feat: support query date tool (#662)

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

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

@@ -0,0 +1,32 @@
+---
+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

@@ -0,0 +1,20 @@
+---
+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

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

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

@@ -1,61 +0,0 @@
-#!/usr/bin/env bash
-
-set -eo pipefail
-
-SHA=$(git rev-parse HEAD)
-REPO_NAME=langgenius/dify
-API_REPO_NAME="${REPO_NAME}-api"
-
-if [[ "${GITHUB_EVENT_NAME}" == "pull_request" ]]; then
-  REFSPEC=$(echo "${GITHUB_HEAD_REF}" | sed 's/[^a-zA-Z0-9]/-/g' | head -c 40)
-  PR_NUM=$(echo "${GITHUB_REF}" | sed 's:refs/pull/::' | sed 's:/merge::')
-  LATEST_TAG="pr-${PR_NUM}"
-  CACHE_FROM_TAG="latest"
-elif [[ "${GITHUB_EVENT_NAME}" == "release" ]]; then
-  REFSPEC=$(echo "${GITHUB_REF}" | sed 's:refs/tags/::' | head -c 40)
-  LATEST_TAG="${REFSPEC}"
-  CACHE_FROM_TAG="latest"
-else
-  REFSPEC=$(echo "${GITHUB_REF}" | sed 's:refs/heads/::' | sed 's/[^a-zA-Z0-9]/-/g' | head -c 40)
-  LATEST_TAG="${REFSPEC}"
-  CACHE_FROM_TAG="${REFSPEC}"
-fi
-
-if [[ "${REFSPEC}" == "main" ]]; then
-  LATEST_TAG="latest"
-  CACHE_FROM_TAG="latest"
-fi
-
-echo "Pulling cache image ${API_REPO_NAME}:${CACHE_FROM_TAG}"
-if docker pull "${API_REPO_NAME}:${CACHE_FROM_TAG}"; then
-  API_CACHE_FROM_SCRIPT="--cache-from ${API_REPO_NAME}:${CACHE_FROM_TAG}"
-else
-  echo "WARNING: Failed to pull ${API_REPO_NAME}:${CACHE_FROM_TAG}, disable build image cache."
-  API_CACHE_FROM_SCRIPT=""
-fi
-
-
-cat<<EOF
-  Rolling with tags:
-  - ${API_REPO_NAME}:${SHA}
-  - ${API_REPO_NAME}:${REFSPEC}
-  - ${API_REPO_NAME}:${LATEST_TAG}
-EOF
-
-#
-# Build image
-#
-cd api
-docker build \
-  ${API_CACHE_FROM_SCRIPT} \
-  --build-arg COMMIT_SHA=${SHA} \
-  -t "${API_REPO_NAME}:${SHA}" \
-  -t "${API_REPO_NAME}:${REFSPEC}" \
-  -t "${API_REPO_NAME}:${LATEST_TAG}" \
-  --label "sha=${SHA}" \
-  --label "built_at=$(date)" \
-  --label "build_actor=${GITHUB_ACTOR}" \
-  .
-
-# push
-docker push --all-tags "${API_REPO_NAME}"

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

@@ -5,18 +5,19 @@ on:
     branches:
       - 'main'
       - 'deploy/dev'
-  pull_request:
-    types: [synchronize, opened, reopened, ready_for_review]
+  release:
+    types: [published]
 
 jobs:
   build-and-push:
     runs-on: ubuntu-latest
     if: github.event.pull_request.draft == false
     steps:
-    - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
-      uses: actions/checkout@v2
-      with:
-        persist-credentials: false
+    - name: Set up QEMU
+      uses: docker/setup-qemu-action@v2
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
 
     - name: Login to Docker Hub
       uses: docker/login-action@v2
@@ -24,13 +25,29 @@ jobs:
         username: ${{ secrets.DOCKERHUB_USER }}
         password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-    - name: Build and push Docker image
-      shell: bash
-      env:
-        DOCKERHUB_USER: ${{ secrets.DOCKERHUB_USER }}
-        DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
-      run: |
-        /bin/bash .github/workflows/build-api-image.sh
+    - name: Extract metadata (tags, labels) for Docker
+      id: meta
+      uses: docker/metadata-action@v4
+      with:
+        images: langgenius/dify-api
+        tags: |
+          type=raw,value=latest,enable={{is_default_branch}}
+          type=ref,event=branch
+          type=sha,enable=true,priority=100,prefix=,suffix=,format=long
+          type=semver,pattern={{major}}.{{minor}}.{{patch}}
+          type=semver,pattern={{major}}.{{minor}}
+          type=semver,pattern={{major}}
+
+    - name: Build and push
+      uses: docker/build-push-action@v4
+      with:
+        context: "{{defaultContext}}:api"
+        platforms: linux/amd64,linux/arm64
+        build-args: |
+          COMMIT_SHA=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.revision'] }}
+        push: true
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}
 
     - name: Deploy to server
       if: github.ref == 'refs/heads/deploy/dev'

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

@@ -1,60 +0,0 @@
-#!/usr/bin/env bash
-
-set -eo pipefail
-
-SHA=$(git rev-parse HEAD)
-REPO_NAME=langgenius/dify
-WEB_REPO_NAME="${REPO_NAME}-web"
-
-if [[ "${GITHUB_EVENT_NAME}" == "pull_request" ]]; then
-  REFSPEC=$(echo "${GITHUB_HEAD_REF}" | sed 's/[^a-zA-Z0-9]/-/g' | head -c 40)
-  PR_NUM=$(echo "${GITHUB_REF}" | sed 's:refs/pull/::' | sed 's:/merge::')
-  LATEST_TAG="pr-${PR_NUM}"
-  CACHE_FROM_TAG="latest"
-elif [[ "${GITHUB_EVENT_NAME}" == "release" ]]; then
-  REFSPEC=$(echo "${GITHUB_REF}" | sed 's:refs/tags/::' | head -c 40)
-  LATEST_TAG="${REFSPEC}"
-  CACHE_FROM_TAG="latest"
-else
-  REFSPEC=$(echo "${GITHUB_REF}" | sed 's:refs/heads/::' | sed 's/[^a-zA-Z0-9]/-/g' | head -c 40)
-  LATEST_TAG="${REFSPEC}"
-  CACHE_FROM_TAG="${REFSPEC}"
-fi
-
-if [[ "${REFSPEC}" == "main" ]]; then
-  LATEST_TAG="latest"
-  CACHE_FROM_TAG="latest"
-fi
-
-echo "Pulling cache image ${WEB_REPO_NAME}:${CACHE_FROM_TAG}"
-if docker pull "${WEB_REPO_NAME}:${CACHE_FROM_TAG}"; then
-  WEB_CACHE_FROM_SCRIPT="--cache-from ${WEB_REPO_NAME}:${CACHE_FROM_TAG}"
-else
-  echo "WARNING: Failed to pull ${WEB_REPO_NAME}:${CACHE_FROM_TAG}, disable build image cache."
-  WEB_CACHE_FROM_SCRIPT=""
-fi
-
-
-cat<<EOF
-  Rolling with tags:
-  - ${WEB_REPO_NAME}:${SHA}
-  - ${WEB_REPO_NAME}:${REFSPEC}
-  - ${WEB_REPO_NAME}:${LATEST_TAG}
-EOF
-
-#
-# Build image
-#
-cd web
-docker build \
-  ${WEB_CACHE_FROM_SCRIPT} \
-  --build-arg COMMIT_SHA=${SHA} \
-  -t "${WEB_REPO_NAME}:${SHA}" \
-  -t "${WEB_REPO_NAME}:${REFSPEC}" \
-  -t "${WEB_REPO_NAME}:${LATEST_TAG}" \
-  --label "sha=${SHA}" \
-  --label "built_at=$(date)" \
-  --label "build_actor=${GITHUB_ACTOR}" \
-  .
-
-docker push --all-tags "${WEB_REPO_NAME}"

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

@@ -5,18 +5,19 @@ on:
     branches:
       - 'main'
       - 'deploy/dev'
-  pull_request:
-    types: [synchronize, opened, reopened, ready_for_review]
+  release:
+    types: [published]
 
 jobs:
   build-and-push:
     runs-on: ubuntu-latest
     if: github.event.pull_request.draft == false
     steps:
-    - name: "Checkout ${{ github.ref }} ( ${{ github.sha }} )"
-      uses: actions/checkout@v2
-      with:
-        persist-credentials: false
+    - name: Set up QEMU
+      uses: docker/setup-qemu-action@v2
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
 
     - name: Login to Docker Hub
       uses: docker/login-action@v2
@@ -24,13 +25,29 @@ jobs:
         username: ${{ secrets.DOCKERHUB_USER }}
         password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-    - name: Build and push Docker image
-      shell: bash
-      env:
-        DOCKERHUB_USER: ${{ secrets.DOCKERHUB_USER }}
-        DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
-      run: |
-        /bin/bash .github/workflows/build-web-image.sh
+    - name: Extract metadata (tags, labels) for Docker
+      id: meta
+      uses: docker/metadata-action@v4
+      with:
+        images: langgenius/dify-web
+        tags: |
+          type=raw,value=latest,enable={{is_default_branch}}
+          type=ref,event=branch
+          type=sha,enable=true,priority=100,prefix=,suffix=,format=long
+          type=semver,pattern={{major}}.{{minor}}.{{patch}}
+          type=semver,pattern={{major}}.{{minor}}
+          type=semver,pattern={{major}}
+
+    - name: Build and push
+      uses: docker/build-push-action@v4
+      with:
+        context: "{{defaultContext}}:web"
+        platforms: linux/amd64,linux/arm64
+        build-args: |
+          COMMIT_SHA=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.revision'] }}
+        push: true
+        tags: ${{ steps.meta.outputs.tags }}
+        labels: ${{ steps.meta.outputs.labels }}
 
     - name: Deploy to server
       if: github.ref == 'refs/heads/deploy/dev'

.github/workflows/check_no_chinese_comments.py

@@ -19,7 +19,7 @@ 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']
 
     for root, _, files in os.walk("."):
         for file in files:

.github/workflows/flake8.yml

@@ -1,19 +0,0 @@
-name: PEP8 Check
-on:
-  push:
-    branches: [main]
-  pull_request:
-    branches: [main]
-jobs:
-  pep8:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python 3.10
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.10'
-      - name: Install flake8
-        run: pip install flake8
-      - name: Run flake8
-        run: flake8 --ignore=E501 .

.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/
@@ -139,7 +140,7 @@ dmypy.json
 api/.env
 api/storage/*
 
-docker/volumes/app/storage/privkeys/*
+docker/volumes/app/storage/*
 docker/volumes/db/data/*
 docker/volumes/redis/data/*
 docker/volumes/weaviate/*
@@ -147,3 +148,5 @@ docker/volumes/weaviate/*
 sdks/python-client/build
 sdks/python-client/dist
 sdks/python-client/dify_client.egg-info
+
+.vscode/

CONTRIBUTING.md

@@ -22,14 +22,14 @@ To set up a working development environment, just fork the project git repositor
 
 ### Fork the repository
 
-you need to fork the [repository](https://github.com/langgenius/langgenius-gateway).
+you need to fork the [repository](https://github.com/langgenius/dify).
 
 ### Clone the repo
 
 Clone your GitHub forked repository:
 
 ```
-git clone git@github.com:<github_username>/langgenius-gateway.git
+git clone git@github.com:<github_username>/dify.git
 ```
 
 ### Install backend
@@ -54,3 +54,8 @@ 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!
+
+### 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

@@ -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

@@ -0,0 +1,55 @@
+# コントリビュート
+
+[Dify](https://dify.ai) に興味を持ち、貢献したいと思うようになったことに感謝します！始める前に、
+[行動規範](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)を読み、
+[既存の問題](https://github.com/langgenius/langgenius-gateway/issues)をチェックしてください。
+本ドキュメントは、[Dify](https://dify.ai) をビルドしてテストするための開発環境の構築方法を説明するものです。
+
+### 依存関係のインストール
+
+[Dify](https://dify.ai)をビルドするには、お使いのマシンに以下の依存関係をインストールし、設定する必要があります:
+
+- [Git](http://git-scm.com/)
+- [Docker](https://www.docker.com/)
+- [Docker Compose](https://docs.docker.com/compose/install/)
+- [Node.js v18.x (LTS)](http://nodejs.org)
+- [npm](https://www.npmjs.com/) バージョン 8.x.x もしくは [Yarn](https://yarnpkg.com/)
+- [Python](https://www.python.org/) バージョン 3.10.x
+
+## ローカル開発
+
+開発環境を構築するには、プロジェクトの git リポジトリをフォークし、適切なパッケージマネージャを使用してバックエンドとフロントエンドの依存関係をインストールし、docker-compose スタックを実行するように作成します。
+
+### リポジトリのフォーク
+
+[リポジトリ](https://github.com/langgenius/dify) をフォークする必要があります。
+
+### リポジトリのクローン
+
+GitHub でフォークしたリポジトリのクローンを作成する:
+
+```
+git clone git@github.com:<github_username>/dify.git
+```
+
+### バックエンドのインストール
+
+バックエンドアプリケーションのインストール方法については、[Backend README](api/README.md) を参照してください。
+
+### フロントエンドのインストール
+
+フロントエンドアプリケーションのインストール方法については、[Frontend README](web/README.md) を参照してください。
+
+### ブラウザで dify にアクセス
+
+[Dify](https://dify.ai) をローカル環境で見ることができるようになりました [http://localhost:3000](http://localhost:3000)。
+
+## プルリクエストの作成
+
+変更後、プルリクエスト (PR) をオープンしてください。プルリクエストを提出すると、Dify チーム/コミュニティの他の人があなたと一緒にそれをレビューします。
+
+マージコンフリクトなどの問題が発生したり、プルリクエストの開き方がわからなくなったりしませんでしたか？ [GitHub's pull request tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests) で、マージコンフリクトやその他の問題を解決する方法をチェックしてみてください。あなたの PR がマージされると、[コントリビュータチャート](https://github.com/langgenius/langgenius-gateway/graphs/contributors)にコントリビュータとして誇らしげに掲載されます。
+
+## 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！

README.md

@@ -1,10 +1,12 @@
 ![](./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_CN.md">简体中文</a> |
+  <a href="./README_JA.md">日本語</a> |
+  <a href="./README_ES.md">Español</a>
 </p>
 
-[Website](http://dify.ai) • [Docs](https://docs.dify.ai) • [Twitter](https://twitter.com/dify_ai)
+[Website](https://dify.ai) • [Docs](https://docs.dify.ai) • [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.
 
@@ -15,13 +17,19 @@ A single API encompassing plugin capabilities, context enhancement, and more, sa
 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
+* **OpenAI** ：GPT4、GPT3.5-turbo、GPT3.5-turbo-16k、text-davinci-003
+
+* **Azure OpenAI**
+
+* **Antropic**：Claude2、Claude-instant
+> We've got 1000 free trial credits available for all cloud service users to try out the Claude model.Visit [Dify.ai](https://dify.ai) and
+try it now.
+
+* **hugging face Hub**：Coming soon.
 
 ## Use Cloud Services
 
-Visit [Dify.ai](http://dify.ai)
+Visit [Dify.ai](https://dify.ai)
 
 ## Install the Community Edition
 
@@ -38,10 +46,15 @@ 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 console in your browser at [http://localhost](http://localhost) and start the initialization operation.
+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
 
@@ -81,22 +94,42 @@ 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:
 
 - Submit an Issue or PR on our GitHub Repo
-- Join the discussion in our [Discord](https://discord.gg/AhzKf7dNgk) Community
+- Join the discussion in our [Discord](https://discord.gg/FngNHpbcY7) Community
 - Send an email to hello@dify.ai
 
 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.

README_CN.md

@@ -1,11 +1,13 @@
 ![](./images/describe-cn.jpg)
 <p align="center">
   <a href="./README.md">English</a> |
-  <a href="./README_CN.md">简体中文</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>
 
 
-[官方网站](http://dify.ai) • [文档](https://docs.dify.ai/v/zh-hans) • [Twitter](https://twitter.com/dify_ai)
+[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)
 
 **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。
 
@@ -15,15 +17,20 @@
 - 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：
+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：
 
-- GPT 3 (text-davinci-003)
-- GPT 3.5 Turbo(ChatGPT)
-- GPT-4
+* **OpenAI**：GPT4、GPT3.5-turbo、GPT3.5-turbo-16k、text-davinci-003 
+
+* **Azure OpenAI Service**
+* **Anthropic**：Claude2、Claude-instant
+
+> 我们为所有注册云端版的用户免费提供了 1000 次 Claude 模型的消息调用额度，登录 [dify.ai](https://cloud.dify.ai) 即可使用。
+
+* **Hugging Face Hub**（即将推出）
 
 ## 使用云服务
 
-访问 [Dify.ai](http://cloud.dify.ai)
+访问 [Dify.ai](https://cloud.dify.ai)
 
 ## 安装社区版
 
@@ -40,10 +47,15 @@ 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](http://localhost) 进入 Dify 控制台，并开始初始化操作。
+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
 
@@ -82,20 +94,37 @@ A: 现已支持英文与中文，你可以为我们贡献语言包。
 
 [![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：
 
 - 在我们的 [GitHub Repo](https://github.com/langgenius/dify) 上提交 Issue 或 PR
-- 在我们的 [Discord 社区](https://discord.gg/AhzKf7dNgk) 上加入讨论
+- 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。

README_ES.md

@@ -0,0 +1,124 @@
+![](./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 >= 1 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
+- Liu, J. (2022). LlamaIndex [Software de computadora]. doi: 10.5281/zenodo.1234.
+
+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

