + str(uuid.uuid4()).replace("-", "_") + '_Node'
+                )
+                db.session.add(dataset_collection_binding)
+                db.session.commit()
+
+            from core.index.vector_index.qdrant_vector_index import QdrantVectorIndex, QdrantConfig
+
+            index = QdrantVectorIndex(
+                dataset=dataset,
+                config=QdrantConfig(
+                    endpoint=current_app.config.get('QDRANT_URL'),
+                    api_key=current_app.config.get('QDRANT_API_KEY'),
+                    root_path=current_app.root_path
+                ),
+                embeddings=embeddings
+            )
+            if index:
+                # index.delete_by_group_id(dataset.id)
+                index.restore_dataset_in_one(dataset, dataset_collection_binding)
+            else:
+                click.echo('passed.')
+            normalization_count.append(1)
+        except Exception as e:
+            click.echo(
+                click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                            fg='red'))
+
+
+@click.command('update_app_model_configs', help='Migrate data to support paragraph variable.')
+@click.option("--batch-size", default=500, help="Number of records to migrate in each batch.")
+def update_app_model_configs(batch_size):
+    pre_prompt_template = '{{default_input}}'
+    user_input_form_template = {
+        "en-US": [
+            {
+                "paragraph": {
+                    "label": "Query",
+                    "variable": "default_input",
+                    "required": False,
+                    "default": ""
+                }
+            }
+        ],
+        "zh-Hans": [
+            {
+                "paragraph": {
+                    "label": "查询内容",
+                    "variable": "default_input",
+                    "required": False,
+                    "default": ""
+                }
+            }
+        ]
+    }
+
+    click.secho("Start migrate old data that the text generator can support paragraph variable.", fg='green')
+
+    total_records = db.session.query(AppModelConfig) \
+        .join(App, App.app_model_config_id == AppModelConfig.id) \
+        .filter(App.mode == 'completion') \
+        .count()
+
+    if total_records == 0:
+        click.secho("No data to migrate.", fg='green')
+        return
+
+    num_batches = (total_records + batch_size - 1) // batch_size
+
+    with tqdm(total=total_records, desc="Migrating Data") as pbar:
+        for i in range(num_batches):
+            offset = i * batch_size
+            limit = min(batch_size, total_records - offset)
+
+            click.secho(f"Fetching batch {i + 1}/{num_batches} from source database...", fg='green')
+
+            data_batch = db.session.query(AppModelConfig) \
+                .join(App, App.app_model_config_id == AppModelConfig.id) \
+                .filter(App.mode == 'completion') \
+                .order_by(App.created_at) \
+                .offset(offset).limit(limit).all()
+
+            if not data_batch:
+                click.secho("No more data to migrate.", fg='green')
+                break
+
+            try:
+                click.secho(f"Migrating {len(data_batch)} records...", fg='green')
+                for data in data_batch:
+                    # click.secho(f"Migrating data {data.id}, pre_prompt: {data.pre_prompt}, user_input_form: {data.user_input_form}", fg='green')
+
+                    if data.pre_prompt is None:
+                        data.pre_prompt = pre_prompt_template
+                    else:
+                        if pre_prompt_template in data.pre_prompt:
+                            continue
+                        data.pre_prompt += pre_prompt_template
+
+                    app_data = db.session.query(App) \
+                        .filter(App.id == data.app_id) \
+                        .one()
+
+                    account_data = db.session.query(Account) \
+                        .join(TenantAccountJoin, Account.id == TenantAccountJoin.account_id) \
+                        .filter(TenantAccountJoin.role == 'owner') \
+                        .filter(TenantAccountJoin.tenant_id == app_data.tenant_id) \
+                        .one_or_none()
+
+                    if not account_data:
+                        continue
+
+                    if data.user_input_form is None or data.user_input_form == 'null':
+                        data.user_input_form = json.dumps(user_input_form_template[account_data.interface_language])
+                    else:
+                        raw_json_data = json.loads(data.user_input_form)
+                        raw_json_data.append(user_input_form_template[account_data.interface_language][0])
+                        data.user_input_form = json.dumps(raw_json_data)
+
+                    # click.secho(f"Updated data {data.id}, pre_prompt: {data.pre_prompt}, user_input_form: {data.user_input_form}", fg='green')
+
+                db.session.commit()
+
+            except Exception as e:
+                click.secho(f"Error while migrating data: {e}, app_id: {data.app_id}, app_model_config_id: {data.id}",
+                            fg='red')
+                continue
+
+            click.secho(f"Successfully migrated batch {i + 1}/{num_batches}.", fg='green')
+
+            pbar.update(len(data_batch))
+
+@click.command('migrate_default_input_to_dataset_query_variable')
+@click.option("--batch-size", default=500, help="Number of records to migrate in each batch.")
+def migrate_default_input_to_dataset_query_variable(batch_size):
+
+    click.secho("Starting...", fg='green')
+
+    total_records = db.session.query(AppModelConfig) \
+        .join(App, App.app_model_config_id == AppModelConfig.id) \
+        .filter(App.mode == 'completion') \
+        .filter(AppModelConfig.dataset_query_variable == None) \
+        .count()
+    
+    if total_records == 0:
+        click.secho("No data to migrate.", fg='green')
+        return
+
+    num_batches = (total_records + batch_size - 1) // batch_size
+    
+    with tqdm(total=total_records, desc="Migrating Data") as pbar:
+        for i in range(num_batches):
+            offset = i * batch_size
+            limit = min(batch_size, total_records - offset)
+
+            click.secho(f"Fetching batch {i + 1}/{num_batches} from source database...", fg='green')
+
+            data_batch = db.session.query(AppModelConfig) \
+                .join(App, App.app_model_config_id == AppModelConfig.id) \
+                .filter(App.mode == 'completion') \
+                .filter(AppModelConfig.dataset_query_variable == None) \
+                .order_by(App.created_at) \
+                .offset(offset).limit(limit).all()
+
+            if not data_batch:
+                click.secho("No more data to migrate.", fg='green')
+                break
+
+            try:
+                click.secho(f"Migrating {len(data_batch)} records...", fg='green')
+                for data in data_batch:
+                    config = AppModelConfig.to_dict(data)
+
+                    tools = config["agent_mode"]["tools"]
+                    dataset_exists = "dataset" in str(tools)
+                    if not dataset_exists:
+                        continue
+
+                    user_input_form = config.get("user_input_form", [])
+                    for form in user_input_form:
+                        paragraph = form.get('paragraph')
+                        if paragraph \
+                            and paragraph.get('variable') == 'query':
+                                data.dataset_query_variable = 'query'
+                                break
+                        
+                        if paragraph \
+                            and paragraph.get('variable') == 'default_input':
+                                data.dataset_query_variable = 'default_input'
+                                break
+
+                db.session.commit()
+
+            except Exception as e:
+                click.secho(f"Error while migrating data: {e}, app_id: {data.app_id}, app_model_config_id: {data.id}",
+                            fg='red')
+                continue
+            
+            click.secho(f"Successfully migrated batch {i + 1}/{num_batches}.", fg='green')
+
+            pbar.update(len(data_batch))
+
+
 def register_commands(app):
     app.cli.add_command(reset_password)
     app.cli.add_command(reset_email)
     app.cli.add_command(generate_invitation_codes)
+    app.cli.add_command(reset_encrypt_key_pair)
+    app.cli.add_command(recreate_all_dataset_indexes)
+    app.cli.add_command(sync_anthropic_hosted_providers)
+    app.cli.add_command(clean_unused_dataset_indexes)
+    app.cli.add_command(create_qdrant_indexes)
+    app.cli.add_command(update_qdrant_indexes)
+    app.cli.add_command(update_app_model_configs)
+    app.cli.add_command(normalization_collections)
+    app.cli.add_command(migrate_default_input_to_dataset_query_variable)

api/config.py

@@ -10,9 +10,6 @@ from extensions.ext_redis import redis_client
 dotenv.load_dotenv()
 
 DEFAULTS = {
-    'COOKIE_HTTPONLY': 'True',
-    'COOKIE_SECURE': 'True',
-    'COOKIE_SAMESITE': 'None',
     'DB_USERNAME': 'postgres',
     'DB_PASSWORD': '',
     'DB_HOST': 'localhost',
@@ -22,32 +19,44 @@ DEFAULTS = {
     'REDIS_PORT': '6379',
     'REDIS_DB': '0',
     'REDIS_USE_SSL': 'False',
-    'SESSION_REDIS_HOST': 'localhost',
-    'SESSION_REDIS_PORT': '6379',
-    'SESSION_REDIS_DB': '2',
-    'SESSION_REDIS_USE_SSL': 'False',
     'OAUTH_REDIRECT_PATH': '/console/api/oauth/authorize',
     'OAUTH_REDIRECT_INDEX_PATH': '/',
-    'CONSOLE_URL': 'https://cloud.dify.ai',
-    'API_URL': 'https://api.dify.ai',
-    'APP_URL': 'https://udify.app',
+    'CONSOLE_WEB_URL': 'https://cloud.dify.ai',
+    'CONSOLE_API_URL': 'https://cloud.dify.ai',
+    'SERVICE_API_URL': 'https://api.dify.ai',
+    'APP_WEB_URL': 'https://udify.app',
+    'APP_API_URL': 'https://udify.app',
     'STORAGE_TYPE': 'local',
     'STORAGE_LOCAL_PATH': 'storage',
     'CHECK_UPDATE_URL': 'https://updates.dify.ai',
-    'SESSION_TYPE': 'sqlalchemy',
-    'SESSION_PERMANENT': 'True',
-    'SESSION_USE_SIGNER': 'True',
     'DEPLOY_ENV': 'PRODUCTION',
     'SQLALCHEMY_POOL_SIZE': 30,
+    'SQLALCHEMY_POOL_RECYCLE': 3600,
     'SQLALCHEMY_ECHO': 'False',
     'SENTRY_TRACES_SAMPLE_RATE': 1.0,
     'SENTRY_PROFILES_SAMPLE_RATE': 1.0,
     'WEAVIATE_GRPC_ENABLED': 'True',
+    'WEAVIATE_BATCH_SIZE': 100,
     'CELERY_BACKEND': 'database',
-    'PDF_PREVIEW': 'True',
     'LOG_LEVEL': 'INFO',
-    'DISABLE_PROVIDER_CONFIG_VALIDATION': 'False',
-    'DEFAULT_LLM_PROVIDER': 'openai'
+    'HOSTED_OPENAI_QUOTA_LIMIT': 200,
+    'HOSTED_OPENAI_ENABLED': 'False',
+    'HOSTED_OPENAI_PAID_ENABLED': 'False',
+    'HOSTED_OPENAI_PAID_INCREASE_QUOTA': 1,
+    'HOSTED_AZURE_OPENAI_ENABLED': 'False',
+    'HOSTED_AZURE_OPENAI_QUOTA_LIMIT': 200,
+    'HOSTED_ANTHROPIC_QUOTA_LIMIT': 600000,
+    'HOSTED_ANTHROPIC_ENABLED': 'False',
+    'HOSTED_ANTHROPIC_PAID_ENABLED': 'False',
+    'HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA': 1000000,
+    'HOSTED_ANTHROPIC_PAID_MIN_QUANTITY': 20,
+    'HOSTED_ANTHROPIC_PAID_MAX_QUANTITY': 100,
+    'HOSTED_MODERATION_ENABLED': 'False',
+    'HOSTED_MODERATION_PROVIDERS': '',
+    'TENANT_DOCUMENT_COUNT': 100,
+    'CLEAN_DAY_SETTING': 30,
+    'UPLOAD_FILE_SIZE_LIMIT': 15,
+    'UPLOAD_FILE_BATCH_LIMIT': 5,
 }
 
 
@@ -75,16 +84,20 @@ class Config:
 
     def __init__(self):
         # app settings
+        self.CONSOLE_API_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_API_URL')
+        self.CONSOLE_WEB_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_WEB_URL')
+        self.SERVICE_API_URL = get_env('API_URL') if get_env('API_URL') else get_env('SERVICE_API_URL')
+        self.APP_WEB_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_WEB_URL')
+        self.APP_API_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_API_URL')
         self.CONSOLE_URL = get_env('CONSOLE_URL')
         self.API_URL = get_env('API_URL')
         self.APP_URL = get_env('APP_URL')
-        self.CURRENT_VERSION = "0.3.0"
+        self.CURRENT_VERSION = "0.3.25"
         self.COMMIT_SHA = get_env('COMMIT_SHA')
         self.EDITION = "SELF_HOSTED"
         self.DEPLOY_ENV = get_env('DEPLOY_ENV')
         self.TESTING = False
         self.LOG_LEVEL = get_env('LOG_LEVEL')
-        self.PDF_PREVIEW = get_bool_env('PDF_PREVIEW')
 
         # Your App secret key will be used for securely signing the session cookie
         # Make sure you are changing this key for your deployment with a strong key.
@@ -92,20 +105,6 @@ class Config:
         # Alternatively you can set it with `SECRET_KEY` environment variable.
         self.SECRET_KEY = get_env('SECRET_KEY')
 
-        # cookie settings
-        self.REMEMBER_COOKIE_HTTPONLY = get_bool_env('COOKIE_HTTPONLY')
-        self.SESSION_COOKIE_HTTPONLY = get_bool_env('COOKIE_HTTPONLY')
-        self.REMEMBER_COOKIE_SAMESITE = get_env('COOKIE_SAMESITE')
-        self.SESSION_COOKIE_SAMESITE = get_env('COOKIE_SAMESITE')
-        self.REMEMBER_COOKIE_SECURE = get_bool_env('COOKIE_SECURE')
-        self.SESSION_COOKIE_SECURE = get_bool_env('COOKIE_SECURE')
-        self.PERMANENT_SESSION_LIFETIME = timedelta(days=7)
-
-        # session settings, only support sqlalchemy, redis
-        self.SESSION_TYPE = get_env('SESSION_TYPE')
-        self.SESSION_PERMANENT = get_bool_env('SESSION_PERMANENT')
-        self.SESSION_USE_SIGNER = get_bool_env('SESSION_USE_SIGNER')
-
         # redis settings
         self.REDIS_HOST = get_env('REDIS_HOST')
         self.REDIS_PORT = get_env('REDIS_PORT')
@@ -114,14 +113,6 @@ class Config:
         self.REDIS_DB = get_env('REDIS_DB')
         self.REDIS_USE_SSL = get_bool_env('REDIS_USE_SSL')
 
-        # session redis settings
-        self.SESSION_REDIS_HOST = get_env('SESSION_REDIS_HOST')
-        self.SESSION_REDIS_PORT = get_env('SESSION_REDIS_PORT')
-        self.SESSION_REDIS_USERNAME = get_env('SESSION_REDIS_USERNAME')
-        self.SESSION_REDIS_PASSWORD = get_env('SESSION_REDIS_PASSWORD')
-        self.SESSION_REDIS_DB = get_env('SESSION_REDIS_DB')
-        self.SESSION_REDIS_USE_SSL = get_bool_env('SESSION_REDIS_USE_SSL')
-
         # storage settings
         self.STORAGE_TYPE = get_env('STORAGE_TYPE')
         self.STORAGE_LOCAL_PATH = get_env('STORAGE_LOCAL_PATH')
@@ -138,6 +129,7 @@ class Config:
         self.WEAVIATE_ENDPOINT = get_env('WEAVIATE_ENDPOINT')
         self.WEAVIATE_API_KEY = get_env('WEAVIATE_API_KEY')
         self.WEAVIATE_GRPC_ENABLED = get_bool_env('WEAVIATE_GRPC_ENABLED')
+        self.WEAVIATE_BATCH_SIZE = int(get_env('WEAVIATE_BATCH_SIZE'))
 
         # qdrant settings
         self.QDRANT_URL = get_env('QDRANT_URL')
@@ -145,10 +137,15 @@ class Config:
 
         # cors settings
         self.CONSOLE_CORS_ALLOW_ORIGINS = get_cors_allow_origins(
-            'CONSOLE_CORS_ALLOW_ORIGINS', self.CONSOLE_URL)
+            'CONSOLE_CORS_ALLOW_ORIGINS', self.CONSOLE_WEB_URL)
         self.WEB_API_CORS_ALLOW_ORIGINS = get_cors_allow_origins(
             'WEB_API_CORS_ALLOW_ORIGINS', '*')
 
+        # mail settings
+        self.MAIL_TYPE = get_env('MAIL_TYPE')
+        self.MAIL_DEFAULT_SEND_FROM = get_env('MAIL_DEFAULT_SEND_FROM')
+        self.RESEND_API_KEY = get_env('RESEND_API_KEY')
+
         # sentry settings
         self.SENTRY_DSN = get_env('SENTRY_DSN')
         self.SENTRY_TRACES_SAMPLE_RATE = float(get_env('SENTRY_TRACES_SAMPLE_RATE'))
@@ -164,7 +161,10 @@ class Config:
         }
 
         self.SQLALCHEMY_DATABASE_URI = f"postgresql://{db_credentials['DB_USERNAME']}:{db_credentials['DB_PASSWORD']}@{db_credentials['DB_HOST']}:{db_credentials['DB_PORT']}/{db_credentials['DB_DATABASE']}"
-        self.SQLALCHEMY_ENGINE_OPTIONS = {'pool_size': int(get_env('SQLALCHEMY_POOL_SIZE'))}
+        self.SQLALCHEMY_ENGINE_OPTIONS = {
+            'pool_size': int(get_env('SQLALCHEMY_POOL_SIZE')),
+            'pool_recycle': int(get_env('SQLALCHEMY_POOL_RECYCLE'))
+        }
 
         self.SQLALCHEMY_ECHO = get_bool_env('SQLALCHEMY_ECHO')
 
@@ -176,15 +176,50 @@ class Config:
         self.BROKER_USE_SSL = self.CELERY_BROKER_URL.startswith('rediss://')
 
         # hosted provider credentials
-        self.OPENAI_API_KEY = get_env('OPENAI_API_KEY')
+        self.HOSTED_OPENAI_ENABLED = get_bool_env('HOSTED_OPENAI_ENABLED')
+        self.HOSTED_OPENAI_API_KEY = get_env('HOSTED_OPENAI_API_KEY')
+        self.HOSTED_OPENAI_API_BASE = get_env('HOSTED_OPENAI_API_BASE')
+        self.HOSTED_OPENAI_API_ORGANIZATION = get_env('HOSTED_OPENAI_API_ORGANIZATION')
+        self.HOSTED_OPENAI_QUOTA_LIMIT = int(get_env('HOSTED_OPENAI_QUOTA_LIMIT'))
+        self.HOSTED_OPENAI_PAID_ENABLED = get_bool_env('HOSTED_OPENAI_PAID_ENABLED')
+        self.HOSTED_OPENAI_PAID_STRIPE_PRICE_ID = get_env('HOSTED_OPENAI_PAID_STRIPE_PRICE_ID')
+        self.HOSTED_OPENAI_PAID_INCREASE_QUOTA = int(get_env('HOSTED_OPENAI_PAID_INCREASE_QUOTA'))
 
-        # By default it is False
-        # You could disable it for compatibility with certain OpenAPI providers
-        self.DISABLE_PROVIDER_CONFIG_VALIDATION = get_bool_env('DISABLE_PROVIDER_CONFIG_VALIDATION')
+        self.HOSTED_AZURE_OPENAI_ENABLED = get_bool_env('HOSTED_AZURE_OPENAI_ENABLED')
+        self.HOSTED_AZURE_OPENAI_API_KEY = get_env('HOSTED_AZURE_OPENAI_API_KEY')
+        self.HOSTED_AZURE_OPENAI_API_BASE = get_env('HOSTED_AZURE_OPENAI_API_BASE')
+        self.HOSTED_AZURE_OPENAI_QUOTA_LIMIT = int(get_env('HOSTED_AZURE_OPENAI_QUOTA_LIMIT'))
+
+        self.HOSTED_ANTHROPIC_ENABLED = get_bool_env('HOSTED_ANTHROPIC_ENABLED')
+        self.HOSTED_ANTHROPIC_API_BASE = get_env('HOSTED_ANTHROPIC_API_BASE')
+        self.HOSTED_ANTHROPIC_API_KEY = get_env('HOSTED_ANTHROPIC_API_KEY')
+        self.HOSTED_ANTHROPIC_QUOTA_LIMIT = int(get_env('HOSTED_ANTHROPIC_QUOTA_LIMIT'))
+        self.HOSTED_ANTHROPIC_PAID_ENABLED = get_bool_env('HOSTED_ANTHROPIC_PAID_ENABLED')
+        self.HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID = get_env('HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID')
+        self.HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA = int(get_env('HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA'))
+        self.HOSTED_ANTHROPIC_PAID_MIN_QUANTITY = int(get_env('HOSTED_ANTHROPIC_PAID_MIN_QUANTITY'))
+        self.HOSTED_ANTHROPIC_PAID_MAX_QUANTITY = int(get_env('HOSTED_ANTHROPIC_PAID_MAX_QUANTITY'))
+
+        self.HOSTED_MODERATION_ENABLED = get_bool_env('HOSTED_MODERATION_ENABLED')
+        self.HOSTED_MODERATION_PROVIDERS = get_env('HOSTED_MODERATION_PROVIDERS')
+
+        self.STRIPE_API_KEY = get_env('STRIPE_API_KEY')
+        self.STRIPE_WEBHOOK_SECRET = get_env('STRIPE_WEBHOOK_SECRET')
+
+        # notion import setting
+        self.NOTION_CLIENT_ID = get_env('NOTION_CLIENT_ID')
+        self.NOTION_CLIENT_SECRET = get_env('NOTION_CLIENT_SECRET')
+        self.NOTION_INTEGRATION_TYPE = get_env('NOTION_INTEGRATION_TYPE')
+        self.NOTION_INTERNAL_SECRET = get_env('NOTION_INTERNAL_SECRET')
+        self.NOTION_INTEGRATION_TOKEN = get_env('NOTION_INTEGRATION_TOKEN')
+
+        self.TENANT_DOCUMENT_COUNT = get_env('TENANT_DOCUMENT_COUNT')
+        self.CLEAN_DAY_SETTING = get_env('CLEAN_DAY_SETTING')
+
+        # uploading settings
+        self.UPLOAD_FILE_SIZE_LIMIT = int(get_env('UPLOAD_FILE_SIZE_LIMIT'))
+        self.UPLOAD_FILE_BATCH_LIMIT = int(get_env('UPLOAD_FILE_BATCH_LIMIT'))
 
-        # For temp use only
-        # set default LLM provider, default is 'openai', support `azure_openai`
-        self.DEFAULT_LLM_PROVIDER = get_env('DEFAULT_LLM_PROVIDER')
 
 class CloudEditionConfig(Config):
 

api/constants/model_template.py

@@ -16,7 +16,7 @@ model_templates = {
         },
         'model_config': {
             'provider': 'openai',
-            'model_id': 'text-davinci-003',
+            'model_id': 'gpt-3.5-turbo-instruct',
             'configs': {
                 'prompt_template': '',
                 'prompt_variables': [],
@@ -30,7 +30,7 @@ model_templates = {
             },
             'model': json.dumps({
                 "provider": "openai",
-                "name": "text-davinci-003",
+                "name": "gpt-3.5-turbo-instruct",
                 "completion_params": {
                     "max_tokens": 512,
                     "temperature": 1,
@@ -38,7 +38,18 @@ model_templates = {
                     "presence_penalty": 0,
                     "frequency_penalty": 0
                 }
-            })
+            }),
+            'user_input_form': json.dumps([
+                {
+                    "paragraph": {
+                        "label": "Query",
+                        "variable": "query",
+                        "required": True,
+                        "default": ""
+                    }
+                }
+            ]),
+            'pre_prompt': '{{query}}'
         }
     },
 
@@ -93,7 +104,7 @@ demo_model_templates = {
             'mode': 'completion',
             'model_config': AppModelConfig(
                 provider='openai',
-                model_id='text-davinci-003',
+                model_id='gpt-3.5-turbo-instruct',
                 configs={
                     'prompt_template': "Please translate the following text into {{target_language}}:\n",
                     'prompt_variables': [
@@ -129,7 +140,7 @@ demo_model_templates = {
                 pre_prompt="Please translate the following text into {{target_language}}:\n",
                 model=json.dumps({
                     "provider": "openai",
-                    "name": "text-davinci-003",
+                    "name": "gpt-3.5-turbo-instruct",
                     "completion_params": {
                         "max_tokens": 1000,
                         "temperature": 0,
@@ -211,7 +222,7 @@ demo_model_templates = {
             'mode': 'completion',
             'model_config': AppModelConfig(
                 provider='openai',
-                model_id='text-davinci-003',
+                model_id='gpt-3.5-turbo-instruct',
                 configs={
                     'prompt_template': "请将以下文本翻译为{{target_language}}:\n",
                     'prompt_variables': [
@@ -247,7 +258,7 @@ demo_model_templates = {
                 pre_prompt="请将以下文本翻译为{{target_language}}:\n",
                 model=json.dumps({
                     "provider": "openai",
-                    "name": "text-davinci-003",
+                    "name": "gpt-3.5-turbo-instruct",
                     "completion_params": {
                         "max_tokens": 1000,
                         "temperature": 0,

api/controllers/console/__init__.py

@@ -9,16 +9,22 @@ api = ExternalApi(bp)
 from . import setup, version, apikey, admin
 
 # Import app controllers
-from .app import app, site, completion, model_config, statistic, conversation, message
+from .app import app, site, completion, model_config, statistic, conversation, message, generator, audio
 
 # Import auth controllers
-from .auth import login, oauth
+from .auth import login, oauth, data_source_oauth, activate
 
 # Import datasets controllers
-from .datasets import datasets, datasets_document, datasets_segments, file, hit_testing
+from .datasets import datasets, datasets_document, datasets_segments, file, hit_testing, data_source
 
 # Import workspace controllers
-from .workspace import workspace, members, providers, account
+from .workspace import workspace, members, providers, model_providers, account, tool_providers, models
 
 # Import explore controllers
-from .explore import installed_app, recommended_app, completion, conversation, message, parameter, saved_message
+from .explore import installed_app, recommended_app, completion, conversation, message, parameter, saved_message, audio
+
+# Import universal chat controllers
+from .universal_chat import chat, conversation, message, parameter, audio
+
+# Import webhook controllers
+from .webhook import stripe

api/controllers/console/admin.py

@@ -8,6 +8,7 @@ from werkzeug.exceptions import NotFound, Unauthorized
 from controllers.console import api
 from controllers.console.wraps import only_edition_cloud
 from extensions.ext_database import db
+from libs.helper import supported_language
 from models.model import RecommendedApp, App, InstalledApp
 
 
@@ -47,15 +48,14 @@ class InsertExploreAppListApi(Resource):
         parser.add_argument('desc', type=str, location='json')
         parser.add_argument('copyright', type=str, location='json')
         parser.add_argument('privacy_policy', type=str, location='json')
-        parser.add_argument('language', type=str, required=True, nullable=False, choices=['en-US', 'zh-Hans'],
-                            location='json')
+        parser.add_argument('language', type=supported_language, required=True, nullable=False, location='json')
         parser.add_argument('category', type=str, required=True, nullable=False, location='json')
         parser.add_argument('position', type=int, required=True, nullable=False, location='json')
         args = parser.parse_args()
 
         app = App.query.filter(App.id == args['app_id']).first()
         if not app:
-            raise NotFound('App not found')
+            raise NotFound(f'App \'{args["app_id"]}\' is not found')
 
         site = app.site
         if not site:
@@ -63,10 +63,12 @@ class InsertExploreAppListApi(Resource):
             copy_right = args['copyright'] if args['copyright'] else ''
             privacy_policy = args['privacy_policy'] if args['privacy_policy'] else ''
         else:
-            desc = site.description if (site.description if not args['desc'] else args['desc']) else ''
-            copy_right = site.copyright if (site.copyright if not args['copyright'] else args['copyright']) else ''
-            privacy_policy = site.privacy_policy \
-                if (site.privacy_policy if not args['privacy_policy'] else args['privacy_policy']) else ''
+            desc = site.description if site.description else \
+                args['desc'] if args['desc'] else ''
+            copy_right = site.copyright if site.copyright else \
+                args['copyright'] if args['copyright'] else ''
+            privacy_policy = site.privacy_policy if site.privacy_policy else \
+                args['privacy_policy'] if args['privacy_policy']  else ''
 
         recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == args['app_id']).first()
 

api/controllers/console/apikey.py

@@ -1,4 +1,5 @@
-from flask_login import login_required, current_user
+from flask_login import current_user
+from libs.login import login_required
 import flask_restful
 from flask_restful import Resource, fields, marshal_with
 from werkzeug.exceptions import Forbidden
@@ -80,6 +81,7 @@ class BaseApiKeyListResource(Resource):
         key = ApiToken.generate_api_key(self.token_prefix, 24)
         api_token = ApiToken()
         setattr(api_token, self.resource_id_field, resource_id)
+        api_token.tenant_id = current_user.current_tenant_id
         api_token.token = key
         api_token.type = self.resource_type
         db.session.add(api_token)

api/controllers/console/app/app.py

@@ -1,54 +1,28 @@
 # -*- coding:utf-8 -*-
 import json
+import logging
 from datetime import datetime
 