@@ -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>
+
+[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)
+
+
+**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。
+
+Difyで作成したアプリケーションは以下の通りです:
+
+フォームモードとチャット会話モードをサポートする、すぐに使える Web サイト
+プラグイン機能、コンテキストの強化などを網羅する単一の API により、バックエンドのコーディングの手間を省きます。
+アプリケーションの視覚的なデータ分析、ログレビュー、アノテーションが可能です。
+Dify は LangChain と互換性があり、複数の LLM を徐々にサポートします:
+
+- GPT 3 (text-davinci-003)
+- GPT 3.5 Turbo(ChatGPT)
+- GPT-4
+
+## クラウドサービスの利用
+
+[Dify.ai](https://dify.ai) をご覧ください
+
+## Community Edition のインストール
+
+### システム要件
+
+Dify をインストールする前に、お使いのマシンが以下の最低システム要件を満たしていることを確認してください:
+
+- CPU >= 1 Core
+- RAM >= 4GB
+
+### クイックスタート
+
+Dify サーバーを起動する最も簡単な方法は、[docker-compose.yml](docker/docker-compose.yaml) ファイルを実行することです。インストールコマンドを実行する前に、[Docker](https://docs.docker.com/get-docker/) と [Docker Compose](https://docs.docker.com/compose/install/) がお使いのマシンにインストールされていることを確認してください:
+
+```bash
+cd docker
+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。
+
+## ロードマップ
+
+開発中の機能:
+
+- **データセット**, Notionやウェブページからのコンテンツ同期など、より多くのデータセットをサポートします
+テキスト、ウェブページ、さらには Notion コンテンツなど、より多くのデータセットをサポートする予定です。ユーザーは、自分のデータソースをもとに AI アプリケーションを構築することができます。
+- **プラグイン**, アプリケーションに ChatGPT プラグイン標準のプラグインを導入する、または Dify 制作のプラグインを利用する
+今後、ChatGPT 規格に準拠したプラグインや、ディファイ独自のプラグインを公開し、より多くの機能をアプリケーションで実現できるようにします。
+- **オープンソースモデル**, 例えばモデルプロバイダーとして Llama を採用したり、さらにファインチューニングを行う
+Llama のような優れたオープンソースモデルを、私たちのプラットフォームのモデルオプションとして提供したり、さらなる微調整のために使用したりすることで、協力していきます。
+
+
+## Q&A
+
+**Q: Dify で何ができるのか？**
+
+A: Dify はシンプルでパワフルな LLM 開発・運用ツールです。商用グレードのアプリケーション、パーソナルアシスタントを構築するために使用することができます。独自のアプリケーションを開発したい場合、LangDifyGenius は OpenAI と統合する際のバックエンド作業を省き、視覚的な操作機能を提供し、GPT モデルを継続的に改善・訓練することが可能です。
+
+**Q: Dify を使って、自分のモデルを「トレーニング」するにはどうすればいいのでしょうか？**
+
+A: プロンプトエンジニアリング、コンテキスト拡張、ファインチューニングからなる価値あるアプリケーションです。プロンプトとプログラミング言語を組み合わせたハイブリッドプログラミングアプローチ（テンプレートエンジンのようなもの）で、長文の埋め込みやユーザー入力の YouTube 動画からの字幕取り込みなどを簡単に実現し、これらはすべて LLM が処理するコンテキストとして提出される予定です。また、アプリケーションの操作性を重視し、ユーザーがアプリケーションを使用する際に生成したデータを分析、アノテーション、継続的なトレーニングに利用できるようにしました。適切なツールがなければ、これらのステップに時間がかかることがあります。
+
+**Q: 自分でアプリケーションを作りたい場合、何を準備すればよいですか？**
+
+A: すでに OpenAI API Key をお持ちだと思いますが、お持ちでない場合はご登録ください。もし、すでにトレーニングのコンテキストとなるコンテンツをお持ちでしたら、それは素晴らしいことです！
+
+**Q: インターフェイスにどの言語が使えますか？**
+
+A: 現在、英語と中国語に対応しており、言語パックを寄贈することも可能です。
+
+## Star ヒストリー
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+
+## お問合せ
+
+ご質問、ご提案、パートナーシップに関するお問い合わせは、以下のチャンネルからお気軽にご連絡ください:
+
+- GitHub Repo で Issue や PR を提出する
+- [Discord](https://discord.gg/FngNHpbcY7) コミュニティで議論に参加する。
+- hello@dify.ai にメールを送信します
+
+私たちは、皆様のお手伝いをさせていただき、より楽しく、より便利な AI アプリケーションを一緒に作っていきたいと思っています！
+
+## コントリビュート
+
+適切なレビューを行うため、コミットへの直接アクセスが可能なコントリビュータを含むすべてのコードコントリビュータは、プルリクエストで提出し、マージされる前にコア開発チームによって承認される必要があります。
+
+私たちはすべてのプルリクエストを歓迎します！協力したい方は、[コントリビューションガイド](CONTRIBUTING.md) をチェックしてみてください。
+
+## セキュリティ
+
+プライバシー保護のため、GitHub へのセキュリティ問題の投稿は避けてください。代わりに、あなたの質問を security@dify.ai に送ってください。より詳細な回答を提供します。
+
+## 引用
+
+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。
+
+## ライセンス
+
+このリポジトリは、[Dify Open Source License](LICENSE) のもとで利用できます。

api/.env.example

@@ -8,13 +8,19 @@ 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 frontend web base URL
+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://127.0.0.1:5001
+# Web APP API base URL
+APP_API_URL=http://127.0.0.1:5001
+
+# Web APP frontend web base URL
+APP_WEB_URL=http://127.0.0.1:3000
 
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
@@ -22,6 +28,7 @@ CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 # redis configuration
 REDIS_HOST=localhost
 REDIS_PORT=6379
+REDIS_USERNAME=
 REDIS_PASSWORD=difyai123456
 REDIS_DB=0
 
@@ -72,14 +79,26 @@ 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
 
+# Mail configuration, support: resend
+MAIL_TYPE=
+MAIL_DEFAULT_SEND_FROM=no-reply <no-reply@dify.ai>
+RESEND_API_KEY=
+
 # Sentry configuration
 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

api/Dockerfile

@@ -5,9 +5,11 @@ LABEL maintainer="takatost@gmail.com"
 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
 
@@ -25,4 +27,4 @@ RUN chmod +x /entrypoint.sh
 ARG COMMIT_SHA
 ENV COMMIT_SHA ${COMMIT_SHA}
 
-ENTRYPOINT ["/entrypoint.sh"]
+ENTRYPOINT ["/bin/bash", "/entrypoint.sh"]

api/README.md

@@ -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
@@ -33,3 +38,4 @@
    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.

api/app.py

@@ -1,5 +1,9 @@
 # -*- coding:utf-8 -*-
 import os
+from datetime import datetime
+
+from werkzeug.exceptions import Forbidden
+
 if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
     from gevent import monkey
     monkey.patch_all()
@@ -12,20 +16,20 @@ from flask import Flask, request, Response, session
 import flask_login
 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 extensions import ext_session, ext_celery, ext_sentry, ext_redis, ext_login, ext_migrate, \
+    ext_database, ext_storage, ext_mail
 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.account import TenantAccountJoin, AccountStatus
 from models.model import Account, EndUser, App
 
 import warnings
@@ -77,11 +81,11 @@ 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)
 
 
@@ -99,6 +103,9 @@ def load_user(user_id):
         account = db.session.query(Account).filter(Account.id == account_id).first()
 
         if account:
+            if account.status == AccountStatus.BANNED.value or account.status == AccountStatus.CLOSED.value:
+                raise Forbidden('Account is banned or closed.')
+
             workspace_id = session.get('workspace_id')
             if workspace_id:
                 tenant_account_join = db.session.query(TenantAccountJoin).filter(
@@ -122,6 +129,9 @@ def load_user(user_id):
                     account.current_tenant_id = tenant_account_join.tenant_id
                     session['workspace_id'] = account.current_tenant_id
 
+            account.last_active_at = datetime.utcnow()
+            db.session.commit()
+
             # Log in the user with the updated user_id
             flask_login.login_user(account, remember=True)
 
@@ -145,13 +155,17 @@ 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']
          )

api/commands.py

@@ -1,18 +1,27 @@
 import datetime
-import json
+import logging
 import random
 import string
+import time
 
 import click
+from flask import current_app
+from werkzeug.exceptions import NotFound
 
+from core.index.index import IndexBuilder
 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, AppModelConfig, ApiToken, Site, App, RecommendedApp
+from libs.rsa import generate_key_pair
+from models.account import InvitationCode, Tenant
+from models.dataset import Dataset, DatasetQuery, Document, DocumentSegment
+from models.model import Account
 import secrets
 import base64
 
+from models.provider import Provider, ProviderName
+from services.provider_service import ProviderService
+
 
 @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')
@@ -74,6 +83,31 @@ 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.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.')
@@ -131,30 +165,127 @@ def generate_upper_string():
     return result
 
 
-@click.command('gen-recommended-apps', help='Number of records to generate')
-def generate_recommended_apps():
-    print('Generating recommended app data...')
-    apps = App.query.all()
-    for app in apps:
-        recommended_app = RecommendedApp(
-            app_id=app.id,
-            description={
-                'en': 'Description for ' + app.name,
-                'zh': '描述 ' + app.name
-            },
-            copyright='Copyright ' + str(random.randint(1990, 2020)),
-            privacy_policy='https://privacypolicy.example.com',
-            category=random.choice(['Games', 'News', 'Music', 'Sports']),
-            position=random.randint(1, 100),
-            install_count=random.randint(100, 100000)
-        )
-        db.session.add(recommended_app)
-    db.session.commit()
-    print('Done!')
+@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:
+                            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():
+    click.echo(click.style('Start sync anthropic hosted providers.', fg='green'))
+    count = 0
+
+    page = 1
+    while True:
+        try:
+            tenants = db.session.query(Tenant).order_by(Tenant.created_at.desc()).paginate(page=page, per_page=50)
+        except NotFound:
+            break
+
+        page += 1
+        for tenant in tenants:
+            try:
+                click.echo('Syncing tenant anthropic hosted provider: {}'.format(tenant.id))
+                ProviderService.create_system_provider(
+                    tenant,
+                    ProviderName.ANTHROPIC.value,
+                    current_app.config['ANTHROPIC_HOSTED_QUOTA_LIMIT'],
+                    True
+                )
+                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'))
 
 
 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(generate_recommended_apps)
+    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)

api/config.py

@@ -21,14 +21,18 @@ DEFAULTS = {
     'REDIS_HOST': 'localhost',
     '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',
@@ -41,9 +45,16 @@ DEFAULTS = {
     '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',
+    'OPENAI_HOSTED_QUOTA_LIMIT': 200,
+    'ANTHROPIC_HOSTED_QUOTA_LIMIT': 1000,
+    'TENANT_DOCUMENT_COUNT': 100,
+    'CLEAN_DAY_SETTING': 30
 }
 
 
@@ -71,10 +82,15 @@ 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 = "0.2.0"
+        self.CURRENT_VERSION = "0.3.11"
         self.COMMIT_SHA = get_env('COMMIT_SHA')
         self.EDITION = "SELF_HOSTED"
         self.DEPLOY_ENV = get_env('DEPLOY_ENV')
@@ -105,14 +121,18 @@ class Config:
         # redis settings
         self.REDIS_HOST = get_env('REDIS_HOST')
         self.REDIS_PORT = get_env('REDIS_PORT')
+        self.REDIS_USERNAME = get_env('REDIS_USERNAME')
         self.REDIS_PASSWORD = get_env('REDIS_PASSWORD')
         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')
@@ -130,6 +150,7 @@ 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')
@@ -137,10 +158,15 @@ 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'))
@@ -165,9 +191,32 @@ class Config:
         self.CELERY_BACKEND = get_env('CELERY_BACKEND')
         self.CELERY_RESULT_BACKEND = 'db+{}'.format(self.SQLALCHEMY_DATABASE_URI) \
             if self.CELERY_BACKEND == 'database' else self.CELERY_BROKER_URL
+        self.BROKER_USE_SSL = self.CELERY_BROKER_URL.startswith('rediss://')
 
         # hosted provider credentials
         self.OPENAI_API_KEY = get_env('OPENAI_API_KEY')
+        self.ANTHROPIC_API_KEY = get_env('ANTHROPIC_API_KEY')
+
+        self.OPENAI_HOSTED_QUOTA_LIMIT = get_env('OPENAI_HOSTED_QUOTA_LIMIT')
+        self.ANTHROPIC_HOSTED_QUOTA_LIMIT = get_env('ANTHROPIC_HOSTED_QUOTA_LIMIT')
+
+        # 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')
+
+        # For temp use only
+        # set default LLM provider, default is 'openai', support `azure_openai`
+        self.DEFAULT_LLM_PROVIDER = get_env('DEFAULT_LLM_PROVIDER')
+
+        # 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')
 
 
 class CloudEditionConfig(Config):

api/controllers/console/__init__.py

@@ -5,16 +5,23 @@ from libs.external_api import ExternalApi
 bp = Blueprint('console', __name__, url_prefix='/console/api')
 api = ExternalApi(bp)
 
+# Import other controllers
+from . import setup, version, apikey, admin
+
 # Import app controllers
-from .app import app, site, explore, 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 other controllers
-from . import setup, version, apikey
+# Import workspace controllers
+from .workspace import workspace, members, model_providers, account, tool_providers
 
-from .workspace import workspace, members, providers, account
+# Import explore controllers
+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

api/controllers/console/admin.py

@@ -0,0 +1,132 @@
+import os
+from functools import wraps
+
+from flask import request
+from flask_restful import Resource, reqparse
+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
+
+
+def admin_required(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        if not os.getenv('ADMIN_API_KEY'):
+            raise Unauthorized('API key is invalid.')
+
+        auth_header = request.headers.get('Authorization')
+        if auth_header is None:
+            raise Unauthorized('Authorization header is missing.')
+
+        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.')
+
+        if os.getenv('ADMIN_API_KEY') != auth_token:
+            raise Unauthorized('API key is invalid.')
+
+        return view(*args, **kwargs)
+
+    return decorated
+
+
+class InsertExploreAppListApi(Resource):
+    @only_edition_cloud
+    @admin_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('app_id', type=str, required=True, nullable=False, location='json')
+        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=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')
+
+        site = app.site
+        if not site:
+            desc = args['desc'] if args['desc'] else ''
+            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 ''
+
+        recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == args['app_id']).first()
+
+        if not recommended_app:
+            recommended_app = RecommendedApp(
+                app_id=app.id,
+                description=desc,
+                copyright=copy_right,
+                privacy_policy=privacy_policy,
+                language=args['language'],
+                category=args['category'],
+                position=args['position']
+            )
+
+            db.session.add(recommended_app)
+
+            app.is_public = True
+            db.session.commit()
+
+            return {'result': 'success'}, 201
+        else:
+            recommended_app.description = desc
+            recommended_app.copyright = copy_right
+            recommended_app.privacy_policy = privacy_policy
+            recommended_app.language = args['language']
+            recommended_app.category = args['category']
+            recommended_app.position = args['position']
+
+            app.is_public = True
+
+            db.session.commit()
+
+            return {'result': 'success'}, 200
+
+
+class InsertExploreAppApi(Resource):
+    @only_edition_cloud
+    @admin_required
+    def delete(self, app_id):
+        recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == str(app_id)).first()
+        if not recommended_app:
+            return {'result': 'success'}, 204
+
+        app = App.query.filter(App.id == recommended_app.app_id).first()
+        if app:
+            app.is_public = False
+
+        installed_apps = InstalledApp.query.filter(
+            InstalledApp.app_id == recommended_app.app_id,
+            InstalledApp.tenant_id != InstalledApp.app_owner_tenant_id
+        ).all()
+
+        for installed_app in installed_apps:
+            db.session.delete(installed_app)
+
+        db.session.delete(recommended_app)
+        db.session.commit()
+
+        return {'result': 'success'}, 204
+
+
+api.add_resource(InsertExploreAppListApi, '/admin/insert-explore-apps')
+api.add_resource(InsertExploreAppApi, '/admin/insert-explore-apps/<uuid:app_id>')

api/controllers/console/app/__init__.py

@@ -17,6 +17,6 @@ def _get_app(app_id, mode=None):
         raise NotFound("App not found")
 
     if mode and app.mode != mode:
-        raise AppUnavailableError()
+        raise NotFound("The {} app not found".format(mode))
 
     return app

api/controllers/console/app/app.py

@@ -9,25 +9,22 @@ from werkzeug.exceptions import Unauthorized, 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
 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 events.app_event import app_was_created, app_was_deleted
 from libs.helper import TimestampField
 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'),
+    'speech_to_text': fields.Raw(attribute='speech_to_text_dict'),
     'more_like_this': fields.Raw(attribute='more_like_this_dict'),
+    'sensitive_word_avoidance': fields.Raw(attribute='sensitive_word_avoidance_dict'),
     'model': fields.Raw(attribute='model_dict'),
     'user_input_form': fields.Raw(attribute='user_input_form_list'),
     'pre_prompt': fields.String,
@@ -100,7 +97,8 @@ 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)
@@ -149,7 +147,9 @@ class AppListApi(Resource):
                 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']),
+                speech_to_text=json.dumps(model_configuration['speech_to_text']),
                 more_like_this=json.dumps(model_configuration['more_like_this']),
+                sensitive_word_avoidance=json.dumps(model_configuration['sensitive_word_avoidance']),
                 model=json.dumps(model_configuration['model']),
                 user_input_form=json.dumps(model_configuration['user_input_form']),
                 pre_prompt=model_configuration['pre_prompt'],
@@ -220,7 +220,11 @@ 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):
@@ -435,7 +439,9 @@ class AppCopy(Resource):
             opening_statement=app_config.opening_statement,
             suggested_questions=app_config.suggested_questions,
             suggested_questions_after_answer=app_config.suggested_questions_after_answer,
+            speech_to_text=app_config.speech_to_text,
             more_like_this=app_config.more_like_this,
+            sensitive_word_avoidance=app_config.sensitive_word_avoidance,
             model=app_config.model,
             user_input_form=app_config.user_input_form,
             pre_prompt=app_config.pre_prompt,
@@ -478,35 +484,6 @@ class AppExport(Resource):
         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>')
@@ -515,4 +492,3 @@ api.add_resource(AppNameApi, '/apps/<uuid:app_id>/name')
 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 flask_login import login_required
+from werkzeug.exceptions import InternalServerError, NotFound
+
+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.llm.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

@@ -63,8 +63,8 @@ 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:
@@ -133,8 +133,8 @@ 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 +164,8 @@ 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

@@ -45,7 +45,7 @@ message_detail_fields = {
     'message_tokens': fields.Integer,
     'answer': fields.String,
     'answer_tokens': fields.Integer,
-    'provider_response_latency': fields.Integer,
+    'provider_response_latency': fields.Float,
     'from_source': fields.String,
     'from_end_user_id': fields.String,
     'from_account_id': fields.String,
@@ -95,6 +95,7 @@ class CompletionConversationApi(Resource):
         'status': fields.String,
         'from_source': fields.String,
         'from_end_user_id': fields.String,
+        'from_end_user_session_id': fields.String(attribute='end_user.session_id'),
         'from_account_id': fields.String,
         'read_at': TimestampField,
         'created_at': TimestampField,
@@ -135,6 +136,8 @@ class CompletionConversationApi(Resource):
 
         query = db.select(Conversation).where(Conversation.app_id == app.id, Conversation.mode == 'completion')
 
+        query = query.options(joinedload(Conversation.end_user))
+
         if args['keyword']:
             query = query.join(
                 Message, Message.conversation_id == Conversation.id
@@ -160,7 +163,7 @@ 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)
@@ -209,6 +212,26 @@ class CompletionConversationDetailApi(Resource):
         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):
@@ -226,6 +249,7 @@ class ChatConversationApi(Resource):
         'status': fields.String,
         'from_source': fields.String,
         'from_end_user_id': fields.String,
+        'from_end_user_session_id': fields.String(attribute='end_user.session_id'),
         'from_account_id': fields.String,
         'summary': fields.String(attribute='summary_or_query'),
         'read_at': TimestampField,
@@ -268,6 +292,8 @@ class ChatConversationApi(Resource):
 
         query = db.select(Conversation).where(Conversation.app_id == app.id, Conversation.mode == 'chat')
 
+        query = query.options(joinedload(Conversation.end_user))
+
         if args['keyword']:
             query = query.join(
                 Message, Message.conversation_id == Conversation.id
@@ -296,7 +322,7 @@ 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)
@@ -356,6 +382,27 @@ 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

@@ -9,31 +9,33 @@ class AppNotFoundError(BaseHTTPException):
 
 class ProviderNotInitializeError(BaseHTTPException):
     error_code = 'provider_not_initialize'
-    description = "Provider Token not initialize."
+    description = "No valid model provider credentials found. " \
+                  "Please go to Settings -> Model Provider to complete your provider credentials."
     code = 400
 
 
 class ProviderQuotaExceededError(BaseHTTPException):
     error_code = 'provider_quota_exceeded'
-    description = "Provider quota exceeded."
+    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
 
 
 class ProviderModelCurrentlyNotSupportError(BaseHTTPException):
     error_code = 'model_currently_not_support'
-    description = "GPT-4 currently not support."
+    description = "Dify Hosted OpenAI trial currently not support the GPT-4 model."
     code = 400
 
 
 class ConversationCompletedError(BaseHTTPException):
     error_code = 'conversation_completed'
-    description = "Conversation was completed."
+    description = "The conversation has ended. Please start a new conversation."
     code = 400
 
 
 class AppUnavailableError(BaseHTTPException):
     error_code = 'app_unavailable'
-    description = "App unavailable."
+    description = "App unavailable, please check your app configurations."
     code = 400
 
 
@@ -45,5 +47,29 @@ class CompletionRequestError(BaseHTTPException):
 
 class AppMoreLikeThisDisabledError(BaseHTTPException):
     error_code = 'app_more_like_this_disabled'
-    description = "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/explore.py

@@ -1,209 +0,0 @@
-# -*- coding:utf-8 -*-
-from datetime import datetime
-
-from flask_login import login_required, current_user
-from flask_restful import Resource, reqparse, fields, marshal_with, abort, inputs
-from sqlalchemy import and_
-
-from controllers.console import api
-from extensions.ext_database import db
-from models.model import Tenant, 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, attribute='app'),
-    'app_owner_tenant_id': fields.String,
-    'is_pinned': fields.Boolean,
-    'last_used_at': fields.DateTime,
-    'editable': fields.Boolean
-}
-
-installed_app_list_fields = {
-    'installed_apps': fields.List(fields.Nested(installed_app_fields))
-}
-
-recommended_app_fields = {
-    'app': fields.Nested(app_fields, attribute='app'),
-    'app_id': fields.String,
-    'description': fields.String(attribute='description'),
-    'copyright': fields.String,
-    'privacy_policy': fields.String,
-    'category': fields.String,
-    'position': fields.Integer,
-    'is_listed': fields.Boolean,
-    'install_count': fields.Integer,
-    'installed': fields.Boolean,
-    'editable': fields.Boolean
-}
-
-recommended_app_list_fields = {
-    'recommended_apps': fields.List(fields.Nested(recommended_app_fields)),
-    'categories': fields.List(fields.String)
-}
-
-
-class InstalledAppsListResource(Resource):
-    @login_required
-    @marshal_with(installed_app_list_fields)
-    def get(self):
-        current_tenant_id = Tenant.query.first().id
-        installed_apps = db.session.query(InstalledApp).filter(
-            InstalledApp.tenant_id == current_tenant_id
-        ).all()
-
-        current_user.role = TenantService.get_user_role(current_user, current_user.current_tenant)
-        installed_apps = [
-            {
-                **installed_app,
-                "editable": current_user.role in ["owner", "admin"],
-            }
-            for installed_app in installed_apps
-        ]
-        installed_apps.sort(key=lambda app: (-app.is_pinned, app.last_used_at))
-
-        return {'installed_apps': installed_apps}
-
-    @login_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument('app_id', type=str, required=True, help='Invalid app_id')
-        args = parser.parse_args()
-
-        current_tenant_id = Tenant.query.first().id
-        app = App.query.get(args['app_id'])
-        if app is None:
-            abort(404, message='App not found')
-        recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == args['app_id']).first()
-        if recommended_app is None:
-            abort(404, message='App not found')
-        if not app.is_public:
-            abort(403, message="You can't install a non-public app")
-
-        installed_app = InstalledApp.query.filter(and_(
-            InstalledApp.app_id == args['app_id'],
-            InstalledApp.tenant_id == current_tenant_id
-        )).first()
-
-        if installed_app is None:
-            # todo: position
-            recommended_app.install_count += 1
-
-            new_installed_app = InstalledApp(
-                app_id=args['app_id'],
-                tenant_id=current_tenant_id,
-                is_pinned=False,
-                last_used_at=datetime.utcnow()
-            )
-            db.session.add(new_installed_app)
-            db.session.commit()
-
-        return {'message': 'App installed successfully'}
-
-
-class InstalledAppResource(Resource):
-
-    @login_required
-    def delete(self, installed_app_id):
-
-        installed_app = InstalledApp.query.filter(and_(
-            InstalledApp.id == str(installed_app_id),
-            InstalledApp.tenant_id == current_user.current_tenant_id
-        )).first()
-
-        if installed_app is None:
-            abort(404, message='App not found')
-
-        if installed_app.app_owner_tenant_id == current_user.current_tenant_id:
-            abort(400, message="You can't uninstall an app owned by the current tenant")
-
-        db.session.delete(installed_app)
-        db.session.commit()
-
-        return {'result': 'success', 'message': 'App uninstalled successfully'}
-
-    @login_required
-    def patch(self, installed_app_id):
-        parser = reqparse.RequestParser()
-        parser.add_argument('is_pinned', type=inputs.boolean)
-        args = parser.parse_args()
-
-        current_tenant_id = Tenant.query.first().id
-        installed_app = InstalledApp.query.filter(and_(
-            InstalledApp.id == str(installed_app_id),
-            InstalledApp.tenant_id == current_tenant_id
-        )).first()
-
-        if installed_app is None:
-            abort(404, message='Installed app not found')
-
-        commit_args = False
-        if 'is_pinned' in args:
-            installed_app.is_pinned = args['is_pinned']
-            commit_args = True
-
-        if commit_args:
-            db.session.commit()
-
-        return {'result': 'success', 'message': 'App info updated successfully'}
-
-
-class RecommendedAppsResource(Resource):
-    @login_required
-    @marshal_with(recommended_app_list_fields)
-    def get(self):
-        recommended_apps = db.session.query(RecommendedApp).filter(
-            RecommendedApp.is_listed == True
-        ).all()
-
-        categories = set()
-        current_user.role = TenantService.get_user_role(current_user, current_user.current_tenant)
-        recommended_apps_result = []
-        for recommended_app in recommended_apps:
-            installed = db.session.query(InstalledApp).filter(
-                and_(
-                    InstalledApp.app_id == recommended_app.app_id,
-                    InstalledApp.tenant_id == current_user.current_tenant_id
-                )
-            ).first() is not None
-
-            language_prefix = current_user.interface_language.split('-')[0]
-            desc = None
-            if recommended_app.description:
-                if language_prefix in recommended_app.description:
-                    desc = recommended_app.description[language_prefix]
-                elif 'en' in recommended_app.description:
-                    desc = recommended_app.description['en']
-
-            recommended_app_result = {
-                'id': recommended_app.id,
-                'app': recommended_app.app,
-                'app_id': recommended_app.app_id,
-                'description': desc,
-                'copyright': recommended_app.copyright,
-                'privacy_policy': recommended_app.privacy_policy,
-                'category': recommended_app.category,
-                'position': recommended_app.position,
-                'is_listed': recommended_app.is_listed,
-                'install_count': recommended_app.install_count,
-                'installed': installed,
-                'editable': current_user.role in ['owner', 'admin'],
-            }
-            recommended_apps_result.append(recommended_app_result)
-
-            categories.add(recommended_app.category)  # add category to categories
-
-        return {'recommended_apps': recommended_apps_result, 'categories': list(categories)}
-
-
-api.add_resource(InstalledAppsListResource, '/installed-apps')
-api.add_resource(InstalledAppResource, '/installed-apps/<uuid:installed_app_id>')
-api.add_resource(RecommendedAppsResource, '/explore/apps')

api/controllers/console/app/generator.py

@@ -0,0 +1,75 @@
+from flask_login import login_required, current_user
+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.llm.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

@@ -26,46 +26,46 @@ 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
+}
 
-class ChatMessageApi(Resource):
-    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),
+}
 
-    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
+}
 
-    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
+}
 
-    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.Integer,
-        '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 = {
         'limit': fields.Integer,
         'has_more': fields.Boolean,
@@ -253,7 +253,8 @@ class MessageMoreLikeThisApi(Resource):
         message_id = str(message_id)
 
         parser = reqparse.RequestParser()
-        parser.add_argument('response_mode', type=str, required=True, choices=['blocking', 'streaming'], location='args')
+        parser.add_argument('response_mode', type=str, required=True, choices=['blocking', 'streaming'],
+                            location='args')
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
@@ -268,8 +269,8 @@ 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:
@@ -296,12 +297,13 @@ 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:
-                yield "data: " + json.dumps(api.handle_error(ProviderModelCurrentlyNotSupportError()).get_json()) + "\n\n"
+                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"
@@ -337,8 +339,8 @@ 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:
@@ -353,9 +355,33 @@ class MessageSuggestedQuestionApi(Resource):
         return {'data': questions}
 
 
+class MessageApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(message_detail_fields)
+    def get(self, app_id, message_id):
+        app_id = str(app_id)
+        message_id = str(message_id)
+
+        # get app info
+        app_model = _get_app(app_id, 'chat')
+
+        message = db.session.query(Message).filter(
+            Message.id == message_id,
+            Message.app_id == app_model.id
+        ).first()
+
+        if not message:
+            raise NotFound("Message Not Exists.")
+
+        return message
+
+
 api.add_resource(MessageMoreLikeThisApi, '/apps/<uuid:app_id>/completion-messages/<uuid:message_id>/more-like-this')
 api.add_resource(MessageSuggestedQuestionApi, '/apps/<uuid:app_id>/chat-messages/<uuid:message_id>/suggested-questions')
-api.add_resource(ChatMessageApi, '/apps/<uuid:app_id>/chat-messages', endpoint='chat_messages')
+api.add_resource(ChatMessageListApi, '/apps/<uuid:app_id>/chat-messages', endpoint='console_chat_messages')
 api.add_resource(MessageFeedbackApi, '/apps/<uuid:app_id>/feedbacks')
 api.add_resource(MessageAnnotationApi, '/apps/<uuid:app_id>/annotations')
 api.add_resource(MessageAnnotationCountApi, '/apps/<uuid:app_id>/annotations/count')
+api.add_resource(MessageApi, '/apps/<uuid:app_id>/messages/<uuid:message_id>', endpoint='console_message')

api/controllers/console/app/model_config.py

@@ -41,7 +41,9 @@ class ModelConfigResource(Resource):
             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']),
+            speech_to_text=json.dumps(model_configuration['speech_to_text']),
             more_like_this=json.dumps(model_configuration['more_like_this']),
+            sensitive_word_avoidance=json.dumps(model_configuration['sensitive_word_avoidance']),
             model=json.dumps(model_configuration['model']),
             user_input_form=json.dumps(model_configuration['user_input_form']),
             pre_prompt=model_configuration['pre_prompt'],

api/controllers/console/app/statistic.py

@@ -1,4 +1,5 @@
 # -*- coding:utf-8 -*-
+from decimal import Decimal
 from datetime import datetime
 
 import pytz
@@ -59,18 +60,20 @@ 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 +122,20 @@ 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 +185,14 @@ 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 +200,207 @@ 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
         })
 
 
 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/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=True, nullable=False, location='args')
+        parser.add_argument('email', type=email, required=True, nullable=False, location='args')
+        parser.add_argument('token', type=str, required=True, nullable=False, location='args')
+        args = parser.parse_args()
+
+        account = RegisterService.get_account_if_token_valid(args['workspace_id'], args['email'], args['token'])
+
+        tenant = db.session.query(Tenant).filter(
+            Tenant.id == args['workspace_id'],
+            Tenant.status == 'normal'
+        ).first()
+
+        return {'is_valid': account is not None, 'workspace_name': tenant.name}
+
+
+class ActivateApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('workspace_id', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('email', type=email, required=True, nullable=False, 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()
+
+        account = RegisterService.get_account_if_token_valid(args['workspace_id'], args['email'], args['token'])
+        if account is None:
+            raise AlreadyActivateError()
+
+        RegisterService.revoke_token(args['workspace_id'], args['email'], args['token'])
+
+        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 +1,101 @@
+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_login import current_user, login_required
+from flask_restful import Resource
+from werkzeug.exceptions import Forbidden
+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 redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source=success')
+        else:
+            auth_url = oauth_provider.get_authorization_url()
+            return redirect(auth_url)
+
+
+
+
+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')
+            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 redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source=success')
+        elif 'error' in request.args:
+            error = request.args.get('error')
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source={error}')
+        else:
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source=access_denied')
+
+
+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(OAuthDataSourceSync, '/oauth/data-source/<string:provider>/<uuid:binding_id>/sync')

api/controllers/console/auth/oauth.py

@@ -20,13 +20,13 @@ 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,
@@ -80,7 +80,7 @@ class OAuthCallback(Resource):
         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')
+        return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_login=success')
 
 
 def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:

api/controllers/console/datasets/data_source.py

@@ -0,0 +1,304 @@
+import datetime
+import json
+
+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, reqparse, marshal
+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 libs.helper import TimestampField
+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)
+
+FILE_SIZE_LIMIT = 15 * 1024 * 1024  # 15MB
+ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm']
+PREVIEW_WORDS_LIMIT = 3000
+
+
+class DataSourceApi(Resource):
+    integrate_icon_fields = {
+        'type': fields.String,
+        'url': fields.String,
+        'emoji': fields.String
+    }
+    integrate_page_fields = {
+        'page_name': fields.String,
+        'page_id': fields.String,
+        'page_icon': fields.Nested(integrate_icon_fields, allow_null=True),
+        'parent_id': fields.String,
+        'type': fields.String
+    }
+    integrate_workspace_fields = {
+        'workspace_name': fields.String,
+        'workspace_id': fields.String,
+        'workspace_icon': fields.String,
+        'pages': fields.List(fields.Nested(integrate_page_fields)),
+        'total': fields.Integer
+    }
+    integrate_fields = {
+        'id': fields.String,
+        'provider': fields.String,
+        'created_at': TimestampField,
+        'is_bound': fields.Boolean,
+        'disabled': fields.Boolean,
+        'link': fields.String,
+        'source_info': fields.Nested(integrate_workspace_fields)
+    }
+    integrate_list_fields = {
+        'data': fields.List(fields.Nested(integrate_fields)),
+    }
+
+    @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):
+    integrate_icon_fields = {
+        'type': fields.String,
+        'url': fields.String,
+        'emoji': fields.String
+    }
+    integrate_page_fields = {
+        'page_name': fields.String,
+        'page_id': fields.String,
+        'page_icon': fields.Nested(integrate_icon_fields, allow_null=True),
+        'is_bound': fields.Boolean,
+        'parent_id': fields.String,
+        'type': fields.String
+    }
+    integrate_workspace_fields = {
+        'workspace_name': fields.String,
+        'workspace_id': fields.String,
+        'workspace_icon': fields.String,
+        'pages': fields.List(fields.Nested(integrate_page_fields))
+    }
+    integrate_notion_info_list_fields = {
+        'notion_info': fields.List(fields.Nested(integrate_workspace_fields)),
+    }
+
+    @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(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

@@ -3,7 +3,6 @@ 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 services
 from controllers.console import api
 from controllers.console.datasets.error import DatasetNameDuplicateError
@@ -12,8 +11,9 @@ from controllers.console.wraps import account_initialization_required
 from core.indexing_runner import IndexingRunner
 from libs.helper import TimestampField
 from extensions.ext_database import db
+from models.dataset import DocumentSegment, Document
 from models.model import UploadFile
-from services.dataset_service import DatasetService
+from services.dataset_service import DatasetService, DocumentService
 
 dataset_detail_fields = {
     'id': fields.String,
@@ -50,8 +50,8 @@ 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
 
 
@@ -217,17 +217,31 @@ 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')
+        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()
+            response = indexing_runner.file_indexing_estimate(file_details, args['process_rule'])
+        elif args['info_list']['data_source_type'] == 'notion_import':
+
+            indexing_runner = IndexingRunner()
+            response = indexing_runner.notion_indexing_estimate(args['info_list']['notion_info_list'],
+                                                                args['process_rule'])
+        else:
+            raise ValueError('Data source type not support')
         return response, 200
 
 
@@ -274,8 +288,54 @@ class DatasetRelatedAppListApi(Resource):
         }, 200
 
 
+class DatasetIndexingStatusApi(Resource):
+    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,
+    }
+
+    document_status_fields_list = {
+        'data': fields.List(fields.Nested(document_status_fields))
+    }
+
+    @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, self.document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
 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/controllers/console/datasets/datasets_document.py

@@ -1,6 +1,7 @@
 # -*- 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
@@ -10,13 +11,14 @@ from werkzeug.exceptions import NotFound, Forbidden
 
 import services
 from controllers.console import api
-from controllers.console.app.error import ProviderNotInitializeError
+from controllers.console.app.error import ProviderNotInitializeError, ProviderQuotaExceededError, \
+    ProviderModelCurrentlyNotSupportError
 from controllers.console.datasets.error import DocumentAlreadyFinishedError, InvalidActionError, DocumentIndexingError, \
     InvalidMetadataError, ArchivedDocumentImmutableError
 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
+from core.llm.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
 from extensions.ext_redis import redis_client
 from libs.helper import TimestampField
 from extensions.ext_database import db
@@ -60,6 +62,29 @@ document_fields = {
     'hit_count': fields.Integer,
 }
 
+document_with_segments_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,
+    'completed_segments': fields.Integer,
+    'total_segments': fields.Integer
+}
 
 class DocumentResource(Resource):
     def get_document(self, dataset_id: str, document_id: str) -> Document:
@@ -82,6 +107,23 @@ 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
@@ -131,9 +173,9 @@ 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.')
@@ -172,9 +214,20 @@ 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,
@@ -183,10 +236,15 @@ 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)
 
@@ -207,9 +265,10 @@ 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')
         args = parser.parse_args()
 
         if not dataset.indexing_technique and not args['indexing_technique']:
@@ -219,17 +278,25 @@ 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)
+        'documents': fields.List(fields.Nested(document_fields)),
+        'batch': fields.String
     }
 
     @setup_required
@@ -252,17 +319,22 @@ class DatasetInitApi(Resource):
         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:
+            raise ProviderModelCurrentlyNotSupportError()
 
         response = {
             'dataset': dataset,
-            'document': document
+            'documents': documents,
+            'batch': batch
         }
 
         return response
@@ -307,11 +379,122 @@ class DocumentIndexingEstimateApi(DocumentResource):
                     raise NotFound('File not found.')
 
                 indexing_runner = IndexingRunner()
-                response = indexing_runner.indexing_estimate(file, data_process_rule_dict)
+
+                response = indexing_runner.file_indexing_estimate([file], data_process_rule_dict)
 
         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()
+            response = indexing_runner.file_indexing_estimate(file_details, data_process_rule_dict)
+        elif dataset.data_source_type:
+
+            indexing_runner = IndexingRunner()
+            response = indexing_runner.notion_indexing_estimate(info_list,
+                                                                data_process_rule_dict)
+        else:
+            raise ValueError('Data source type not support')
+        return response
+
+
+class DocumentBatchIndexingStatusApi(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,
+    }
+
+    document_status_fields_list = {
+        'data': fields.List(fields.Nested(document_status_fields))
+    }
+
+    @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
+            documents_status.append(marshal(document, self.document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
 class DocumentIndexingStatusApi(DocumentResource):
     document_status_fields = {
         'id': fields.String,
@@ -338,10 +521,12 @@ 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
@@ -396,7 +581,7 @@ 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
             }
@@ -416,7 +601,7 @@ 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,
@@ -567,6 +752,8 @@ 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.')
 