-import flask
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, fields, marshal_with, abort, inputs
-from werkzeug.exceptions import Unauthorized, Forbidden
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with, abort, inputs
+from werkzeug.exceptions import Forbidden
 
 from constants.model_template import model_templates, demo_model_templates
 from controllers.console import api
-from controllers.console.app.error import AppNotFoundError, ProviderNotInitializeError, ProviderQuotaExceededError, \
-    CompletionRequestError, ProviderModelCurrentlyNotSupportError
+from controllers.console.app.error import AppNotFoundError, ProviderNotInitializeError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.generator.llm_generator import LLMGenerator
-from core.llm.error import ProviderTokenNotInitError, QuotaExceededError, LLMBadRequestError, LLMAPIConnectionError, \
-    LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError, ModelCurrentlyNotSupportError
+from core.model_providers.error import ProviderTokenNotInitError, LLMBadRequestError
+from core.model_providers.model_factory import ModelFactory
+from core.model_providers.model_provider_factory import ModelProviderFactory
 from events.app_event import app_was_created, app_was_deleted
-from libs.helper import TimestampField
+from fields.app_fields import app_pagination_fields, app_detail_fields, template_list_fields, \
+    app_detail_fields_with_site
 from extensions.ext_database import db
-from models.model import App, AppModelConfig, Site, InstalledApp
-from services.account_service import TenantService
+from models.model import App, AppModelConfig, Site
 from services.app_model_config_service import AppModelConfigService
 
-model_config_fields = {
-    'opening_statement': fields.String,
-    'suggested_questions': fields.Raw(attribute='suggested_questions_list'),
-    'suggested_questions_after_answer': fields.Raw(attribute='suggested_questions_after_answer_dict'),
-    'more_like_this': fields.Raw(attribute='more_like_this_dict'),
-    'model': fields.Raw(attribute='model_dict'),
-    'user_input_form': fields.Raw(attribute='user_input_form_list'),
-    'pre_prompt': fields.String,
-    'agent_mode': fields.Raw(attribute='agent_mode_dict'),
-}
-
-app_detail_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'mode': fields.String,
-    'icon': fields.String,
-    'icon_background': fields.String,
-    'enable_site': fields.Boolean,
-    'enable_api': fields.Boolean,
-    'api_rpm': fields.Integer,
-    'api_rph': fields.Integer,
-    'is_demo': fields.Boolean,
-    'model_config': fields.Nested(model_config_fields, attribute='app_model_config'),
-    'created_at': TimestampField
-}
-
 
 def _get_app(app_id, tenant_id):
     app = db.session.query(App).filter(App.id == app_id, App.tenant_id == tenant_id).first()
@@ -58,35 +32,6 @@ def _get_app(app_id, tenant_id):
 
 
 class AppListApi(Resource):
-    prompt_config_fields = {
-        'prompt_template': fields.String,
-    }
-
-    model_config_partial_fields = {
-        'model': fields.Raw(attribute='model_dict'),
-        'pre_prompt': fields.String,
-    }
-
-    app_partial_fields = {
-        'id': fields.String,
-        'name': fields.String,
-        'mode': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'enable_site': fields.Boolean,
-        'enable_api': fields.Boolean,
-        'is_demo': fields.Boolean,
-        'model_config': fields.Nested(model_config_partial_fields, attribute='app_model_config'),
-        'created_at': TimestampField
-    }
-
-    app_pagination_fields = {
-        'page': fields.Integer,
-        'limit': fields.Integer(attribute='per_page'),
-        'total': fields.Integer,
-        'has_more': fields.Boolean(attribute='has_next'),
-        'data': fields.List(fields.Nested(app_partial_fields), attribute='items')
-    }
 
     @setup_required
     @login_required
@@ -100,7 +45,8 @@ class AppListApi(Resource):
         args = parser.parse_args()
 
         app_models = db.paginate(
-            db.select(App).where(App.tenant_id == current_user.current_tenant_id).order_by(App.created_at.desc()),
+            db.select(App).where(App.tenant_id == current_user.current_tenant_id,
+                                 App.is_universal == False).order_by(App.created_at.desc()),
             page=args['page'],
             per_page=args['limit'],
             error_out=False)
@@ -125,11 +71,39 @@ class AppListApi(Resource):
         if current_user.current_tenant.current_role not in ['admin', 'owner']:
             raise Forbidden()
 
+        try:
+            default_model = ModelFactory.get_text_generation_model(
+                tenant_id=current_user.current_tenant_id
+            )
+        except (ProviderTokenNotInitError, LLMBadRequestError):
+            default_model = None
+        except Exception as e:
+            logging.exception(e)
+            default_model = None
+
         if args['model_config'] is not None:
             # validate config
+            model_config_dict = args['model_config']
+
+            # get model provider
+            model_provider = ModelProviderFactory.get_preferred_model_provider(
+                current_user.current_tenant_id,
+                model_config_dict["model"]["provider"]
+            )
+
+            if not model_provider:
+                if not default_model:
+                    raise ProviderNotInitializeError(
+                        f"No Default System Reasoning Model available. Please configure "
+                        f"in the Settings -> Model Provider.")
+                else:
+                    model_config_dict["model"]["provider"] = default_model.model_provider.provider_name
+                    model_config_dict["model"]["name"] = default_model.name
+
             model_configuration = AppModelConfigService.validate_configuration(
+                tenant_id=current_user.current_tenant_id,
                 account=current_user,
-                config=args['model_config'],
+                config=model_config_dict,
                 mode=args['mode']
             )
 
@@ -142,19 +116,8 @@ class AppListApi(Resource):
                 status='normal'
             )
 
-            app_model_config = AppModelConfig(
-                provider="",
-                model_id="",
-                configs={},
-                opening_statement=model_configuration['opening_statement'],
-                suggested_questions=json.dumps(model_configuration['suggested_questions']),
-                suggested_questions_after_answer=json.dumps(model_configuration['suggested_questions_after_answer']),
-                more_like_this=json.dumps(model_configuration['more_like_this']),
-                model=json.dumps(model_configuration['model']),
-                user_input_form=json.dumps(model_configuration['user_input_form']),
-                pre_prompt=model_configuration['pre_prompt'],
-                agent_mode=json.dumps(model_configuration['agent_mode']),
-            )
+            app_model_config = AppModelConfig()
+            app_model_config = app_model_config.from_model_config_dict(model_configuration)
         else:
             if 'mode' not in args or args['mode'] is None:
                 abort(400, message="mode is required")
@@ -164,6 +127,23 @@ class AppListApi(Resource):
             app = App(**model_config_template['app'])
             app_model_config = AppModelConfig(**model_config_template['model_config'])
 
+            # get model provider
+            model_provider = ModelProviderFactory.get_preferred_model_provider(
+                current_user.current_tenant_id,
+                app_model_config.model_dict["provider"]
+            )
+
+            if not model_provider:
+                if not default_model:
+                    raise ProviderNotInitializeError(
+                        f"No Default System Reasoning Model available. Please configure "
+                        f"in the Settings -> Model Provider.")
+                else:
+                    model_dict = app_model_config.model_dict
+                    model_dict['provider'] = default_model.model_provider.provider_name
+                    model_dict['name'] = default_model.name
+                    app_model_config.model = json.dumps(model_dict)
+
         app.name = args['name']
         app.mode = args['mode']
         app.icon = args['icon']
@@ -198,18 +178,6 @@ class AppListApi(Resource):
 
 
 class AppTemplateApi(Resource):
-    template_fields = {
-        'name': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'description': fields.String,
-        'mode': fields.String,
-        'model_config': fields.Nested(model_config_fields),
-    }
-
-    template_list_fields = {
-        'data': fields.List(fields.Nested(template_fields)),
-    }
 
     @setup_required
     @login_required
@@ -220,42 +188,14 @@ class AppTemplateApi(Resource):
         account = current_user
         interface_language = account.interface_language
 
-        return {'data': demo_model_templates.get(interface_language)}
+        templates = demo_model_templates.get(interface_language)
+        if not templates:
+            templates = demo_model_templates.get('en-US')
+
+        return {'data': templates}
 
 
 class AppApi(Resource):
-    site_fields = {
-        'access_token': fields.String(attribute='code'),
-        'code': fields.String,
-        'title': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'description': fields.String,
-        'default_language': fields.String,
-        'customize_domain': fields.String,
-        'copyright': fields.String,
-        'privacy_policy': fields.String,
-        'customize_token_strategy': fields.String,
-        'prompt_public': fields.Boolean,
-        'app_base_url': fields.String,
-    }
-
-    app_detail_fields_with_site = {
-        'id': fields.String,
-        'name': fields.String,
-        'mode': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'enable_site': fields.Boolean,
-        'enable_api': fields.Boolean,
-        'api_rpm': fields.Integer,
-        'api_rph': fields.Integer,
-        'is_demo': fields.Boolean,
-        'model_config': fields.Nested(model_config_fields, attribute='app_model_config'),
-        'site': fields.Nested(site_fields),
-        'api_base_url': fields.String,
-        'created_at': TimestampField
-    }
 
     @setup_required
     @login_required
@@ -274,6 +214,10 @@ class AppApi(Resource):
     def delete(self, app_id):
         """Delete app"""
         app_id = str(app_id)
+
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
         app = _get_app(app_id, current_user.current_tenant_id)
 
         db.session.delete(app)
@@ -293,19 +237,13 @@ class AppNameApi(Resource):
     @account_initialization_required
     @marshal_with(app_detail_fields)
     def post(self, app_id):
-
-        # The role of the current user in the ta table must be admin or owner
-        if current_user.current_tenant.current_role not in ['admin', 'owner']:
-            raise Forbidden()
+        app_id = str(app_id)
+        app = _get_app(app_id, current_user.current_tenant_id)
 
         parser = reqparse.RequestParser()
         parser.add_argument('name', type=str, required=True, location='json')
         args = parser.parse_args()
 
-        app = db.get_or_404(App, str(app_id))
-        if app.tenant_id != flask.session.get('tenant_id'):
-            raise Unauthorized()
-
         app.name = args.get('name')
         app.updated_at = datetime.utcnow()
         db.session.commit()
@@ -318,20 +256,14 @@ class AppIconApi(Resource):
     @account_initialization_required
     @marshal_with(app_detail_fields)
     def post(self, app_id):
-
-        # The role of the current user in the ta table must be admin or owner
-        if current_user.current_tenant.current_role not in ['admin', 'owner']:
-            raise Forbidden()
+        app_id = str(app_id)
+        app = _get_app(app_id, current_user.current_tenant_id)
 
         parser = reqparse.RequestParser()
         parser.add_argument('icon', type=str, location='json')
         parser.add_argument('icon_background', type=str, location='json')
         args = parser.parse_args()
 
-        app = db.get_or_404(App, str(app_id))
-        if app.tenant_id != flask.session.get('tenant_id'):
-            raise Unauthorized()
-
         app.icon = args.get('icon')
         app.icon_background = args.get('icon_background')
         app.updated_at = datetime.utcnow()
@@ -385,29 +317,6 @@ class AppApiStatus(Resource):
         return app
 
 
-class AppRateLimit(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @marshal_with(app_detail_fields)
-    def post(self, app_id):
-        parser = reqparse.RequestParser()
-        parser.add_argument('api_rpm', type=inputs.natural, required=False, location='json')
-        parser.add_argument('api_rph', type=inputs.natural, required=False, location='json')
-        args = parser.parse_args()
-
-        app_id = str(app_id)
-        app = _get_app(app_id, current_user.current_tenant_id)
-
-        if args.get('api_rpm'):
-            app.api_rpm = args.get('api_rpm')
-        if args.get('api_rph'):
-            app.api_rph = args.get('api_rph')
-        app.updated_at = datetime.utcnow()
-        db.session.commit()
-        return app
-
-
 class AppCopy(Resource):
     @staticmethod
     def create_app_copy(app):
@@ -427,20 +336,9 @@ class AppCopy(Resource):
 
     @staticmethod
     def create_app_model_config_copy(app_config, copy_app_id):
-        copy_app_model_config = AppModelConfig(
-            app_id=copy_app_id,
-            provider=app_config.provider,
-            model_id=app_config.model_id,
-            configs=app_config.configs,
-            opening_statement=app_config.opening_statement,
-            suggested_questions=app_config.suggested_questions,
-            suggested_questions_after_answer=app_config.suggested_questions_after_answer,
-            more_like_this=app_config.more_like_this,
-            model=app_config.model,
-            user_input_form=app_config.user_input_form,
-            pre_prompt=app_config.pre_prompt,
-            agent_mode=app_config.agent_mode
-        )
+        copy_app_model_config = app_config.copy()
+        copy_app_model_config.app_id = copy_app_id
+
         return copy_app_model_config
 
     @setup_required
@@ -468,51 +366,11 @@ class AppCopy(Resource):
         return copy_app, 201
 
 
-class AppExport(Resource):
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self, app_id):
-        # todo
-        pass
-
-
-class IntroductionGenerateApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument('prompt_template', type=str, required=True, location='json')
-        args = parser.parse_args()
-
-        account = current_user
-
-        try:
-            answer = LLMGenerator.generate_introduction(
-                account.current_tenant_id,
-                args['prompt_template']
-            )
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
-        except QuotaExceededError:
-            raise ProviderQuotaExceededError()
-        except ModelCurrentlyNotSupportError:
-            raise ProviderModelCurrentlyNotSupportError()
-        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
-                LLMRateLimitError, LLMAuthorizationError) as e:
-            raise CompletionRequestError(str(e))
-
-        return {'introduction': answer}
-
-
 api.add_resource(AppListApi, '/apps')
 api.add_resource(AppTemplateApi, '/app-templates')
 api.add_resource(AppApi, '/apps/<uuid:app_id>')
 api.add_resource(AppCopy, '/apps/<uuid:app_id>/copy')
 api.add_resource(AppNameApi, '/apps/<uuid:app_id>/name')
+api.add_resource(AppIconApi, '/apps/<uuid:app_id>/icon')
 api.add_resource(AppSiteStatus, '/apps/<uuid:app_id>/site-enable')
 api.add_resource(AppApiStatus, '/apps/<uuid:app_id>/api-enable')
-api.add_resource(AppRateLimit, '/apps/<uuid:app_id>/rate-limit')
-api.add_resource(IntroductionGenerateApi, '/introduction-generate')

api/controllers/console/app/audio.py

@@ -0,0 +1,69 @@
+# -*- coding:utf-8 -*-
+import logging
+
+from flask import request
+from libs.login import login_required
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.console import api
+from controllers.console.app import _get_app
+from controllers.console.app.error import AppUnavailableError, \
+    ProviderNotInitializeError, CompletionRequestError, ProviderQuotaExceededError, \
+    ProviderModelCurrentlyNotSupportError, NoAudioUploadedError, AudioTooLargeError, \
+    UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from flask_restful import Resource
+from services.audio_service import AudioService
+from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
+    UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
+
+
+class ChatMessageAudioApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, app_id):
+        app_id = str(app_id)
+        app_model = _get_app(app_id, 'chat')
+
+        file = request.files['file']
+
+        try:
+            response = AudioService.transcript(
+                tenant_id=app_model.tenant_id,
+                file=file,
+            )
+
+            return response
+        except services.errors.app_model_config.AppModelConfigBrokenError:
+            logging.exception("App model config broken.")
+            raise AppUnavailableError()
+        except NoAudioUploadedServiceError:
+            raise NoAudioUploadedError()
+        except AudioTooLargeServiceError as e:
+            raise AudioTooLargeError(str(e))
+        except UnsupportedAudioTypeServiceError:
+            raise UnsupportedAudioTypeError()
+        except ProviderNotSupportSpeechToTextServiceError:
+            raise ProviderNotSupportSpeechToTextError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+        except ValueError as e:
+            raise e
+        except Exception as e:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+        
+
+api.add_resource(ChatMessageAudioApi, '/apps/<uuid:app_id>/audio-to-text')

api/controllers/console/app/completion.py

@@ -5,7 +5,7 @@ from typing import Generator, Union
 
 import flask_login
 from flask import Response, stream_with_context
-from flask_login import login_required
+from libs.login import login_required
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services
@@ -17,7 +17,7 @@ from controllers.console.app.error import ConversationCompletedError, AppUnavail
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.conversation_message_task import PubHandler
-from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
+from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
     LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
 from libs.helper import uuid_value
 from flask_restful import Resource, reqparse
@@ -39,10 +39,14 @@ class CompletionMessageApi(Resource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
-        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('query', type=str, location='json', default='')
         parser.add_argument('model_config', type=dict, required=True, location='json')
+        parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
         args = parser.parse_args()
 
+        streaming = args['response_mode'] != 'blocking'
+
         account = flask_login.current_user
 
         try:
@@ -51,7 +55,7 @@ class CompletionMessageApi(Resource):
                 user=account,
                 args=args,
                 from_source='console',
-                streaming=True,
+                streaming=streaming,
                 is_model_config_override=True
             )
 
@@ -63,8 +67,8 @@ class CompletionMessageApi(Resource):
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")
             raise AppUnavailableError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -111,8 +115,12 @@ class ChatMessageApi(Resource):
         parser.add_argument('query', type=str, required=True, location='json')
         parser.add_argument('model_config', type=dict, required=True, location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
+        parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
         args = parser.parse_args()
 
+        streaming = args['response_mode'] != 'blocking'
+
         account = flask_login.current_user
 
         try:
@@ -121,7 +129,7 @@ class ChatMessageApi(Resource):
                 user=account,
                 args=args,
                 from_source='console',
-                streaming=True,
+                streaming=streaming,
                 is_model_config_override=True
             )
 
@@ -133,8 +141,8 @@ class ChatMessageApi(Resource):
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")
             raise AppUnavailableError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -164,8 +172,8 @@ def compact_response(response: Union[dict | Generator]) -> Response:
             except services.errors.app_model_config.AppModelConfigBrokenError:
                 logging.exception("App model config broken.")
                 yield "data: " + json.dumps(api.handle_error(AppUnavailableError()).get_json()) + "\n\n"
-            except ProviderTokenNotInitError:
-                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError()).get_json()) + "\n\n"
+            except ProviderTokenNotInitError as ex:
+                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError(ex.description)).get_json()) + "\n\n"
             except QuotaExceededError:
                 yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
             except ModelCurrentlyNotSupportError:

api/controllers/console/app/conversation.py

@@ -1,8 +1,9 @@
 from datetime import datetime
 
 import pytz
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, fields, marshal_with
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with
 from flask_restful.inputs import int_range
 from sqlalchemy import or_, func
 from sqlalchemy.orm import joinedload
@@ -12,106 +13,14 @@ from controllers.console import api
 from controllers.console.app import _get_app
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from libs.helper import TimestampField, datetime_string, uuid_value
+from fields.conversation_fields import conversation_pagination_fields, conversation_detail_fields, \
+    conversation_message_detail_fields, conversation_with_summary_pagination_fields
+from libs.helper import datetime_string
 from extensions.ext_database import db
 from models.model import Message, MessageAnnotation, Conversation
 
-account_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'email': fields.String
-}
-
-feedback_fields = {
-    'rating': fields.String,
-    'content': fields.String,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account': fields.Nested(account_fields, allow_null=True),
-}
-
-annotation_fields = {
-    'content': fields.String,
-    'account': fields.Nested(account_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
-message_detail_fields = {
-    'id': fields.String,
-    'conversation_id': fields.String,
-    'inputs': fields.Raw,
-    'query': fields.String,
-    'message': fields.Raw,
-    'message_tokens': fields.Integer,
-    'answer': fields.String,
-    'answer_tokens': fields.Integer,
-    'provider_response_latency': fields.Float,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account_id': fields.String,
-    'feedbacks': fields.List(fields.Nested(feedback_fields)),
-    'annotation': fields.Nested(annotation_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
-feedback_stat_fields = {
-    'like': fields.Integer,
-    'dislike': fields.Integer
-}
-
-model_config_fields = {
-    'opening_statement': fields.String,
-    'suggested_questions': fields.Raw,
-    'model': fields.Raw,
-    'user_input_form': fields.Raw,
-    'pre_prompt': fields.String,
-    'agent_mode': fields.Raw,
-}
-
 
 class CompletionConversationApi(Resource):
-    class MessageTextField(fields.Raw):
-        def format(self, value):
-            return value[0]['text'] if value else ''
-
-    simple_configs_fields = {
-        'prompt_template': fields.String,
-    }
-
-    simple_model_config_fields = {
-        'model': fields.Raw(attribute='model_dict'),
-        'pre_prompt': fields.String,
-    }
-
-    simple_message_detail_fields = {
-        'inputs': fields.Raw,
-        'query': fields.String,
-        'message': MessageTextField,
-        'answer': fields.String,
-    }
-
-    conversation_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_account_id': fields.String,
-        'read_at': TimestampField,
-        'created_at': TimestampField,
-        'annotation': fields.Nested(annotation_fields, allow_null=True),
-        'model_config': fields.Nested(simple_model_config_fields),
-        'user_feedback_stats': fields.Nested(feedback_stat_fields),
-        'admin_feedback_stats': fields.Nested(feedback_stat_fields),
-        'message': fields.Nested(simple_message_detail_fields, attribute='first_message')
-    }
-
-    conversation_pagination_fields = {
-        'page': fields.Integer,
-        'limit': fields.Integer(attribute='per_page'),
-        'total': fields.Integer,
-        'has_more': fields.Boolean(attribute='has_next'),
-        'data': fields.List(fields.Nested(conversation_fields), attribute='items')
-    }
 
     @setup_required
     @login_required
@@ -160,7 +69,7 @@ class CompletionConversationApi(Resource):
 
         if args['end']:
             end_datetime = datetime.strptime(args['end'], '%Y-%m-%d %H:%M')
-            end_datetime = end_datetime.replace(second=0)
+            end_datetime = end_datetime.replace(second=59)
 
             end_datetime_timezone = timezone.localize(end_datetime)
             end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
@@ -189,66 +98,44 @@ class CompletionConversationApi(Resource):
 
 
 class CompletionConversationDetailApi(Resource):
-    conversation_detail_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_account_id': fields.String,
-        'created_at': TimestampField,
-        'model_config': fields.Nested(model_config_fields),
-        'message': fields.Nested(message_detail_fields, attribute='first_message'),
-    }
 
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(conversation_detail_fields)
+    @marshal_with(conversation_message_detail_fields)
     def get(self, app_id, conversation_id):
         app_id = str(app_id)
         conversation_id = str(conversation_id)
 
         return _get_conversation(app_id, conversation_id, 'completion')
+    
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, app_id, conversation_id):
+        app_id = str(app_id)
+        conversation_id = str(conversation_id)
+
+        app = _get_app(app_id, 'chat')
+
+        conversation = db.session.query(Conversation) \
+            .filter(Conversation.id == conversation_id, Conversation.app_id == app.id).first()
+
+        if not conversation:
+            raise NotFound("Conversation Not Exists.")
+
+        conversation.is_deleted = True
+        db.session.commit()
+
+        return {'result': 'success'}, 204
 
 
 class ChatConversationApi(Resource):
-    simple_configs_fields = {
-        'prompt_template': fields.String,
-    }
-
-    simple_model_config_fields = {
-        'model': fields.Raw(attribute='model_dict'),
-        'pre_prompt': fields.String,
-    }
-
-    conversation_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_account_id': fields.String,
-        'summary': fields.String(attribute='summary_or_query'),
-        'read_at': TimestampField,
-        'created_at': TimestampField,
-        'annotated': fields.Boolean,
-        'model_config': fields.Nested(simple_model_config_fields),
-        'message_count': fields.Integer,
-        'user_feedback_stats': fields.Nested(feedback_stat_fields),
-        'admin_feedback_stats': fields.Nested(feedback_stat_fields)
-    }
-
-    conversation_pagination_fields = {
-        'page': fields.Integer,
-        'limit': fields.Integer(attribute='per_page'),
-        'total': fields.Integer,
-        'has_more': fields.Boolean(attribute='has_next'),
-        'data': fields.List(fields.Nested(conversation_fields), attribute='items')
-    }
 
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(conversation_pagination_fields)
+    @marshal_with(conversation_with_summary_pagination_fields)
     def get(self, app_id):
         app_id = str(app_id)
 
@@ -296,7 +183,7 @@ class ChatConversationApi(Resource):
 
         if args['end']:
             end_datetime = datetime.strptime(args['end'], '%Y-%m-%d %H:%M')
-            end_datetime = end_datetime.replace(second=0)
+            end_datetime = end_datetime.replace(second=59)
 
             end_datetime_timezone = timezone.localize(end_datetime)
             end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
@@ -333,19 +220,6 @@ class ChatConversationApi(Resource):
 
 
 class ChatConversationDetailApi(Resource):
-    conversation_detail_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_account_id': fields.String,
-        'created_at': TimestampField,
-        'annotated': fields.Boolean,
-        'model_config': fields.Nested(model_config_fields),
-        'message_count': fields.Integer,
-        'user_feedback_stats': fields.Nested(feedback_stat_fields),
-        'admin_feedback_stats': fields.Nested(feedback_stat_fields)
-    }
 
     @setup_required
     @login_required
@@ -356,6 +230,27 @@ class ChatConversationDetailApi(Resource):
         conversation_id = str(conversation_id)
 
         return _get_conversation(app_id, conversation_id, 'chat')
+    
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, app_id, conversation_id):
+        app_id = str(app_id)
+        conversation_id = str(conversation_id)
+
+        # get app info
+        app = _get_app(app_id, 'chat')
+
+        conversation = db.session.query(Conversation) \
+            .filter(Conversation.id == conversation_id, Conversation.app_id == app.id).first()
+
+        if not conversation:
+            raise NotFound("Conversation Not Exists.")
+
+        conversation.is_deleted = True
+        db.session.commit()
+
+        return {'result': 'success'}, 204
 
 
 

api/controllers/console/app/error.py

@@ -16,7 +16,7 @@ class ProviderNotInitializeError(BaseHTTPException):
 
 class ProviderQuotaExceededError(BaseHTTPException):
     error_code = 'provider_quota_exceeded'
-    description = "Your quota for Dify Hosted OpenAI has been exhausted. " \
+    description = "Your quota for Dify Hosted Model Provider has been exhausted. " \
                   "Please go to Settings -> Model Provider to complete your own provider credentials."
     code = 400
 