@@ -666,6 +853,10 @@ 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,

api/controllers/console/datasets/datasets_segments.py

@@ -78,12 +78,14 @@ 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 +106,9 @@ 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)

api/controllers/console/datasets/error.py

@@ -3,7 +3,7 @@ from libs.exception import BaseHTTPException
 
 class NoFileUploadedError(BaseHTTPException):
     error_code = 'no_file_uploaded'
-    description = "No file uploaded."
+    description = "Please upload your file."
     code = 400
 
 
@@ -27,25 +27,25 @@ class UnsupportedFileTypeError(BaseHTTPException):
 
 class HighQualityDatasetOnlyError(BaseHTTPException):
     error_code = 'high_quality_dataset_only'
-    description = "High quality dataset only."
+    description = "Current operation only supports 'high-quality' datasets."
     code = 400
 
 
 class DatasetNotInitializedError(BaseHTTPException):
     error_code = 'dataset_not_initialized'
-    description = "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 process an archived document."
+    description = "The archived document is not editable."
     code = 403
 
 
 class DatasetNameDuplicateError(BaseHTTPException):
     error_code = 'dataset_name_duplicate'
-    description = "Dataset name already exists."
+    description = "The dataset name already exists. Please modify your dataset name."
     code = 409
 
 
@@ -57,17 +57,17 @@ class InvalidActionError(BaseHTTPException):
 
 class DocumentAlreadyFinishedError(BaseHTTPException):
     error_code = 'document_already_finished'
-    description = "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 = "Document indexing."
+    description = "The document is being processed and cannot be edited."
     code = 400
 
 
 class InvalidMetadataError(BaseHTTPException):
     error_code = 'invalid_metadata'
-    description = "Invalid metadata."
+    description = "The metadata content is incorrect. Please check and verify."
     code = 400

api/controllers/console/datasets/file.py

@@ -1,6 +1,7 @@
 import datetime
 import hashlib
 import tempfile
+import chardet
 import time
 import uuid
 from pathlib import Path
@@ -16,8 +17,7 @@ from controllers.console.datasets.error import NoFileUploadedError, TooManyFiles
     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 core.data_loader.file_extractor import FileExtractor
 from extensions.ext_storage import storage
 from libs.helper import TimestampField
 from extensions.ext_database import db
@@ -26,7 +26,7 @@ from models.model import UploadFile
 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']
 PREVIEW_WORDS_LIMIT = 3000
 
 
@@ -121,24 +121,7 @@ class FilePreviewApi(Resource):
         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 = FileExtractor.load(upload_file, return_text=True)
         text = text[0:PREVIEW_WORDS_LIMIT] if text else ''
         return {'content': text}
 

api/controllers/console/datasets/hit_testing.py

@@ -6,9 +6,12 @@ from werkzeug.exceptions import InternalServerError, NotFound, Forbidden
 
 import services
 from controllers.console import api
+from controllers.console.app.error import ProviderNotInitializeError, ProviderQuotaExceededError, \
+    ProviderModelCurrentlyNotSupportError
 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 services.dataset_service import DatasetService
 from services.hit_testing_service import HitTestingService
@@ -92,6 +95,12 @@ class HitTestingApi(Resource):
             return {"query": response['query'], 'records': marshal(response['records'], hit_testing_record_fields)}
         except services.errors.index.IndexNotInitializedError:
             raise DatasetNotInitializedError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
         except Exception as e:
             logging.exception("Hit testing failed.")
             raise InternalServerError(str(e))

api/controllers/console/error.py

@@ -3,13 +3,14 @@ from libs.exception import BaseHTTPException
 
 class AlreadySetupError(BaseHTTPException):
     error_code = 'already_setup'
-    description = "Application already setup."
+    description = "Dify has been successfully installed. Please refresh the page or return to the dashboard homepage."
     code = 403
 
 
 class NotSetupError(BaseHTTPException):
     error_code = 'not_setup'
-    description = "Application not setup."
+    description = "Dify has not been initialized and installed yet. " \
+                  "Please proceed with the initialization and installation process first."
     code = 401
 
 
@@ -17,3 +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.llm.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

@@ -0,0 +1,180 @@
+# -*- coding:utf-8 -*-
+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.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, \
+    LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from libs.helper import uuid_value
+from services.completion_service import CompletionService
+
+
+# define completion api for user
+class CompletionApi(InstalledAppResource):
+
+    def post(self, installed_app):
+        app_model = installed_app.app
+        if app_model.mode != 'completion':
+            raise NotCompletionAppError()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('inputs', type=dict, required=True, location='json')
+        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        args = parser.parse_args()
+
+        streaming = args['response_mode'] == 'streaming'
+
+        try:
+            response = CompletionService.completion(
+                app_model=app_model,
+                user=current_user,
+                args=args,
+                from_source='console',
+                streaming=streaming
+            )
+
+            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 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()
+
+
+class CompletionStopApi(InstalledAppResource):
+    def post(self, installed_app, task_id):
+        app_model = installed_app.app
+        if app_model.mode != 'completion':
+            raise NotCompletionAppError()
+
+        PubHandler.stop(current_user, task_id)
+
+        return {'result': 'success'}, 200
+
+
+class ChatApi(InstalledAppResource):
+    def post(self, installed_app):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('inputs', type=dict, required=True, location='json')
+        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')
+        args = parser.parse_args()
+
+        streaming = args['response_mode'] == 'streaming'
+
+        try:
+            response = CompletionService.completion(
+                app_model=app_model,
+                user=current_user,
+                args=args,
+                from_source='console',
+                streaming=streaming
+            )
+
+            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 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()
+
+
+class ChatStopApi(InstalledAppResource):
+    def post(self, installed_app, task_id):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        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 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:
+                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(CompletionApi, '/installed-apps/<uuid:installed_app_id>/completion-messages', endpoint='installed_app_completion')
+api.add_resource(CompletionStopApi, '/installed-apps/<uuid:installed_app_id>/completion-messages/<string:task_id>/stop', endpoint='installed_app_stop_completion')
+api.add_resource(ChatApi, '/installed-apps/<uuid:installed_app_id>/chat-messages', endpoint='installed_app_chat_completion')
+api.add_resource(ChatStopApi, '/installed-apps/<uuid:installed_app_id>/chat-messages/<string:task_id>/stop', endpoint='installed_app_stop_chat_completion')

api/controllers/console/explore/conversation.py

@@ -0,0 +1,130 @@
+# -*- 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.explore.error import NotChatAppError
+from controllers.console.explore.wraps import InstalledAppResource
+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):
+
+    @marshal_with(conversation_infinite_scroll_pagination_fields)
+    def get(self, installed_app):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        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 ConversationApi(InstalledAppResource):
+    def delete(self, installed_app, c_id):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        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 ConversationRenameApi(InstalledAppResource):
+
+    @marshal_with(conversation_fields)
+    def post(self, installed_app, c_id):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        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 ConversationPinApi(InstalledAppResource):
+
+    def patch(self, installed_app, c_id):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        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 ConversationUnPinApi(InstalledAppResource):
+    def patch(self, installed_app, c_id):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        conversation_id = str(c_id)
+        WebConversationService.unpin(app_model, conversation_id, current_user)
+
+        return {"result": "success"}
+
+
+api.add_resource(ConversationRenameApi, '/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/name', endpoint='installed_app_conversation_rename')
+api.add_resource(ConversationListApi, '/installed-apps/<uuid:installed_app_id>/conversations', endpoint='installed_app_conversations')
+api.add_resource(ConversationApi, '/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>', endpoint='installed_app_conversation')
+api.add_resource(ConversationPinApi, '/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/pin', endpoint='installed_app_conversation_pin')
+api.add_resource(ConversationUnPinApi, '/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/unpin', endpoint='installed_app_conversation_unpin')

api/controllers/console/explore/error.py

@@ -0,0 +1,20 @@
+# -*- coding:utf-8 -*-
+from libs.exception import BaseHTTPException
+
+
+class NotCompletionAppError(BaseHTTPException):
+    error_code = 'not_completion_app'
+    description = "Not Completion App"
+    code = 400
+
+
+class NotChatAppError(BaseHTTPException):
+    error_code = 'not_chat_app'
+    description = "Not Chat App"
+    code = 400
+
+
+class AppSuggestedQuestionsAfterAnswerDisabledError(BaseHTTPException):
+    error_code = 'app_suggested_questions_after_answer_disabled'
+    description = "Function Suggested questions after answer disabled."
+    code = 403

api/controllers/console/explore/installed_app.py

@@ -0,0 +1,143 @@
+# -*- 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 sqlalchemy import and_
+from werkzeug.exceptions import NotFound, Forbidden, BadRequest
+
+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 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
+    @account_initialization_required
+    @marshal_with(installed_app_list_fields)
+    def get(self):
+        current_tenant_id = current_user.current_tenant_id
+        installed_apps = db.session.query(InstalledApp).filter(
+            InstalledApp.tenant_id == current_tenant_id
+        ).all()
+
+        current_user.role = TenantService.get_user_role(current_user, current_user.current_tenant)
+        installed_apps = [
+            {
+                'id': installed_app.id,
+                'app': installed_app.app,
+                'app_owner_tenant_id': installed_app.app_owner_tenant_id,
+                'is_pinned': installed_app.is_pinned,
+                'last_used_at': installed_app.last_used_at,
+                "editable": current_user.role in ["owner", "admin"],
+                "uninstallable": current_tenant_id == installed_app.app_owner_tenant_id
+            }
+            for installed_app in installed_apps
+        ]
+        installed_apps.sort(key=lambda app: (-app['is_pinned'], app['last_used_at']
+                            if app['last_used_at'] is not None else datetime.min))
+
+        return {'installed_apps': installed_apps}
+
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('app_id', type=str, required=True, help='Invalid app_id')
+        args = parser.parse_args()
+
+        recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == args['app_id']).first()
+        if recommended_app is None:
+            raise NotFound('App not found')
+
+        current_tenant_id = current_user.current_tenant_id
+        app = db.session.query(App).filter(
+            App.id == args['app_id']
+        ).first()
+
+        if app is None:
+            raise NotFound('App not found')
+
+        if not app.is_public:
+            raise Forbidden('You can\'t install a non-public app')
+
+        installed_app = InstalledApp.query.filter(and_(
+            InstalledApp.app_id == args['app_id'],
+            InstalledApp.tenant_id == current_tenant_id
+        )).first()
+
+        if installed_app is None:
+            # todo: position
+            recommended_app.install_count += 1
+
+            new_installed_app = InstalledApp(
+                app_id=args['app_id'],
+                tenant_id=current_tenant_id,
+                app_owner_tenant_id=app.tenant_id,
+                is_pinned=False,
+                last_used_at=datetime.utcnow()
+            )
+            db.session.add(new_installed_app)
+            db.session.commit()
+
+        return {'message': 'App installed successfully'}
+
+
+class InstalledAppApi(InstalledAppResource):
+    """
+    update and delete an installed app
+    use InstalledAppResource to apply default decorators and get installed_app
+    """
+    def delete(self, installed_app):
+        if installed_app.app_owner_tenant_id == current_user.current_tenant_id:
+            raise BadRequest('You can\'t uninstall an app owned by the current tenant')
+
+        db.session.delete(installed_app)
+        db.session.commit()
+
+        return {'result': 'success', 'message': 'App uninstalled successfully'}
+
+    def patch(self, installed_app):
+        parser = reqparse.RequestParser()
+        parser.add_argument('is_pinned', type=inputs.boolean)
+        args = parser.parse_args()
+
+        commit_args = False
+        if 'is_pinned' in args:
+            installed_app.is_pinned = args['is_pinned']
+            commit_args = True
+
+        if commit_args:
+            db.session.commit()
+
+        return {'result': 'success', 'message': 'App info updated successfully'}
+
+
+api.add_resource(InstalledAppsListApi, '/installed-apps')
+api.add_resource(InstalledAppApi, '/installed-apps/<uuid:installed_app_id>')

api/controllers/console/explore/message.py

@@ -0,0 +1,196 @@
+# -*- coding:utf-8 -*-
+import json
+import logging
+from typing import Generator, Union
+
+from flask import stream_with_context, Response
+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 AppMoreLikeThisDisabledError, ProviderNotInitializeError, \
+    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, \
+    ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
+from libs.helper import uuid_value, TimestampField
+from services.completion_service import CompletionService
+from services.errors.app import MoreLikeThisDisabledError
+from services.errors.conversation import ConversationNotExistsError
+from services.errors.message import MessageNotExistsError, SuggestedQuestionsAfterAnswerDisabledError
+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):
+        app_model = installed_app.app
+
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+
+        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 MessageFeedbackApi(InstalledAppResource):
+    def post(self, installed_app, message_id):
+        app_model = installed_app.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 MessageMoreLikeThisApi(InstalledAppResource):
+    def get(self, installed_app, message_id):
+        app_model = installed_app.app
+        if app_model.mode != 'completion':
+            raise NotCompletionAppError()
+
+        message_id = str(message_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('response_mode', type=str, required=True, choices=['blocking', 'streaming'], location='args')
+        args = parser.parse_args()
+
+        streaming = args['response_mode'] == 'streaming'
+
+        try:
+            response = CompletionService.generate_more_like_this(app_model, current_user, message_id, streaming)
+            return compact_response(response)
+        except MessageNotExistsError:
+            raise NotFound("Message Not Exists.")
+        except MoreLikeThisDisabledError:
+            raise AppMoreLikeThisDisabledError()
+        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:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+
+
+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 MessageNotExistsError:
+                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 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:
+                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')
+
+
+class MessageSuggestedQuestionApi(InstalledAppResource):
+    def get(self, installed_app, message_id):
+        app_model = installed_app.app
+        if app_model.mode != 'chat':
+            raise NotCompletionAppError()
+
+        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 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 Exception:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+
+        return {'data': questions}
+
+
+api.add_resource(MessageListApi, '/installed-apps/<uuid:installed_app_id>/messages', endpoint='installed_app_messages')
+api.add_resource(MessageFeedbackApi, '/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/feedbacks', endpoint='installed_app_message_feedback')
+api.add_resource(MessageMoreLikeThisApi, '/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/more-like-this', endpoint='installed_app_more_like_this')
+api.add_resource(MessageSuggestedQuestionApi, '/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/suggested-questions', endpoint='installed_app_suggested_question')

api/controllers/console/explore/parameter.py

@@ -0,0 +1,50 @@
+# -*- coding:utf-8 -*-
+from flask_restful import marshal_with, fields
+
+from controllers.console import api
+from controllers.console.explore.wraps import InstalledAppResource
+
+from core.llm.llm_builder import LLMBuilder
+from models.provider import ProviderName
+from models.model import InstalledApp
+
+
+class AppParameterApi(InstalledAppResource):
+    """Resource for app variables."""
+    variable_fields = {
+        'key': fields.String,
+        'name': fields.String,
+        'description': fields.String,
+        'type': fields.String,
+        'default': fields.String,
+        'max_length': fields.Integer,
+        'options': fields.List(fields.String)
+    }
+
+    parameters_fields = {
+        'opening_statement': fields.String,
+        'suggested_questions': fields.Raw,
+        'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': fields.Raw,
+        'more_like_this': fields.Raw,
+        'user_input_form': fields.Raw,
+    }
+
+    @marshal_with(parameters_fields)
+    def get(self, installed_app: InstalledApp):
+        """Retrieve app parameters."""
+        app_model = installed_app.app
+        app_model_config = app_model.app_model_config
+        provider_name = LLMBuilder.get_default_provider(installed_app.tenant_id, 'whisper-1')
+
+        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 if provider_name == ProviderName.OPENAI.value else { 'enabled': False },
+            'more_like_this': app_model_config.more_like_this_dict,
+            'user_input_form': app_model_config.user_input_form_list
+        }
+
+
+api.add_resource(AppParameterApi, '/installed-apps/<uuid:installed_app_id>/parameters', endpoint='installed_app_parameters')

api/controllers/console/explore/recommended_app.py

@@ -0,0 +1,138 @@
+# -*- coding:utf-8 -*-
+from flask_login import login_required, current_user
+from flask_restful import Resource, fields, marshal_with
+from sqlalchemy import and_
+
+from controllers.console import api
+from controllers.console.app.error import AppNotFoundError
+from controllers.console.wraps import account_initialization_required
+from extensions.ext_database import db
+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
+}
+
+recommended_app_fields = {
+    'app': fields.Nested(app_fields, attribute='app'),
+    'app_id': fields.String,
+    'description': fields.String(attribute='description'),
+    'copyright': fields.String,
+    'privacy_policy': fields.String,
+    'category': fields.String,
+    'position': fields.Integer,
+    'is_listed': fields.Boolean,
+    'install_count': fields.Integer,
+    'installed': fields.Boolean,
+    'editable': fields.Boolean
+}
+
+recommended_app_list_fields = {
+    'recommended_apps': fields.List(fields.Nested(recommended_app_fields)),
+    'categories': fields.List(fields.String)
+}
+
+
+class RecommendedAppListApi(Resource):
+    @login_required
+    @account_initialization_required
+    @marshal_with(recommended_app_list_fields)
+    def get(self):
+        language_prefix = current_user.interface_language if current_user.interface_language else 'en-US'
+
+        recommended_apps = db.session.query(RecommendedApp).filter(
+            RecommendedApp.is_listed == True,
+            RecommendedApp.language == language_prefix
+        ).all()
+
+        categories = set()
+        current_user.role = TenantService.get_user_role(current_user, current_user.current_tenant)
+        recommended_apps_result = []
+        for recommended_app in recommended_apps:
+            installed = db.session.query(InstalledApp).filter(
+                and_(
+                    InstalledApp.app_id == recommended_app.app_id,
+                    InstalledApp.tenant_id == current_user.current_tenant_id
+                )
+            ).first() is not None
+
+            app = recommended_app.app
+            if not app or not app.is_public:
+                continue
+
+            site = app.site
+            if not site:
+                continue
+
+            recommended_app_result = {
+                'id': recommended_app.id,
+                'app': app,
+                'app_id': recommended_app.app_id,
+                'description': site.description,
+                'copyright': site.copyright,
+                'privacy_policy': site.privacy_policy,
+                'category': recommended_app.category,
+                'position': recommended_app.position,
+                'is_listed': recommended_app.is_listed,
+                'install_count': recommended_app.install_count,
+                'installed': installed,
+                'editable': current_user.role in ['owner', 'admin'],
+            }
+            recommended_apps_result.append(recommended_app_result)
+
+            categories.add(recommended_app.category)  # add category to categories
+
+        return {'recommended_apps': recommended_apps_result, 'categories': list(categories)}
+
+
+class RecommendedAppApi(Resource):
+    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_simple_detail_fields = {
+        'id': fields.String,
+        'name': fields.String,
+        'icon': fields.String,
+        'icon_background': fields.String,
+        'mode': fields.String,
+        'app_model_config': fields.Nested(model_config_fields),
+    }
+
+    @login_required
+    @account_initialization_required
+    @marshal_with(app_simple_detail_fields)
+    def get(self, app_id):
+        app_id = str(app_id)
+
+        # is in public recommended list
+        recommended_app = db.session.query(RecommendedApp).filter(
+            RecommendedApp.is_listed == True,
+            RecommendedApp.app_id == app_id
+        ).first()
+
+        if not recommended_app:
+            raise AppNotFoundError
+
+        # get app detail
+        app = db.session.query(App).filter(App.id == app_id).first()
+        if not app or not app.is_public:
+            raise AppNotFoundError
+
+        return app
+
+
+api.add_resource(RecommendedAppListApi, '/explore/apps')
+api.add_resource(RecommendedAppApi, '/explore/apps/<uuid:app_id>')

api/controllers/console/explore/saved_message.py

@@ -0,0 +1,79 @@
+from flask_login import current_user
+from flask_restful import reqparse, marshal_with, fields
+from flask_restful.inputs import int_range
+from werkzeug.exceptions import NotFound
+
+from controllers.console import api
+from controllers.console.explore.error import NotCompletionAppError
+from controllers.console.explore.wraps import InstalledAppResource
+from libs.helper import uuid_value, TimestampField
+from services.errors.message import MessageNotExistsError
+from services.saved_message_service import SavedMessageService
+
+feedback_fields = {
+    'rating': fields.String
+}
+
+message_fields = {
+    '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
+}
+
+
+class SavedMessageListApi(InstalledAppResource):
+    saved_message_infinite_scroll_pagination_fields = {
+        'limit': fields.Integer,
+        'has_more': fields.Boolean,
+        'data': fields.List(fields.Nested(message_fields))
+    }
+
+    @marshal_with(saved_message_infinite_scroll_pagination_fields)
+    def get(self, installed_app):
+        app_model = installed_app.app
+        if app_model.mode != 'completion':
+            raise NotCompletionAppError()
+
+        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')
+        args = parser.parse_args()
+
+        return SavedMessageService.pagination_by_last_id(app_model, current_user, args['last_id'], args['limit'])
+
+    def post(self, installed_app):
+        app_model = installed_app.app
+        if app_model.mode != 'completion':
+            raise NotCompletionAppError()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('message_id', type=uuid_value, required=True, location='json')
+        args = parser.parse_args()
+
+        try:
+            SavedMessageService.save(app_model, current_user, args['message_id'])
+        except MessageNotExistsError:
+            raise NotFound("Message Not Exists.")
+
+        return {'result': 'success'}
+
+
+class SavedMessageApi(InstalledAppResource):
+    def delete(self, installed_app, message_id):
+        app_model = installed_app.app
+
+        message_id = str(message_id)
+
+        if app_model.mode != 'completion':
+            raise NotCompletionAppError()
+
+        SavedMessageService.delete(app_model, current_user, message_id)
+
+        return {'result': 'success'}
+
+
+api.add_resource(SavedMessageListApi, '/installed-apps/<uuid:installed_app_id>/saved-messages', endpoint='installed_app_saved_messages')
+api.add_resource(SavedMessageApi, '/installed-apps/<uuid:installed_app_id>/saved-messages/<uuid:message_id>', endpoint='installed_app_saved_message')

api/controllers/console/explore/wraps.py

@@ -0,0 +1,48 @@
+from flask_login import login_required, current_user
+from flask_restful import Resource
+from functools import wraps
+
+from werkzeug.exceptions import NotFound
+
+from controllers.console.wraps import account_initialization_required
+from extensions.ext_database import db
+from models.model import InstalledApp
+
+
+def installed_app_required(view=None):
+    def decorator(view):
+        @wraps(view)
+        def decorated(*args, **kwargs):
+            if not kwargs.get('installed_app_id'):
+                raise ValueError('missing installed_app_id in path parameters')
+
+            installed_app_id = kwargs.get('installed_app_id')
+            installed_app_id = str(installed_app_id)
+
+            del kwargs['installed_app_id']
+
+            installed_app = db.session.query(InstalledApp).filter(
+                InstalledApp.id == str(installed_app_id),
+                InstalledApp.tenant_id == current_user.current_tenant_id
+            ).first()
+
+            if installed_app is None:
+                raise NotFound('Installed app not found')
+
+            if not installed_app.app:
+                db.session.delete(installed_app)
+                db.session.commit()
+
+                raise NotFound('Installed app not found')
+
+            return view(installed_app, *args, **kwargs)
+        return decorated
+
+    if view:
+        return decorator(view)
+    return decorator
+
+
+class InstalledAppResource(Resource):
+    # must be reversed if there are multiple decorators
+    method_decorators = [installed_app_required, account_initialization_required, login_required]

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.llm.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 +1,142 @@
+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.constant import llm_constant
+from core.conversation_message_task import PubHandler
+from core.llm.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('model', type=str, required=True, location='json')
+        parser.add_argument('tools', type=list, required=True, 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']
+
+        if not llm_constant.models[args['model']]:
+            raise ValueError("Model not exists.")
+
+        args['model_config']['model']['provider'] = llm_constant.models[args['model']]
+        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 +1,118 @@
+# -*- 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 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,
+    'model_config': fields.Raw,
+}
+
+conversation_infinite_scroll_pagination_fields = {
+    'limit': fields.Integer,
+    'has_more': fields.Boolean,
+    'data': fields.List(fields.Nested(conversation_fields))
+}
+
+
+class UniversalChatConversationListApi(UniversalChatResource):
+
+    @marshal_with(conversation_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_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 +1,127 @@
+# -*- 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.llm.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
+    }
+
+    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,
+        '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 +1,36 @@
+# -*- coding:utf-8 -*-
+from flask_restful import marshal_with, fields
+
+from controllers.console import api
+from controllers.console.universal_chat.wraps import UniversalChatResource
+
+from core.llm.llm_builder import LLMBuilder
+from models.provider import ProviderName
+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,
+    }
+
+    @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
+        provider_name = LLMBuilder.get_default_provider(universal_app.tenant_id, 'whisper-1')
+
+        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 if provider_name == ProviderName.OPENAI.value else { 'enabled': False },
+        }
+
+
+api.add_resource(UniversalChatParameterApi, '/universal-chat/parameters')

api/controllers/console/universal_chat/wraps.py

@@ -0,0 +1,84 @@
+import json
+from functools import wraps
+
+from flask_login import login_required, current_user
+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}),
+                    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

@@ -19,13 +19,26 @@ class VersionApi(Resource):
         args = parser.parse_args()
         check_update_url = current_app.config['CHECK_UPDATE_URL']
 
+        if not check_update_url:
+            return {
+                'version': '0.0.0',
+                'release_date': '',
+                'release_notes': '',
+                'can_auto_update': False
+            }
+
         try:
             response = requests.get(check_update_url, {
                 '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/workspace/account.py

@@ -6,22 +6,23 @@ from flask import current_app, request
 from flask_login import login_required, current_user
 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 +195,11 @@ 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
@@ -21,11 +27,11 @@ class InvalidInvitationCodeError(BaseHTTPException):
 
 class AccountAlreadyInitedError(BaseHTTPException):
     error_code = 'account_already_inited'
-    description = "Account already inited."
+    description = "The account has been initialized. Please refresh the page."
     code = 400
 
 
 class AccountNotInitializedError(BaseHTTPException):
     error_code = 'account_not_initialized'
-    description = "Account not initialized."
+    description = "The account has not been initialized yet. Please proceed with the initialization process first."
     code = 400

api/controllers/console/workspace/members.py

@@ -1,5 +1,5 @@
 # -*- coding:utf-8 -*-
-
+from flask import current_app
 from flask_login import login_required, current_user
 from flask_restful import Resource, reqparse, marshal_with, abort, fields, marshal
 
@@ -60,7 +60,8 @@ class MemberInviteEmailApi(Resource):
         inviter = current_user
 
         try:
-            RegisterService.invite_new_member(inviter.current_tenant, invitee_email, role=invitee_role, inviter=inviter)
+            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 == args['email']).first()
@@ -78,7 +79,16 @@ class MemberInviteEmailApi(Resource):
 
         # todo:413
 
-        return {'result': 'success', 'account': account}, 201
+        return {
+            'result': 'success',
+            'account': account,
+            'invite_url': '{}/activate?workspace_id={}&email={}&token={}'.format(
+                current_app.config.get("CONSOLE_WEB_URL"),
+                str(current_user.current_tenant_id),
+                invitee_email,
+                token
+            )
+        }, 201
 
 
 class MemberCancelInviteApi(Resource):
@@ -88,7 +98,7 @@ 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

@@ -3,6 +3,7 @@ import base64
 import json
 import logging
 
+from flask import current_app
 from flask_login import login_required, current_user
 from flask_restful import Resource, reqparse, abort
 from werkzeug.exceptions import Forbidden
@@ -34,7 +35,7 @@ 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")
+        ProviderService.init_supported_provider(current_user.current_tenant)
         providers = Provider.query.filter_by(tenant_id=tenant_id).all()
 
         provider_list = [
@@ -50,7 +51,8 @@ class ProviderListApi(Resource):
                        '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))
+                                                                ProviderName(p.provider_name), only_custom=True)
+                if p.provider_type == ProviderType.CUSTOM.value else None
             }
             for p in providers
         ]
@@ -82,29 +84,33 @@ class ProviderTokenApi(Resource):
 
         args = parser.parse_args()
 
-        if not args['token']:
-            raise ValueError('Token is empty')
+        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))
 
-        try:
-            ProviderService.validate_provider_configs(
+            base64_encrypted_token = ProviderService.get_encrypted_token(
                 tenant=current_user.current_tenant,
                 provider_name=ProviderName(provider),
                 configs=args['token']
             )
-            token_is_valid = True
-        except ValidateFailedError:
+        else:
+            base64_encrypted_token = None
             token_is_valid = False
 
         tenant = current_user.current_tenant
 
-        base64_encrypted_token = ProviderService.get_encrypted_token(
-            tenant=current_user.current_tenant,
-            provider_name=ProviderName(provider),
-            configs=args['token']
-        )
-
-        provider_model = Provider.query.filter_by(tenant_id=tenant.id, provider_name=provider,
-                                                  provider_type=ProviderType.CUSTOM.value).first()
+        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:
@@ -117,9 +123,20 @@ class ProviderTokenApi(Resource):
                                       is_valid=token_is_valid)
             db.session.add(provider_model)
 
+        if provider in [ProviderName.OPENAI.value, ProviderName.AZURE_OPENAI.value] and provider_model.is_valid:
+            other_providers = db.session.query(Provider).filter(
+                Provider.tenant_id == tenant.id,
+                Provider.provider_name.in_([ProviderName.OPENAI.value, ProviderName.AZURE_OPENAI.value]),
+                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,
+        if provider in [ProviderName.AZURE_OPENAI.value, ProviderName.COHERE.value,
                         ProviderName.HUGGINGFACEHUB.value]:
             return {'result': 'success', 'warning': 'MOCK: This provider is not supported yet.'}, 201
 
@@ -143,7 +160,7 @@ class ProviderTokenValidateApi(Resource):
         args = parser.parse_args()
 
         # todo: remove this when the provider is supported
-        if provider in [ProviderName.ANTHROPIC.value, ProviderName.AZURE_OPENAI.value, ProviderName.COHERE.value,
+        if provider in [ProviderName.COHERE.value,
                         ProviderName.HUGGINGFACEHUB.value]:
             return {'result': 'success', 'warning': 'MOCK: This provider is not supported yet.'}
 
@@ -189,7 +206,19 @@ class ProviderSystemApi(Resource):
             provider_model.is_valid = args['is_enabled']
             db.session.commit()
         elif not provider_model:
-            ProviderService.create_system_provider(tenant, provider, args['is_enabled'])
+            if provider == ProviderName.OPENAI.value:
+                quota_limit = current_app.config['OPENAI_HOSTED_QUOTA_LIMIT']
+            elif provider == ProviderName.ANTHROPIC.value:
+                quota_limit = current_app.config['ANTHROPIC_HOSTED_QUOTA_LIMIT']
+            else:
+                quota_limit = 0
+
+            ProviderService.create_system_provider(
+                tenant,
+                provider,
+                quota_limit,
+                args['is_enabled']
+            )
         else:
             abort(403)
 

api/controllers/console/workspace/tool_providers.py

@@ -0,0 +1,136 @@
+import json
+
+from flask_login import login_required, current_user
+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/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

api/controllers/service_api/app/app.py

@@ -4,6 +4,10 @@ from flask_restful import fields, marshal_with
 from controllers.service_api import api
 from controllers.service_api.wraps import AppApiResource
 
+from core.llm.llm_builder import LLMBuilder
+from models.provider import ProviderName
+from models.model import App
+
 
 class AppParameterApi(AppApiResource):
     """Resource for app variables."""
@@ -22,19 +26,22 @@ class AppParameterApi(AppApiResource):
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': 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
+        provider_name = LLMBuilder.get_default_provider(app_model.tenant_id, 'whisper-1')
 
         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 if provider_name == ProviderName.OPENAI.value else { 'enabled': False },
             '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.llm.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

@@ -54,8 +54,8 @@ 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:
@@ -115,8 +115,8 @@ 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 +156,8 @@ 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
@@ -48,6 +49,24 @@ class ConversationApi(AppApiResource):
         except services.errors.conversation.LastConversationNotExistsError:
             raise NotFound("Last Conversation Not Exists.")
 
+class ConversationDetailApi(AppApiResource):
+    @marshal_with(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)
+            return {"result": "success"}
+        except services.errors.conversation.ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
 
 class ConversationRenameApi(AppApiResource):
 
@@ -74,3 +93,5 @@ 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

@@ -4,43 +4,45 @@ from libs.exception import BaseHTTPException
 
 class AppUnavailableError(BaseHTTPException):
     error_code = 'app_unavailable'
-    description = "App unavailable."
+    description = "App unavailable, please check your app configurations."
     code = 400
 
 
 class NotCompletionAppError(BaseHTTPException):
     error_code = 'not_completion_app'
-    description = "Not Completion App"
+    description = "Please check if your Completion app mode matches the right API route."
     code = 400
 
 
 class NotChatAppError(BaseHTTPException):
     error_code = 'not_chat_app'
-    description = "Not Chat App"
+    description = "Please check if your Chat app mode matches the right API route."
     code = 400
 
 
 class ConversationCompletedError(BaseHTTPException):
     error_code = 'conversation_completed'
-    description = "Conversation Completed."
+    description = "The conversation has ended. Please start a new conversation."
     code = 400
 
 
 class ProviderNotInitializeError(BaseHTTPException):
     error_code = 'provider_not_initialize'
-    description = "Provider Token not initialize."
+    description = "No valid model provider credentials found. " \
+                  "Please go to Settings -> Model Provider to complete your provider credentials."
     code = 400
 
 
 class ProviderQuotaExceededError(BaseHTTPException):
     error_code = 'provider_quota_exceeded'
-    description = "Provider quota exceeded."
+    description = "Your quota for Dify Hosted OpenAI has been exhausted. " \
+                  "Please go to Settings -> Model Provider to complete your own provider credentials."
     code = 400
 
 
 class ProviderModelCurrentlyNotSupportError(BaseHTTPException):
     error_code = 'model_currently_not_support'
-    description = "GPT-4 currently not support."
+    description = "Dify Hosted OpenAI trial currently not support the GPT-4 model."
     code = 400
 
 
@@ -49,3 +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/dataset/document.py

@@ -69,21 +69,25 @@ class DocumentListApi(DatasetApiResource):
         document_data = {
             'data_source': {
                 'type': 'upload_file',
-                'info': upload_file.id
+                'info': [
+                    {
+                        'upload_file_id': upload_file.id
+                    }
+                ]
             }
         }
 
         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,
                 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]
 

api/controllers/service_api/dataset/error.py

@@ -16,5 +16,5 @@ class DocumentIndexingError(BaseHTTPException):
 
 class DatasetNotInitedError(BaseHTTPException):
     error_code = 'dataset_not_inited'
-    description = "Dataset not inited."
+    description = "The dataset is still being initialized or indexing. Please wait a moment."
     code = 403

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

api/controllers/web/app.py

@@ -4,6 +4,10 @@ from flask_restful import marshal_with, fields
 from controllers.web import api
 from controllers.web.wraps import WebApiResource
 