@@ -49,3 +49,27 @@ class AppMoreLikeThisDisabledError(BaseHTTPException):
     error_code = 'app_more_like_this_disabled'
     description = "The 'More like this' feature is disabled. Please refresh your page."
     code = 403
+
+
+class NoAudioUploadedError(BaseHTTPException):
+    error_code = 'no_audio_uploaded'
+    description = "Please upload your audio."
+    code = 400
+
+
+class AudioTooLargeError(BaseHTTPException):
+    error_code = 'audio_too_large'
+    description = "Audio size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedAudioTypeError(BaseHTTPException):
+    error_code = 'unsupported_audio_type'
+    description = "Audio type not allowed."
+    code = 415
+
+
+class ProviderNotSupportSpeechToTextError(BaseHTTPException):
+    error_code = 'provider_not_support_speech_to_text'
+    description = "Provider not support speech to text."
+    code = 400

api/controllers/console/app/generator.py

@@ -0,0 +1,76 @@
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse
+
+from controllers.console import api
+from controllers.console.app.error import ProviderNotInitializeError, ProviderQuotaExceededError, \
+    CompletionRequestError, ProviderModelCurrentlyNotSupportError
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.generator.llm_generator import LLMGenerator
+from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, LLMBadRequestError, LLMAPIConnectionError, \
+    LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError, ModelCurrentlyNotSupportError
+
+
+class IntroductionGenerateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('prompt_template', type=str, required=True, location='json')
+        args = parser.parse_args()
+
+        account = current_user
+
+        try:
+            answer = LLMGenerator.generate_introduction(
+                account.current_tenant_id,
+                args['prompt_template']
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+
+        return {'introduction': answer}
+
+
+class RuleGenerateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('audiences', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('hoping_to_solve', type=str, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        account = current_user
+
+        try:
+            rules = LLMGenerator.generate_rule_config(
+                account.current_tenant_id,
+                args['audiences'],
+                args['hoping_to_solve']
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+
+        return rules
+
+
+api.add_resource(IntroductionGenerateApi, '/introduction-generate')
+api.add_resource(RuleGenerateApi, '/rule-generate')

api/controllers/console/app/message.py

@@ -3,7 +3,7 @@ import logging
 from typing import Union, Generator
 
 from flask import Response, stream_with_context
-from flask_login import current_user, login_required
+from flask_login import current_user
 from flask_restful import Resource, reqparse, marshal_with, fields
 from flask_restful.inputs import int_range
 from werkzeug.exceptions import InternalServerError, NotFound
@@ -14,9 +14,11 @@ from controllers.console.app.error import CompletionRequestError, ProviderNotIni
     AppMoreLikeThisDisabledError, ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.llm.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
+from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
     ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
-from libs.helper import uuid_value, TimestampField
+from libs.login import login_required
+from fields.conversation_fields import message_detail_fields
+from libs.helper import uuid_value
 from libs.infinite_scroll_pagination import InfiniteScrollPagination
 from extensions.ext_database import db
 from models.model import MessageAnnotation, Conversation, Message, MessageFeedback
@@ -26,44 +28,6 @@ from services.errors.conversation import ConversationNotExistsError
 from services.errors.message import MessageNotExistsError
 from services.message_service import MessageService
 
-account_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'email': fields.String
-}
-
-feedback_fields = {
-    'rating': fields.String,
-    'content': fields.String,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account': fields.Nested(account_fields, allow_null=True),
-}
-
-annotation_fields = {
-    'content': fields.String,
-    'account': fields.Nested(account_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
-message_detail_fields = {
-    'id': fields.String,
-    'conversation_id': fields.String,
-    'inputs': fields.Raw,
-    'query': fields.String,
-    'message': fields.Raw,
-    'message_tokens': fields.Integer,
-    'answer': fields.String,
-    'answer_tokens': fields.Integer,
-    'provider_response_latency': fields.Float,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account_id': fields.String,
-    'feedbacks': fields.List(fields.Nested(feedback_fields)),
-    'annotation': fields.Nested(annotation_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
 
 class ChatMessageListApi(Resource):
     message_infinite_scroll_pagination_fields = {
@@ -269,8 +233,8 @@ class MessageMoreLikeThisApi(Resource):
             raise NotFound("Message Not Exists.")
         except MoreLikeThisDisabledError:
             raise AppMoreLikeThisDisabledError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -297,8 +261,8 @@ def compact_response(response: Union[dict | Generator]) -> Response:
                 yield "data: " + json.dumps(api.handle_error(NotFound("Message Not Exists.")).get_json()) + "\n\n"
             except MoreLikeThisDisabledError:
                 yield "data: " + json.dumps(api.handle_error(AppMoreLikeThisDisabledError()).get_json()) + "\n\n"
-            except ProviderTokenNotInitError:
-                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError()).get_json()) + "\n\n"
+            except ProviderTokenNotInitError as ex:
+                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError(ex.description)).get_json()) + "\n\n"
             except QuotaExceededError:
                 yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
             except ModelCurrentlyNotSupportError:
@@ -339,8 +303,8 @@ class MessageSuggestedQuestionApi(Resource):
             raise NotFound("Message not found")
         except ConversationNotExistsError:
             raise NotFound("Conversation not found")
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:

api/controllers/console/app/model_config.py

@@ -1,14 +1,14 @@
 # -*- coding:utf-8 -*-
-import json
 
 from flask import request
 from flask_restful import Resource
-from flask_login import login_required, current_user
+from flask_login import current_user
 
 from controllers.console import api
 from controllers.console.app import _get_app
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
+from libs.login import login_required
 from events.app_event import app_model_config_was_updated
 from extensions.ext_database import db
 from models.model import AppModelConfig
@@ -28,6 +28,7 @@ class ModelConfigResource(Resource):
 
         # validate config
         model_configuration = AppModelConfigService.validate_configuration(
+            tenant_id=current_user.current_tenant_id,
             account=current_user,
             config=request.json,
             mode=app_model.mode
@@ -35,18 +36,8 @@ class ModelConfigResource(Resource):
 
         new_app_model_config = AppModelConfig(
             app_id=app_model.id,
-            provider="",
-            model_id="",
-            configs={},
-            opening_statement=model_configuration['opening_statement'],
-            suggested_questions=json.dumps(model_configuration['suggested_questions']),
-            suggested_questions_after_answer=json.dumps(model_configuration['suggested_questions_after_answer']),
-            more_like_this=json.dumps(model_configuration['more_like_this']),
-            model=json.dumps(model_configuration['model']),
-            user_input_form=json.dumps(model_configuration['user_input_form']),
-            pre_prompt=model_configuration['pre_prompt'],
-            agent_mode=json.dumps(model_configuration['agent_mode']),
         )
+        new_app_model_config = new_app_model_config.from_model_config_dict(model_configuration)
 
         db.session.add(new_app_model_config)
         db.session.flush()

api/controllers/console/app/site.py

@@ -1,32 +1,18 @@
 # -*- coding:utf-8 -*-
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, fields, marshal_with
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with
 from werkzeug.exceptions import NotFound, Forbidden
 
 from controllers.console import api
 from controllers.console.app import _get_app
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
+from fields.app_fields import app_site_fields
 from libs.helper import supported_language
 from extensions.ext_database import db
 from models.model import Site
 
-app_site_fields = {
-    'app_id': fields.String,
-    'access_token': fields.String(attribute='code'),
-    'code': fields.String,
-    'title': fields.String,
-    'icon': fields.String,
-    'icon_background': fields.String,
-    'description': fields.String,
-    'default_language': fields.String,
-    'customize_domain': fields.String,
-    'copyright': fields.String,
-    'privacy_policy': fields.String,
-    'customize_token_strategy': fields.String,
-    'prompt_public': fields.Boolean
-}
-
 
 def parse_app_site_args():
     parser = reqparse.RequestParser()
@@ -80,6 +66,13 @@ class AppSite(Resource):
             if value is not None:
                 setattr(site, attr_name, value)
 
+                if attr_name == 'title':
+                    app_model.name = value
+                elif attr_name == 'icon':
+                    app_model.icon = value
+                elif attr_name == 'icon_background':
+                    app_model.icon_background = value
+
         db.session.commit()
 
         return site

api/controllers/console/app/statistic.py

@@ -1,9 +1,11 @@
 # -*- coding:utf-8 -*-
+from decimal import Decimal
 from datetime import datetime
 
 import pytz
 from flask import jsonify
-from flask_login import login_required, current_user
+from flask_login import current_user
+from libs.login import login_required
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
@@ -59,18 +61,20 @@ class DailyConversationStatistic(Resource):
             arg_dict['end'] = end_datetime_utc
 
         sql_query += ' GROUP BY date order by date'
-        rs = db.session.execute(sql_query, arg_dict)
 
-        response_date = []
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+
+        response_data = []
 
         for i in rs:
-            response_date.append({
+            response_data.append({
                 'date': str(i.date),
                 'conversation_count': i.conversation_count
             })
 
         return jsonify({
-            'data': response_date
+            'data': response_data
         })
 
 
@@ -119,18 +123,20 @@ class DailyTerminalsStatistic(Resource):
             arg_dict['end'] = end_datetime_utc
 
         sql_query += ' GROUP BY date order by date'
-        rs = db.session.execute(sql_query, arg_dict)
 
-        response_date = []
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+
+        response_data = []
 
         for i in rs:
-            response_date.append({
+            response_data.append({
                 'date': str(i.date),
                 'terminal_count': i.terminal_count
             })
 
         return jsonify({
-            'data': response_date
+            'data': response_data
         })
 
 
@@ -180,12 +186,14 @@ class DailyTokenCostStatistic(Resource):
             arg_dict['end'] = end_datetime_utc
 
         sql_query += ' GROUP BY date order by date'
-        rs = db.session.execute(sql_query, arg_dict)
 
-        response_date = []
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+
+        response_data = []
 
         for i in rs:
-            response_date.append({
+            response_data.append({
                 'date': str(i.date),
                 'token_count': i.token_count,
                 'total_price': i.total_price,
@@ -193,10 +201,272 @@ class DailyTokenCostStatistic(Resource):
             })
 
         return jsonify({
-            'data': response_date
+            'data': response_data
+        })
+
+
+class AverageSessionInteractionStatistic(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, app_id):
+        account = current_user
+        app_id = str(app_id)
+        app_model = _get_app(app_id, 'chat')
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('start', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        parser.add_argument('end', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        args = parser.parse_args()
+
+        sql_query = """SELECT date(DATE_TRUNC('day', c.created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date, 
+AVG(subquery.message_count) AS interactions
+FROM (SELECT m.conversation_id, COUNT(m.id) AS message_count
+    FROM conversations c
+    JOIN messages m ON c.id = m.conversation_id
+    WHERE c.override_model_configs IS NULL AND c.app_id = :app_id"""
+        arg_dict = {'tz': account.timezone, 'app_id': app_model.id}
+
+        timezone = pytz.timezone(account.timezone)
+        utc_timezone = pytz.utc
+
+        if args['start']:
+            start_datetime = datetime.strptime(args['start'], '%Y-%m-%d %H:%M')
+            start_datetime = start_datetime.replace(second=0)
+
+            start_datetime_timezone = timezone.localize(start_datetime)
+            start_datetime_utc = start_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and c.created_at >= :start'
+            arg_dict['start'] = start_datetime_utc
+
+        if args['end']:
+            end_datetime = datetime.strptime(args['end'], '%Y-%m-%d %H:%M')
+            end_datetime = end_datetime.replace(second=0)
+
+            end_datetime_timezone = timezone.localize(end_datetime)
+            end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and c.created_at < :end'
+            arg_dict['end'] = end_datetime_utc
+
+        sql_query += """
+        GROUP BY m.conversation_id) subquery
+LEFT JOIN conversations c on c.id=subquery.conversation_id
+GROUP BY date
+ORDER BY date"""
+
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+
+        response_data = []
+
+        for i in rs:
+            response_data.append({
+                'date': str(i.date),
+                'interactions': float(i.interactions.quantize(Decimal('0.01')))
+            })
+
+        return jsonify({
+            'data': response_data
+        })
+
+
+class UserSatisfactionRateStatistic(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, app_id):
+        account = current_user
+        app_id = str(app_id)
+        app_model = _get_app(app_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('start', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        parser.add_argument('end', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        args = parser.parse_args()
+
+        sql_query = '''
+                        SELECT date(DATE_TRUNC('day', m.created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date, 
+                            COUNT(m.id) as message_count, COUNT(mf.id) as feedback_count 
+                            FROM messages m
+                            LEFT JOIN message_feedbacks mf on mf.message_id=m.id
+                            WHERE m.app_id = :app_id 
+                        '''
+        arg_dict = {'tz': account.timezone, 'app_id': app_model.id}
+
+        timezone = pytz.timezone(account.timezone)
+        utc_timezone = pytz.utc
+
+        if args['start']:
+            start_datetime = datetime.strptime(args['start'], '%Y-%m-%d %H:%M')
+            start_datetime = start_datetime.replace(second=0)
+
+            start_datetime_timezone = timezone.localize(start_datetime)
+            start_datetime_utc = start_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and m.created_at >= :start'
+            arg_dict['start'] = start_datetime_utc
+
+        if args['end']:
+            end_datetime = datetime.strptime(args['end'], '%Y-%m-%d %H:%M')
+            end_datetime = end_datetime.replace(second=0)
+
+            end_datetime_timezone = timezone.localize(end_datetime)
+            end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and m.created_at < :end'
+            arg_dict['end'] = end_datetime_utc
+
+        sql_query += ' GROUP BY date order by date'
+
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+
+        response_data = []
+
+        for i in rs:
+            response_data.append({
+                'date': str(i.date),
+                'rate': round((i.feedback_count * 1000 / i.message_count) if i.message_count > 0 else 0, 2),
+            })
+
+        return jsonify({
+                'data': response_data
+            })
+
+
+class AverageResponseTimeStatistic(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, app_id):
+        account = current_user
+        app_id = str(app_id)
+        app_model = _get_app(app_id, 'completion')
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('start', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        parser.add_argument('end', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        args = parser.parse_args()
+
+        sql_query = '''
+                SELECT date(DATE_TRUNC('day', created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date, 
+                    AVG(provider_response_latency) as latency
+                    FROM messages
+                    WHERE app_id = :app_id
+                '''
+        arg_dict = {'tz': account.timezone, 'app_id': app_model.id}
+
+        timezone = pytz.timezone(account.timezone)
+        utc_timezone = pytz.utc
+
+        if args['start']:
+            start_datetime = datetime.strptime(args['start'], '%Y-%m-%d %H:%M')
+            start_datetime = start_datetime.replace(second=0)
+
+            start_datetime_timezone = timezone.localize(start_datetime)
+            start_datetime_utc = start_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and created_at >= :start'
+            arg_dict['start'] = start_datetime_utc
+
+        if args['end']:
+            end_datetime = datetime.strptime(args['end'], '%Y-%m-%d %H:%M')
+            end_datetime = end_datetime.replace(second=0)
+
+            end_datetime_timezone = timezone.localize(end_datetime)
+            end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and created_at < :end'
+            arg_dict['end'] = end_datetime_utc
+
+        sql_query += ' GROUP BY date order by date'
+
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+
+        response_data = []
+
+        for i in rs:
+            response_data.append({
+                'date': str(i.date),
+                'latency': round(i.latency * 1000, 4)
+            })
+
+        return jsonify({
+            'data': response_data
+        })
+
+
+class TokensPerSecondStatistic(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, app_id):
+        account = current_user
+        app_id = str(app_id)
+        app_model = _get_app(app_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('start', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        parser.add_argument('end', type=datetime_string('%Y-%m-%d %H:%M'), location='args')
+        args = parser.parse_args()
+
+        sql_query = '''SELECT date(DATE_TRUNC('day', created_at AT TIME ZONE 'UTC' AT TIME ZONE :tz )) AS date, 
+    CASE 
+        WHEN SUM(provider_response_latency) = 0 THEN 0
+        ELSE (SUM(answer_tokens) / SUM(provider_response_latency))
+    END as tokens_per_second
+FROM messages
+WHERE app_id = :app_id'''
+        arg_dict = {'tz': account.timezone, 'app_id': app_model.id}
+
+        timezone = pytz.timezone(account.timezone)
+        utc_timezone = pytz.utc
+
+        if args['start']:
+            start_datetime = datetime.strptime(args['start'], '%Y-%m-%d %H:%M')
+            start_datetime = start_datetime.replace(second=0)
+
+            start_datetime_timezone = timezone.localize(start_datetime)
+            start_datetime_utc = start_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and created_at >= :start'
+            arg_dict['start'] = start_datetime_utc
+
+        if args['end']:
+            end_datetime = datetime.strptime(args['end'], '%Y-%m-%d %H:%M')
+            end_datetime = end_datetime.replace(second=0)
+
+            end_datetime_timezone = timezone.localize(end_datetime)
+            end_datetime_utc = end_datetime_timezone.astimezone(utc_timezone)
+
+            sql_query += ' and created_at < :end'
+            arg_dict['end'] = end_datetime_utc
+
+        sql_query += ' GROUP BY date order by date'
+
+        with db.engine.begin() as conn:
+            rs = conn.execute(db.text(sql_query), arg_dict)
+
+        response_data = []
+
+        for i in rs:
+            response_data.append({
+                'date': str(i.date),
+                'tps': round(i.tokens_per_second, 4)
+            })
+
+        return jsonify({
+            'data': response_data
         })
 
 
 api.add_resource(DailyConversationStatistic, '/apps/<uuid:app_id>/statistics/daily-conversations')
 api.add_resource(DailyTerminalsStatistic, '/apps/<uuid:app_id>/statistics/daily-end-users')
 api.add_resource(DailyTokenCostStatistic, '/apps/<uuid:app_id>/statistics/token-costs')
+api.add_resource(AverageSessionInteractionStatistic, '/apps/<uuid:app_id>/statistics/average-session-interactions')
+api.add_resource(UserSatisfactionRateStatistic, '/apps/<uuid:app_id>/statistics/user-satisfaction-rate')
+api.add_resource(AverageResponseTimeStatistic, '/apps/<uuid:app_id>/statistics/average-response-time')
+api.add_resource(TokensPerSecondStatistic, '/apps/<uuid:app_id>/statistics/tokens-per-second')

api/controllers/console/auth/activate.py

@@ -0,0 +1,75 @@
+import base64
+import secrets
+from datetime import datetime
+
+from flask_restful import Resource, reqparse
+
+from controllers.console import api
+from controllers.console.error import AlreadyActivateError
+from extensions.ext_database import db
+from libs.helper import email, str_len, supported_language, timezone
+from libs.password import valid_password, hash_password
+from models.account import AccountStatus, Tenant
+from services.account_service import RegisterService
+
+
+class ActivateCheckApi(Resource):
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('workspace_id', type=str, required=False, nullable=True, location='args')
+        parser.add_argument('email', type=email, required=False, nullable=True, location='args')
+        parser.add_argument('token', type=str, required=True, nullable=False, location='args')
+        args = parser.parse_args()
+
+        workspaceId = args['workspace_id']
+        reg_email = args['email']
+        token = args['token']
+
+        invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
+
+        return {'is_valid': invitation is not None, 'workspace_name': invitation['tenant'].name if invitation else None}
+
+
+class ActivateApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('workspace_id', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('email', type=email, required=False, nullable=True, location='json')
+        parser.add_argument('token', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('name', type=str_len(30), required=True, nullable=False, location='json')
+        parser.add_argument('password', type=valid_password, required=True, nullable=False, location='json')
+        parser.add_argument('interface_language', type=supported_language, required=True, nullable=False,
+                            location='json')
+        parser.add_argument('timezone', type=timezone, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        invitation = RegisterService.get_invitation_if_token_valid(args['workspace_id'], args['email'], args['token'])
+        if invitation is None:
+            raise AlreadyActivateError()
+
+        RegisterService.revoke_token(args['workspace_id'], args['email'], args['token'])
+
+        account = invitation['account']
+        account.name = args['name']
+
+        # generate password salt
+        salt = secrets.token_bytes(16)
+        base64_salt = base64.b64encode(salt).decode()
+
+        # encrypt password with salt
+        password_hashed = hash_password(args['password'], salt)
+        base64_password_hashed = base64.b64encode(password_hashed).decode()
+        account.password = base64_password_hashed
+        account.password_salt = base64_salt
+        account.interface_language = args['interface_language']
+        account.timezone = args['timezone']
+        account.interface_theme = 'light'
+        account.status = AccountStatus.ACTIVE.value
+        account.initialized_at = datetime.utcnow()
+        db.session.commit()
+
+        return {'result': 'success'}
+
+
+api.add_resource(ActivateCheckApi, '/activate/check')
+api.add_resource(ActivateApi, '/activate')

api/controllers/console/auth/data_source_oauth.py

@@ -0,0 +1,116 @@
+import logging
+
+import requests
+from flask import request, redirect, current_app
+from flask_login import current_user
+
+from flask_restful import Resource
+from werkzeug.exceptions import Forbidden
+
+from libs.login import login_required
+from libs.oauth_data_source import NotionOAuth
+from controllers.console import api
+from ..setup import setup_required
+from ..wraps import account_initialization_required
+
+
+def get_oauth_providers():
+    with current_app.app_context():
+        notion_oauth = NotionOAuth(client_id=current_app.config.get('NOTION_CLIENT_ID'),
+                                   client_secret=current_app.config.get(
+                                       'NOTION_CLIENT_SECRET'),
+                                   redirect_uri=current_app.config.get(
+                                       'CONSOLE_API_URL') + '/console/api/oauth/data-source/callback/notion')
+
+        OAUTH_PROVIDERS = {
+            'notion': notion_oauth
+        }
+        return OAUTH_PROVIDERS
+
+
+class OAuthDataSource(Resource):
+    def get(self, provider: str):
+        # The role of the current user in the table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+        OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
+        with current_app.app_context():
+            oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
+            print(vars(oauth_provider))
+        if not oauth_provider:
+            return {'error': 'Invalid provider'}, 400
+        if current_app.config.get('NOTION_INTEGRATION_TYPE') == 'internal':
+            internal_secret = current_app.config.get('NOTION_INTERNAL_SECRET')
+            oauth_provider.save_internal_access_token(internal_secret)
+            return { 'data': '' }
+        else:
+            auth_url = oauth_provider.get_authorization_url()
+            return { 'data': auth_url }, 200
+
+
+
+
+class OAuthDataSourceCallback(Resource):
+    def get(self, provider: str):
+        OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
+        with current_app.app_context():
+            oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
+        if not oauth_provider:
+            return {'error': 'Invalid provider'}, 400
+        if 'code' in request.args:
+            code = request.args.get('code')
+
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?type=notion&code={code}')
+        elif 'error' in request.args:
+            error = request.args.get('error')
+
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?type=notion&error={error}')
+        else:
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?type=notion&error=Access denied')
+        
+
+class OAuthDataSourceBinding(Resource):
+    def get(self, provider: str):
+        OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
+        with current_app.app_context():
+            oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
+        if not oauth_provider:
+            return {'error': 'Invalid provider'}, 400
+        if 'code' in request.args:
+            code = request.args.get('code')
+            try:
+                oauth_provider.get_access_token(code)
+            except requests.exceptions.HTTPError as e:
+                logging.exception(
+                    f"An error occurred during the OAuthCallback process with {provider}: {e.response.text}")
+                return {'error': 'OAuth data source process failed'}, 400
+
+            return {'result': 'success'}, 200
+
+
+class OAuthDataSourceSync(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider, binding_id):
+        provider = str(provider)
+        binding_id = str(binding_id)
+        OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
+        with current_app.app_context():
+            oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
+        if not oauth_provider:
+            return {'error': 'Invalid provider'}, 400
+        try:
+            oauth_provider.sync_data_source(binding_id)
+        except requests.exceptions.HTTPError as e:
+            logging.exception(
+                f"An error occurred during the OAuthCallback process with {provider}: {e.response.text}")
+            return {'error': 'OAuth data source process failed'}, 400
+
+        return {'result': 'success'}, 200
+
+
+api.add_resource(OAuthDataSource, '/oauth/data-source/<string:provider>')
+api.add_resource(OAuthDataSourceCallback, '/oauth/data-source/callback/<string:provider>')
+api.add_resource(OAuthDataSourceBinding, '/oauth/data-source/binding/<string:provider>')
+api.add_resource(OAuthDataSourceSync, '/oauth/data-source/<string:provider>/<uuid:binding_id>/sync')

api/controllers/console/auth/login.py

@@ -6,7 +6,6 @@ from flask_restful import Resource, reqparse
 
 import services
 from controllers.console import api
-from controllers.console.error import AccountNotLinkTenantError
 from controllers.console.setup import setup_required
 from libs.helper import email
 from libs.password import valid_password
@@ -35,14 +34,14 @@ class LoginApi(Resource):
         try:
             TenantService.switch_tenant(account)
         except Exception:
-            raise AccountNotLinkTenantError("Account not link tenant")
+            pass
 
-        flask_login.login_user(account, remember=args['remember_me'])
         AccountService.update_last_login(account, request)
 
         # todo: return the user info
+        token = AccountService.get_account_jwt_token(account)
 
-        return {'result': 'success'}
+        return {'result': 'success', 'data': token}
 
 
 class LogoutApi(Resource):

api/controllers/console/auth/oauth.py

@@ -2,9 +2,8 @@ import logging
 from datetime import datetime
 from typing import Optional
 
-import flask_login
 import requests
-from flask import request, redirect, current_app, session
+from flask import request, redirect, current_app
 from flask_restful import Resource
 
 from libs.oauth import OAuthUserInfo, GitHubOAuth, GoogleOAuth
@@ -20,13 +19,13 @@ def get_oauth_providers():
                                    client_secret=current_app.config.get(
                                        'GITHUB_CLIENT_SECRET'),
                                    redirect_uri=current_app.config.get(
-                                       'CONSOLE_URL') + '/console/api/oauth/authorize/github')
+                                       'CONSOLE_API_URL') + '/console/api/oauth/authorize/github')
 
         google_oauth = GoogleOAuth(client_id=current_app.config.get('GOOGLE_CLIENT_ID'),
                                    client_secret=current_app.config.get(
                                        'GOOGLE_CLIENT_SECRET'),
                                    redirect_uri=current_app.config.get(
-                                       'CONSOLE_URL') + '/console/api/oauth/authorize/google')
+                                       'CONSOLE_API_URL') + '/console/api/oauth/authorize/google')
 
         OAUTH_PROVIDERS = {
             'github': github_oauth,
@@ -75,12 +74,11 @@ class OAuthCallback(Resource):
             account.initialized_at = datetime.utcnow()
             db.session.commit()
 
-        # login user
-        session.clear()
-        flask_login.login_user(account, remember=True)
         AccountService.update_last_login(account, request)
 