+from core.llm.llm_builder import LLMBuilder
+from models.provider import ProviderName
+from models.model import App
+
 
 class AppParameterApi(WebApiResource):
     """Resource for app variables."""
@@ -21,19 +25,22 @@ class AppParameterApi(WebApiResource):
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
+        'speech_to_text': 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
+        provider_name = LLMBuilder.get_default_provider(app_model.tenant_id, 'whisper-1')
 
         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 if provider_name == ProviderName.OPENAI.value else { 'enabled': False },
             'more_like_this': app_model_config.more_like_this_dict,
             'user_input_form': app_model_config.user_input_form_list
         }

api/controllers/web/audio.py

@@ -0,0 +1,63 @@
+# -*- coding:utf-8 -*-
+import logging
+
+from flask import request
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.web import api
+from controllers.web.error import AppUnavailableError, ProviderNotInitializeError, CompletionRequestError, \
+    ProviderQuotaExceededError, ProviderModelCurrentlyNotSupportError, NoAudioUploadedError, AudioTooLargeError, \
+    UnsupportedAudioTypeError, ProviderNotSupportSpeechToTextError
+from controllers.web.wraps import WebApiResource
+from core.llm.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 App, AppModelConfig
+
+
+class AudioApi(WebApiResource):
+    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/web/completion.py

@@ -52,8 +52,8 @@ class CompletionApi(WebApiResource):
         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:
@@ -109,8 +109,8 @@ class ChatApi(WebApiResource):
         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:
@@ -150,8 +150,8 @@ 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/web/conversation.py

@@ -47,7 +47,7 @@ class ConversationListApi(WebApiResource):
         try:
             return WebConversationService.pagination_by_last_id(
                 app_model=app_model,
-                end_user=end_user,
+                user=end_user,
                 last_id=args['last_id'],
                 limit=args['limit'],
                 pinned=pinned
@@ -62,7 +62,10 @@ class ConversationApi(WebApiResource):
             raise NotChatAppError()
 
         conversation_id = str(c_id)
-        ConversationService.delete(app_model, conversation_id, end_user)
+        try:
+            ConversationService.delete(app_model, conversation_id, end_user)
+        except ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
         WebConversationService.unpin(app_model, conversation_id, end_user)
 
         return {"result": "success"}, 204

api/controllers/web/error.py

@@ -4,43 +4,45 @@ from libs.exception import BaseHTTPException
 
 class AppUnavailableError(BaseHTTPException):
     error_code = 'app_unavailable'
-    description = "App unavailable."
+    description = "App unavailable, please check your app configurations."
     code = 400
 
 
 class NotCompletionAppError(BaseHTTPException):
     error_code = 'not_completion_app'
-    description = "Not Completion App"
+    description = "Please check if your Completion app mode matches the right API route."
     code = 400
 
 
 class NotChatAppError(BaseHTTPException):
     error_code = 'not_chat_app'
-    description = "Not Chat App"
+    description = "Please check if your Chat app mode matches the right API route."
     code = 400
 
 
 class ConversationCompletedError(BaseHTTPException):
     error_code = 'conversation_completed'
-    description = "Conversation Completed."
+    description = "The conversation has ended. Please start a new conversation."
     code = 400
 
 
 class ProviderNotInitializeError(BaseHTTPException):
     error_code = 'provider_not_initialize'
-    description = "Provider Token not initialize."
+    description = "No valid model provider credentials found. " \
+                  "Please go to Settings -> Model Provider to complete your provider credentials."
     code = 400
 
 
 class ProviderQuotaExceededError(BaseHTTPException):
     error_code = 'provider_quota_exceeded'
-    description = "Provider quota exceeded."
+    description = "Your quota for Dify Hosted OpenAI has been exhausted. " \
+                  "Please go to Settings -> Model Provider to complete your own provider credentials."
     code = 400
 
 
 class ProviderModelCurrentlyNotSupportError(BaseHTTPException):
     error_code = 'model_currently_not_support'
-    description = "GPT-4 currently not support."
+    description = "Dify Hosted OpenAI trial currently not support the GPT-4 model."
     code = 400
 
 
@@ -52,11 +54,35 @@ class CompletionRequestError(BaseHTTPException):
 
 class AppMoreLikeThisDisabledError(BaseHTTPException):
     error_code = 'app_more_like_this_disabled'
-    description = "More like this disabled."
+    description = "The 'More like this' feature is disabled. Please refresh your page."
     code = 403
 
 
 class AppSuggestedQuestionsAfterAnswerDisabledError(BaseHTTPException):
     error_code = 'app_suggested_questions_after_answer_disabled'
-    description = "Function Suggested questions after answer disabled."
+    description = "The 'Suggested Questions After Answer' 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/web/message.py

@@ -101,8 +101,8 @@ class MessageMoreLikeThisApi(WebApiResource):
             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:
@@ -129,8 +129,8 @@ 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:
@@ -167,8 +167,8 @@ class MessageSuggestedQuestionApi(WebApiResource):
             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/web/passport.py

@@ -0,0 +1,64 @@
+# -*- coding:utf-8 -*-
+import uuid
+from controllers.web import api
+from flask_restful import Resource
+from flask import request
+from werkzeug.exceptions import Unauthorized, NotFound
+from models.model import Site, EndUser, App
+from extensions.ext_database import db
+from libs.passport import PassportService
+
+class PassportResource(Resource):
+    """Base resource for passport."""
+    def get(self):
+        app_id = request.headers.get('X-App-Code')
+        if app_id is None:
+            raise Unauthorized('X-App-Code header is missing.')
+
+        # get site from db and check if it is normal
+        site = db.session.query(Site).filter(
+            Site.code == app_id,
+            Site.status == 'normal'
+        ).first()
+        if not site:
+            raise NotFound()
+        # get app from db and check if it is normal and enable_site
+        app_model = db.session.query(App).filter(App.id == site.app_id).first()
+        if not app_model or app_model.status != 'normal' or not app_model.enable_site:
+            raise NotFound()
+        
+        end_user = EndUser(
+            tenant_id=app_model.tenant_id,
+            app_id=app_model.id,
+            type='browser',
+            is_anonymous=True,
+            session_id=generate_session_id(),
+        )
+        db.session.add(end_user)
+        db.session.commit()
+
+        payload = {
+            "iss": site.app_id,
+            'sub': 'Web API Passport',
+            'app_id': site.app_id,
+            'end_user_id': end_user.id,
+        }
+
+        tk = PassportService().issue(payload)
+
+        return {
+            'access_token': tk,
+        }
+
+api.add_resource(PassportResource, '/passport')
+
+def generate_session_id():
+    """
+    Generate a unique session ID.
+    """
+    while True:
+        session_id = str(uuid.uuid4())
+        existing_count = db.session.query(EndUser) \
+            .filter(EndUser.session_id == session_id).count()
+        if existing_count == 0:
+            return session_id

api/controllers/web/wraps.py

@@ -1,107 +1,50 @@
 # -*- coding:utf-8 -*-
-import uuid
 from functools import wraps
 
-from flask import request, session
+from flask import request
 from flask_restful import Resource
 from werkzeug.exceptions import NotFound, Unauthorized
 
 from extensions.ext_database import db
-from models.model import App, Site, EndUser
+from models.model import App, EndUser
+from libs.passport import PassportService
 
-
-def validate_token(view=None):
+def validate_jwt_token(view=None):
     def decorator(view):
         @wraps(view)
         def decorated(*args, **kwargs):
-            site = validate_and_get_site()
-
-            app_model = db.session.query(App).get(site.app_id)
-            if not app_model:
-                raise NotFound()
-
-            if app_model.status != 'normal':
-                raise NotFound()
-
-            if not app_model.enable_site:
-                raise NotFound()
-
-            end_user = create_or_update_end_user_for_session(app_model)
+            app_model, end_user = decode_jwt_token()
 
             return view(app_model, end_user, *args, **kwargs)
         return decorated
-
     if view:
         return decorator(view)
     return decorator
 
-
-def validate_and_get_site():
-    """
-    Validate and get API token.
-    """
+def decode_jwt_token():
     auth_header = request.headers.get('Authorization')
     if auth_header is None:
-        raise Unauthorized()
+        raise Unauthorized('Authorization header is missing.')
 
-    auth_scheme, auth_token = auth_header.split(None, 1)
+    if ' ' not in auth_header:
+        raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+    
+    auth_scheme, tk = auth_header.split(None, 1)
     auth_scheme = auth_scheme.lower()
 
     if auth_scheme != 'bearer':
-        raise Unauthorized()
-
-    site = db.session.query(Site).filter(
-        Site.code == auth_token,
-        Site.status == 'normal'
-    ).first()
-
-    if not site:
+        raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+    decoded = PassportService().verify(tk)
+    app_model = db.session.query(App).filter(App.id == decoded['app_id']).first()
+    if not app_model:
+        raise NotFound()
+    if app_model.enable_site is False:
+        raise Unauthorized('Site is disabled.')
+    end_user = db.session.query(EndUser).filter(EndUser.id == decoded['end_user_id']).first()
+    if not end_user:
         raise NotFound()
 
-    return site
-
-
-def create_or_update_end_user_for_session(app_model):
-    """
-    Create or update session terminal based on session ID.
-    """
-    if 'session_id' not in session:
-        session['session_id'] = generate_session_id()
-
-    session_id = session.get('session_id')
-    end_user = db.session.query(EndUser) \
-        .filter(
-        EndUser.session_id == session_id,
-        EndUser.type == 'browser'
-    ).first()
-
-    if end_user is None:
-        end_user = EndUser(
-            tenant_id=app_model.tenant_id,
-            app_id=app_model.id,
-            type='browser',
-            is_anonymous=True,
-            session_id=session_id
-        )
-        db.session.add(end_user)
-        db.session.commit()
-
-    return end_user
-
-
-def generate_session_id():
-    """
-    Generate a unique session ID.
-    """
-    count = 1
-    session_id = ''
-    while count != 0:
-        session_id = str(uuid.uuid4())
-        count = db.session.query(EndUser) \
-            .filter(EndUser.session_id == session_id).count()
-
-    return session_id
-
+    return app_model, end_user
 
 class WebApiResource(Resource):
-    method_decorators = [validate_token]
+    method_decorators = [validate_jwt_token]

api/core/__init__.py

@@ -3,50 +3,34 @@ from typing import Optional
 
 import langchain
 from flask import Flask
-from jieba.analyse import default_tfidf
-from langchain import set_handler
-from langchain.prompts.base import DEFAULT_FORMATTER_MAPPING
-from llama_index import IndexStructType, QueryMode
-from llama_index.indices.registry import INDEX_STRUT_TYPE_TO_QUERY_MAP
 from pydantic import BaseModel
 
 from core.callback_handler.std_out_callback_handler import DifyStdOutCallbackHandler
-from core.index.keyword_table.jieba_keyword_table import GPTJIEBAKeywordTableIndex
-from core.index.keyword_table.stopwords import STOPWORDS
 from core.prompt.prompt_template import OneLineFormatter
-from core.vector_store.vector_store import VectorStore
-from core.vector_store.vector_store_index_query import EnhanceGPTVectorStoreIndexQuery
 
 
 class HostedOpenAICredential(BaseModel):
     api_key: str
 
 
+class HostedAnthropicCredential(BaseModel):
+    api_key: str
+
+
 class HostedLLMCredentials(BaseModel):
     openai: Optional[HostedOpenAICredential] = None
+    anthropic: Optional[HostedAnthropicCredential] = None
 
 
 hosted_llm_credentials = HostedLLMCredentials()
 
 
 def init_app(app: Flask):
-    formatter = OneLineFormatter()
-    DEFAULT_FORMATTER_MAPPING['f-string'] = formatter.format
-    INDEX_STRUT_TYPE_TO_QUERY_MAP[IndexStructType.KEYWORD_TABLE] = GPTJIEBAKeywordTableIndex.get_query_map()
-    INDEX_STRUT_TYPE_TO_QUERY_MAP[IndexStructType.WEAVIATE] = {
-        QueryMode.DEFAULT: EnhanceGPTVectorStoreIndexQuery,
-        QueryMode.EMBEDDING: EnhanceGPTVectorStoreIndexQuery,
-    }
-    INDEX_STRUT_TYPE_TO_QUERY_MAP[IndexStructType.QDRANT] = {
-        QueryMode.DEFAULT: EnhanceGPTVectorStoreIndexQuery,
-        QueryMode.EMBEDDING: EnhanceGPTVectorStoreIndexQuery,
-    }
-
-    default_tfidf.stop_words = STOPWORDS
-
     if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
         langchain.verbose = True
-        set_handler(DifyStdOutCallbackHandler())
 
     if app.config.get("OPENAI_API_KEY"):
         hosted_llm_credentials.openai = HostedOpenAICredential(api_key=app.config.get("OPENAI_API_KEY"))
+
+    if app.config.get("ANTHROPIC_API_KEY"):
+        hosted_llm_credentials.anthropic = HostedAnthropicCredential(api_key=app.config.get("ANTHROPIC_API_KEY"))

api/core/agent/agent/calc_token_mixin.py

@@ -0,0 +1,35 @@
+from typing import cast, List
+
+from langchain import OpenAI
+from langchain.base_language import BaseLanguageModel
+from langchain.chat_models.openai import ChatOpenAI
+from langchain.schema import BaseMessage
+
+from core.constant import llm_constant
+
+
+class CalcTokenMixin:
+
+    def get_num_tokens_from_messages(self, llm: BaseLanguageModel, messages: List[BaseMessage], **kwargs) -> int:
+        llm = cast(ChatOpenAI, llm)
+        return llm.get_num_tokens_from_messages(messages)
+
+    def get_message_rest_tokens(self, llm: BaseLanguageModel, messages: List[BaseMessage], **kwargs) -> int:
+        """
+        Got the rest tokens available for the model after excluding messages tokens and completion max tokens
+
+        :param llm:
+        :param messages:
+        :return:
+        """
+        llm = cast(ChatOpenAI, llm)
+        llm_max_tokens = llm_constant.max_context_token_length[llm.model_name]
+        completion_max_tokens = llm.max_tokens
+        used_tokens = self.get_num_tokens_from_messages(llm, messages, **kwargs)
+        rest_tokens = llm_max_tokens - completion_max_tokens - used_tokens
+
+        return rest_tokens
+
+
+class ExceededLLMTokensLimitError(Exception):
+    pass

api/core/agent/agent/multi_dataset_router_agent.py

@@ -0,0 +1,83 @@
+from typing import Tuple, List, Any, Union, Sequence, Optional, cast
+
+from langchain.agents import OpenAIFunctionsAgent, BaseSingleActionAgent
+from langchain.callbacks.base import BaseCallbackManager
+from langchain.callbacks.manager import Callbacks
+from langchain.prompts.chat import BaseMessagePromptTemplate
+from langchain.schema import AgentAction, AgentFinish, BaseLanguageModel, SystemMessage
+from langchain.tools import BaseTool
+
+from core.tool.dataset_retriever_tool import DatasetRetrieverTool
+
+
+class MultiDatasetRouterAgent(OpenAIFunctionsAgent):
+    """
+    An Multi Dataset Retrieve Agent driven by Router.
+    """
+
+    def should_use_agent(self, query: str):
+        """
+        return should use agent
+
+        :param query:
+        :return:
+        """
+        return True
+
+    def plan(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        callbacks: Callbacks = None,
+        **kwargs: Any,
+    ) -> Union[AgentAction, AgentFinish]:
+        """Given input, decided what to do.
+
+        Args:
+            intermediate_steps: Steps the LLM has taken to date, along with observations
+            **kwargs: User inputs.
+
+        Returns:
+            Action specifying what tool to use.
+        """
+        if len(self.tools) == 0:
+            return AgentFinish(return_values={"output": ''}, log='')
+        elif len(self.tools) == 1:
+            tool = next(iter(self.tools))
+            tool = cast(DatasetRetrieverTool, tool)
+            rst = tool.run(tool_input={'dataset_id': tool.dataset_id, 'query': kwargs['input']})
+            return AgentFinish(return_values={"output": rst}, log=rst)
+
+        if intermediate_steps:
+            _, observation = intermediate_steps[-1]
+            return AgentFinish(return_values={"output": observation}, log=observation)
+
+        return super().plan(intermediate_steps, callbacks, **kwargs)
+
+    async def aplan(
+            self,
+            intermediate_steps: List[Tuple[AgentAction, str]],
+            callbacks: Callbacks = None,
+            **kwargs: Any,
+    ) -> Union[AgentAction, AgentFinish]:
+        raise NotImplementedError()
+
+    @classmethod
+    def from_llm_and_tools(
+            cls,
+            llm: BaseLanguageModel,
+            tools: Sequence[BaseTool],
+            callback_manager: Optional[BaseCallbackManager] = None,
+            extra_prompt_messages: Optional[List[BaseMessagePromptTemplate]] = None,
+            system_message: Optional[SystemMessage] = SystemMessage(
+                content="You are a helpful AI assistant."
+            ),
+            **kwargs: Any,
+    ) -> BaseSingleActionAgent:
+        return super().from_llm_and_tools(
+            llm=llm,
+            tools=tools,
+            callback_manager=callback_manager,
+            extra_prompt_messages=extra_prompt_messages,
+            system_message=system_message,
+            **kwargs,
+        )