-        return redirect(f'{current_app.config.get("CONSOLE_URL")}?oauth_login=success')
+        token = AccountService.get_account_jwt_token(account)
+
+        return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?console_token={token}')
 
 
 def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:

api/controllers/console/datasets/data_source.py

@@ -0,0 +1,248 @@
+import datetime
+import json
+
+from cachetools import TTLCache
+from flask import request
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, marshal_with, reqparse
+from werkzeug.exceptions import NotFound
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.data_loader.loader.notion import NotionLoader
+from core.indexing_runner import IndexingRunner
+from extensions.ext_database import db
+from fields.data_source_fields import integrate_notion_info_list_fields, integrate_list_fields
+from models.dataset import Document
+from models.source import DataSourceBinding
+from services.dataset_service import DatasetService, DocumentService
+from tasks.document_indexing_sync_task import document_indexing_sync_task
+
+cache = TTLCache(maxsize=None, ttl=30)
+
+
+class DataSourceApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(integrate_list_fields)
+    def get(self):
+        # get workspace data source integrates
+        data_source_integrates = db.session.query(DataSourceBinding).filter(
+            DataSourceBinding.tenant_id == current_user.current_tenant_id,
+            DataSourceBinding.disabled == False
+        ).all()
+
+        base_url = request.url_root.rstrip('/')
+        data_source_oauth_base_path = "/console/api/oauth/data-source"
+        providers = ["notion"]
+
+        integrate_data = []
+        for provider in providers:
+            # existing_integrate = next((ai for ai in data_source_integrates if ai.provider == provider), None)
+            existing_integrates = filter(lambda item: item.provider == provider, data_source_integrates)
+            if existing_integrates:
+                for existing_integrate in list(existing_integrates):
+                    integrate_data.append({
+                        'id': existing_integrate.id,
+                        'provider': provider,
+                        'created_at': existing_integrate.created_at,
+                        'is_bound': True,
+                        'disabled': existing_integrate.disabled,
+                        'source_info': existing_integrate.source_info,
+                        'link': f'{base_url}{data_source_oauth_base_path}/{provider}'
+                })
+            else:
+                integrate_data.append({
+                    'id': None,
+                    'provider': provider,
+                    'created_at': None,
+                    'source_info': None,
+                    'is_bound': False,
+                    'disabled': None,
+                    'link': f'{base_url}{data_source_oauth_base_path}/{provider}'
+                })
+        return {'data': integrate_data}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, binding_id, action):
+        binding_id = str(binding_id)
+        action = str(action)
+        data_source_binding = DataSourceBinding.query.filter_by(
+            id=binding_id
+        ).first()
+        if data_source_binding is None:
+            raise NotFound('Data source binding not found.')
+        # enable binding
+        if action == 'enable':
+            if data_source_binding.disabled:
+                data_source_binding.disabled = False
+                data_source_binding.updated_at = datetime.datetime.utcnow()
+                db.session.add(data_source_binding)
+                db.session.commit()
+            else:
+                raise ValueError('Data source is not disabled.')
+        # disable binding
+        if action == 'disable':
+            if not data_source_binding.disabled:
+                data_source_binding.disabled = True
+                data_source_binding.updated_at = datetime.datetime.utcnow()
+                db.session.add(data_source_binding)
+                db.session.commit()
+            else:
+                raise ValueError('Data source is disabled.')
+        return {'result': 'success'}, 200
+
+
+class DataSourceNotionListApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(integrate_notion_info_list_fields)
+    def get(self):
+        dataset_id = request.args.get('dataset_id', default=None, type=str)
+        exist_page_ids = []
+        # import notion in the exist dataset
+        if dataset_id:
+            dataset = DatasetService.get_dataset(dataset_id)
+            if not dataset:
+                raise NotFound('Dataset not found.')
+            if dataset.data_source_type != 'notion_import':
+                raise ValueError('Dataset is not notion type.')
+            documents = Document.query.filter_by(
+                dataset_id=dataset_id,
+                tenant_id=current_user.current_tenant_id,
+                data_source_type='notion_import',
+                enabled=True
+            ).all()
+            if documents:
+                for document in documents:
+                    data_source_info = json.loads(document.data_source_info)
+                    exist_page_ids.append(data_source_info['notion_page_id'])
+        # get all authorized pages
+        data_source_bindings = DataSourceBinding.query.filter_by(
+            tenant_id=current_user.current_tenant_id,
+            provider='notion',
+            disabled=False
+        ).all()
+        if not data_source_bindings:
+            return {
+                'notion_info': []
+            }, 200
+        pre_import_info_list = []
+        for data_source_binding in data_source_bindings:
+            source_info = data_source_binding.source_info
+            pages = source_info['pages']
+            # Filter out already bound pages
+            for page in pages:
+                if page['page_id'] in exist_page_ids:
+                    page['is_bound'] = True
+                else:
+                    page['is_bound'] = False
+            pre_import_info = {
+                'workspace_name': source_info['workspace_name'],
+                'workspace_icon': source_info['workspace_icon'],
+                'workspace_id': source_info['workspace_id'],
+                'pages': pages,
+            }
+            pre_import_info_list.append(pre_import_info)
+        return {
+            'notion_info': pre_import_info_list
+        }, 200
+
+
+class DataSourceNotionApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, workspace_id, page_id, page_type):
+        workspace_id = str(workspace_id)
+        page_id = str(page_id)
+        data_source_binding = DataSourceBinding.query.filter(
+            db.and_(
+                DataSourceBinding.tenant_id == current_user.current_tenant_id,
+                DataSourceBinding.provider == 'notion',
+                DataSourceBinding.disabled == False,
+                DataSourceBinding.source_info['workspace_id'] == f'"{workspace_id}"'
+            )
+        ).first()
+        if not data_source_binding:
+            raise NotFound('Data source binding not found.')
+
+        loader = NotionLoader(
+            notion_access_token=data_source_binding.access_token,
+            notion_workspace_id=workspace_id,
+            notion_obj_id=page_id,
+            notion_page_type=page_type
+        )
+
+        text_docs = loader.load()
+        return {
+            'content': "\n".join([doc.page_content for doc in text_docs])
+        }, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('notion_info_list', type=list, required=True, nullable=True, location='json')
+        parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
+        args = parser.parse_args()
+        # validate args
+        DocumentService.estimate_args_validate(args)
+        indexing_runner = IndexingRunner()
+        response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id, args['notion_info_list'], args['process_rule'])
+        return response, 200
+
+
+class DataSourceNotionDatasetSyncApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        documents = DocumentService.get_document_by_dataset_id(dataset_id_str)
+        for document in documents:
+            document_indexing_sync_task.delay(dataset_id_str, document.id)
+        return 200
+
+
+class DataSourceNotionDocumentSyncApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id):
+        dataset_id_str = str(dataset_id)
+        document_id_str = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        document = DocumentService.get_document(dataset_id_str, document_id_str)
+        if document is None:
+            raise NotFound("Document not found.")
+        document_indexing_sync_task.delay(dataset_id_str, document_id_str)
+        return 200
+
+
+api.add_resource(DataSourceApi, '/data-source/integrates', '/data-source/integrates/<uuid:binding_id>/<string:action>')
+api.add_resource(DataSourceNotionListApi, '/notion/pre-import/pages')
+api.add_resource(DataSourceNotionApi,
+                 '/notion/workspaces/<uuid:workspace_id>/pages/<uuid:page_id>/<string:page_type>/preview',
+                 '/datasets/notion-indexing-estimate')
+api.add_resource(DataSourceNotionDatasetSyncApi, '/datasets/<uuid:dataset_id>/notion/sync')
+api.add_resource(DataSourceNotionDocumentSyncApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/notion/sync')

api/controllers/console/datasets/datasets.py

@@ -1,46 +1,29 @@
 # -*- coding:utf-8 -*-
-from flask import request
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, fields, marshal, marshal_with
-from werkzeug.exceptions import NotFound, Forbidden
+import flask_restful
+from flask import request, current_app
+from flask_login import current_user
 
+from controllers.console.apikey import api_key_list, api_key_fields
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal, marshal_with
+from werkzeug.exceptions import NotFound, Forbidden
 import services
 from controllers.console import api
+from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetNameDuplicateError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.indexing_runner import IndexingRunner
-from libs.helper import TimestampField
+from core.model_providers.error import LLMBadRequestError, ProviderTokenNotInitError
+from core.model_providers.models.entity.model_params import ModelType
+from fields.app_fields import related_app_list
+from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
+from fields.document_fields import document_status_fields
 from extensions.ext_database import db
-from models.model import UploadFile
-from services.dataset_service import DatasetService
-
-dataset_detail_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'description': fields.String,
-    'provider': fields.String,
-    'permission': fields.String,
-    'data_source_type': fields.String,
-    'indexing_technique': fields.String,
-    'app_count': fields.Integer,
-    'document_count': fields.Integer,
-    'word_count': fields.Integer,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'updated_by': fields.String,
-    'updated_at': TimestampField,
-}
-
-dataset_query_detail_fields = {
-    "id": fields.String,
-    "content": fields.String,
-    "source": fields.String,
-    "source_app_id": fields.String,
-    "created_by_role": fields.String,
-    "created_by": fields.String,
-    "created_at": TimestampField
-}
+from models.dataset import DocumentSegment, Document
+from models.model import UploadFile, ApiToken
+from services.dataset_service import DatasetService, DocumentService
+from services.provider_service import ProviderService
 
 
 def _validate_name(name):
@@ -50,8 +33,8 @@ def _validate_name(name):
 
 
 def _validate_description_length(description):
-    if len(description) > 200:
-        raise ValueError('Description cannot exceed 200 characters.')
+    if len(description) > 400:
+        raise ValueError('Description cannot exceed 400 characters.')
     return description
 
 
@@ -71,8 +54,29 @@ class DatasetListApi(Resource):
             datasets, total = DatasetService.get_datasets(page, limit, provider,
                                                           current_user.current_tenant_id, current_user)
 
+        # check embedding setting
+        provider_service = ProviderService()
+        valid_model_list = provider_service.get_valid_model_list(current_user.current_tenant_id,
+                                                                 ModelType.EMBEDDINGS.value)
+        # if len(valid_model_list) == 0:
+        #     raise ProviderNotInitializeError(
+        #         f"No Embedding Model available. Please configure a valid provider "
+        #         f"in the Settings -> Model Provider.")
+        model_names = []
+        for valid_model in valid_model_list:
+            model_names.append(f"{valid_model['model_name']}:{valid_model['model_provider']['provider_name']}")
+        data = marshal(datasets, dataset_detail_fields)
+        for item in data:
+            if item['indexing_technique'] == 'high_quality':
+                item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
+                if item_model in model_names:
+                    item['embedding_available'] = True
+                else:
+                    item['embedding_available'] = False
+            else:
+                item['embedding_available'] = True
         response = {
-            'data': marshal(datasets, dataset_detail_fields),
+            'data': data,
             'has_more': len(datasets) == limit,
             'limit': limit,
             'total': total,
@@ -119,20 +123,40 @@ class DatasetApi(Resource):
         dataset = DatasetService.get_dataset(dataset_id_str)
         if dataset is None:
             raise NotFound("Dataset not found.")
-
         try:
             DatasetService.check_dataset_permission(
                 dataset, current_user)
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
-
-        return marshal(dataset, dataset_detail_fields), 200
+        data = marshal(dataset, dataset_detail_fields)
+        # check embedding setting
+        provider_service = ProviderService()
+        # get valid model list
+        valid_model_list = provider_service.get_valid_model_list(current_user.current_tenant_id,
+                                                                 ModelType.EMBEDDINGS.value)
+        model_names = []
+        for valid_model in valid_model_list:
+            model_names.append(f"{valid_model['model_name']}:{valid_model['model_provider']['provider_name']}")
+        if data['indexing_technique'] == 'high_quality':
+            item_model = f"{data['embedding_model']}:{data['embedding_model_provider']}"
+            if item_model in model_names:
+                data['embedding_available'] = True
+            else:
+                data['embedding_available'] = False
+        else:
+            data['embedding_available'] = True
+        return data, 200
 
     @setup_required
     @login_required
     @account_initialization_required
     def patch(self, dataset_id):
         dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
 
         parser = reqparse.RequestParser()
         parser.add_argument('name', nullable=False,
@@ -217,33 +241,62 @@ class DatasetIndexingEstimateApi(Resource):
     @login_required
     @account_initialization_required
     def post(self):
-        segment_rule = request.get_json()
-        file_detail = db.session.query(UploadFile).filter(
-            UploadFile.tenant_id == current_user.current_tenant_id,
-            UploadFile.id == segment_rule["file_id"]
-        ).first()
+        parser = reqparse.RequestParser()
+        parser.add_argument('info_list', type=dict, required=True, nullable=True, location='json')
+        parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
+        parser.add_argument('indexing_technique', type=str, required=True, nullable=True, location='json')
+        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
+        parser.add_argument('dataset_id', type=str, required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
+        args = parser.parse_args()
+        # validate args
+        DocumentService.estimate_args_validate(args)
+        if args['info_list']['data_source_type'] == 'upload_file':
+            file_ids = args['info_list']['file_info_list']['file_ids']
+            file_details = db.session.query(UploadFile).filter(
+                UploadFile.tenant_id == current_user.current_tenant_id,
+                UploadFile.id.in_(file_ids)
+            ).all()
 
-        if file_detail is None:
-            raise NotFound("File not found.")
+            if file_details is None:
+                raise NotFound("File not found.")
 
-        indexing_runner = IndexingRunner()
-        response = indexing_runner.indexing_estimate(file_detail, segment_rule['process_rule'])
+            indexing_runner = IndexingRunner()
+
+            try:
+                response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, file_details,
+                                                                  args['process_rule'], args['doc_form'],
+                                                                  args['doc_language'], args['dataset_id'],
+                                                                  args['indexing_technique'])
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        elif args['info_list']['data_source_type'] == 'notion_import':
+
+            indexing_runner = IndexingRunner()
+
+            try:
+                response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id,
+                                                                    args['info_list']['notion_info_list'],
+                                                                    args['process_rule'], args['doc_form'],
+                                                                    args['doc_language'], args['dataset_id'],
+                                                                    args['indexing_technique'])
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        else:
+            raise ValueError('Data source type not support')
         return response, 200
 
 
 class DatasetRelatedAppListApi(Resource):
-    app_detail_kernel_fields = {
-        'id': fields.String,
-        'name': fields.String,
-        'mode': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-    }
-
-    related_app_list = {
-        'data': fields.List(fields.Nested(app_detail_kernel_fields)),
-        'total': fields.Integer,
-    }
 
     @setup_required
     @login_required
@@ -274,8 +327,121 @@ class DatasetRelatedAppListApi(Resource):
         }, 200
 
 
+class DatasetIndexingStatusApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id = str(dataset_id)
+        documents = db.session.query(Document).filter(
+            Document.dataset_id == dataset_id,
+            Document.tenant_id == current_user.current_tenant_id
+        ).all()
+        documents_status = []
+        for document in documents:
+            completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                              DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+            total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                          DocumentSegment.status != 're_segment').count()
+            document.completed_segments = completed_segments
+            document.total_segments = total_segments
+            documents_status.append(marshal(document, document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
+class DatasetApiKeyApi(Resource):
+    max_keys = 10
+    token_prefix = 'dataset-'
+    resource_type = 'dataset'
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_key_list)
+    def get(self):
+        keys = db.session.query(ApiToken). \
+            filter(ApiToken.type == self.resource_type, ApiToken.tenant_id == current_user.current_tenant_id). \
+            all()
+        return {"items": keys}
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_key_fields)
+    def post(self):
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        current_key_count = db.session.query(ApiToken). \
+            filter(ApiToken.type == self.resource_type, ApiToken.tenant_id == current_user.current_tenant_id). \
+            count()
+
+        if current_key_count >= self.max_keys:
+            flask_restful.abort(
+                400,
+                message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
+                code='max_keys_exceeded'
+            )
+
+        key = ApiToken.generate_api_key(self.token_prefix, 24)
+        api_token = ApiToken()
+        api_token.tenant_id = current_user.current_tenant_id
+        api_token.token = key
+        api_token.type = self.resource_type
+        db.session.add(api_token)
+        db.session.commit()
+        return api_token, 200
+
+
+class DatasetApiDeleteApi(Resource):
+    resource_type = 'dataset'
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, api_key_id):
+        api_key_id = str(api_key_id)
+
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        key = db.session.query(ApiToken). \
+            filter(ApiToken.tenant_id == current_user.current_tenant_id, ApiToken.type == self.resource_type,
+                   ApiToken.id == api_key_id). \
+            first()
+
+        if key is None:
+            flask_restful.abort(404, message='API key not found')
+
+        db.session.query(ApiToken).filter(ApiToken.id == api_key_id).delete()
+        db.session.commit()
+
+        return {'result': 'success'}, 204
+
+
+class DatasetApiBaseUrlApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        return {
+            'api_base_url': (current_app.config['SERVICE_API_URL'] if current_app.config['SERVICE_API_URL']
+                             else request.host_url.rstrip('/')) + '/v1'
+        }
+
+
 api.add_resource(DatasetListApi, '/datasets')
 api.add_resource(DatasetApi, '/datasets/<uuid:dataset_id>')
 api.add_resource(DatasetQueryApi, '/datasets/<uuid:dataset_id>/queries')
-api.add_resource(DatasetIndexingEstimateApi, '/datasets/file-indexing-estimate')
+api.add_resource(DatasetIndexingEstimateApi, '/datasets/indexing-estimate')
 api.add_resource(DatasetRelatedAppListApi, '/datasets/<uuid:dataset_id>/related-apps')
+api.add_resource(DatasetIndexingStatusApi, '/datasets/<uuid:dataset_id>/indexing-status')
+api.add_resource(DatasetApiKeyApi, '/datasets/api-keys')
+api.add_resource(DatasetApiDeleteApi, '/datasets/api-keys/<uuid:api_key_id>')
+api.add_resource(DatasetApiBaseUrlApi, '/datasets/api-base-info')

api/controllers/console/datasets/datasets_document.py

@@ -1,9 +1,10 @@
 # -*- coding:utf-8 -*-
-import random
 from datetime import datetime
+from typing import List
 
-from flask import request
-from flask_login import login_required, current_user
+from flask import request, current_app
+from flask_login import current_user
+from libs.login import login_required
 from flask_restful import Resource, fields, marshal, marshal_with, reqparse
 from sqlalchemy import desc, asc
 from werkzeug.exceptions import NotFound, Forbidden
@@ -17,9 +18,12 @@ from controllers.console.datasets.error import DocumentAlreadyFinishedError, Inv
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.indexing_runner import IndexingRunner
-from core.llm.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError, \
+    LLMBadRequestError
+from core.model_providers.model_factory import ModelFactory
 from extensions.ext_redis import redis_client
-from libs.helper import TimestampField
+from fields.document_fields import document_with_segments_fields, document_fields, \
+    dataset_and_document_fields, document_status_fields
 from extensions.ext_database import db
 from models.dataset import DatasetProcessRule, Dataset
 from models.dataset import Document, DocumentSegment
@@ -28,39 +32,6 @@ from services.dataset_service import DocumentService, DatasetService
 from tasks.add_document_to_index_task import add_document_to_index_task
 from tasks.remove_document_from_index_task import remove_document_from_index_task
 
-dataset_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'description': fields.String,
-    'permission': fields.String,
-    'data_source_type': fields.String,
-    'indexing_technique': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-}
-
-document_fields = {
-    'id': fields.String,
-    'position': fields.Integer,
-    'data_source_type': fields.String,
-    'data_source_info': fields.Raw(attribute='data_source_info_dict'),
-    'dataset_process_rule_id': fields.String,
-    'name': fields.String,
-    'created_from': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'tokens': fields.Integer,
-    'indexing_status': fields.String,
-    'error': fields.String,
-    'enabled': fields.Boolean,
-    'disabled_at': TimestampField,
-    'disabled_by': fields.String,
-    'archived': fields.Boolean,
-    'display_status': fields.String,
-    'word_count': fields.Integer,
-    'hit_count': fields.Integer,
-}
-
 
 class DocumentResource(Resource):
     def get_document(self, dataset_id: str, document_id: str) -> Document:
@@ -83,6 +54,23 @@ class DocumentResource(Resource):
 
         return document
 
+    def get_batch_documents(self, dataset_id: str, batch: str) -> List[Document]:
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound('Dataset not found.')
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        documents = DocumentService.get_batch_documents(dataset_id, batch)
+
+        if not documents:
+            raise NotFound('Documents not found.')
+
+        return documents
+
 
 class GetProcessRuleApi(Resource):
     @setup_required
@@ -92,6 +80,10 @@ class GetProcessRuleApi(Resource):
         req_data = request.args
 
         document_id = req_data.get('document_id')
+        
+        # get default rules
+        mode = DocumentService.DEFAULT_RULES['mode']
+        rules = DocumentService.DEFAULT_RULES['rules']
         if document_id:
             # get the latest process rule
             document = Document.query.get_or_404(document_id)
@@ -112,11 +104,9 @@ class GetProcessRuleApi(Resource):
                 order_by(DatasetProcessRule.created_at.desc()). \
                 limit(1). \
                 one_or_none()
-            mode = dataset_process_rule.mode
-            rules = dataset_process_rule.rules_dict
-        else:
-            mode = DocumentService.DEFAULT_RULES['mode']
-            rules = DocumentService.DEFAULT_RULES['rules']
+            if dataset_process_rule:
+                mode = dataset_process_rule.mode
+                rules = dataset_process_rule.rules_dict
 
         return {
             'mode': mode,
@@ -132,9 +122,9 @@ class DatasetDocumentListApi(Resource):
         dataset_id = str(dataset_id)
         page = request.args.get('page', default=1, type=int)
         limit = request.args.get('limit', default=20, type=int)
-        search = request.args.get('search', default=None, type=str)
+        search = request.args.get('keyword', default=None, type=str)
         sort = request.args.get('sort', default='-created_at', type=str)
-
+        fetch = request.args.get('fetch', default=False, type=bool)
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
             raise NotFound('Dataset not found.')
@@ -173,9 +163,20 @@ class DatasetDocumentListApi(Resource):
         paginated_documents = query.paginate(
             page=page, per_page=limit, max_per_page=100, error_out=False)
         documents = paginated_documents.items
-
+        if fetch:
+            for document in documents:
+                completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                                  DocumentSegment.document_id == str(document.id),
+                                                                  DocumentSegment.status != 're_segment').count()
+                total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+                document.completed_segments = completed_segments
+                document.total_segments = total_segments
+            data = marshal(documents, document_with_segments_fields)
+        else:
+            data = marshal(documents, document_fields)
         response = {
-            'data': marshal(documents, document_fields),
+            'data': data,
             'has_more': len(documents) == limit,
             'limit': limit,
             'total': paginated_documents.total,
@@ -184,10 +185,15 @@ class DatasetDocumentListApi(Resource):
 
         return response
 
+    documents_and_batch_fields = {
+        'documents': fields.List(fields.Nested(document_fields)),
+        'batch': fields.String
+    }
+
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(document_fields)
+    @marshal_with(documents_and_batch_fields)
     def post(self, dataset_id):
         dataset_id = str(dataset_id)
 
@@ -208,9 +214,13 @@ class DatasetDocumentListApi(Resource):
         parser = reqparse.RequestParser()
         parser.add_argument('indexing_technique', type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False,
                             location='json')
-        parser.add_argument('data_source', type=dict, required=True, nullable=True, location='json')
-        parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
+        parser.add_argument('data_source', type=dict, required=False, location='json')
+        parser.add_argument('process_rule', type=dict, required=False, location='json')
         parser.add_argument('duplicate', type=bool, nullable=False, location='json')
+        parser.add_argument('original_document_id', type=str, required=False, location='json')
+        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
         args = parser.parse_args()
 
         if not dataset.indexing_technique and not args['indexing_technique']:
@@ -220,22 +230,21 @@ class DatasetDocumentListApi(Resource):
         DocumentService.document_create_args_validate(args)
 
         try:
-            document = DocumentService.save_document_with_dataset_id(dataset, args, current_user)
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+            documents, batch = DocumentService.save_document_with_dataset_id(dataset, args, current_user)
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
             raise ProviderModelCurrentlyNotSupportError()
 
-        return document
+        return {
+            'documents': documents,
+            'batch': batch
+        }
 
 
 class DatasetInitApi(Resource):
-    dataset_and_document_fields = {
-        'dataset': fields.Nested(dataset_fields),
-        'document': fields.Nested(document_fields)
-    }
 
     @setup_required
     @login_required
@@ -251,19 +260,33 @@ class DatasetInitApi(Resource):
                             nullable=False, location='json')
         parser.add_argument('data_source', type=dict, required=True, nullable=True, location='json')
         parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
+        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
         args = parser.parse_args()
+        if args['indexing_technique'] == 'high_quality':
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
 
         # validate args
         DocumentService.document_create_args_validate(args)
 
         try:
-            dataset, document = DocumentService.save_document_without_dataset_id(
+            dataset, documents, batch = DocumentService.save_document_without_dataset_id(
                 tenant_id=current_user.current_tenant_id,
                 document_data=args,
                 account=current_user
             )
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -271,7 +294,8 @@ class DatasetInitApi(Resource):
 
         response = {
             'dataset': dataset,
-            'document': document
+            'documents': documents,
+            'batch': batch
         }
 
         return response
@@ -316,26 +340,134 @@ class DocumentIndexingEstimateApi(DocumentResource):
                     raise NotFound('File not found.')
 
                 indexing_runner = IndexingRunner()
-                response = indexing_runner.indexing_estimate(file, data_process_rule_dict)
+
+                try:
+                    response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, [file],
+                                                                      data_process_rule_dict, None,
+                                                                      'English', dataset_id)
+                except LLMBadRequestError:
+                    raise ProviderNotInitializeError(
+                        f"No Embedding Model available. Please configure a valid provider "
+                        f"in the Settings -> Model Provider.")
+                except ProviderTokenNotInitError as ex:
+                    raise ProviderNotInitializeError(ex.description)
 
         return response
 
 
+class DocumentBatchIndexingEstimateApi(DocumentResource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, batch):
+        dataset_id = str(dataset_id)
+        batch = str(batch)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        documents = self.get_batch_documents(dataset_id, batch)
+        response = {
+            "tokens": 0,
+            "total_price": 0,
+            "currency": "USD",
+            "total_segments": 0,
+            "preview": []
+        }
+        if not documents:
+            return response
+        data_process_rule = documents[0].dataset_process_rule
+        data_process_rule_dict = data_process_rule.to_dict()
+        info_list = []
+        for document in documents:
+            if document.indexing_status in ['completed', 'error']:
+                raise DocumentAlreadyFinishedError()
+            data_source_info = document.data_source_info_dict
+            # format document files info
+            if data_source_info and 'upload_file_id' in data_source_info:
+                file_id = data_source_info['upload_file_id']
+                info_list.append(file_id)
+            # format document notion info
+            elif data_source_info and 'notion_workspace_id' in data_source_info and 'notion_page_id' in data_source_info:
+                pages = []
+                page = {
+                    'page_id': data_source_info['notion_page_id'],
+                    'type': data_source_info['type']
+                }
+                pages.append(page)
+                notion_info = {
+                    'workspace_id': data_source_info['notion_workspace_id'],
+                    'pages': pages
+                }
+                info_list.append(notion_info)
+
+        if dataset.data_source_type == 'upload_file':
+            file_details = db.session.query(UploadFile).filter(
+                UploadFile.tenant_id == current_user.current_tenant_id,
+                UploadFile.id in info_list
+            ).all()
+
+            if file_details is None:
+                raise NotFound("File not found.")
+
+            indexing_runner = IndexingRunner()
+            try:
+                response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, file_details,
+                                                                  data_process_rule_dict, None,
+                                                                  'English', dataset_id)
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        elif dataset.data_source_type == 'notion_import':
+
+            indexing_runner = IndexingRunner()
+            try:
+                response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id,
+                                                                    info_list,
+                                                                    data_process_rule_dict,
+                                                                    None, 'English', dataset_id)
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        else:
+            raise ValueError('Data source type not support')
+        return response
+
+
+class DocumentBatchIndexingStatusApi(DocumentResource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, batch):
+        dataset_id = str(dataset_id)
+        batch = str(batch)
+        documents = self.get_batch_documents(dataset_id, batch)
+        documents_status = []
+        for document in documents:
+            completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                              DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+            total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                          DocumentSegment.status != 're_segment').count()
+            document.completed_segments = completed_segments
+            document.total_segments = total_segments
+            if document.is_paused:
+                document.indexing_status = 'paused'
+            documents_status.append(marshal(document, document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
 class DocumentIndexingStatusApi(DocumentResource):
-    document_status_fields = {
-        'id': fields.String,
-        'indexing_status': fields.String,
-        'processing_started_at': TimestampField,
-        'parsing_completed_at': TimestampField,
-        'cleaning_completed_at': TimestampField,
-        'splitting_completed_at': TimestampField,
-        'completed_at': TimestampField,
-        'paused_at': TimestampField,
-        'error': fields.String,
-        'stopped_at': TimestampField,
-        'completed_segments': fields.Integer,
-        'total_segments': fields.Integer,
-    }
 
     @setup_required
     @login_required
@@ -347,16 +479,19 @@ class DocumentIndexingStatusApi(DocumentResource):
 
         completed_segments = DocumentSegment.query \
             .filter(DocumentSegment.completed_at.isnot(None),
-                    DocumentSegment.document_id == str(document_id)) \
+                    DocumentSegment.document_id == str(document_id),
+                    DocumentSegment.status != 're_segment') \
             .count()
         total_segments = DocumentSegment.query \
-            .filter_by(document_id=str(document_id)) \
+            .filter(DocumentSegment.document_id == str(document_id),
+                    DocumentSegment.status != 're_segment') \
             .count()
 
         document.completed_segments = completed_segments
         document.total_segments = total_segments
-
-        return marshal(document, self.document_status_fields)
+        if document.is_paused:
+            document.indexing_status = 'paused'
+        return marshal(document, document_status_fields)
 
 
 class DocumentDetailApi(DocumentResource):
@@ -405,9 +540,10 @@ class DocumentDetailApi(DocumentResource):
                 'disabled_by': document.disabled_by,
                 'archived': document.archived,
                 'segment_count': document.segment_count,
-                'average_segment_length':   document.average_segment_length,
+                'average_segment_length': document.average_segment_length,
                 'hit_count': document.hit_count,
-                'display_status': document.display_status
+                'display_status': document.display_status,
+                'doc_form': document.doc_form
             }
         else:
             process_rules = DatasetService.get_process_rules(dataset_id)
@@ -425,7 +561,7 @@ class DocumentDetailApi(DocumentResource):
                 'created_at': document.created_at.timestamp(),
                 'tokens': document.tokens,
                 'indexing_status': document.indexing_status,
-                'completed_at': int(document.completed_at.timestamp())if document.completed_at else None,
+                'completed_at': int(document.completed_at.timestamp()) if document.completed_at else None,
                 'updated_at': int(document.updated_at.timestamp()) if document.updated_at else None,
                 'indexing_latency': document.indexing_latency,
                 'error': document.error,
@@ -438,7 +574,8 @@ class DocumentDetailApi(DocumentResource):
                 'segment_count': document.segment_count,
                 'average_segment_length': document.average_segment_length,
                 'hit_count': document.hit_count,
-                'display_status': document.display_status
+                'display_status': document.display_status,
+                'doc_form': document.doc_form
             }
 
         return response, 200
@@ -487,6 +624,12 @@ class DocumentDeleteApi(DocumentResource):
     def delete(self, dataset_id, document_id):
         dataset_id = str(dataset_id)
         document_id = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+
         document = self.get_document(dataset_id, document_id)
 
         try:
@@ -527,11 +670,13 @@ class DocumentMetadataApi(DocumentResource):
         metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[doc_type]
 
         document.doc_metadata = {}
-
-        for key, value_type in metadata_schema.items():
-            value = doc_metadata.get(key)
-            if value is not None and isinstance(value, value_type):
-                document.doc_metadata[key] = value
+        if doc_type == 'others':
+            document.doc_metadata = doc_metadata
+        else:
+            for key, value_type in metadata_schema.items():
+                value = doc_metadata.get(key)
+                if value is not None and isinstance(value, value_type):
+                    document.doc_metadata[key] = value
 
         document.doc_type = doc_type
         document.updated_at = datetime.utcnow()
@@ -547,6 +692,12 @@ class DocumentStatusApi(DocumentResource):
     def patch(self, dataset_id, document_id, action):
         dataset_id = str(dataset_id)
         document_id = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+
         document = self.get_document(dataset_id, document_id)
 
         # The role of the current user in the ta table must be admin or owner
@@ -576,6 +727,8 @@ class DocumentStatusApi(DocumentResource):
             return {'result': 'success'}, 200
 
         elif action == "disable":
+            if not document.completed_at or document.indexing_status != 'completed':
+                raise InvalidActionError('Document is not completed.')
             if not document.enabled:
                 raise InvalidActionError('Document already disabled.')
 
@@ -608,12 +761,40 @@ class DocumentStatusApi(DocumentResource):
 
                 remove_document_from_index_task.delay(document_id)
 
+            return {'result': 'success'}, 200
+        elif action == "un_archive":
+            if not document.archived:
+                raise InvalidActionError('Document is not archived.')
+
+            # check document limit
+            if current_app.config['EDITION'] == 'CLOUD':
+                documents_count = DocumentService.get_tenant_documents_count()
+                total_count = documents_count + 1
+                tenant_document_count = int(current_app.config['TENANT_DOCUMENT_COUNT'])
+                if total_count > tenant_document_count:
+                    raise ValueError(f"All your documents have overed limit {tenant_document_count}.")
+
+            document.archived = False
+            document.archived_at = None
+            document.archived_by = None
+            document.updated_at = datetime.utcnow()
+            db.session.commit()
+
+            # Set cache to prevent indexing the same document multiple times
+            redis_client.setex(indexing_cache_key, 600, 1)
+
+            add_document_to_index_task.delay(document_id)
+
             return {'result': 'success'}, 200
         else:
             raise InvalidActionError()
 
 
 class DocumentPauseApi(DocumentResource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
     def patch(self, dataset_id, document_id):
         """pause document."""
         dataset_id = str(dataset_id)
@@ -643,6 +824,9 @@ class DocumentPauseApi(DocumentResource):
 
 
 class DocumentRecoverApi(DocumentResource):
+    @setup_required
+    @login_required
+    @account_initialization_required
     def patch(self, dataset_id, document_id):
         """recover document."""
         dataset_id = str(dataset_id)
@@ -668,6 +852,21 @@ class DocumentRecoverApi(DocumentResource):
         return {'result': 'success'}, 204
 
 
+class DocumentLimitApi(DocumentResource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        """get document limit"""
+        documents_count = DocumentService.get_tenant_documents_count()
+        tenant_document_count = int(current_app.config['TENANT_DOCUMENT_COUNT'])
+
+        return {
+            'documents_count': documents_count,
+            'documents_limit': tenant_document_count
+                }, 200
+
+
 api.add_resource(GetProcessRuleApi, '/datasets/process-rule')
 api.add_resource(DatasetDocumentListApi,
                  '/datasets/<uuid:dataset_id>/documents')
@@ -675,6 +874,10 @@ api.add_resource(DatasetInitApi,
                  '/datasets/init')
 api.add_resource(DocumentIndexingEstimateApi,
                  '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-estimate')
+api.add_resource(DocumentBatchIndexingEstimateApi,
+                 '/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-estimate')
+api.add_resource(DocumentBatchIndexingStatusApi,
+                 '/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-status')
 api.add_resource(DocumentIndexingStatusApi,
                  '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-status')
 api.add_resource(DocumentDetailApi,
@@ -689,3 +892,4 @@ api.add_resource(DocumentStatusApi,
                  '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/status/<string:action>')
 api.add_resource(DocumentPauseApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/pause')
 api.add_resource(DocumentRecoverApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/resume')
+api.add_resource(DocumentLimitApi, '/datasets/limit')

api/controllers/console/datasets/datasets_segments.py

@@ -1,52 +1,30 @@
 # -*- coding:utf-8 -*-
+import uuid
 from datetime import datetime
-
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, fields, marshal
+from flask import request
+from flask_login import current_user
+from flask_restful import Resource, reqparse, marshal
 from werkzeug.exceptions import NotFound, Forbidden
 
 import services
 from controllers.console import api
-from controllers.console.datasets.error import InvalidActionError
+from controllers.console.app.error import ProviderNotInitializeError
+from controllers.console.datasets.error import InvalidActionError, NoFileUploadedError, TooManyFilesError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
+from core.model_providers.error import LLMBadRequestError, ProviderTokenNotInitError
+from core.model_providers.model_factory import ModelFactory
+from libs.login import login_required
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
+from fields.segment_fields import segment_fields
 from models.dataset import DocumentSegment
 
-from libs.helper import TimestampField
-from services.dataset_service import DatasetService, DocumentService
-from tasks.add_segment_to_index_task import add_segment_to_index_task
-from tasks.remove_segment_from_index_task import remove_segment_from_index_task
-
-segment_fields = {
-    'id': fields.String,
-    'position': fields.Integer,
-    'document_id': fields.String,
-    'content': fields.String,
-    'word_count': fields.Integer,
-    'tokens': fields.Integer,
-    'keywords': fields.List(fields.String),
-    'index_node_id': fields.String,
-    'index_node_hash': fields.String,
-    'hit_count': fields.Integer,
-    'enabled': fields.Boolean,
-    'disabled_at': TimestampField,
-    'disabled_by': fields.String,
-    'status': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'indexing_at': TimestampField,
-    'completed_at': TimestampField,
-    'error': fields.String,
-    'stopped_at': TimestampField
-}
-
-segment_list_response = {
-    'data': fields.List(fields.Nested(segment_fields)),
-    'has_more': fields.Boolean,
-    'limit': fields.Integer
-}
+from services.dataset_service import DatasetService, DocumentService, SegmentService
+from tasks.enable_segment_to_index_task import enable_segment_to_index_task
+from tasks.disable_segment_from_index_task import disable_segment_from_index_task
+from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
+import pandas as pd
 
 
 class DatasetDocumentSegmentListApi(Resource):
@@ -78,12 +56,14 @@ class DatasetDocumentSegmentListApi(Resource):
         parser.add_argument('hit_count_gte', type=int,
                             default=None, location='args')
         parser.add_argument('enabled', type=str, default='all', location='args')
+        parser.add_argument('keyword', type=str, default=None, location='args')
         args = parser.parse_args()
 
         last_id = args['last_id']
         limit = min(args['limit'], 100)
         status_list = args['status']
         hit_count_gte = args['hit_count_gte']
+        keyword = args['keyword']
 
         query = DocumentSegment.query.filter(
             DocumentSegment.document_id == str(document_id),
@@ -104,6 +84,9 @@ class DatasetDocumentSegmentListApi(Resource):
         if hit_count_gte is not None:
             query = query.filter(DocumentSegment.hit_count >= hit_count_gte)
 
+        if keyword:
+            query = query.where(DocumentSegment.content.ilike(f'%{keyword}%'))
+
         if args['enabled'].lower() != 'all':
             if args['enabled'].lower() == 'true':
                 query = query.filter(DocumentSegment.enabled == True)
@@ -120,6 +103,7 @@ class DatasetDocumentSegmentListApi(Resource):
 
         return {
             'data': marshal(segments, segment_fields),
+            'doc_form': document.doc_form,
             'has_more': has_more,
             'limit': limit,
             'total': total
@@ -135,7 +119,8 @@ class DatasetDocumentSegmentApi(Resource):
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
             raise NotFound('Dataset not found.')
-
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
         # The role of the current user in the ta table must be admin or owner
         if current_user.current_tenant.current_role not in ['admin', 'owner']:
             raise Forbidden()
@@ -144,6 +129,20 @@ class DatasetDocumentSegmentApi(Resource):
             DatasetService.check_dataset_permission(dataset, current_user)
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
+        if dataset.indexing_technique == 'high_quality':
+            # check embedding model setting
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
 
         segment = DocumentSegment.query.filter(
             DocumentSegment.id == str(segment_id),
@@ -175,7 +174,7 @@ class DatasetDocumentSegmentApi(Resource):
             # Set cache to prevent indexing the same segment multiple times
             redis_client.setex(indexing_cache_key, 600, 1)
 
-            add_segment_to_index_task.delay(segment.id)
+            enable_segment_to_index_task.delay(segment.id)
 
             return {'result': 'success'}, 200
         elif action == "disable":
@@ -190,14 +189,234 @@ class DatasetDocumentSegmentApi(Resource):
             # Set cache to prevent indexing the same segment multiple times
             redis_client.setex(indexing_cache_key, 600, 1)
 
-            remove_segment_from_index_task.delay(segment.id)
+            disable_segment_from_index_task.delay(segment.id)
 
             return {'result': 'success'}, 200
         else:
             raise InvalidActionError()
 
 
+class DatasetDocumentSegmentAddApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, dataset_id, document_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+        # check embedding model setting
+        if dataset.indexing_technique == 'high_quality':
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument('content', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('answer', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('keywords', type=list, required=False, nullable=True, location='json')
+        args = parser.parse_args()
+        SegmentService.segment_create_args_validate(args, document)
+        segment = SegmentService.create_segment(args, document, dataset)
+        return {
+            'data': marshal(segment, segment_fields),
+            'doc_form': document.doc_form
+        }, 200
+
+
+class DatasetDocumentSegmentUpdateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        if dataset.indexing_technique == 'high_quality':
+            # check embedding model setting
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+            # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id),
+            DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound('Segment not found.')
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument('content', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('answer', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('keywords', type=list, required=False, nullable=True, location='json')
+        args = parser.parse_args()
+        SegmentService.segment_create_args_validate(args, document)
+        segment = SegmentService.update_segment(args, segment, document, dataset)
+        return {
+            'data': marshal(segment, segment_fields),
+            'doc_form': document.doc_form
+        }, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id),
+            DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound('Segment not found.')
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        SegmentService.delete_segment(segment, document, dataset)
+        return {'result': 'success'}, 200
+
+
+class DatasetDocumentSegmentBatchImportApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, dataset_id, document_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        # get file from request
+        file = request.files['file']
+        # check file
+        if 'file' not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+        # check file type
+        if not file.filename.endswith('.csv'):
+            raise ValueError("Invalid file type. Only CSV files are allowed")
+
+        try:
+            # Skip the first row
+            df = pd.read_csv(file)
+            result = []
+            for index, row in df.iterrows():
+                if document.doc_form == 'qa_model':
+                    data = {'content': row[0], 'answer': row[1]}
+                else:
+                    data = {'content': row[0]}
+                result.append(data)
+            if len(result) == 0:
+                raise ValueError("The CSV file is empty.")
+            # async job
+            job_id = str(uuid.uuid4())
+            indexing_cache_key = 'segment_batch_import_{}'.format(str(job_id))
+            # send batch add segments task
+            redis_client.setnx(indexing_cache_key, 'waiting')
+            batch_create_segment_to_index_task.delay(str(job_id), result, dataset_id, document_id,
+                                                     current_user.current_tenant_id, current_user.id)
+        except Exception as e:
+            return {'error': str(e)}, 500
+        return {
+            'job_id': job_id,
+            'job_status': 'waiting'
+        }, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, job_id):
+        job_id = str(job_id)
+        indexing_cache_key = 'segment_batch_import_{}'.format(job_id)
+        cache_result = redis_client.get(indexing_cache_key)
+        if cache_result is None:
+            raise ValueError("The job is not exist.")
+
+        return {
+            'job_id': job_id,
+            'job_status': cache_result.decode()
+        }, 200
+
+
 api.add_resource(DatasetDocumentSegmentListApi,
                  '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments')
 api.add_resource(DatasetDocumentSegmentApi,
                  '/datasets/<uuid:dataset_id>/segments/<uuid:segment_id>/<string:action>')
+api.add_resource(DatasetDocumentSegmentAddApi,
+                 '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment')
+api.add_resource(DatasetDocumentSegmentUpdateApi,
+                 '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>')
+api.add_resource(DatasetDocumentSegmentBatchImportApi,
+                 '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/batch_import',
+                 '/datasets/batch_import_status/<uuid:job_id>')

api/controllers/console/datasets/file.py

@@ -1,45 +1,39 @@
-import datetime
-import hashlib
-import tempfile
-import time
-import uuid
-from pathlib import Path
-
 from cachetools import TTLCache
 from flask import request, current_app
-from flask_login import login_required, current_user
-from flask_restful import Resource, marshal_with, fields
-from werkzeug.exceptions import NotFound
+
+import services
+from libs.login import login_required
+from flask_restful import Resource, marshal_with
 
 from controllers.console import api
 from controllers.console.datasets.error import NoFileUploadedError, TooManyFilesError, FileTooLargeError, \
     UnsupportedFileTypeError
+
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.index.readers.html_parser import HTMLParser
-from core.index.readers.pdf_parser import PDFParser
-from extensions.ext_storage import storage
-from libs.helper import TimestampField
-from extensions.ext_database import db
-from models.model import UploadFile
+from fields.file_fields import upload_config_fields, file_fields
+
+from services.file_service import FileService
 
 cache = TTLCache(maxsize=None, ttl=30)
 
-FILE_SIZE_LIMIT = 15 * 1024 * 1024  # 15MB
-ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm']
+ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'docx', 'csv']
 PREVIEW_WORDS_LIMIT = 3000
 
 
 class FileApi(Resource):
-    file_fields = {
-        'id': fields.String,
-        'name': fields.String,
-        'size': fields.Integer,
-        'extension': fields.String,
-        'mime_type': fields.String,
-        'created_by': fields.String,
-        'created_at': TimestampField,
-    }
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(upload_config_fields)
+    def get(self):
+        file_size_limit = current_app.config.get("UPLOAD_FILE_SIZE_LIMIT")
+        batch_count_limit = current_app.config.get("UPLOAD_FILE_BATCH_LIMIT")
+        return {
+            'file_size_limit': file_size_limit,
+            'batch_count_limit': batch_count_limit
+        }, 200
 
     @setup_required
     @login_required
@@ -56,44 +50,13 @@ class FileApi(Resource):
 
         if len(request.files) > 1:
             raise TooManyFilesError()
-
-        file_content = file.read()
-        file_size = len(file_content)
-
-        if file_size > FILE_SIZE_LIMIT:
-            message = "({file_size} > {FILE_SIZE_LIMIT})"
-            raise FileTooLargeError(message)
-
-        extension = file.filename.split('.')[-1]
-        if extension not in ALLOWED_EXTENSIONS:
+        try:
+            upload_file = FileService.upload_file(file)
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
             raise UnsupportedFileTypeError()
 
-        # user uuid as file name
-        file_uuid = str(uuid.uuid4())
-        file_key = 'upload_files/' + current_user.current_tenant_id + '/' + file_uuid + '.' + extension
-
-        # save file to storage
-        storage.save(file_key, file_content)
-
-        # save file to db
-        config = current_app.config
-        upload_file = UploadFile(
-            tenant_id=current_user.current_tenant_id,
-            storage_type=config['STORAGE_TYPE'],
-            key=file_key,
-            name=file.filename,
-            size=file_size,
-            extension=extension,
-            mime_type=file.mimetype,
-            created_by=current_user.id,
-            created_at=datetime.datetime.utcnow(),
-            used=False,
-            hash=hashlib.sha3_256(file_content).hexdigest()
-        )
-
-        db.session.add(upload_file)
-        db.session.commit()
-
         return upload_file, 201
 
 
@@ -103,43 +66,7 @@ class FilePreviewApi(Resource):
     @account_initialization_required
     def get(self, file_id):
         file_id = str(file_id)
-
-        key = file_id + request.path
-        cached_response = cache.get(key)
-        if cached_response and time.time() - cached_response['timestamp'] < cache.ttl:
-            return cached_response['response']
-
-        upload_file = db.session.query(UploadFile) \
-            .filter(UploadFile.id == file_id) \
-            .first()
-
-        if not upload_file:
-            raise NotFound("File not found")
-
-        # extract text from file
-        extension = upload_file.extension
-        if extension not in ALLOWED_EXTENSIONS:
-            raise UnsupportedFileTypeError()
-
-        with tempfile.TemporaryDirectory() as temp_dir:
-            suffix = Path(upload_file.key).suffix
-            filepath = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"
-            storage.download(upload_file.key, filepath)
-
-            if extension == 'pdf':
-                parser = PDFParser({'upload_file': upload_file})
-                text = parser.parse_file(Path(filepath))
-            elif extension in ['html', 'htm']:
-                # Use BeautifulSoup to extract text
-                parser = HTMLParser()
-                text = parser.parse_file(Path(filepath))
-            else:
-                # ['txt', 'markdown', 'md']
-                with open(filepath, "rb") as fp:
-                    data = fp.read()
-                    text = data.decode(encoding='utf-8').strip() if data else ''
-
-        text = text[0:PREVIEW_WORDS_LIMIT] if text else ''
+        text = FileService.get_file_preview(file_id)
         return {'content': text}
 
 

api/controllers/console/datasets/hit_testing.py

@@ -1,7 +1,8 @@
 import logging
 
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, marshal, fields
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal
 from werkzeug.exceptions import InternalServerError, NotFound, Forbidden
 
 import services
@@ -11,48 +12,12 @@ from controllers.console.app.error import ProviderNotInitializeError, ProviderQu
 from controllers.console.datasets.error import HighQualityDatasetOnlyError, DatasetNotInitializedError
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.llm.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
-from libs.helper import TimestampField
+from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError, \
+    LLMBadRequestError
+from fields.hit_testing_fields import hit_testing_record_fields
 from services.dataset_service import DatasetService
 from services.hit_testing_service import HitTestingService
 
-document_fields = {
-    'id': fields.String,
-    'data_source_type': fields.String,
-    'name': fields.String,
-    'doc_type': fields.String,
-}
-
-segment_fields = {
-    'id': fields.String,
-    'position': fields.Integer,
-    'document_id': fields.String,
-    'content': fields.String,
-    'word_count': fields.Integer,
-    'tokens': fields.Integer,
-    'keywords': fields.List(fields.String),
-    'index_node_id': fields.String,
-    'index_node_hash': fields.String,
-    'hit_count': fields.Integer,
-    'enabled': fields.Boolean,
-    'disabled_at': TimestampField,
-    'disabled_by': fields.String,
-    'status': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'indexing_at': TimestampField,
-    'completed_at': TimestampField,
-    'error': fields.String,
-    'stopped_at': TimestampField,
-    'document': fields.Nested(document_fields),
-}
-
-hit_testing_record_fields = {
-    'segment': fields.Nested(segment_fields),
-    'score': fields.Float,
-    'tsne_position': fields.Raw
-}
-
 
 class HitTestingApi(Resource):
 
@@ -95,12 +60,18 @@ class HitTestingApi(Resource):
             return {"query": response['query'], 'records': marshal(response['records'], hit_testing_record_fields)}
         except services.errors.index.IndexNotInitializedError:
             raise DatasetNotInitializedError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
             raise ProviderModelCurrentlyNotSupportError()
+        except LLMBadRequestError:
+            raise ProviderNotInitializeError(
+                f"No Embedding Model available. Please configure a valid provider "
+                f"in the Settings -> Model Provider.")
+        except ValueError as e:
+            raise ValueError(str(e))
         except Exception as e:
             logging.exception("Hit testing failed.")
             raise InternalServerError(str(e))

api/controllers/console/error.py

@@ -18,3 +18,9 @@ class AccountNotLinkTenantError(BaseHTTPException):
     error_code = 'account_not_link_tenant'
     description = "Account not link tenant."
     code = 403
+
+
+class AlreadyActivateError(BaseHTTPException):
+    error_code = 'already_activate'
+    description = "Auth Token is invalid or account already activated, please check again."
+    code = 403

api/controllers/console/explore/audio.py

@@ -0,0 +1,66 @@
+# -*- coding:utf-8 -*-
+import logging
+
+from flask import request
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.console import api
+from controllers.console.app.error import AppUnavailableError, ProviderNotInitializeError, \
+    ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError, \
+    NoAudioUploadedError, AudioTooLargeError, \
+    UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
+from controllers.console.explore.wraps import InstalledAppResource
+from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from services.audio_service import AudioService
+from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
+    UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
+from models.model import AppModelConfig
+
+
+class ChatAudioApi(InstalledAppResource):
+    def post(self, installed_app):
+        app_model = installed_app.app
+        app_model_config: AppModelConfig = app_model.app_model_config
+
+        if not app_model_config.speech_to_text_dict['enabled']:
+            raise AppUnavailableError()
+
+        file = request.files['file']
+
+        try:
+            response = AudioService.transcript(
+                tenant_id=app_model.tenant_id,
+                file=file,
+            )
+
+            return response
+        except services.errors.app_model_config.AppModelConfigBrokenError:
+            logging.exception("App model config broken.")
+            raise AppUnavailableError()
+        except NoAudioUploadedServiceError:
+            raise NoAudioUploadedError()
+        except AudioTooLargeServiceError as e:
+            raise AudioTooLargeError(str(e))
+        except UnsupportedAudioTypeServiceError:
+            raise UnsupportedAudioTypeError()
+        except ProviderNotSupportSpeechToTextServiceError:
+            raise ProviderNotSupportSpeechToTextError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+        except ValueError as e:
+            raise e
+        except Exception as e:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+        
+
+api.add_resource(ChatAudioApi, '/installed-apps/<uuid:installed_app_id>/audio-to-text', endpoint='installed_app_audio')

api/controllers/console/explore/completion.py

@@ -15,7 +15,7 @@ from controllers.console.app.error import ConversationCompletedError, AppUnavail
 from controllers.console.explore.error import NotCompletionAppError, NotChatAppError
 from controllers.console.explore.wraps import InstalledAppResource
 from core.conversation_message_task import PubHandler
-from core.llm.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
+from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
     LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
 from libs.helper import uuid_value
 from services.completion_service import CompletionService
@@ -31,8 +31,9 @@ class CompletionApi(InstalledAppResource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
-        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('query', type=str, location='json', default='')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='explore_app', location='json')
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
@@ -54,8 +55,8 @@ class CompletionApi(InstalledAppResource):
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")
             raise AppUnavailableError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -92,6 +93,7 @@ class ChatApi(InstalledAppResource):
         parser.add_argument('query', type=str, required=True, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='explore_app', location='json')
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
@@ -113,8 +115,8 @@ class ChatApi(InstalledAppResource):
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")
             raise AppUnavailableError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -155,8 +157,8 @@ def compact_response(response: Union[dict | Generator]) -> Response:
             except services.errors.app_model_config.AppModelConfigBrokenError:
                 logging.exception("App model config broken.")
                 yield "data: " + json.dumps(api.handle_error(AppUnavailableError()).get_json()) + "\n\n"
-            except ProviderTokenNotInitError:
-                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError()).get_json()) + "\n\n"
+            except ProviderTokenNotInitError as ex:
+                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError(ex.description)).get_json()) + "\n\n"
             except QuotaExceededError:
                 yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
             except ModelCurrentlyNotSupportError:

api/controllers/console/explore/conversation.py

@@ -7,26 +7,12 @@ from werkzeug.exceptions import NotFound
 from controllers.console import api
 from controllers.console.explore.error import NotChatAppError
 from controllers.console.explore.wraps import InstalledAppResource
+from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import TimestampField, uuid_value
 from services.conversation_service import ConversationService
 from services.errors.conversation import LastConversationNotExistsError, ConversationNotExistsError
 from services.web_conversation_service import WebConversationService
 
-conversation_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'inputs': fields.Raw,
-    'status': fields.String,
-    'introduction': fields.String,
-    'created_at': TimestampField
-}
-
-conversation_infinite_scroll_pagination_fields = {
-    'limit': fields.Integer,
-    'has_more': fields.Boolean,
-    'data': fields.List(fields.Nested(conversation_fields))
-}
-
 
 class ConversationListApi(InstalledAppResource):
 
@@ -65,7 +51,10 @@ class ConversationApi(InstalledAppResource):
             raise NotChatAppError()
 
         conversation_id = str(c_id)
-        ConversationService.delete(app_model, conversation_id, current_user)
+        try:
+            ConversationService.delete(app_model, conversation_id, current_user)
+        except ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
         WebConversationService.unpin(app_model, conversation_id, current_user)
 
         return {"result": "success"}, 204
@@ -73,7 +62,7 @@ class ConversationApi(InstalledAppResource):
 
 class ConversationRenameApi(InstalledAppResource):
 
-    @marshal_with(conversation_fields)
+    @marshal_with(simple_conversation_fields)
     def post(self, installed_app, c_id):
         app_model = installed_app.app
         if app_model.mode != 'chat':

api/controllers/console/explore/installed_app.py

@@ -1,8 +1,9 @@
 # -*- coding:utf-8 -*-
 from datetime import datetime
 
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, fields, marshal_with, inputs
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with, inputs
 from sqlalchemy import and_
 from werkzeug.exceptions import NotFound, Forbidden, BadRequest
 
@@ -10,32 +11,10 @@ from controllers.console import api
 from controllers.console.explore.wraps import InstalledAppResource
 from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
-from libs.helper import TimestampField
+from fields.installed_app_fields import installed_app_list_fields
 from models.model import App, InstalledApp, RecommendedApp
 from services.account_service import TenantService
 
-app_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'mode': fields.String,
-    'icon': fields.String,
-    'icon_background': fields.String
-}
-
-installed_app_fields = {
-    'id': fields.String,
-    'app': fields.Nested(app_fields),
-    'app_owner_tenant_id': fields.String,
-    'is_pinned': fields.Boolean,
-    'last_used_at': TimestampField,
-    'editable': fields.Boolean,
-    'uninstallable': fields.Boolean,
-}
-
-installed_app_list_fields = {
-    'installed_apps': fields.List(fields.Nested(installed_app_fields))
-}
-
 
 class InstalledAppsListApi(Resource):
     @login_required

api/controllers/console/explore/message.py

@@ -15,8 +15,9 @@ from controllers.console.app.error import AppMoreLikeThisDisabledError, Provider
     ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError
 from controllers.console.explore.error import NotCompletionAppError, AppSuggestedQuestionsAfterAnswerDisabledError
 from controllers.console.explore.wraps import InstalledAppResource
-from core.llm.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
+from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
     ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
+from fields.message_fields import message_infinite_scroll_pagination_fields
 from libs.helper import uuid_value, TimestampField
 from services.completion_service import CompletionService
 from services.errors.app import MoreLikeThisDisabledError
@@ -26,25 +27,6 @@ from services.message_service import MessageService
 
 
 class MessageListApi(InstalledAppResource):
-    feedback_fields = {
-        'rating': fields.String
-    }
-
-    message_fields = {
-        'id': fields.String,
-        'conversation_id': fields.String,
-        'inputs': fields.Raw,
-        'query': fields.String,
-        'answer': fields.String,
-        'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
-        'created_at': TimestampField
-    }
-
-    message_infinite_scroll_pagination_fields = {
-        'limit': fields.Integer,
-        'has_more': fields.Boolean,
-        'data': fields.List(fields.Nested(message_fields))
-    }
 
     @marshal_with(message_infinite_scroll_pagination_fields)
     def get(self, installed_app):
@@ -107,8 +89,8 @@ class MessageMoreLikeThisApi(InstalledAppResource):
             raise NotFound("Message Not Exists.")
         except MoreLikeThisDisabledError:
             raise AppMoreLikeThisDisabledError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -135,8 +117,8 @@ def compact_response(response: Union[dict | Generator]) -> Response:
                 yield "data: " + json.dumps(api.handle_error(NotFound("Message Not Exists.")).get_json()) + "\n\n"
             except MoreLikeThisDisabledError:
                 yield "data: " + json.dumps(api.handle_error(AppMoreLikeThisDisabledError()).get_json()) + "\n\n"
-            except ProviderTokenNotInitError:
-                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError()).get_json()) + "\n\n"
+            except ProviderTokenNotInitError as ex:
+                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError(ex.description)).get_json()) + "\n\n"
             except QuotaExceededError:
                 yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
             except ModelCurrentlyNotSupportError:
@@ -174,8 +156,8 @@ class MessageSuggestedQuestionApi(InstalledAppResource):
             raise NotFound("Conversation not found")
         except SuggestedQuestionsAfterAnswerDisabledError:
             raise AppSuggestedQuestionsAfterAnswerDisabledError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:

api/controllers/console/explore/parameter.py

@@ -4,6 +4,8 @@ from flask_restful import marshal_with, fields
 from controllers.console import api
 from controllers.console.explore.wraps import InstalledAppResource
 