api/core/agent/agent/openai_function_call.py

@@ -0,0 +1,112 @@
+from typing import List, Tuple, Any, Union, Sequence, Optional
+
+from langchain.agents import OpenAIFunctionsAgent, BaseSingleActionAgent
+from langchain.agents.openai_functions_agent.base import _parse_ai_message, \
+    _format_intermediate_steps
+from langchain.callbacks.base import BaseCallbackManager
+from langchain.callbacks.manager import Callbacks
+from langchain.prompts.chat import BaseMessagePromptTemplate
+from langchain.schema import AgentAction, AgentFinish, SystemMessage, BaseLanguageModel
+from langchain.tools import BaseTool
+
+from core.agent.agent.calc_token_mixin import ExceededLLMTokensLimitError
+from core.agent.agent.openai_function_call_summarize_mixin import OpenAIFunctionCallSummarizeMixin
+
+
+class AutoSummarizingOpenAIFunctionCallAgent(OpenAIFunctionsAgent, OpenAIFunctionCallSummarizeMixin):
+
+    @classmethod
+    def from_llm_and_tools(
+            cls,
+            llm: BaseLanguageModel,
+            tools: Sequence[BaseTool],
+            callback_manager: Optional[BaseCallbackManager] = None,
+            extra_prompt_messages: Optional[List[BaseMessagePromptTemplate]] = None,
+            system_message: Optional[SystemMessage] = SystemMessage(
+                content="You are a helpful AI assistant."
+            ),
+            **kwargs: Any,
+    ) -> BaseSingleActionAgent:
+        return super().from_llm_and_tools(
+            llm=llm,
+            tools=tools,
+            callback_manager=callback_manager,
+            extra_prompt_messages=extra_prompt_messages,
+            system_message=cls.get_system_message(),
+            **kwargs,
+        )
+
+    def should_use_agent(self, query: str):
+        """
+        return should use agent
+
+        :param query:
+        :return:
+        """
+        original_max_tokens = self.llm.max_tokens
+        self.llm.max_tokens = 15
+
+        prompt = self.prompt.format_prompt(input=query, agent_scratchpad=[])
+        messages = prompt.to_messages()
+
+        predicted_message = self.llm.predict_messages(
+            messages, functions=self.functions, callbacks=None
+        )
+
+        function_call = predicted_message.additional_kwargs.get("function_call", {})
+
+        self.llm.max_tokens = original_max_tokens
+
+        return True if function_call else False
+
+    def plan(
+            self,
+            intermediate_steps: List[Tuple[AgentAction, str]],
+            callbacks: Callbacks = None,
+            **kwargs: Any,
+    ) -> Union[AgentAction, AgentFinish]:
+        """Given input, decided what to do.
+
+        Args:
+            intermediate_steps: Steps the LLM has taken to date, along with observations
+            **kwargs: User inputs.
+
+        Returns:
+            Action specifying what tool to use.
+        """
+        agent_scratchpad = _format_intermediate_steps(intermediate_steps)
+        selected_inputs = {
+            k: kwargs[k] for k in self.prompt.input_variables if k != "agent_scratchpad"
+        }
+        full_inputs = dict(**selected_inputs, agent_scratchpad=agent_scratchpad)
+        prompt = self.prompt.format_prompt(**full_inputs)
+        messages = prompt.to_messages()
+
+        # summarize messages if rest_tokens < 0
+        try:
+            messages = self.summarize_messages_if_needed(self.llm, messages, functions=self.functions)
+        except ExceededLLMTokensLimitError as e:
+            return AgentFinish(return_values={"output": str(e)}, log=str(e))
+
+        predicted_message = self.llm.predict_messages(
+            messages, functions=self.functions, callbacks=callbacks
+        )
+        agent_decision = _parse_ai_message(predicted_message)
+        return agent_decision
+
+    @classmethod
+    def get_system_message(cls):
+        return SystemMessage(content="You are a helpful AI assistant.\n"
+                                     "The current date or current time you know is wrong.\n"
+                                     "Respond directly if appropriate.")
+
+    def return_stopped_response(
+            self,
+            early_stopping_method: str,
+            intermediate_steps: List[Tuple[AgentAction, str]],
+            **kwargs: Any,
+    ) -> AgentFinish:
+        try:
+            return super().return_stopped_response(early_stopping_method, intermediate_steps, **kwargs)
+        except ValueError:
+            return AgentFinish({"output": "I'm sorry, I don't know how to respond to that."}, "")

api/core/agent/agent/openai_function_call_summarize_mixin.py

@@ -0,0 +1,132 @@
+from typing import cast, List
+
+from langchain.chat_models import ChatOpenAI
+from langchain.chat_models.openai import _convert_message_to_dict
+from langchain.memory.summary import SummarizerMixin
+from langchain.schema import SystemMessage, HumanMessage, BaseMessage, AIMessage, BaseLanguageModel
+from pydantic import BaseModel
+
+from core.agent.agent.calc_token_mixin import ExceededLLMTokensLimitError, CalcTokenMixin
+
+
+class OpenAIFunctionCallSummarizeMixin(BaseModel, CalcTokenMixin):
+    moving_summary_buffer: str = ""
+    moving_summary_index: int = 0
+    summary_llm: BaseLanguageModel
+
+    def summarize_messages_if_needed(self, llm: BaseLanguageModel, messages: List[BaseMessage], **kwargs) -> List[BaseMessage]:
+        # calculate rest tokens and summarize previous function observation messages if rest_tokens < 0
+        rest_tokens = self.get_message_rest_tokens(llm, messages, **kwargs)
+        rest_tokens = rest_tokens - 20  # to deal with the inaccuracy of rest_tokens
+        if rest_tokens >= 0:
+            return messages
+
+        system_message = None
+        human_message = None
+        should_summary_messages = []
+        for message in messages:
+            if isinstance(message, SystemMessage):
+                system_message = message
+            elif isinstance(message, HumanMessage):
+                human_message = message
+            else:
+                should_summary_messages.append(message)
+
+        if len(should_summary_messages) > 2:
+            ai_message = should_summary_messages[-2]
+            function_message = should_summary_messages[-1]
+            should_summary_messages = should_summary_messages[self.moving_summary_index:-2]
+            self.moving_summary_index = len(should_summary_messages)
+        else:
+            error_msg = "Exceeded LLM tokens limit, stopped."
+            raise ExceededLLMTokensLimitError(error_msg)
+
+        new_messages = [system_message, human_message]
+
+        if self.moving_summary_index == 0:
+            should_summary_messages.insert(0, human_message)
+
+        summary_handler = SummarizerMixin(llm=self.summary_llm)
+        self.moving_summary_buffer = summary_handler.predict_new_summary(
+            messages=should_summary_messages,
+            existing_summary=self.moving_summary_buffer
+        )
+
+        new_messages.append(AIMessage(content=self.moving_summary_buffer))
+        new_messages.append(ai_message)
+        new_messages.append(function_message)
+
+        return new_messages
+
+    def get_num_tokens_from_messages(self, llm: BaseLanguageModel, messages: List[BaseMessage], **kwargs) -> int:
+        """Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.
+
+        Official documentation: https://github.com/openai/openai-cookbook/blob/
+        main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
+        llm = cast(ChatOpenAI, llm)
+        model, encoding = llm._get_encoding_model()
+        if model.startswith("gpt-3.5-turbo"):
+            # every message follows <im_start>{role/name}\n{content}<im_end>\n
+            tokens_per_message = 4
+            # if there's a name, the role is omitted
+            tokens_per_name = -1
+        elif model.startswith("gpt-4"):
+            tokens_per_message = 3
+            tokens_per_name = 1
+        else:
+            raise NotImplementedError(
+                f"get_num_tokens_from_messages() is not presently implemented "
+                f"for model {model}."
+                "See https://github.com/openai/openai-python/blob/main/chatml.md for "
+                "information on how messages are converted to tokens."
+            )
+        num_tokens = 0
+        for m in messages:
+            message = _convert_message_to_dict(m)
+            num_tokens += tokens_per_message
+            for key, value in message.items():
+                if key == "function_call":
+                    for f_key, f_value in value.items():
+                        num_tokens += len(encoding.encode(f_key))
+                        num_tokens += len(encoding.encode(f_value))
+                else:
+                    num_tokens += len(encoding.encode(value))
+
+                if key == "name":
+                    num_tokens += tokens_per_name
+        # every reply is primed with <im_start>assistant
+        num_tokens += 3
+
+        if kwargs.get('functions'):
+            for function in kwargs.get('functions'):
+                num_tokens += len(encoding.encode('name'))
+                num_tokens += len(encoding.encode(function.get("name")))
+                num_tokens += len(encoding.encode('description'))
+                num_tokens += len(encoding.encode(function.get("description")))
+                parameters = function.get("parameters")
+                num_tokens += len(encoding.encode('parameters'))
+                if 'title' in parameters:
+                    num_tokens += len(encoding.encode('title'))
+                    num_tokens += len(encoding.encode(parameters.get("title")))
+                num_tokens += len(encoding.encode('type'))
+                num_tokens += len(encoding.encode(parameters.get("type")))
+                if 'properties' in parameters:
+                    num_tokens += len(encoding.encode('properties'))
+                    for key, value in parameters.get('properties').items():
+                        num_tokens += len(encoding.encode(key))
+                        for field_key, field_value in value.items():
+                            num_tokens += len(encoding.encode(field_key))
+                            if field_key == 'enum':
+                                for enum_field in field_value:
+                                    num_tokens += 3
+                                    num_tokens += len(encoding.encode(enum_field))
+                            else:
+                                num_tokens += len(encoding.encode(field_key))
+                                num_tokens += len(encoding.encode(str(field_value)))
+                if 'required' in parameters:
+                    num_tokens += len(encoding.encode('required'))
+                    for required_field in parameters['required']:
+                        num_tokens += 3
+                        num_tokens += len(encoding.encode(required_field))
+
+        return num_tokens

api/core/agent/agent/openai_multi_function_call.py

@@ -0,0 +1,102 @@
+from typing import List, Tuple, Any, Union, Sequence, Optional
+
+from langchain.agents import BaseMultiActionAgent
+from langchain.agents.openai_functions_multi_agent.base import OpenAIMultiFunctionsAgent, _format_intermediate_steps, \
+    _parse_ai_message
+from langchain.callbacks.base import BaseCallbackManager
+from langchain.callbacks.manager import Callbacks
+from langchain.prompts.chat import BaseMessagePromptTemplate
+from langchain.schema import AgentAction, AgentFinish, SystemMessage, BaseLanguageModel
+from langchain.tools import BaseTool
+
+from core.agent.agent.calc_token_mixin import ExceededLLMTokensLimitError
+from core.agent.agent.openai_function_call_summarize_mixin import OpenAIFunctionCallSummarizeMixin
+
+
+class AutoSummarizingOpenMultiAIFunctionCallAgent(OpenAIMultiFunctionsAgent, OpenAIFunctionCallSummarizeMixin):
+
+    @classmethod
+    def from_llm_and_tools(
+            cls,
+            llm: BaseLanguageModel,
+            tools: Sequence[BaseTool],
+            callback_manager: Optional[BaseCallbackManager] = None,
+            extra_prompt_messages: Optional[List[BaseMessagePromptTemplate]] = None,
+            system_message: Optional[SystemMessage] = SystemMessage(
+                content="You are a helpful AI assistant."
+            ),
+            **kwargs: Any,
+    ) -> BaseMultiActionAgent:
+        return super().from_llm_and_tools(
+            llm=llm,
+            tools=tools,
+            callback_manager=callback_manager,
+            extra_prompt_messages=extra_prompt_messages,
+            system_message=cls.get_system_message(),
+            **kwargs,
+        )
+
+    def should_use_agent(self, query: str):
+        """
+        return should use agent
+
+        :param query:
+        :return:
+        """
+        original_max_tokens = self.llm.max_tokens
+        self.llm.max_tokens = 15
+
+        prompt = self.prompt.format_prompt(input=query, agent_scratchpad=[])
+        messages = prompt.to_messages()
+
+        predicted_message = self.llm.predict_messages(
+            messages, functions=self.functions, callbacks=None
+        )
+
+        function_call = predicted_message.additional_kwargs.get("function_call", {})
+
+        self.llm.max_tokens = original_max_tokens
+
+        return True if function_call else False
+
+    def plan(
+            self,
+            intermediate_steps: List[Tuple[AgentAction, str]],
+            callbacks: Callbacks = None,
+            **kwargs: Any,
+    ) -> Union[AgentAction, AgentFinish]:
+        """Given input, decided what to do.
+
+        Args:
+            intermediate_steps: Steps the LLM has taken to date, along with observations
+            **kwargs: User inputs.
+
+        Returns:
+            Action specifying what tool to use.
+        """
+        agent_scratchpad = _format_intermediate_steps(intermediate_steps)
+        selected_inputs = {
+            k: kwargs[k] for k in self.prompt.input_variables if k != "agent_scratchpad"
+        }
+        full_inputs = dict(**selected_inputs, agent_scratchpad=agent_scratchpad)
+        prompt = self.prompt.format_prompt(**full_inputs)
+        messages = prompt.to_messages()
+
+        # summarize messages if rest_tokens < 0
+        try:
+            messages = self.summarize_messages_if_needed(self.llm, messages, functions=self.functions)
+        except ExceededLLMTokensLimitError as e:
+            return AgentFinish(return_values={"output": str(e)}, log=str(e))
+
+        predicted_message = self.llm.predict_messages(
+            messages, functions=self.functions, callbacks=callbacks
+        )
+        agent_decision = _parse_ai_message(predicted_message)
+        return agent_decision
+
+    @classmethod
+    def get_system_message(cls):
+        # get current time
+        return SystemMessage(content="You are a helpful AI assistant.\n"
+                                     "The current date or current time you know is wrong.\n"
+                                     "Respond directly if appropriate.")

api/core/agent/agent/output_parser/structured_chat.py

@@ -0,0 +1,29 @@
+import json
+import re
+from typing import Union
+
+from langchain.agents.structured_chat.output_parser import StructuredChatOutputParser as LCStructuredChatOutputParser, \
+    logger
+from langchain.schema import AgentAction, AgentFinish, OutputParserException
+
+
+class StructuredChatOutputParser(LCStructuredChatOutputParser):
+    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
+        try:
+            action_match = re.search(r"```(.*?)\n(.*?)```?", text, re.DOTALL)
+            if action_match is not None:
+                response = json.loads(action_match.group(2).strip(), strict=False)
+                if isinstance(response, list):
+                    # gpt turbo frequently ignores the directive to emit a single action
+                    logger.warning("Got multiple action responses: %s", response)
+                    response = response[0]
+                if response["action"] == "Final Answer":
+                    return AgentFinish({"output": response["action_input"]}, text)
+                else:
+                    return AgentAction(
+                        response["action"], response.get("action_input", {}), text
+                    )
+            else:
+                return AgentFinish({"output": text}, text)
+        except Exception as e:
+            raise OutputParserException(f"Could not parse LLM output: {text}") from e

api/core/agent/agent/structured_chat.py

@@ -0,0 +1,182 @@
+import re
+from typing import List, Tuple, Any, Union, Sequence, Optional
+
+from langchain import BasePromptTemplate
+from langchain.agents import StructuredChatAgent, AgentOutputParser, Agent
+from langchain.agents.structured_chat.base import HUMAN_MESSAGE_TEMPLATE
+from langchain.base_language import BaseLanguageModel
+from langchain.callbacks.base import BaseCallbackManager
+from langchain.callbacks.manager import Callbacks
+from langchain.memory.summary import SummarizerMixin
+from langchain.prompts import SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate
+from langchain.schema import AgentAction, AgentFinish, AIMessage, HumanMessage
+from langchain.tools import BaseTool
+from langchain.agents.structured_chat.prompt import PREFIX, SUFFIX
+
+from core.agent.agent.calc_token_mixin import CalcTokenMixin, ExceededLLMTokensLimitError
+
+
+FORMAT_INSTRUCTIONS = """Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).
+The nouns in the format of "Thought", "Action", "Action Input", "Final Answer" must be expressed in English.
+Valid "action" values: "Final Answer" or {tool_names}
+
+Provide only ONE action per $JSON_BLOB, as shown:
+
+```
+{{{{
+  "action": $TOOL_NAME,
+  "action_input": $INPUT
+}}}}
+```
+
+Follow this format:
+
+Question: input question to answer
+Thought: consider previous and subsequent steps
+Action:
+```
+$JSON_BLOB
+```
+Observation: action result
+... (repeat Thought/Action/Observation N times)
+Thought: I know what to respond
+Action:
+```
+{{{{
+  "action": "Final Answer",
+  "action_input": "Final response to human"
+}}}}
+```"""
+
+
+class AutoSummarizingStructuredChatAgent(StructuredChatAgent, CalcTokenMixin):
+    moving_summary_buffer: str = ""
+    moving_summary_index: int = 0
+    summary_llm: BaseLanguageModel
+
+    def should_use_agent(self, query: str):
+        """
+        return should use agent
+        Using the ReACT mode to determine whether an agent is needed is costly,
+        so it's better to just use an Agent for reasoning, which is cheaper.
+
+        :param query:
+        :return:
+        """
+        return True
+
+    def plan(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        callbacks: Callbacks = None,
+        **kwargs: Any,
+    ) -> Union[AgentAction, AgentFinish]:
+        """Given input, decided what to do.
+
+        Args:
+            intermediate_steps: Steps the LLM has taken to date,
+                along with observations
+            callbacks: Callbacks to run.
+            **kwargs: User inputs.
+
+        Returns:
+            Action specifying what tool to use.
+        """
+        full_inputs = self.get_full_inputs(intermediate_steps, **kwargs)
+
+        prompts, _ = self.llm_chain.prep_prompts(input_list=[self.llm_chain.prep_inputs(full_inputs)])
+        messages = []
+        if prompts:
+            messages = prompts[0].to_messages()
+
+        rest_tokens = self.get_message_rest_tokens(self.llm_chain.llm, messages)
+        if rest_tokens < 0:
+            full_inputs = self.summarize_messages(intermediate_steps, **kwargs)
+
+        full_output = self.llm_chain.predict(callbacks=callbacks, **full_inputs)
+        return self.output_parser.parse(full_output)
+
+    def summarize_messages(self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs):
+        if len(intermediate_steps) >= 2:
+            should_summary_intermediate_steps = intermediate_steps[self.moving_summary_index:-1]
+            should_summary_messages = [AIMessage(content=observation)
+                                       for _, observation in should_summary_intermediate_steps]
+            if self.moving_summary_index == 0:
+                should_summary_messages.insert(0, HumanMessage(content=kwargs.get("input")))
+
+            self.moving_summary_index = len(intermediate_steps)
+        else:
+            error_msg = "Exceeded LLM tokens limit, stopped."
+            raise ExceededLLMTokensLimitError(error_msg)
+
+        summary_handler = SummarizerMixin(llm=self.summary_llm)
+        if self.moving_summary_buffer and 'chat_history' in kwargs:
+            kwargs["chat_history"].pop()
+
+        self.moving_summary_buffer = summary_handler.predict_new_summary(
+            messages=should_summary_messages,
+            existing_summary=self.moving_summary_buffer
+        )
+
+        if 'chat_history' in kwargs:
+            kwargs["chat_history"].append(AIMessage(content=self.moving_summary_buffer))
+
+        return self.get_full_inputs([intermediate_steps[-1]], **kwargs)
+
+    @classmethod
+    def create_prompt(
+            cls,
+            tools: Sequence[BaseTool],
+            prefix: str = PREFIX,
+            suffix: str = SUFFIX,
+            human_message_template: str = HUMAN_MESSAGE_TEMPLATE,
+            format_instructions: str = FORMAT_INSTRUCTIONS,
+            input_variables: Optional[List[str]] = None,
+            memory_prompts: Optional[List[BasePromptTemplate]] = None,
+    ) -> BasePromptTemplate:
+        tool_strings = []
+        for tool in tools:
+            args_schema = re.sub("}", "}}}}", re.sub("{", "{{{{", str(tool.args)))
+            tool_strings.append(f"{tool.name}: {tool.description}, args: {args_schema}")
+        formatted_tools = "\n".join(tool_strings)
+        tool_names = ", ".join([('"' + tool.name + '"') for tool in tools])
+        format_instructions = format_instructions.format(tool_names=tool_names)
+        template = "\n\n".join([prefix, formatted_tools, format_instructions, suffix])
+        if input_variables is None:
+            input_variables = ["input", "agent_scratchpad"]
+        _memory_prompts = memory_prompts or []
+        messages = [
+            SystemMessagePromptTemplate.from_template(template),
+            *_memory_prompts,
+            HumanMessagePromptTemplate.from_template(human_message_template),
+        ]
+        return ChatPromptTemplate(input_variables=input_variables, messages=messages)
+
+    @classmethod
+    def from_llm_and_tools(
+            cls,
+            llm: BaseLanguageModel,
+            tools: Sequence[BaseTool],
+            callback_manager: Optional[BaseCallbackManager] = None,
+            output_parser: Optional[AgentOutputParser] = None,
+            prefix: str = PREFIX,
+            suffix: str = SUFFIX,
+            human_message_template: str = HUMAN_MESSAGE_TEMPLATE,
+            format_instructions: str = FORMAT_INSTRUCTIONS,
+            input_variables: Optional[List[str]] = None,
+            memory_prompts: Optional[List[BasePromptTemplate]] = None,
+            **kwargs: Any,
+    ) -> Agent:
+        return super().from_llm_and_tools(
+            llm=llm,
+            tools=tools,
+            callback_manager=callback_manager,
+            output_parser=output_parser,
+            prefix=prefix,
+            suffix=suffix,
+            human_message_template=human_message_template,
+            format_instructions=format_instructions,
+            input_variables=input_variables,
+            memory_prompts=memory_prompts,
+            **kwargs,
+        )