+from models.model import InstalledApp
+
 
 class AppParameterApi(InstalledAppResource):
     """Resource for app variables."""
@@ -21,12 +23,14 @@ class AppParameterApi(InstalledAppResource):
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': fields.Raw,
+        'retriever_resource': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
     }
 
     @marshal_with(parameters_fields)
-    def get(self, installed_app):
+    def get(self, installed_app: InstalledApp):
         """Retrieve app parameters."""
         app_model = installed_app.app
         app_model_config = app_model.app_model_config
@@ -35,6 +39,8 @@ class AppParameterApi(InstalledAppResource):
             'opening_statement': app_model_config.opening_statement,
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
+            'speech_to_text': app_model_config.speech_to_text_dict,
+            'retriever_resource': app_model_config.retriever_resource_dict,
             'more_like_this': app_model_config.more_like_this_dict,
             'user_input_form': app_model_config.user_input_form_list
         }

api/controllers/console/explore/recommended_app.py

@@ -1,5 +1,6 @@
 # -*- coding:utf-8 -*-
-from flask_login import login_required, current_user
+from flask_login import current_user
+from libs.login import login_required
 from flask_restful import Resource, fields, marshal_with
 from sqlalchemy import and_
 

api/controllers/console/explore/wraps.py

@@ -1,4 +1,5 @@
-from flask_login import login_required, current_user
+from flask_login import current_user
+from libs.login import login_required
 from flask_restful import Resource
 from functools import wraps
 

api/controllers/console/setup.py

@@ -1,7 +1,6 @@
 # -*- coding:utf-8 -*-
 from functools import wraps
 
-import flask_login
 from flask import request, current_app
 from flask_restful import Resource, reqparse
 
@@ -19,15 +18,16 @@ from .wraps import only_edition_self_hosted
 
 class SetupApi(Resource):
 
-    @only_edition_self_hosted
     def get(self):
-        setup_status = get_setup_status()
-        if setup_status:
-            return {
-                'step': 'finished',
-                'setup_at': setup_status.setup_at.isoformat()
-            }  
-        return {'step': 'not_start'}
+        if current_app.config['EDITION'] == 'SELF_HOSTED':
+            setup_status = get_setup_status()
+            if setup_status:
+                return {
+                    'step': 'finished',
+                    'setup_at': setup_status.setup_at.isoformat()
+                }
+            return {'step': 'not_start'}
+        return {'step': 'finished'}
 
     @only_edition_self_hosted
     def post(self):
@@ -57,9 +57,6 @@ class SetupApi(Resource):
         )
 
         setup()
-
-        # Login
-        flask_login.login_user(account)
         AccountService.update_last_login(account, request)
 
         return {'result': 'success'}, 201

api/controllers/console/universal_chat/audio.py

@@ -0,0 +1,66 @@
+# -*- coding:utf-8 -*-
+import logging
+
+from flask import request
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.console import api
+from controllers.console.app.error import AppUnavailableError, ProviderNotInitializeError, \
+    ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError, \
+    NoAudioUploadedError, AudioTooLargeError, \
+    UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
+from controllers.console.universal_chat.wraps import UniversalChatResource
+from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from services.audio_service import AudioService
+from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
+    UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
+from models.model import AppModelConfig
+
+
+class UniversalChatAudioApi(UniversalChatResource):
+    def post(self, universal_app):
+        app_model = universal_app
+        app_model_config: AppModelConfig = app_model.app_model_config
+
+        if not app_model_config.speech_to_text_dict['enabled']:
+            raise AppUnavailableError()
+
+        file = request.files['file']
+
+        try:
+            response = AudioService.transcript(
+                tenant_id=app_model.tenant_id,
+                file=file,
+            )
+
+            return response
+        except services.errors.app_model_config.AppModelConfigBrokenError:
+            logging.exception("App model config broken.")
+            raise AppUnavailableError()
+        except NoAudioUploadedServiceError:
+            raise NoAudioUploadedError()
+        except AudioTooLargeServiceError as e:
+            raise AudioTooLargeError(str(e))
+        except UnsupportedAudioTypeServiceError:
+            raise UnsupportedAudioTypeError()
+        except ProviderNotSupportSpeechToTextServiceError:
+            raise ProviderNotSupportSpeechToTextError()
+        except ProviderTokenNotInitError:
+            raise ProviderNotInitializeError()
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+        except ValueError as e:
+            raise e
+        except Exception as e:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+        
+
+api.add_resource(UniversalChatAudioApi, '/universal-chat/audio-to-text')

api/controllers/console/universal_chat/chat.py

@@ -0,0 +1,139 @@
+import json
+import logging
+from typing import Generator, Union
+
+from flask import Response, stream_with_context
+from flask_login import current_user
+from flask_restful import reqparse
+from werkzeug.exceptions import InternalServerError, NotFound
+
+import services
+from controllers.console import api
+from controllers.console.app.error import ConversationCompletedError, AppUnavailableError, ProviderNotInitializeError, \
+    ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError
+from controllers.console.universal_chat.wraps import UniversalChatResource
+from core.conversation_message_task import PubHandler
+from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError, \
+    LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError
+from libs.helper import uuid_value
+from services.completion_service import CompletionService
+
+
+class UniversalChatApi(UniversalChatResource):
+    def post(self, universal_app):
+        app_model = universal_app
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('query', type=str, required=True, location='json')
+        parser.add_argument('conversation_id', type=uuid_value, location='json')
+        parser.add_argument('provider', type=str, required=True, location='json')
+        parser.add_argument('model', type=str, required=True, location='json')
+        parser.add_argument('tools', type=list, required=True, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='universal_app', location='json')
+        args = parser.parse_args()
+
+        app_model_config = app_model.app_model_config
+
+        # update app model config
+        args['model_config'] = app_model_config.to_dict()
+        args['model_config']['model']['name'] = args['model']
+        args['model_config']['model']['provider'] = args['provider']
+        args['model_config']['agent_mode']['tools'] = args['tools']
+
+        if not args['model_config']['agent_mode']['tools']:
+            args['model_config']['agent_mode']['tools'] = [
+                {
+                    "current_datetime": {
+                        "enabled": True
+                    }
+                }
+            ]
+        else:
+            args['model_config']['agent_mode']['tools'].append({
+                    "current_datetime": {
+                        "enabled": True
+                    }
+                })
+
+        args['inputs'] = {}
+
+        del args['model']
+        del args['tools']
+
+        try:
+            response = CompletionService.completion(
+                app_model=app_model,
+                user=current_user,
+                args=args,
+                from_source='console',
+                streaming=True,
+                is_model_config_override=True,
+            )
+
+            return compact_response(response)
+        except services.errors.conversation.ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
+        except services.errors.conversation.ConversationCompletedError:
+            raise ConversationCompletedError()
+        except services.errors.app_model_config.AppModelConfigBrokenError:
+            logging.exception("App model config broken.")
+            raise AppUnavailableError()
+        except ProviderTokenNotInitError:
+            raise ProviderNotInitializeError()
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+        except ValueError as e:
+            raise e
+        except Exception as e:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+
+
+class UniversalChatStopApi(UniversalChatResource):
+    def post(self, universal_app, task_id):
+        PubHandler.stop(current_user, task_id)
+
+        return {'result': 'success'}, 200
+
+
+def compact_response(response: Union[dict | Generator]) -> Response:
+    if isinstance(response, dict):
+        return Response(response=json.dumps(response), status=200, mimetype='application/json')
+    else:
+        def generate() -> Generator:
+            try:
+                for chunk in response:
+                    yield chunk
+            except services.errors.conversation.ConversationNotExistsError:
+                yield "data: " + json.dumps(api.handle_error(NotFound("Conversation Not Exists.")).get_json()) + "\n\n"
+            except services.errors.conversation.ConversationCompletedError:
+                yield "data: " + json.dumps(api.handle_error(ConversationCompletedError()).get_json()) + "\n\n"
+            except services.errors.app_model_config.AppModelConfigBrokenError:
+                logging.exception("App model config broken.")
+                yield "data: " + json.dumps(api.handle_error(AppUnavailableError()).get_json()) + "\n\n"
+            except ProviderTokenNotInitError:
+                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError()).get_json()) + "\n\n"
+            except QuotaExceededError:
+                yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
+            except ModelCurrentlyNotSupportError:
+                yield "data: " + json.dumps(api.handle_error(ProviderModelCurrentlyNotSupportError()).get_json()) + "\n\n"
+            except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                    LLMRateLimitError, LLMAuthorizationError) as e:
+                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(str(e))).get_json()) + "\n\n"
+            except ValueError as e:
+                yield "data: " + json.dumps(api.handle_error(e).get_json()) + "\n\n"
+            except Exception:
+                logging.exception("internal server error.")
+                yield "data: " + json.dumps(api.handle_error(InternalServerError()).get_json()) + "\n\n"
+
+        return Response(stream_with_context(generate()), status=200,
+                        mimetype='text/event-stream')
+
+
+api.add_resource(UniversalChatApi, '/universal-chat/messages')
+api.add_resource(UniversalChatStopApi, '/universal-chat/messages/<string:task_id>/stop')

api/controllers/console/universal_chat/conversation.py

@@ -0,0 +1,104 @@
+# -*- coding:utf-8 -*-
+from flask_login import current_user
+from flask_restful import fields, reqparse, marshal_with
+from flask_restful.inputs import int_range
+from werkzeug.exceptions import NotFound
+
+from controllers.console import api
+from controllers.console.universal_chat.wraps import UniversalChatResource
+from fields.conversation_fields import conversation_with_model_config_infinite_scroll_pagination_fields, \
+    conversation_with_model_config_fields
+from libs.helper import TimestampField, uuid_value
+from services.conversation_service import ConversationService
+from services.errors.conversation import LastConversationNotExistsError, ConversationNotExistsError
+from services.web_conversation_service import WebConversationService
+
+
+class UniversalChatConversationListApi(UniversalChatResource):
+
+    @marshal_with(conversation_with_model_config_infinite_scroll_pagination_fields)
+    def get(self, universal_app):
+        app_model = universal_app
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('last_id', type=uuid_value, location='args')
+        parser.add_argument('limit', type=int_range(1, 100), required=False, default=20, location='args')
+        parser.add_argument('pinned', type=str, choices=['true', 'false', None], location='args')
+        args = parser.parse_args()
+
+        pinned = None
+        if 'pinned' in args and args['pinned'] is not None:
+            pinned = True if args['pinned'] == 'true' else False
+
+        try:
+            return WebConversationService.pagination_by_last_id(
+                app_model=app_model,
+                user=current_user,
+                last_id=args['last_id'],
+                limit=args['limit'],
+                pinned=pinned
+            )
+        except LastConversationNotExistsError:
+            raise NotFound("Last Conversation Not Exists.")
+
+
+class UniversalChatConversationApi(UniversalChatResource):
+    def delete(self, universal_app, c_id):
+        app_model = universal_app
+        conversation_id = str(c_id)
+
+        try:
+            ConversationService.delete(app_model, conversation_id, current_user)
+        except ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
+
+        WebConversationService.unpin(app_model, conversation_id, current_user)
+
+        return {"result": "success"}, 204
+
+
+class UniversalChatConversationRenameApi(UniversalChatResource):
+
+    @marshal_with(conversation_with_model_config_fields)
+    def post(self, universal_app, c_id):
+        app_model = universal_app
+        conversation_id = str(c_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', type=str, required=True, location='json')
+        args = parser.parse_args()
+
+        try:
+            return ConversationService.rename(app_model, conversation_id, current_user, args['name'])
+        except ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
+
+
+class UniversalChatConversationPinApi(UniversalChatResource):
+
+    def patch(self, universal_app, c_id):
+        app_model = universal_app
+        conversation_id = str(c_id)
+
+        try:
+            WebConversationService.pin(app_model, conversation_id, current_user)
+        except ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
+
+        return {"result": "success"}
+
+
+class UniversalChatConversationUnPinApi(UniversalChatResource):
+    def patch(self, universal_app, c_id):
+        app_model = universal_app
+        conversation_id = str(c_id)
+        WebConversationService.unpin(app_model, conversation_id, current_user)
+
+        return {"result": "success"}
+
+
+api.add_resource(UniversalChatConversationRenameApi, '/universal-chat/conversations/<uuid:c_id>/name')
+api.add_resource(UniversalChatConversationListApi, '/universal-chat/conversations')
+api.add_resource(UniversalChatConversationApi, '/universal-chat/conversations/<uuid:c_id>')
+api.add_resource(UniversalChatConversationPinApi, '/universal-chat/conversations/<uuid:c_id>/pin')
+api.add_resource(UniversalChatConversationUnPinApi, '/universal-chat/conversations/<uuid:c_id>/unpin')

api/controllers/console/universal_chat/message.py

@@ -0,0 +1,147 @@
+# -*- coding:utf-8 -*-
+import logging
+
+from flask_login import current_user
+from flask_restful import reqparse, fields, marshal_with
+from flask_restful.inputs import int_range
+from werkzeug.exceptions import NotFound, InternalServerError
+
+import services
+from controllers.console import api
+from controllers.console.app.error import ProviderNotInitializeError, \
+    ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, CompletionRequestError
+from controllers.console.explore.error import AppSuggestedQuestionsAfterAnswerDisabledError
+from controllers.console.universal_chat.wraps import UniversalChatResource
+from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
+    ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
+from libs.helper import uuid_value, TimestampField
+from services.errors.conversation import ConversationNotExistsError
+from services.errors.message import MessageNotExistsError, SuggestedQuestionsAfterAnswerDisabledError
+from services.message_service import MessageService
+
+
+class UniversalChatMessageListApi(UniversalChatResource):
+    feedback_fields = {
+        'rating': fields.String
+    }
+
+    agent_thought_fields = {
+        'id': fields.String,
+        'chain_id': fields.String,
+        'message_id': fields.String,
+        'position': fields.Integer,
+        'thought': fields.String,
+        'tool': fields.String,
+        'tool_input': fields.String,
+        'created_at': TimestampField
+    }
+
+    retriever_resource_fields = {
+        'id': fields.String,
+        'message_id': fields.String,
+        'position': fields.Integer,
+        'dataset_id': fields.String,
+        'dataset_name': fields.String,
+        'document_id': fields.String,
+        'document_name': fields.String,
+        'data_source_type': fields.String,
+        'segment_id': fields.String,
+        'score': fields.Float,
+        'hit_count': fields.Integer,
+        'word_count': fields.Integer,
+        'segment_position': fields.Integer,
+        'index_node_hash': fields.String,
+        'content': fields.String,
+        'created_at': TimestampField
+    }
+
+    message_fields = {
+        'id': fields.String,
+        'conversation_id': fields.String,
+        'inputs': fields.Raw,
+        'query': fields.String,
+        'answer': fields.String,
+        'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
+        'retriever_resources': fields.List(fields.Nested(retriever_resource_fields)),
+        'created_at': TimestampField,
+        'agent_thoughts': fields.List(fields.Nested(agent_thought_fields))
+    }
+
+    message_infinite_scroll_pagination_fields = {
+        'limit': fields.Integer,
+        'has_more': fields.Boolean,
+        'data': fields.List(fields.Nested(message_fields))
+    }
+
+    @marshal_with(message_infinite_scroll_pagination_fields)
+    def get(self, universal_app):
+        app_model = universal_app
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('conversation_id', required=True, type=uuid_value, location='args')
+        parser.add_argument('first_id', type=uuid_value, location='args')
+        parser.add_argument('limit', type=int_range(1, 100), required=False, default=20, location='args')
+        args = parser.parse_args()
+
+        try:
+            return MessageService.pagination_by_first_id(app_model, current_user,
+                                                     args['conversation_id'], args['first_id'], args['limit'])
+        except services.errors.conversation.ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
+        except services.errors.message.FirstMessageNotExistsError:
+            raise NotFound("First Message Not Exists.")
+
+
+class UniversalChatMessageFeedbackApi(UniversalChatResource):
+    def post(self, universal_app, message_id):
+        app_model = universal_app
+        message_id = str(message_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('rating', type=str, choices=['like', 'dislike', None], location='json')
+        args = parser.parse_args()
+
+        try:
+            MessageService.create_feedback(app_model, message_id, current_user, args['rating'])
+        except services.errors.message.MessageNotExistsError:
+            raise NotFound("Message Not Exists.")
+
+        return {'result': 'success'}
+
+
+class UniversalChatMessageSuggestedQuestionApi(UniversalChatResource):
+    def get(self, universal_app, message_id):
+        app_model = universal_app
+        message_id = str(message_id)
+
+        try:
+            questions = MessageService.get_suggested_questions_after_answer(
+                app_model=app_model,
+                user=current_user,
+                message_id=message_id
+            )
+        except MessageNotExistsError:
+            raise NotFound("Message not found")
+        except ConversationNotExistsError:
+            raise NotFound("Conversation not found")
+        except SuggestedQuestionsAfterAnswerDisabledError:
+            raise AppSuggestedQuestionsAfterAnswerDisabledError()
+        except ProviderTokenNotInitError:
+            raise ProviderNotInitializeError()
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+        except Exception:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+
+        return {'data': questions}
+
+
+api.add_resource(UniversalChatMessageListApi, '/universal-chat/messages')
+api.add_resource(UniversalChatMessageFeedbackApi, '/universal-chat/messages/<uuid:message_id>/feedbacks')
+api.add_resource(UniversalChatMessageSuggestedQuestionApi, '/universal-chat/messages/<uuid:message_id>/suggested-questions')

api/controllers/console/universal_chat/parameter.py

@@ -0,0 +1,38 @@
+# -*- coding:utf-8 -*-
+import json
+
+from flask_restful import marshal_with, fields
+
+from controllers.console import api
+from controllers.console.universal_chat.wraps import UniversalChatResource
+
+from models.model import App
+
+
+class UniversalChatParameterApi(UniversalChatResource):
+    """Resource for app variables."""
+    parameters_fields = {
+        'opening_statement': fields.String,
+        'suggested_questions': fields.Raw,
+        'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': fields.Raw,
+        'retriever_resource': fields.Raw,
+    }
+
+    @marshal_with(parameters_fields)
+    def get(self, universal_app: App):
+        """Retrieve app parameters."""
+        app_model = universal_app
+        app_model_config = app_model.app_model_config
+        app_model_config.retriever_resource = json.dumps({'enabled': True})
+
+        return {
+            'opening_statement': app_model_config.opening_statement,
+            'suggested_questions': app_model_config.suggested_questions_list,
+            'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
+            'speech_to_text': app_model_config.speech_to_text_dict,
+            'retriever_resource': app_model_config.retriever_resource_dict,
+        }
+
+
+api.add_resource(UniversalChatParameterApi, '/universal-chat/parameters')

api/controllers/console/universal_chat/wraps.py

@@ -0,0 +1,86 @@
+import json
+from functools import wraps
+
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from extensions.ext_database import db
+from models.model import App, AppModelConfig
+
+
+def universal_chat_app_required(view=None):
+    def decorator(view):
+        @wraps(view)
+        def decorated(*args, **kwargs):
+            # get universal chat app
+            universal_app = db.session.query(App).filter(
+                App.tenant_id == current_user.current_tenant_id,
+                App.is_universal == True
+            ).first()
+
+            if universal_app is None:
+                # create universal app if not exists
+                universal_app = App(
+                    tenant_id=current_user.current_tenant_id,
+                    name='Universal Chat',
+                    mode='chat',
+                    is_universal=True,
+                    icon='',
+                    icon_background='',
+                    api_rpm=0,
+                    api_rph=0,
+                    enable_site=False,
+                    enable_api=False,
+                    status='normal'
+                )
+
+                db.session.add(universal_app)
+                db.session.flush()
+
+                app_model_config = AppModelConfig(
+                    provider="",
+                    model_id="",
+                    configs={},
+                    opening_statement='',
+                    suggested_questions=json.dumps([]),
+                    suggested_questions_after_answer=json.dumps({'enabled': True}),
+                    speech_to_text=json.dumps({'enabled': True}),
+                    retriever_resource=json.dumps({'enabled': True}),
+                    more_like_this=None,
+                    sensitive_word_avoidance=None,
+                    model=json.dumps({
+                        "provider": "openai",
+                        "name": "gpt-3.5-turbo-16k",
+                        "completion_params": {
+                            "max_tokens": 800,
+                            "temperature": 0.8,
+                            "top_p": 1,
+                            "presence_penalty": 0,
+                            "frequency_penalty": 0
+                        }
+                    }),
+                    user_input_form=json.dumps([]),
+                    pre_prompt='',
+                    agent_mode=json.dumps({"enabled": True, "strategy": "function_call", "tools": []}),
+                )
+
+                app_model_config.app_id = universal_app.id
+                db.session.add(app_model_config)
+                db.session.flush()
+
+                universal_app.app_model_config_id = app_model_config.id
+                db.session.commit()
+
+            return view(universal_app, *args, **kwargs)
+        return decorated
+
+    if view:
+        return decorator(view)
+    return decorator
+
+
+class UniversalChatResource(Resource):
+    # must be reversed if there are multiple decorators
+    method_decorators = [universal_chat_app_required, account_initialization_required, login_required, setup_required]

api/controllers/console/version.py

@@ -32,8 +32,13 @@ class VersionApi(Resource):
                 'current_version': args.get('current_version')
             })
         except Exception as error:
-            logging.exception("Check update error.")
-            raise InternalServerError()
+            logging.warning("Check update version error: {}.".format(str(error)))
+            return {
+                'version': args.get('current_version'),
+                'release_date': '',
+                'release_notes': '',
+                'can_auto_update': False
+            }
 
         content = json.loads(response.content)
         return {

api/controllers/console/webhook/stripe.py

@@ -0,0 +1,61 @@
+import logging
+
+import stripe
+from flask import request, current_app
+from flask_restful import Resource
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import only_edition_cloud
+from services.provider_checkout_service import ProviderCheckoutService
+
+
+class StripeWebhookApi(Resource):
+    @setup_required
+    @only_edition_cloud
+    def post(self):
+        payload = request.data
+        sig_header = request.headers.get('STRIPE_SIGNATURE')
+        webhook_secret = current_app.config.get('STRIPE_WEBHOOK_SECRET')
+
+        try:
+            event = stripe.Webhook.construct_event(
+                payload, sig_header, webhook_secret
+            )
+        except ValueError as e:
+            # Invalid payload
+            return 'Invalid payload', 400
+        except stripe.error.SignatureVerificationError as e:
+            # Invalid signature
+            return 'Invalid signature', 400
+
+        # Handle the checkout.session.completed event
+        if event['type'] == 'checkout.session.completed':
+            logging.debug(event['data']['object']['id'])
+            logging.debug(event['data']['object']['amount_subtotal'])
+            logging.debug(event['data']['object']['currency'])
+            logging.debug(event['data']['object']['payment_intent'])
+            logging.debug(event['data']['object']['payment_status'])
+            logging.debug(event['data']['object']['metadata'])
+
+            session = stripe.checkout.Session.retrieve(
+                event['data']['object']['id'],
+                expand=['line_items'],
+            )
+
+            logging.debug(session.line_items['data'][0]['quantity'])
+
+            # Fulfill the purchase...
+            provider_checkout_service = ProviderCheckoutService()
+
+            try:
+                provider_checkout_service.fulfill_provider_order(event, session.line_items)
+            except Exception as e:
+
+                logging.debug(str(e))
+                return 'success', 200
+
+        return 'success', 200
+
+
+api.add_resource(StripeWebhookApi, '/webhook/stripe')

api/controllers/console/workspace/account.py

@@ -3,25 +3,27 @@ from datetime import datetime
 
 import pytz
 from flask import current_app, request
-from flask_login import login_required, current_user
+from flask_login import current_user
+from libs.login import login_required
 from flask_restful import Resource, reqparse, fields, marshal_with
 
+from services.errors.account import CurrentPasswordIncorrectError as ServiceCurrentPasswordIncorrectError
 from controllers.console import api
 from controllers.console.setup import setup_required
 from controllers.console.workspace.error import AccountAlreadyInitedError, InvalidInvitationCodeError, \
-    RepeatPasswordNotMatchError
+    RepeatPasswordNotMatchError, CurrentPasswordIncorrectError
 from controllers.console.wraps import account_initialization_required
 from libs.helper import TimestampField, supported_language, timezone
 from extensions.ext_database import db
 from models.account import InvitationCode, AccountIntegrate
 from services.account_service import AccountService
 
-
 account_fields = {
     'id': fields.String,
     'name': fields.String,
     'avatar': fields.String,
     'email': fields.String,
+    'is_password_set': fields.Boolean,
     'interface_language': fields.String,
     'interface_theme': fields.String,
     'timezone': fields.String,
@@ -194,8 +196,11 @@ class AccountPasswordApi(Resource):
         if args['new_password'] != args['repeat_new_password']:
             raise RepeatPasswordNotMatchError()
 
-        AccountService.update_account_password(
-            current_user, args['password'], args['new_password'])
+        try:
+            AccountService.update_account_password(
+                current_user, args['password'], args['new_password'])
+        except ServiceCurrentPasswordIncorrectError:
+            raise CurrentPasswordIncorrectError()
 
         return {"result": "success"}
 

api/controllers/console/workspace/error.py

@@ -7,6 +7,12 @@ class RepeatPasswordNotMatchError(BaseHTTPException):
     code = 400
 
 
+class CurrentPasswordIncorrectError(BaseHTTPException):
+    error_code = 'current_password_incorrect'
+    description = "Current password is incorrect."
+    code = 400
+
+
 class ProviderRequestFailedError(BaseHTTPException):
     error_code = 'provider_request_failed'
     description = None

api/controllers/console/workspace/members.py

@@ -1,6 +1,7 @@
 # -*- coding:utf-8 -*-
-
-from flask_login import login_required, current_user
+from flask import current_app
+from flask_login import current_user
+from libs.login import login_required
 from flask_restful import Resource, reqparse, marshal_with, abort, fields, marshal
 
 import services
@@ -48,37 +49,44 @@ class MemberInviteEmailApi(Resource):
     @account_initialization_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument('email', type=str, required=True, location='json')
+        parser.add_argument('emails', type=str, required=True, location='json', action='append')
         parser.add_argument('role', type=str, required=True, default='admin', location='json')
         args = parser.parse_args()
 
-        invitee_email = args['email']
+        invitee_emails = args['emails']
         invitee_role = args['role']
         if invitee_role not in ['admin', 'normal']:
             return {'code': 'invalid-role', 'message': 'Invalid role'}, 400
 
         inviter = current_user
+        invitation_results = []
+        console_web_url = current_app.config.get("CONSOLE_WEB_URL")
+        for invitee_email in invitee_emails:
+            try:
+                token = RegisterService.invite_new_member(inviter.current_tenant, invitee_email, role=invitee_role,
+                                                        inviter=inviter)
+                account = db.session.query(Account, TenantAccountJoin.role).join(
+                    TenantAccountJoin, Account.id == TenantAccountJoin.account_id
+                ).filter(Account.email == invitee_email).first()
+                account, role = account
+                invitation_results.append({
+                    'status': 'success',
+                    'email': invitee_email,
+                    'url': f'{console_web_url}/activate?email={invitee_email}&token={token}'
+                })
+                account = marshal(account, account_fields)
+                account['role'] = role
+            except Exception as e:
+                invitation_results.append({
+                    'status': 'failed',
+                    'email': invitee_email,
+                    'message': str(e)
+                })
 
-        try:
-            RegisterService.invite_new_member(inviter.current_tenant, invitee_email, role=invitee_role, inviter=inviter)
-            account = db.session.query(Account, TenantAccountJoin.role).join(
-                TenantAccountJoin, Account.id == TenantAccountJoin.account_id
-            ).filter(Account.email == args['email']).first()
-            account, role = account
-            account = marshal(account, account_fields)
-            account['role'] = role
-        except services.errors.account.CannotOperateSelfError as e:
-            return {'code': 'cannot-operate-self', 'message': str(e)}, 400
-        except services.errors.account.NoPermissionError as e:
-            return {'code': 'forbidden', 'message': str(e)}, 403
-        except services.errors.account.AccountAlreadyInTenantError as e:
-            return {'code': 'email-taken', 'message': str(e)}, 409
-        except Exception as e:
-            return {'code': 'unexpected-error', 'message': str(e)}, 500
-
-        # todo:413
-
-        return {'result': 'success', 'account': account}, 201
+        return {
+            'result': 'success',
+            'invitation_results': invitation_results,
+        }, 201
 
 
 class MemberCancelInviteApi(Resource):
@@ -88,7 +96,7 @@ class MemberCancelInviteApi(Resource):
     @login_required
     @account_initialization_required
     def delete(self, member_id):
-        member = Account.query.get(str(member_id))
+        member = db.session.query(Account).filter(Account.id == str(member_id)).first()
         if not member:
             abort(404)
 

api/controllers/console/workspace/model_providers.py

@@ -0,0 +1,324 @@
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse
+from werkzeug.exceptions import Forbidden
+
+from controllers.console import api
+from controllers.console.app.error import ProviderNotInitializeError
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.model_providers.error import LLMBadRequestError
+from core.model_providers.providers.base import CredentialsValidateFailedError
+from services.provider_checkout_service import ProviderCheckoutService
+from services.provider_service import ProviderService
+
+
+class ModelProviderListApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        tenant_id = current_user.current_tenant_id
+
+        provider_service = ProviderService()
+        provider_list = provider_service.get_provider_list(tenant_id)
+
+        return provider_list
+
+
+class ModelProviderValidateApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider_name: str):
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('config', type=dict, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+
+        result = True
+        error = None
+
+        try:
+            provider_service.custom_provider_config_validate(
+                provider_name=provider_name,
+                config=args['config']
+            )
+        except CredentialsValidateFailedError as ex:
+            result = False
+            error = str(ex)
+
+        response = {'result': 'success' if result else 'error'}
+
+        if not result:
+            response['error'] = error
+
+        return response
+
+
+class ModelProviderUpdateApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider_name: str):
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('config', type=dict, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+
+        try:
+            provider_service.save_custom_provider_config(
+                tenant_id=current_user.current_tenant_id,
+                provider_name=provider_name,
+                config=args['config']
+            )
+        except CredentialsValidateFailedError as ex:
+            raise ValueError(str(ex))
+
+        return {'result': 'success'}, 201
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, provider_name: str):
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        provider_service = ProviderService()
+        provider_service.delete_custom_provider(
+            tenant_id=current_user.current_tenant_id,
+            provider_name=provider_name
+        )
+
+        return {'result': 'success'}, 204
+
+
+class ModelProviderModelValidateApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider_name: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument('model_name', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('model_type', type=str, required=True, nullable=False,
+                            choices=['text-generation', 'embeddings', 'speech2text'], location='json')
+        parser.add_argument('config', type=dict, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+
+        result = True
+        error = None
+
+        try:
+            provider_service.custom_provider_model_config_validate(
+                provider_name=provider_name,
+                model_name=args['model_name'],
+                model_type=args['model_type'],
+                config=args['config']
+            )
+        except CredentialsValidateFailedError as ex:
+            result = False
+            error = str(ex)
+
+        response = {'result': 'success' if result else 'error'}
+
+        if not result:
+            response['error'] = error
+
+        return response
+
+
+class ModelProviderModelUpdateApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider_name: str):
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('model_name', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('model_type', type=str, required=True, nullable=False,
+                            choices=['text-generation', 'embeddings', 'speech2text'], location='json')
+        parser.add_argument('config', type=dict, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+
+        try:
+            provider_service.add_or_save_custom_provider_model_config(
+                tenant_id=current_user.current_tenant_id,
+                provider_name=provider_name,
+                model_name=args['model_name'],
+                model_type=args['model_type'],
+                config=args['config']
+            )
+        except CredentialsValidateFailedError as ex:
+            raise ValueError(str(ex))
+
+        return {'result': 'success'}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, provider_name: str):
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('model_name', type=str, required=True, nullable=False, location='args')
+        parser.add_argument('model_type', type=str, required=True, nullable=False,
+                            choices=['text-generation', 'embeddings', 'speech2text'], location='args')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+        provider_service.delete_custom_provider_model(
+            tenant_id=current_user.current_tenant_id,
+            provider_name=provider_name,
+            model_name=args['model_name'],
+            model_type=args['model_type']
+        )
+
+        return {'result': 'success'}, 204
+
+
+class PreferredProviderTypeUpdateApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider_name: str):
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('preferred_provider_type', type=str, required=True, nullable=False,
+                            choices=['system', 'custom'], location='json')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+        provider_service.switch_preferred_provider(
+            tenant_id=current_user.current_tenant_id,
+            provider_name=provider_name,
+            preferred_provider_type=args['preferred_provider_type']
+        )
+
+        return {'result': 'success'}
+
+
+class ModelProviderModelParameterRuleApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider_name: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument('model_name', type=str, required=True, nullable=False, location='args')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+
+        try:
+            parameter_rules = provider_service.get_model_parameter_rules(
+                tenant_id=current_user.current_tenant_id,
+                model_provider_name=provider_name,
+                model_name=args['model_name'],
+                model_type='text-generation'
+            )
+        except LLMBadRequestError:
+            raise ProviderNotInitializeError(
+                f"Current Text Generation Model is invalid. Please switch to the available model.")
+
+        rules = {
+            k: {
+                'enabled': v.enabled,
+                'min': v.min,
+                'max': v.max,
+                'default': v.default,
+                'precision': v.precision
+            }
+            for k, v in vars(parameter_rules).items()
+        }
+
+        return rules
+
+
+class ModelProviderPaymentCheckoutUrlApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider_name: str):
+        provider_service = ProviderCheckoutService()
+        provider_checkout = provider_service.create_checkout(
+            tenant_id=current_user.current_tenant_id,
+            provider_name=provider_name,
+            account=current_user
+        )
+
+        return {
+            'url': provider_checkout.get_checkout_url()
+        }
+
+
+class ModelProviderFreeQuotaSubmitApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider_name: str):
+        provider_service = ProviderService()
+        result = provider_service.free_quota_submit(
+            tenant_id=current_user.current_tenant_id,
+            provider_name=provider_name
+        )
+
+        return result
+
+
+class ModelProviderFreeQuotaQualificationVerifyApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider_name: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument('token', type=str, required=False, nullable=True, location='args')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+        result = provider_service.free_quota_qualification_verify(
+            tenant_id=current_user.current_tenant_id,
+            provider_name=provider_name,
+            token=args['token']
+        )
+
+        return result
+
+
+api.add_resource(ModelProviderListApi, '/workspaces/current/model-providers')
+api.add_resource(ModelProviderValidateApi, '/workspaces/current/model-providers/<string:provider_name>/validate')
+api.add_resource(ModelProviderUpdateApi, '/workspaces/current/model-providers/<string:provider_name>')
+api.add_resource(ModelProviderModelValidateApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/models/validate')
+api.add_resource(ModelProviderModelUpdateApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/models')
+api.add_resource(PreferredProviderTypeUpdateApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/preferred-provider-type')
+api.add_resource(ModelProviderModelParameterRuleApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/models/parameter-rules')
+api.add_resource(ModelProviderPaymentCheckoutUrlApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/checkout-url')
+api.add_resource(ModelProviderFreeQuotaSubmitApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/free-quota-submit')
+api.add_resource(ModelProviderFreeQuotaQualificationVerifyApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/free-quota-qualification-verify')

api/controllers/console/workspace/models.py

@@ -0,0 +1,109 @@
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.model_providers.model_provider_factory import ModelProviderFactory
+from core.model_providers.models.entity.model_params import ModelType
+from models.provider import ProviderType
+from services.provider_service import ProviderService
+
+
+class DefaultModelApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('model_type', type=str, required=True, nullable=False,
+                            choices=['text-generation', 'embeddings', 'speech2text'], location='args')
+        args = parser.parse_args()
+
+        tenant_id = current_user.current_tenant_id
+
+        provider_service = ProviderService()
+        default_model = provider_service.get_default_model_of_model_type(
+            tenant_id=tenant_id,
+            model_type=args['model_type']
+        )
+
+        if not default_model:
+            return None
+
+        model_provider = ModelProviderFactory.get_preferred_model_provider(
+            tenant_id,
+            default_model.provider_name
+        )
+
+        if not model_provider:
+            return {
+                'model_name': default_model.model_name,
+                'model_type': default_model.model_type,
+                'model_provider': {
+                    'provider_name': default_model.provider_name
+                }
+            }
+
+        provider = model_provider.provider
+        rst = {
+            'model_name': default_model.model_name,
+            'model_type': default_model.model_type,
+            'model_provider': {
+                'provider_name': provider.provider_name,
+                'provider_type': provider.provider_type
+            }
+        }
+
+        model_provider_rules = ModelProviderFactory.get_provider_rule(default_model.provider_name)
+        if provider.provider_type == ProviderType.SYSTEM.value:
+            rst['model_provider']['quota_type'] = provider.quota_type
+            rst['model_provider']['quota_unit'] = model_provider_rules['system_config']['quota_unit']
+            rst['model_provider']['quota_limit'] = provider.quota_limit
+            rst['model_provider']['quota_used'] = provider.quota_used
+
+        return rst
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('model_name', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('model_type', type=str, required=True, nullable=False,
+                            choices=['text-generation', 'embeddings', 'speech2text'], location='json')
+        parser.add_argument('provider_name', type=str, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+        provider_service.update_default_model_of_model_type(
+            tenant_id=current_user.current_tenant_id,
+            model_type=args['model_type'],
+            provider_name=args['provider_name'],
+            model_name=args['model_name']
+        )
+
+        return {'result': 'success'}
+
+
+class ValidModelApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, model_type):
+        ModelType.value_of(model_type)
+
+        provider_service = ProviderService()
+        valid_models = provider_service.get_valid_model_list(
+            tenant_id=current_user.current_tenant_id,
+            model_type=model_type
+        )
+
+        return valid_models
+
+
+api.add_resource(DefaultModelApi, '/workspaces/current/default-model')
+api.add_resource(ValidModelApi, '/workspaces/current/models/model-type/<string:model_type>')

api/controllers/console/workspace/providers.py

@@ -1,19 +1,14 @@
 # -*- coding:utf-8 -*-
-import base64
-import json
-import logging
-
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, abort
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.llm.provider.errors import ValidateFailedError
-from extensions.ext_database import db
-from libs import rsa
-from models.provider import Provider, ProviderType, ProviderName
+from core.model_providers.providers.base import CredentialsValidateFailedError
+from models.provider import ProviderType
 from services.provider_service import ProviderService
 
 
@@ -34,25 +29,26 @@ class ProviderListApi(Resource):
         plaintext, the rest is replaced by * and the last two bits are displayed in plaintext
         """
 
-        ProviderService.init_supported_provider(current_user.current_tenant, "cloud")
-        providers = Provider.query.filter_by(tenant_id=tenant_id).all()
+        provider_service = ProviderService()
+        provider_info_list = provider_service.get_provider_list(tenant_id)
 
         provider_list = [
             {
-                'provider_name': p.provider_name,
-                'provider_type': p.provider_type,
-                'is_valid': p.is_valid,
-                'last_used': p.last_used,
-                'is_enabled': p.is_enabled,
+                'provider_name': p['provider_name'],
+                'provider_type': p['provider_type'],
+                'is_valid': p['is_valid'],
+                'last_used': p['last_used'],
+                'is_enabled': p['is_valid'],
                 **({
-                       'quota_type': p.quota_type,
-                       'quota_limit': p.quota_limit,
-                       'quota_used': p.quota_used
-                   } if p.provider_type == ProviderType.SYSTEM.value else {}),
-                'token': ProviderService.get_obfuscated_api_key(current_user.current_tenant,
-                                                                ProviderName(p.provider_name))
+                       'quota_type': p['quota_type'],
+                       'quota_limit': p['quota_limit'],
+                       'quota_used': p['quota_used']
+                   } if p['provider_type'] == ProviderType.SYSTEM.value else {}),
+                'token': (p['config'] if p['provider_name'] != 'openai' else p['config']['openai_api_key'])
+                        if p['config'] else None
             }
-            for p in providers
+            for name, provider_info in provider_info_list.items()
+            for p in provider_info['providers']
         ]
 
         return provider_list
@@ -64,78 +60,28 @@ class ProviderTokenApi(Resource):
     @login_required
     @account_initialization_required
     def post(self, provider):
-        if provider not in [p.value for p in ProviderName]:
-            abort(404)
-
         # The role of the current user in the ta table must be admin or owner
         if current_user.current_tenant.current_role not in ['admin', 'owner']:
-            logging.log(logging.ERROR,
-                        f'User {current_user.id} is not authorized to update provider token, current_role is {current_user.current_tenant.current_role}')
             raise Forbidden()
 
         parser = reqparse.RequestParser()
-
-        parser.add_argument('token', type=ProviderService.get_token_type(
-            tenant=current_user.current_tenant,
-            provider_name=ProviderName(provider)
-        ), required=True, nullable=False, location='json')
-
+        parser.add_argument('token', required=True, nullable=False, location='json')
         args = parser.parse_args()
 
-        if args['token']:
-            try:
-                ProviderService.validate_provider_configs(
-                    tenant=current_user.current_tenant,
-                    provider_name=ProviderName(provider),
-                    configs=args['token']
-                )
-                token_is_valid = True
-            except ValidateFailedError as ex:
-                raise ValueError(str(ex))
+        if provider == 'openai':
+            args['token'] = {
+                'openai_api_key': args['token']
+            }
 
-            base64_encrypted_token = ProviderService.get_encrypted_token(
-                tenant=current_user.current_tenant,
-                provider_name=ProviderName(provider),
-                configs=args['token']
+        provider_service = ProviderService()
+        try:
+            provider_service.save_custom_provider_config(
+                tenant_id=current_user.current_tenant_id,
+                provider_name=provider,
+                config=args['token']
             )
-        else:
-            base64_encrypted_token = None
-            token_is_valid = False
-
-        tenant = current_user.current_tenant
-
-        provider_model = db.session.query(Provider).filter(
-                Provider.tenant_id == tenant.id,
-                Provider.provider_name == provider,
-                Provider.provider_type == ProviderType.CUSTOM.value
-            ).first()
-
-        # Only allow updating token for CUSTOM provider type
-        if provider_model:
-            provider_model.encrypted_config = base64_encrypted_token
-            provider_model.is_valid = token_is_valid
-        else:
-            provider_model = Provider(tenant_id=tenant.id, provider_name=provider,
-                                      provider_type=ProviderType.CUSTOM.value,
-                                      encrypted_config=base64_encrypted_token,
-                                      is_valid=token_is_valid)
-            db.session.add(provider_model)
-
-        if provider_model.is_valid:
-            other_providers = db.session.query(Provider).filter(
-                Provider.tenant_id == tenant.id,
-                Provider.provider_name != provider,
-                Provider.provider_type == ProviderType.CUSTOM.value
-            ).all()
-
-            for other_provider in other_providers:
-                other_provider.is_valid = False
-
-        db.session.commit()
-
-        if provider in [ProviderName.ANTHROPIC.value, ProviderName.AZURE_OPENAI.value, ProviderName.COHERE.value,
-                        ProviderName.HUGGINGFACEHUB.value]:
-            return {'result': 'success', 'warning': 'MOCK: This provider is not supported yet.'}, 201
+        except CredentialsValidateFailedError as ex:
+            raise ValueError(str(ex))
 
         return {'result': 'success'}, 201
 
@@ -146,33 +92,28 @@ class ProviderTokenValidateApi(Resource):
     @login_required
     @account_initialization_required
     def post(self, provider):
-        if provider not in [p.value for p in ProviderName]:
-            abort(404)
-
         parser = reqparse.RequestParser()
-        parser.add_argument('token', type=ProviderService.get_token_type(
-            tenant=current_user.current_tenant,
-            provider_name=ProviderName(provider)
-        ), required=True, nullable=False, location='json')
+        parser.add_argument('token', required=True, nullable=False, location='json')
         args = parser.parse_args()
 
-        # todo: remove this when the provider is supported
-        if provider in [ProviderName.ANTHROPIC.value, ProviderName.COHERE.value,
-                        ProviderName.HUGGINGFACEHUB.value]:
-            return {'result': 'success', 'warning': 'MOCK: This provider is not supported yet.'}
+        provider_service = ProviderService()
+
+        if provider == 'openai':
+            args['token'] = {
+                'openai_api_key': args['token']
+            }
 
         result = True
         error = None
 
         try:
-            ProviderService.validate_provider_configs(
-                tenant=current_user.current_tenant,
-                provider_name=ProviderName(provider),
-                configs=args['token']
+            provider_service.custom_provider_config_validate(
+                provider_name=provider,
+                config=args['token']
             )
-        except ValidateFailedError as e:
+        except CredentialsValidateFailedError as ex:
             result = False
-            error = str(e)
+            error = str(ex)
 
         response = {'result': 'success' if result else 'error'}
 
@@ -182,79 +123,9 @@ class ProviderTokenValidateApi(Resource):
         return response
 
 
-class ProviderSystemApi(Resource):
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def put(self, provider):
-        if provider not in [p.value for p in ProviderName]:
-            abort(404)
-
-        parser = reqparse.RequestParser()
-        parser.add_argument('is_enabled', type=bool, required=True, location='json')
-        args = parser.parse_args()
-
-        tenant = current_user.current_tenant_id
-
-        provider_model = Provider.query.filter_by(tenant_id=tenant.id, provider_name=provider).first()
-
-        if provider_model and provider_model.provider_type == ProviderType.SYSTEM.value:
-            provider_model.is_valid = args['is_enabled']
-            db.session.commit()
-        elif not provider_model:
-            ProviderService.create_system_provider(tenant, provider, args['is_enabled'])
-        else:
-            abort(403)
-
-        return {'result': 'success'}
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def get(self, provider):
-        if provider not in [p.value for p in ProviderName]:
-            abort(404)
-
-        # The role of the current user in the ta table must be admin or owner
-        if current_user.current_tenant.current_role not in ['admin', 'owner']:
-            raise Forbidden()
-
-        provider_model = db.session.query(Provider).filter(Provider.tenant_id == current_user.current_tenant_id,
-                                                           Provider.provider_name == provider,
-                                                           Provider.provider_type == ProviderType.SYSTEM.value).first()
-
-        system_model = None
-        if provider_model:
-            system_model = {
-                'result': 'success',
-                'provider': {
-                    'provider_name': provider_model.provider_name,
-                    'provider_type': provider_model.provider_type,
-                    'is_valid': provider_model.is_valid,
-                    'last_used': provider_model.last_used,
-                    'is_enabled': provider_model.is_enabled,
-                    'quota_type': provider_model.quota_type,
-                    'quota_limit': provider_model.quota_limit,
-                    'quota_used': provider_model.quota_used
-                }
-            }
-        else:
-            abort(404)
-
-        return system_model
-
-
-api.add_resource(ProviderTokenApi, '/providers/<provider>/token',
-                 endpoint='current_providers_token')  # Deprecated
-api.add_resource(ProviderTokenValidateApi, '/providers/<provider>/token-validate',
-                 endpoint='current_providers_token_validate')  # Deprecated
-
 api.add_resource(ProviderTokenApi, '/workspaces/current/providers/<provider>/token',
                  endpoint='workspaces_current_providers_token')  # PUT for updating provider token
 api.add_resource(ProviderTokenValidateApi, '/workspaces/current/providers/<provider>/token-validate',
                  endpoint='workspaces_current_providers_token_validate')  # POST for validating provider token
 
 api.add_resource(ProviderListApi, '/workspaces/current/providers')  # GET for getting providers list
-api.add_resource(ProviderSystemApi, '/workspaces/current/providers/<provider>/system',
-                 endpoint='workspaces_current_providers_system')  # GET for getting provider quota, PUT for updating provider status

api/controllers/console/workspace/tool_providers.py

@@ -0,0 +1,137 @@
+import json
+
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, abort, reqparse
+from werkzeug.exceptions import Forbidden
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.tool.provider.errors import ToolValidateFailedError
+from core.tool.provider.tool_provider_service import ToolProviderService
+from extensions.ext_database import db
+from models.tool import ToolProvider, ToolProviderName
+
+
+class ToolProviderListApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        tenant_id = current_user.current_tenant_id
+
+        tool_credential_dict = {}
+        for tool_name in ToolProviderName:
+            tool_credential_dict[tool_name.value] = {
+                'tool_name': tool_name.value,
+                'is_enabled': False,
+                'credentials': None
+            }
+
+        tool_providers = db.session.query(ToolProvider).filter(ToolProvider.tenant_id == tenant_id).all()
+
+        for p in tool_providers:
+            if p.is_enabled:
+                tool_credential_dict[p.tool_name] = {
+                    'tool_name': p.tool_name,
+                    'is_enabled': p.is_enabled,
+                    'credentials': ToolProviderService(tenant_id, p.tool_name).get_credentials(obfuscated=True)
+                }
+
+        return list(tool_credential_dict.values())
+
+
+class ToolProviderCredentialsApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider):
+        if provider not in [p.value for p in ToolProviderName]:
+            abort(404)
+
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden(f'User {current_user.id} is not authorized to update provider token, '
+                            f'current_role is {current_user.current_tenant.current_role}')
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('credentials', type=dict, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        tenant_id = current_user.current_tenant_id
+
+        tool_provider_service = ToolProviderService(tenant_id, provider)
+
+        try:
+            tool_provider_service.credentials_validate(args['credentials'])
+        except ToolValidateFailedError as ex:
+            raise ValueError(str(ex))
+
+        encrypted_credentials = json.dumps(tool_provider_service.encrypt_credentials(args['credentials']))
+
+        tenant = current_user.current_tenant
+
+        tool_provider_model = db.session.query(ToolProvider).filter(
+                ToolProvider.tenant_id == tenant.id,
+                ToolProvider.tool_name == provider,
+            ).first()
+
+        # Only allow updating token for CUSTOM provider type
+        if tool_provider_model:
+            tool_provider_model.encrypted_credentials = encrypted_credentials
+            tool_provider_model.is_enabled = True
+        else:
+            tool_provider_model = ToolProvider(
+                tenant_id=tenant.id,
+                tool_name=provider,
+                encrypted_credentials=encrypted_credentials,
+                is_enabled=True
+            )
+            db.session.add(tool_provider_model)
+
+        db.session.commit()
+
+        return {'result': 'success'}, 201
+
+
+class ToolProviderCredentialsValidateApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self, provider):
+        if provider not in [p.value for p in ToolProviderName]:
+            abort(404)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('credentials', type=dict, required=True, nullable=False, location='json')
+        args = parser.parse_args()
+
+        result = True
+        error = None
+
+        tenant_id = current_user.current_tenant_id
+
+        tool_provider_service = ToolProviderService(tenant_id, provider)
+
+        try:
+            tool_provider_service.credentials_validate(args['credentials'])
+        except ToolValidateFailedError as ex:
+            result = False
+            error = str(ex)
+
+        response = {'result': 'success' if result else 'error'}
+
+        if not result:
+            response['error'] = error
+
+        return response
+
+
+api.add_resource(ToolProviderListApi, '/workspaces/current/tool-providers')
+api.add_resource(ToolProviderCredentialsApi, '/workspaces/current/tool-providers/<provider>/credentials')
+api.add_resource(ToolProviderCredentialsValidateApi,
+                 '/workspaces/current/tool-providers/<provider>/credentials-validate')

api/controllers/console/workspace/workspace.py

@@ -2,10 +2,12 @@
 import logging
 
 from flask import request
-from flask_login import login_required, current_user
-from flask_restful import Resource, fields, marshal_with, reqparse, marshal
+from flask_login import current_user
+from libs.login import login_required
+from flask_restful import Resource, fields, marshal_with, reqparse, marshal, inputs
 
 from controllers.console import api
+from controllers.console.admin import admin_required
 from controllers.console.setup import setup_required
 from controllers.console.error import AccountNotLinkTenantError
 from controllers.console.wraps import account_initialization_required
@@ -30,7 +32,7 @@ tenant_fields = {
     'created_at': TimestampField,
     'role': fields.String,
     'providers': fields.List(fields.Nested(provider_fields)),
-    'in_trail': fields.Boolean,
+    'in_trial': fields.Boolean,
     'trial_end_reason': fields.String,
 }
 
@@ -43,6 +45,13 @@ tenants_fields = {
     'current': fields.Boolean
 }
 
+workspace_fields = {
+    'id': fields.String,
+    'name': fields.String,
+    'status': fields.String,
+    'created_at': TimestampField
+}
+
 
 class TenantListApi(Resource):
     @setup_required
@@ -57,6 +66,38 @@ class TenantListApi(Resource):
         return {'workspaces': marshal(tenants, tenants_fields)}, 200
 
 
+class WorkspaceListApi(Resource):
+    @setup_required
+    @admin_required
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('page', type=inputs.int_range(1, 99999), required=False, default=1, location='args')
+        parser.add_argument('limit', type=inputs.int_range(1, 100), required=False, default=20, location='args')
+        args = parser.parse_args()
+
+        tenants = db.session.query(Tenant).order_by(Tenant.created_at.desc())\
+            .paginate(page=args['page'], per_page=args['limit'])
+
+        has_more = False
+        if len(tenants.items) == args['limit']:
+            current_page_first_tenant = tenants[-1]
+            rest_count = db.session.query(Tenant).filter(
+                Tenant.created_at < current_page_first_tenant.created_at,
+                Tenant.id != current_page_first_tenant.id
+            ).count()
+
+            if rest_count > 0:
+                has_more = True
+        total = db.session.query(Tenant).count()
+        return {
+            'data': marshal(tenants.items, workspace_fields),
+            'has_more': has_more,
+            'limit': args['limit'],
+            'page': args['page'],
+            'total': total
+                }, 200
+
+
 class TenantApi(Resource):
     @setup_required
     @login_required
@@ -92,6 +133,7 @@ class SwitchWorkspaceApi(Resource):
 
 
 api.add_resource(TenantListApi, '/workspaces')  # GET for getting all tenants
+api.add_resource(WorkspaceListApi, '/all-workspaces')  # GET for getting all tenants
 api.add_resource(TenantApi, '/workspaces/current', endpoint='workspaces_current')  # GET for getting current tenant info
 api.add_resource(TenantApi, '/info', endpoint='info')  # Deprecated
 api.add_resource(SwitchWorkspaceApi, '/workspaces/switch')  # POST for switching tenant

api/controllers/service_api/__init__.py

@@ -7,6 +7,6 @@ bp = Blueprint('service_api', __name__, url_prefix='/v1')
 api = ExternalApi(bp)
 
 
-from .app import completion, app, conversation, message
+from .app import completion, app, conversation, message, audio
 
-from .dataset import document
+from .dataset import document, segment, dataset

api/controllers/service_api/app/app.py

@@ -4,6 +4,8 @@ from flask_restful import fields, marshal_with
 from controllers.service_api import api
 from controllers.service_api.wraps import AppApiResource
 
+from models.model import App
+
 
 class AppParameterApi(AppApiResource):
     """Resource for app variables."""
@@ -22,12 +24,14 @@ class AppParameterApi(AppApiResource):
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': fields.Raw,
+        'retriever_resource': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
     }
 
     @marshal_with(parameters_fields)
-    def get(self, app_model, end_user):
+    def get(self, app_model: App, end_user):
         """Retrieve app parameters."""
         app_model_config = app_model.app_model_config
 
@@ -35,6 +39,8 @@ class AppParameterApi(AppApiResource):
             'opening_statement': app_model_config.opening_statement,
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
+            'speech_to_text': app_model_config.speech_to_text_dict,
+            'retriever_resource': app_model_config.retriever_resource_dict,
             'more_like_this': app_model_config.more_like_this_dict,
             'user_input_form': app_model_config.user_input_form_list
         }

api/controllers/service_api/app/audio.py

@@ -0,0 +1,61 @@
+import logging
+
+from flask import request
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.service_api import api
+from controllers.service_api.app.error import AppUnavailableError, ProviderNotInitializeError, CompletionRequestError, ProviderQuotaExceededError, \
+    ProviderModelCurrentlyNotSupportError, NoAudioUploadedError, AudioTooLargeError, UnsupportedAudioTypeError, \
+    ProviderNotSupportSpeechToTextError
+from controllers.service_api.wraps import AppApiResource
+from core.model_providers.error import LLMBadRequestError, LLMAuthorizationError, LLMAPIUnavailableError, LLMAPIConnectionError, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from models.model import App, AppModelConfig
+from services.audio_service import AudioService
+from services.errors.audio import NoAudioUploadedServiceError, AudioTooLargeServiceError, \
+    UnsupportedAudioTypeServiceError, ProviderNotSupportSpeechToTextServiceError
+
+class AudioApi(AppApiResource):
+    def post(self, app_model: App, end_user):
+        app_model_config: AppModelConfig = app_model.app_model_config
+
+        if not app_model_config.speech_to_text_dict['enabled']:
+            raise AppUnavailableError() 
+
+        file = request.files['file']
+
+        try:
+            response = AudioService.transcript(
+                tenant_id=app_model.tenant_id,
+                file=file,
+            )
+
+            return response
+        except services.errors.app_model_config.AppModelConfigBrokenError:
+            logging.exception("App model config broken.")
+            raise AppUnavailableError()
+        except NoAudioUploadedServiceError:
+            raise NoAudioUploadedError()
+        except AudioTooLargeServiceError as e:
+            raise AudioTooLargeError(str(e))
+        except UnsupportedAudioTypeServiceError:
+            raise UnsupportedAudioTypeError()
+        except ProviderNotSupportSpeechToTextServiceError:
+            raise ProviderNotSupportSpeechToTextError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
+                LLMRateLimitError, LLMAuthorizationError) as e:
+            raise CompletionRequestError(str(e))
+        except ValueError as e:
+            raise e
+        except Exception as e:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+        
+api.add_resource(AudioApi, '/audio-to-text')

api/controllers/service_api/app/completion.py

@@ -14,7 +14,7 @@ from controllers.service_api.app.error import AppUnavailableError, ProviderNotIn
     ProviderModelCurrentlyNotSupportError
 from controllers.service_api.wraps import AppApiResource
 from core.conversation_message_task import PubHandler
-from core.llm.error import LLMBadRequestError, LLMAuthorizationError, LLMAPIUnavailableError, LLMAPIConnectionError, \
+from core.model_providers.error import LLMBadRequestError, LLMAuthorizationError, LLMAPIUnavailableError, LLMAPIConnectionError, \
     LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
 from libs.helper import uuid_value
 from services.completion_service import CompletionService
@@ -27,9 +27,11 @@ class CompletionApi(AppApiResource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
-        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('query', type=str, location='json', default='')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
         parser.add_argument('user', type=str, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
+
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
@@ -54,8 +56,8 @@ class CompletionApi(AppApiResource):
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")
             raise AppUnavailableError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -91,6 +93,8 @@ class ChatApi(AppApiResource):
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
         parser.add_argument('user', type=str, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
+
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
@@ -115,8 +119,8 @@ class ChatApi(AppApiResource):
         except services.errors.app_model_config.AppModelConfigBrokenError:
             logging.exception("App model config broken.")
             raise AppUnavailableError()
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
@@ -156,8 +160,8 @@ def compact_response(response: Union[dict | Generator]) -> Response:
             except services.errors.app_model_config.AppModelConfigBrokenError:
                 logging.exception("App model config broken.")
                 yield "data: " + json.dumps(api.handle_error(AppUnavailableError()).get_json()) + "\n\n"
-            except ProviderTokenNotInitError:
-                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError()).get_json()) + "\n\n"
+            except ProviderTokenNotInitError as ex:
+                yield "data: " + json.dumps(api.handle_error(ProviderNotInitializeError(ex.description)).get_json()) + "\n\n"
             except QuotaExceededError:
                 yield "data: " + json.dumps(api.handle_error(ProviderQuotaExceededError()).get_json()) + "\n\n"
             except ModelCurrentlyNotSupportError:

api/controllers/service_api/app/conversation.py

@@ -1,4 +1,5 @@
 # -*- coding:utf-8 -*-
+from flask import request
 from flask_restful import fields, marshal_with, reqparse
 from flask_restful.inputs import int_range
 from werkzeug.exceptions import NotFound
@@ -7,25 +8,11 @@ from controllers.service_api import api
 from controllers.service_api.app import create_or_update_end_user_for_user_id
 from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import AppApiResource
+from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import TimestampField, uuid_value
 import services
 from services.conversation_service import ConversationService
 
-conversation_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'inputs': fields.Raw,
-    'status': fields.String,
-    'introduction': fields.String,
-    'created_at': TimestampField
-}
-
-conversation_infinite_scroll_pagination_fields = {
-    'limit': fields.Integer,
-    'has_more': fields.Boolean,
-    'data': fields.List(fields.Nested(conversation_fields))
-}
-
 
 class ConversationApi(AppApiResource):
 
@@ -48,10 +35,28 @@ class ConversationApi(AppApiResource):
         except services.errors.conversation.LastConversationNotExistsError:
             raise NotFound("Last Conversation Not Exists.")
 
+class ConversationDetailApi(AppApiResource):
+    @marshal_with(simple_conversation_fields)
+    def delete(self, app_model, end_user, c_id):
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        conversation_id = str(c_id)
+
+        user = request.get_json().get('user')
+
+        if end_user is None and user is not None:
+            end_user = create_or_update_end_user_for_user_id(app_model, user)
+
+        try:
+            ConversationService.delete(app_model, conversation_id, end_user)
+        except services.errors.conversation.ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
+        return {"result": "success"}, 204
 
 class ConversationRenameApi(AppApiResource):
 
-    @marshal_with(conversation_fields)
+    @marshal_with(simple_conversation_fields)
     def post(self, app_model, end_user, c_id):
         if app_model.mode != 'chat':
             raise NotChatAppError()
@@ -74,3 +79,5 @@ class ConversationRenameApi(AppApiResource):
 
 api.add_resource(ConversationRenameApi, '/conversations/<uuid:c_id>/name', endpoint='conversation_name')
 api.add_resource(ConversationApi, '/conversations')
+api.add_resource(ConversationApi, '/conversations/<uuid:c_id>', endpoint='conversation')
+api.add_resource(ConversationDetailApi, '/conversations/<uuid:c_id>', endpoint='conversation_detail')

api/controllers/service_api/app/error.py

@@ -51,3 +51,27 @@ class CompletionRequestError(BaseHTTPException):
     description = "Completion request failed."
     code = 400
 
+
+class NoAudioUploadedError(BaseHTTPException):
+    error_code = 'no_audio_uploaded'
+    description = "Please upload your audio."
+    code = 400
+
+
+class AudioTooLargeError(BaseHTTPException):
+    error_code = 'audio_too_large'
+    description = "Audio size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedAudioTypeError(BaseHTTPException):
+    error_code = 'unsupported_audio_type'
+    description = "Audio type not allowed."
+    code = 415
+
+
+class ProviderNotSupportSpeechToTextError(BaseHTTPException):
+    error_code = 'provider_not_support_speech_to_text'
+    description = "Provider not support speech to text."
+    code = 400
+

api/controllers/service_api/app/message.py

@@ -16,6 +16,24 @@ class MessageListApi(AppApiResource):
     feedback_fields = {
         'rating': fields.String
     }
+    retriever_resource_fields = {
+        'id': fields.String,
+        'message_id': fields.String,
+        'position': fields.Integer,
+        'dataset_id': fields.String,
+        'dataset_name': fields.String,
+        'document_id': fields.String,
+        'document_name': fields.String,
+        'data_source_type': fields.String,
+        'segment_id': fields.String,
+        'score': fields.Float,
+        'hit_count': fields.Integer,
+        'word_count': fields.Integer,
+        'segment_position': fields.Integer,
+        'index_node_hash': fields.String,
+        'content': fields.String,
+        'created_at': TimestampField
+    }
 
     message_fields = {
         'id': fields.String,
@@ -24,6 +42,7 @@ class MessageListApi(AppApiResource):
         'query': fields.String,
         'answer': fields.String,
         'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
+        'retriever_resources': fields.List(fields.Nested(retriever_resource_fields)),
         'created_at': TimestampField
     }
 

api/controllers/service_api/dataset/dataset.py

@@ -0,0 +1,81 @@
+from flask import request
+from flask_restful import reqparse, marshal
+import services.dataset_service
+from controllers.service_api import api
+from controllers.service_api.dataset.error import DatasetNameDuplicateError
+from controllers.service_api.wraps import DatasetApiResource
+from libs.login import current_user
+from core.model_providers.models.entity.model_params import ModelType
+from fields.dataset_fields import dataset_detail_fields
+from services.dataset_service import DatasetService
+from services.provider_service import ProviderService
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 40:
+        raise ValueError('Name must be between 1 to 40 characters.')
+    return name
+
+
+class DatasetApi(DatasetApiResource):
+    """Resource for get datasets."""
+
+    def get(self, tenant_id):
+        page = request.args.get('page', default=1, type=int)
+        limit = request.args.get('limit', default=20, type=int)
+        provider = request.args.get('provider', default="vendor")
+        datasets, total = DatasetService.get_datasets(page, limit, provider,
+                                                      tenant_id, current_user)
+        # check embedding setting
+        provider_service = ProviderService()
+        valid_model_list = provider_service.get_valid_model_list(current_user.current_tenant_id,
+                                                                 ModelType.EMBEDDINGS.value)
+        model_names = []
+        for valid_model in valid_model_list:
+            model_names.append(f"{valid_model['model_name']}:{valid_model['model_provider']['provider_name']}")
+        data = marshal(datasets, dataset_detail_fields)
+        for item in data:
+            if item['indexing_technique'] == 'high_quality':
+                item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
+                if item_model in model_names:
+                    item['embedding_available'] = True
+                else:
+                    item['embedding_available'] = False
+            else:
+                item['embedding_available'] = True
+        response = {
+            'data': data,
+            'has_more': len(datasets) == limit,
+            'limit': limit,
+            'total': total,
+            'page': page
+        }
+        return response, 200
+
+    """Resource for datasets."""
+
+    def post(self, tenant_id):
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', nullable=False, required=True,
+                            help='type is required. Name must be between 1 to 40 characters.',
+                            type=_validate_name)
+        parser.add_argument('indexing_technique', type=str, location='json',
+                            choices=('high_quality', 'economy'),
+                            help='Invalid indexing technique.')
+        args = parser.parse_args()
+
+        try:
+            dataset = DatasetService.create_empty_dataset(
+                tenant_id=tenant_id,
+                name=args['name'],
+                indexing_technique=args['indexing_technique'],
+                account=current_user
+            )
+        except services.errors.dataset.DatasetNameDuplicateError:
+            raise DatasetNameDuplicateError()
+
+        return marshal(dataset, dataset_detail_fields), 200
+
+
+api.add_resource(DatasetApi, '/datasets')
+

api/controllers/service_api/dataset/document.py

@@ -1,110 +1,287 @@
-import datetime
-import uuid
+import json
 
-from flask import current_app
-from flask_restful import reqparse
+from flask import request
+from flask_restful import reqparse, marshal
+from sqlalchemy import desc
 from werkzeug.exceptions import NotFound
 
 import services.dataset_service
 from controllers.service_api import api
 from controllers.service_api.app.error import ProviderNotInitializeError
 from controllers.service_api.dataset.error import ArchivedDocumentImmutableError, DocumentIndexingError, \
-    DatasetNotInitedError
+    NoFileUploadedError, TooManyFilesError
 from controllers.service_api.wraps import DatasetApiResource
-from core.llm.error import ProviderTokenNotInitError
+from libs.login import current_user
+from core.model_providers.error import ProviderTokenNotInitError
 from extensions.ext_database import db
-from extensions.ext_storage import storage
-from models.model import UploadFile
+from fields.document_fields import document_fields, document_status_fields
+from models.dataset import Dataset, Document, DocumentSegment
 from services.dataset_service import DocumentService
+from services.file_service import FileService
 
 
-class DocumentListApi(DatasetApiResource):
+class DocumentAddByTextApi(DatasetApiResource):
     """Resource for documents."""
 
-    def post(self, dataset):
-        """Create document."""
+    def post(self, tenant_id, dataset_id):
+        """Create document by text."""
         parser = reqparse.RequestParser()
         parser.add_argument('name', type=str, required=True, nullable=False, location='json')
         parser.add_argument('text', type=str, required=True, nullable=False, location='json')
-        parser.add_argument('doc_type', type=str, location='json')
-        parser.add_argument('doc_metadata', type=dict, location='json')
+        parser.add_argument('process_rule', type=dict, required=False, nullable=True, location='json')
+        parser.add_argument('original_document_id', type=str, required=False, location='json')
+        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
+        parser.add_argument('indexing_technique', type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False,
+                            location='json')
         args = parser.parse_args()
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
 
-        if not dataset.indexing_technique:
-            raise DatasetNotInitedError("Dataset indexing technique must be set.")
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
 
-        doc_type = args.get('doc_type')
-        doc_metadata = args.get('doc_metadata')
+        if not dataset.indexing_technique and not args['indexing_technique']:
+            raise ValueError('indexing_technique is required.')
 
-        if doc_type and doc_type not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-            raise ValueError('Invalid doc_type.')
-
-        # user uuid as file name
-        file_uuid = str(uuid.uuid4())
-        file_key = 'upload_files/' + dataset.tenant_id + '/' + file_uuid + '.txt'
-
-        # save file to storage
-        storage.save(file_key, args.get('text'))
-
-        # save file to db
-        config = current_app.config
-        upload_file = UploadFile(
-            tenant_id=dataset.tenant_id,
-            storage_type=config['STORAGE_TYPE'],
-            key=file_key,
-            name=args.get('name') + '.txt',
-            size=len(args.get('text')),
-            extension='txt',
-            mime_type='text/plain',
-            created_by=dataset.created_by,
-            created_at=datetime.datetime.utcnow(),
-            used=True,
-            used_by=dataset.created_by,
-            used_at=datetime.datetime.utcnow()
-        )
-
-        db.session.add(upload_file)
-        db.session.commit()
-
-        document_data = {
-            'data_source': {
-                'type': 'upload_file',
-                'info': upload_file.id
+        upload_file = FileService.upload_text(args.get('text'), args.get('name'))
+        data_source = {
+            'type': 'upload_file',
+            'info_list': {
+                'data_source_type': 'upload_file',
+                'file_info_list': {
+                    'file_ids': [upload_file.id]
+                }
             }
         }
+        args['data_source'] = data_source
+        # validate args
+        DocumentService.document_create_args_validate(args)
 
         try:
-            document = DocumentService.save_document_with_dataset_id(
+            documents, batch = DocumentService.save_document_with_dataset_id(
                 dataset=dataset,
-                document_data=document_data,
-                account=dataset.created_by_account,
-                dataset_process_rule=dataset.latest_process_rule,
+                document_data=args,
+                account=current_user,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
                 created_from='api'
             )
-        except ProviderTokenNotInitError:
-            raise ProviderNotInitializeError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        document = documents[0]
 
-        if doc_type and doc_metadata:
-            metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[doc_type]
-
-            document.doc_metadata = {}
-
-            for key, value_type in metadata_schema.items():
-                value = doc_metadata.get(key)
-                if value is not None and isinstance(value, value_type):
-                    document.doc_metadata[key] = value
-
-            document.doc_type = doc_type
-            document.updated_at = datetime.datetime.utcnow()
-            db.session.commit()
-
-        return {'id': document.id}
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
 
 
-class DocumentApi(DatasetApiResource):
-    def delete(self, dataset, document_id):
+class DocumentUpdateByTextApi(DatasetApiResource):
+    """Resource for update documents."""
+
+    def post(self, tenant_id, dataset_id, document_id):
+        """Update document by text."""
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('text', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('process_rule', type=dict, required=False, nullable=True, location='json')
+        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
+        args = parser.parse_args()
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
+
+        if args['text']:
+            upload_file = FileService.upload_text(args.get('text'), args.get('name'))
+            data_source = {
+                'type': 'upload_file',
+                'info_list': {
+                    'data_source_type': 'upload_file',
+                    'file_info_list': {
+                        'file_ids': [upload_file.id]
+                    }
+                }
+            }
+            args['data_source'] = data_source
+        # validate args
+        args['original_document_id'] = str(document_id)
+        DocumentService.document_create_args_validate(args)
+
+        try:
+            documents, batch = DocumentService.save_document_with_dataset_id(
+                dataset=dataset,
+                document_data=args,
+                account=current_user,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
+                created_from='api'
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        document = documents[0]
+
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
+
+
+class DocumentAddByFileApi(DatasetApiResource):
+    """Resource for documents."""
+    def post(self, tenant_id, dataset_id):
+        """Create document by upload file."""
+        args = {}
+        if 'data' in request.form:
+            args = json.loads(request.form['data'])
+        if 'doc_form' not in args:
+            args['doc_form'] = 'text_model'
+        if 'doc_language' not in args:
+            args['doc_language'] = 'English'
+        # get dataset info
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
+        if not dataset.indexing_technique and not args['indexing_technique']:
+            raise ValueError('indexing_technique is required.')
+
+        # save file info
+        file = request.files['file']
+        # check file
+        if 'file' not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        upload_file = FileService.upload_file(file)
+        data_source = {
+            'type': 'upload_file',
+            'info_list': {
+                'file_info_list': {
+                    'file_ids': [upload_file.id]
+                }
+            }
+        }
+        args['data_source'] = data_source
+        # validate args
+        DocumentService.document_create_args_validate(args)
+
+        try:
+            documents, batch = DocumentService.save_document_with_dataset_id(
+                dataset=dataset,
+                document_data=args,
+                account=dataset.created_by_account,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
+                created_from='api'
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        document = documents[0]
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
+
+
+class DocumentUpdateByFileApi(DatasetApiResource):
+    """Resource for update documents."""
+
+    def post(self, tenant_id, dataset_id, document_id):
+        """Update document by upload file."""
+        args = {}
+        if 'data' in request.form:
+            args = json.loads(request.form['data'])
+        if 'doc_form' not in args:
+            args['doc_form'] = 'text_model'
+        if 'doc_language' not in args:
+            args['doc_language'] = 'English'
+
+        # get dataset info
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
+        if 'file' in request.files:
+            # save file info
+            file = request.files['file']
+
+
+            if len(request.files) > 1:
+                raise TooManyFilesError()
+
+            upload_file = FileService.upload_file(file)
+            data_source = {
+                'type': 'upload_file',
+                'info_list': {
+                    'file_info_list': {
+                        'file_ids': [upload_file.id]
+                    }
+                }
+            }
+            args['data_source'] = data_source
+        # validate args
+        args['original_document_id'] = str(document_id)
+        DocumentService.document_create_args_validate(args)
+
+        try:
+            documents, batch = DocumentService.save_document_with_dataset_id(
+                dataset=dataset,
+                document_data=args,
+                account=dataset.created_by_account,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
+                created_from='api'
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        document = documents[0]
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
+
+
+class DocumentDeleteApi(DatasetApiResource):
+    def delete(self, tenant_id, dataset_id, document_id):
         """Delete document."""
         document_id = str(document_id)
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+
+        # get dataset info
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
 
         document = DocumentService.get_document(dataset.id, document_id)
 
@@ -122,8 +299,85 @@ class DocumentApi(DatasetApiResource):
         except services.errors.document.DocumentIndexingError:
             raise DocumentIndexingError('Cannot delete document during indexing.')
 
-        return {'result': 'success'}, 204
+        return {'result': 'success'}, 200
 
 
-api.add_resource(DocumentListApi, '/documents')
-api.add_resource(DocumentApi, '/documents/<uuid:document_id>')
+class DocumentListApi(DatasetApiResource):
+    def get(self, tenant_id, dataset_id):
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        page = request.args.get('page', default=1, type=int)
+        limit = request.args.get('limit', default=20, type=int)
+        search = request.args.get('keyword', default=None, type=str)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+
+        query = Document.query.filter_by(
+            dataset_id=str(dataset_id), tenant_id=tenant_id)
+
+        if search:
+            search = f'%{search}%'
+            query = query.filter(Document.name.like(search))
+
+        query = query.order_by(desc(Document.created_at))
+
+        paginated_documents = query.paginate(
+            page=page, per_page=limit, max_per_page=100, error_out=False)
+        documents = paginated_documents.items
+
+        response = {
+            'data': marshal(documents, document_fields),
+            'has_more': len(documents) == limit,
+            'limit': limit,
+            'total': paginated_documents.total,
+            'page': page
+        }
+
+        return response
+
+
+class DocumentIndexingStatusApi(DatasetApiResource):
+    def get(self, tenant_id, dataset_id, batch):
+        dataset_id = str(dataset_id)
+        batch = str(batch)
+        tenant_id = str(tenant_id)
+        # get dataset
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # get documents
+        documents = DocumentService.get_batch_documents(dataset_id, batch)
+        if not documents:
+            raise NotFound('Documents not found.')
+        documents_status = []
+        for document in documents:
+            completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                              DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+            total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                          DocumentSegment.status != 're_segment').count()
+            document.completed_segments = completed_segments
+            document.total_segments = total_segments
+            if document.is_paused:
+                document.indexing_status = 'paused'
+            documents_status.append(marshal(document, document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
+api.add_resource(DocumentAddByTextApi, '/datasets/<uuid:dataset_id>/document/create_by_text')
+api.add_resource(DocumentAddByFileApi, '/datasets/<uuid:dataset_id>/document/create_by_file')
+api.add_resource(DocumentUpdateByTextApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text')
+api.add_resource(DocumentUpdateByFileApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file')
+api.add_resource(DocumentDeleteApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>')
+api.add_resource(DocumentListApi, '/datasets/<uuid:dataset_id>/documents')
+api.add_resource(DocumentIndexingStatusApi, '/datasets/<uuid:dataset_id>/documents/<string:batch>/indexing-status')

api/controllers/service_api/dataset/error.py

@@ -1,20 +1,73 @@
-# -*- coding:utf-8 -*-
 from libs.exception import BaseHTTPException
 
 
+class NoFileUploadedError(BaseHTTPException):
+    error_code = 'no_file_uploaded'
+    description = "Please upload your file."
+    code = 400
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = 'too_many_files'
+    description = "Only one file is allowed."
+    code = 400
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = 'file_too_large'
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = 'unsupported_file_type'
+    description = "File type not allowed."
+    code = 415
+
+
+class HighQualityDatasetOnlyError(BaseHTTPException):
+    error_code = 'high_quality_dataset_only'
+    description = "Current operation only supports 'high-quality' datasets."
+    code = 400
+
+
+class DatasetNotInitializedError(BaseHTTPException):
+    error_code = 'dataset_not_initialized'
+    description = "The dataset is still being initialized or indexing. Please wait a moment."
+    code = 400
+
+
 class ArchivedDocumentImmutableError(BaseHTTPException):
     error_code = 'archived_document_immutable'
-    description = "Cannot operate when document was archived."
+    description = "The archived document is not editable."
     code = 403
 
 
+class DatasetNameDuplicateError(BaseHTTPException):
+    error_code = 'dataset_name_duplicate'
+    description = "The dataset name already exists. Please modify your dataset name."
+    code = 409
+
+
+class InvalidActionError(BaseHTTPException):
+    error_code = 'invalid_action'
+    description = "Invalid action."
+    code = 400
+
+
+class DocumentAlreadyFinishedError(BaseHTTPException):
+    error_code = 'document_already_finished'
+    description = "The document has been processed. Please refresh the page or go to the document details."
+    code = 400
+
+
 class DocumentIndexingError(BaseHTTPException):
     error_code = 'document_indexing'
-    description = "Cannot operate document during indexing."
-    code = 403
+    description = "The document is being processed and cannot be edited."
+    code = 400
 
 
-class DatasetNotInitedError(BaseHTTPException):
-    error_code = 'dataset_not_inited'
-    description = "The dataset is still being initialized or indexing. Please wait a moment."
-    code = 403
+class InvalidMetadataError(BaseHTTPException):
+    error_code = 'invalid_metadata'
+    description = "The metadata content is incorrect. Please check and verify."
+    code = 400

api/controllers/service_api/dataset/segment.py

@@ -0,0 +1,59 @@
+from flask_login import current_user
+from flask_restful import reqparse, marshal
+from werkzeug.exceptions import NotFound
+
+from controllers.service_api import api
+from controllers.service_api.app.error import ProviderNotInitializeError
+from controllers.service_api.wraps import DatasetApiResource
+from core.model_providers.error import ProviderTokenNotInitError, LLMBadRequestError
+from core.model_providers.model_factory import ModelFactory
+from extensions.ext_database import db
+from fields.segment_fields import segment_fields
+from models.dataset import Dataset
+from services.dataset_service import DocumentService, SegmentService
+
+
+class SegmentApi(DatasetApiResource):
+    """Resource for segments."""
+    def post(self, tenant_id, dataset_id, document_id):
+        """Create single segment."""
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        # check embedding model setting
+        if dataset.indexing_technique == 'high_quality':
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument('segments', type=list, required=False, nullable=True, location='json')
+        args = parser.parse_args()
+        for args_item in args['segments']:
+            SegmentService.segment_create_args_validate(args_item, document)
+        segments = SegmentService.multi_create_segment(args['segments'], document, dataset)
+        return {
+            'data': marshal(segments, segment_fields),
+            'doc_form': document.doc_form
+        }, 200
+
+
+api.add_resource(SegmentApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments')

api/controllers/service_api/wraps.py

@@ -2,12 +2,14 @@
 from datetime import datetime
 from functools import wraps
 
-from flask import request
+from flask import request, current_app
+from flask_login import user_logged_in
 from flask_restful import Resource
 from werkzeug.exceptions import NotFound, Unauthorized
 
+from libs.login import _get_user
 from extensions.ext_database import db
-from models.dataset import Dataset
+from models.account import Tenant, TenantAccountJoin, Account
 from models.model import ApiToken, App
 
 
@@ -17,7 +19,7 @@ def validate_app_token(view=None):
         def decorated(*args, **kwargs):
             api_token = validate_and_get_api_token('app')
 
-            app_model = db.session.query(App).get(api_token.app_id)
+            app_model = db.session.query(App).filter(App.id == api_token.app_id).first()
             if not app_model:
                 raise NotFound()
 
@@ -43,12 +45,24 @@ def validate_dataset_token(view=None):
         @wraps(view)
         def decorated(*args, **kwargs):
             api_token = validate_and_get_api_token('dataset')
-
-            dataset = db.session.query(Dataset).get(api_token.dataset_id)
-            if not dataset:
-                raise NotFound()
-
-            return view(dataset, *args, **kwargs)
+            tenant_account_join = db.session.query(Tenant, TenantAccountJoin) \
+                .filter(Tenant.id == api_token.tenant_id) \
+                .filter(TenantAccountJoin.tenant_id == Tenant.id) \
+                .filter(TenantAccountJoin.role == 'owner') \
+                .one_or_none()
+            if tenant_account_join:
+                tenant, ta = tenant_account_join
+                account = Account.query.filter_by(id=ta.account_id).first()
+                # Login admin
+                if account:
+                    account.current_tenant = tenant
+                    current_app.login_manager._update_request_context_with_user(account)
+                    user_logged_in.send(current_app._get_current_object(), user=_get_user())
+                else:
+                    raise Unauthorized("Tenant owner account is not exist.")
+            else:
+                raise Unauthorized("Tenant is not exist.")
+            return view(api_token.tenant_id, *args, **kwargs)
         return decorated
 
     if view:
@@ -64,14 +78,14 @@ def validate_and_get_api_token(scope=None):
     Validate and get API token.
     """
     auth_header = request.headers.get('Authorization')
-    if auth_header is None:
-        raise Unauthorized()
+    if auth_header is None or ' ' not in auth_header:
+        raise Unauthorized("Authorization header must be provided and start with 'Bearer'")
 
     auth_scheme, auth_token = auth_header.split(None, 1)
     auth_scheme = auth_scheme.lower()
 
     if auth_scheme != 'bearer':
-        raise Unauthorized()
+        raise Unauthorized("Authorization scheme must be 'Bearer'")
 
     api_token = db.session.query(ApiToken).filter(
         ApiToken.token == auth_token,
@@ -79,7 +93,7 @@ def validate_and_get_api_token(scope=None):
     ).first()
 
     if not api_token:
-        raise Unauthorized()
+        raise Unauthorized("Access token is invalid")
 
     api_token.last_used_at = datetime.utcnow()
     db.session.commit()

api/controllers/web/__init__.py

@@ -7,4 +7,4 @@ bp = Blueprint('web', __name__, url_prefix='/api')
 api = ExternalApi(bp)
 
 
-from . import completion, app, conversation, message, site, saved_message
+from . import completion, app, conversation, message, site, saved_message, audio, passport