api/core/agent/agent_builder.py

@@ -1,89 +0,0 @@
-from typing import Optional
-
-from langchain import LLMChain
-from langchain.agents import ZeroShotAgent, AgentExecutor, ConversationalAgent
-from langchain.callbacks import CallbackManager
-from langchain.memory.chat_memory import BaseChatMemory
-
-from core.callback_handler.agent_loop_gather_callback_handler import AgentLoopGatherCallbackHandler
-from core.callback_handler.dataset_tool_callback_handler import DatasetToolCallbackHandler
-from core.callback_handler.std_out_callback_handler import DifyStdOutCallbackHandler
-from core.llm.llm_builder import LLMBuilder
-
-
-class AgentBuilder:
-    @classmethod
-    def to_agent_chain(cls, tenant_id: str, tools, memory: Optional[BaseChatMemory],
-                       dataset_tool_callback_handler: DatasetToolCallbackHandler,
-                       agent_loop_gather_callback_handler: AgentLoopGatherCallbackHandler):
-        llm_callback_manager = CallbackManager([agent_loop_gather_callback_handler, DifyStdOutCallbackHandler()])
-        llm = LLMBuilder.to_llm(
-            tenant_id=tenant_id,
-            model_name=agent_loop_gather_callback_handler.model_name,
-            temperature=0,
-            max_tokens=1024,
-            callback_manager=llm_callback_manager
-        )
-
-        tool_callback_manager = CallbackManager([
-            agent_loop_gather_callback_handler,
-            dataset_tool_callback_handler,
-            DifyStdOutCallbackHandler()
-        ])
-
-        for tool in tools:
-            tool.callback_manager = tool_callback_manager
-
-        prompt = cls.build_agent_prompt_template(
-            tools=tools,
-            memory=memory,
-        )
-
-        agent_llm_chain = LLMChain(
-            llm=llm,
-            prompt=prompt,
-        )
-
-        agent = cls.build_agent(agent_llm_chain=agent_llm_chain, memory=memory)
-
-        agent_callback_manager = CallbackManager(
-            [agent_loop_gather_callback_handler, DifyStdOutCallbackHandler()]
-        )
-
-        agent_chain = AgentExecutor.from_agent_and_tools(
-            tools=tools,
-            agent=agent,
-            memory=memory,
-            callback_manager=agent_callback_manager,
-            max_iterations=6,
-            early_stopping_method="generate",
-            # `generate` will continue to complete the last inference after reaching the iteration limit or request time limit
-        )
-
-        return agent_chain
-
-    @classmethod
-    def build_agent_prompt_template(cls, tools, memory: Optional[BaseChatMemory]):
-        if memory:
-            prompt = ConversationalAgent.create_prompt(
-                tools=tools,
-            )
-        else:
-            prompt = ZeroShotAgent.create_prompt(
-                tools=tools,
-            )
-
-        return prompt
-
-    @classmethod
-    def build_agent(cls, agent_llm_chain: LLMChain, memory: Optional[BaseChatMemory]):
-        if memory:
-            agent = ConversationalAgent(
-                llm_chain=agent_llm_chain
-            )
-        else:
-            agent = ZeroShotAgent(
-                llm_chain=agent_llm_chain
-            )
-
-        return agent

api/core/agent/agent_executor.py

@@ -0,0 +1,122 @@
+import enum
+import logging
+from typing import Union, Optional
+
+from langchain.agents import BaseSingleActionAgent, BaseMultiActionAgent
+from langchain.base_language import BaseLanguageModel
+from langchain.callbacks.manager import Callbacks
+from langchain.memory.chat_memory import BaseChatMemory
+from langchain.tools import BaseTool
+from pydantic import BaseModel, Extra
+
+from core.agent.agent.multi_dataset_router_agent import MultiDatasetRouterAgent
+from core.agent.agent.openai_function_call import AutoSummarizingOpenAIFunctionCallAgent
+from core.agent.agent.openai_multi_function_call import AutoSummarizingOpenMultiAIFunctionCallAgent
+from core.agent.agent.output_parser.structured_chat import StructuredChatOutputParser
+from core.agent.agent.structured_chat import AutoSummarizingStructuredChatAgent
+from langchain.agents import AgentExecutor as LCAgentExecutor
+
+from core.tool.dataset_retriever_tool import DatasetRetrieverTool
+
+
+class PlanningStrategy(str, enum.Enum):
+    ROUTER = 'router'
+    REACT = 'react'
+    FUNCTION_CALL = 'function_call'
+    MULTI_FUNCTION_CALL = 'multi_function_call'
+
+
+class AgentConfiguration(BaseModel):
+    strategy: PlanningStrategy
+    llm: BaseLanguageModel
+    tools: list[BaseTool]
+    summary_llm: BaseLanguageModel
+    dataset_llm: BaseLanguageModel
+    memory: Optional[BaseChatMemory] = None
+    callbacks: Callbacks = None
+    max_iterations: int = 6
+    max_execution_time: Optional[float] = None
+    early_stopping_method: str = "generate"
+    # `generate` will continue to complete the last inference after reaching the iteration limit or request time limit
+
+    class Config:
+        """Configuration for this pydantic object."""
+
+        extra = Extra.forbid
+        arbitrary_types_allowed = True
+
+
+class AgentExecuteResult(BaseModel):
+    strategy: PlanningStrategy
+    output: Optional[str]
+    configuration: AgentConfiguration
+
+
+class AgentExecutor:
+    def __init__(self, configuration: AgentConfiguration):
+        self.configuration = configuration
+        self.agent = self._init_agent()
+
+    def _init_agent(self) -> Union[BaseSingleActionAgent | BaseMultiActionAgent]:
+        if self.configuration.strategy == PlanningStrategy.REACT:
+            agent = AutoSummarizingStructuredChatAgent.from_llm_and_tools(
+                llm=self.configuration.llm,
+                tools=self.configuration.tools,
+                output_parser=StructuredChatOutputParser(),
+                summary_llm=self.configuration.summary_llm,
+                verbose=True
+            )
+        elif self.configuration.strategy == PlanningStrategy.FUNCTION_CALL:
+            agent = AutoSummarizingOpenAIFunctionCallAgent.from_llm_and_tools(
+                llm=self.configuration.llm,
+                tools=self.configuration.tools,
+                extra_prompt_messages=self.configuration.memory.buffer if self.configuration.memory else None,  # used for read chat histories memory
+                summary_llm=self.configuration.summary_llm,
+                verbose=True
+            )
+        elif self.configuration.strategy == PlanningStrategy.MULTI_FUNCTION_CALL:
+            agent = AutoSummarizingOpenMultiAIFunctionCallAgent.from_llm_and_tools(
+                llm=self.configuration.llm,
+                tools=self.configuration.tools,
+                extra_prompt_messages=self.configuration.memory.buffer if self.configuration.memory else None,  # used for read chat histories memory
+                summary_llm=self.configuration.summary_llm,
+                verbose=True
+            )
+        elif self.configuration.strategy == PlanningStrategy.ROUTER:
+            self.configuration.tools = [t for t in self.configuration.tools if isinstance(t, DatasetRetrieverTool)]
+            agent = MultiDatasetRouterAgent.from_llm_and_tools(
+                llm=self.configuration.dataset_llm,
+                tools=self.configuration.tools,
+                extra_prompt_messages=self.configuration.memory.buffer if self.configuration.memory else None,
+                verbose=True
+            )
+        else:
+            raise NotImplementedError(f"Unknown Agent Strategy: {self.configuration.strategy}")
+
+        return agent
+
+    def should_use_agent(self, query: str) -> bool:
+        return self.agent.should_use_agent(query)
+
+    def run(self, query: str) -> AgentExecuteResult:
+        agent_executor = LCAgentExecutor.from_agent_and_tools(
+            agent=self.agent,
+            tools=self.configuration.tools,
+            memory=self.configuration.memory,
+            max_iterations=self.configuration.max_iterations,
+            max_execution_time=self.configuration.max_execution_time,
+            early_stopping_method=self.configuration.early_stopping_method,
+            callbacks=self.configuration.callbacks
+        )
+
+        try:
+            output = agent_executor.run(query)
+        except Exception:
+            logging.exception("agent_executor run failed")
+            output = None
+
+        return AgentExecuteResult(
+            output=output,
+            strategy=self.configuration.strategy,
+            configuration=self.configuration
+        )

api/core/callback_handler/agent_loop_gather_callback_handler.py

@@ -1,10 +1,12 @@
+import json
 import logging
 import time
 
 from typing import Any, Dict, List, Union, Optional
 
+from langchain.agents import openai_functions_agent, openai_functions_multi_agent
 from langchain.callbacks.base import BaseCallbackHandler
-from langchain.schema import AgentAction, AgentFinish, LLMResult
+from langchain.schema import AgentAction, AgentFinish, LLMResult, ChatGeneration
 
 from core.callback_handler.entity.agent_loop import AgentLoop
 from core.conversation_message_task import ConversationMessageTask
@@ -12,6 +14,7 @@ from core.conversation_message_task import ConversationMessageTask
 
 class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
     """Callback Handler that prints to std out."""
+    raise_error: bool = True
 
     def __init__(self, model_name, conversation_message_task: ConversationMessageTask) -> None:
         """Initialize callback handler."""
@@ -19,6 +22,7 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
         self.conversation_message_task = conversation_message_task
         self._agent_loops = []
         self._current_loop = None
+        self._message_agent_thought = None
         self.current_chain = None
 
     @property
@@ -28,6 +32,7 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
     def clear_agent_loops(self) -> None:
         self._agent_loops = []
         self._current_loop = None
+        self._message_agent_thought = None
 
     @property
     def always_verbose(self) -> bool:
@@ -60,13 +65,21 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
         # kwargs={}
         if self._current_loop and self._current_loop.status == 'llm_started':
             self._current_loop.status = 'llm_end'
-            self._current_loop.prompt_tokens = response.llm_output['token_usage']['prompt_tokens']
-            self._current_loop.completion = response.generations[0][0].text
-            self._current_loop.completion_tokens = response.llm_output['token_usage']['completion_tokens']
+            if response.llm_output:
+                self._current_loop.prompt_tokens = response.llm_output['token_usage']['prompt_tokens']
+            completion_generation = response.generations[0][0]
+            if isinstance(completion_generation, ChatGeneration):
+                completion_message = completion_generation.message
+                if 'function_call' in completion_message.additional_kwargs:
+                    self._current_loop.completion \
+                        = json.dumps({'function_call': completion_message.additional_kwargs['function_call']})
+                else:
+                    self._current_loop.completion = response.generations[0][0].text
+            else:
+                self._current_loop.completion = completion_generation.text
 
-    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
-        """Do nothing."""
-        pass
+            if response.llm_output:
+                self._current_loop.completion_tokens = response.llm_output['token_usage']['completion_tokens']
 
     def on_llm_error(
         self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
@@ -74,21 +87,7 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
         logging.error(error)
         self._agent_loops = []
         self._current_loop = None
-
-    def on_chain_start(
-        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
-    ) -> None:
-        """Print out that we are entering a chain."""
-        pass
-
-    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
-        """Print out that we finished a chain."""
-        pass
-
-    def on_chain_error(
-        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
-    ) -> None:
-        logging.error(error)
+        self._message_agent_thought = None
 
     def on_tool_start(
         self,
@@ -107,15 +106,29 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
     ) -> Any:
         """Run on agent action."""
         tool = action.tool
-        tool_input = action.tool_input
-        action_name_position = action.log.index("\nAction:") + 1 if action.log else -1
-        thought = action.log[:action_name_position].strip() if action.log else ''
+        tool_input = json.dumps({"query": action.tool_input}
+                                if isinstance(action.tool_input, str) else action.tool_input)
+        completion = None
+        if isinstance(action, openai_functions_agent.base._FunctionsAgentAction) \
+                or isinstance(action, openai_functions_multi_agent.base._FunctionsAgentAction):
+            thought = action.log.strip()
+            completion = json.dumps({'function_call': action.message_log[0].additional_kwargs['function_call']})
+        else:
+            action_name_position = action.log.index("Action:") if action.log else -1
+            thought = action.log[:action_name_position].strip() if action.log else ''
 
         if self._current_loop and self._current_loop.status == 'llm_end':
             self._current_loop.status = 'agent_action'
             self._current_loop.thought = thought
             self._current_loop.tool_name = tool
             self._current_loop.tool_input = tool_input
+            if completion is not None:
+                self._current_loop.completion = completion
+
+            self._message_agent_thought = self.conversation_message_task.on_agent_start(
+                self.current_chain,
+                self._current_loop
+            )
 
     def on_tool_end(
         self,
@@ -138,10 +151,13 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
             self._current_loop.completed_at = time.perf_counter()
             self._current_loop.latency = self._current_loop.completed_at - self._current_loop.started_at
 
-            self.conversation_message_task.on_agent_end(self.current_chain, self.model_name, self._current_loop)
+            self.conversation_message_task.on_agent_end(
+                self._message_agent_thought, self.model_name, self._current_loop
+            )
 
             self._agent_loops.append(self._current_loop)
             self._current_loop = None
+            self._message_agent_thought = None
 
     def on_tool_error(
         self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
@@ -150,16 +166,7 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
         logging.error(error)
         self._agent_loops = []
         self._current_loop = None
-
-    def on_text(
-        self,
-        text: str,
-        color: Optional[str] = None,
-        end: str = "",
-        **kwargs: Optional[str],
-    ) -> None:
-        """Run on additional input from chains and agents."""
-        pass
+        self._message_agent_thought = None
 
     def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> Any:
         """Run on agent end."""
@@ -169,10 +176,18 @@ class AgentLoopGatherCallbackHandler(BaseCallbackHandler):
             self._current_loop.completed = True
             self._current_loop.completed_at = time.perf_counter()
             self._current_loop.latency = self._current_loop.completed_at - self._current_loop.started_at
+            self._current_loop.thought = '[DONE]'
+            self._message_agent_thought = self.conversation_message_task.on_agent_start(
+                self.current_chain,
+                self._current_loop
+            )
 
-            self.conversation_message_task.on_agent_end(self.current_chain, self.model_name, self._current_loop)
+            self.conversation_message_task.on_agent_end(
+                self._message_agent_thought, self.model_name, self._current_loop
+            )
 
             self._agent_loops.append(self._current_loop)
             self._current_loop = None
+            self._message_agent_thought = None
         elif not self._current_loop and self._agent_loops:
             self._agent_loops[-1].status = 'agent_finish'

api/core/callback_handler/dataset_tool_callback_handler.py

@@ -1,9 +1,9 @@
+import json
 import logging
 
 from typing import Any, Dict, List, Union, Optional
 
 from langchain.callbacks.base import BaseCallbackHandler
-from langchain.schema import AgentAction, AgentFinish, LLMResult
 
 from core.callback_handler.entity.dataset_query import DatasetQueryObj
 from core.conversation_message_task import ConversationMessageTask
@@ -11,6 +11,7 @@ from core.conversation_message_task import ConversationMessageTask
 
 class DatasetToolCallbackHandler(BaseCallbackHandler):
     """Callback Handler that prints to std out."""
+    raise_error: bool = True
 
     def __init__(self, conversation_message_task: ConversationMessageTask) -> None:
         """Initialize callback handler."""
@@ -43,9 +44,11 @@ class DatasetToolCallbackHandler(BaseCallbackHandler):
         input_str: str,
         **kwargs: Any,
     ) -> None:
-        tool_name = serialized.get('name')
-        dataset_id = tool_name[len("dataset-"):]
-        self.conversation_message_task.on_dataset_query_end(DatasetQueryObj(dataset_id=dataset_id, query=input_str))
+        # tool_name = serialized.get('name')
+        input_dict = json.loads(input_str.replace("'", "\""))
+        dataset_id = input_dict.get('dataset_id')
+        query = input_dict.get('query')
+        self.conversation_message_task.on_dataset_query_end(DatasetQueryObj(dataset_id=dataset_id, query=query))
 
     def on_tool_end(
         self,
@@ -66,52 +69,3 @@ class DatasetToolCallbackHandler(BaseCallbackHandler):
     ) -> None:
         """Do nothing."""
         logging.error(error)
-
-    def on_chain_start(
-        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
-    ) -> None:
-        pass
-
-    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
-        pass
-
-    def on_chain_error(
-        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
-    ) -> None:
-        pass
-
-    def on_llm_start(
-        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
-    ) -> None:
-        pass
-
-    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
-        pass
-
-    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
-        """Do nothing."""
-        pass
-
-    def on_llm_error(
-        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
-    ) -> None:
-        logging.error(error)
-
-    def on_agent_action(
-        self, action: AgentAction, color: Optional[str] = None, **kwargs: Any
-    ) -> Any:
-        pass
-
-    def on_text(
-        self,
-        text: str,
-        color: Optional[str] = None,
-        end: str = "",
-        **kwargs: Optional[str],
-    ) -> None:
-        """Run on additional input from chains and agents."""
-        pass
-
-    def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> Any:
-        """Run on agent end."""
-        pass

api/core/callback_handler/entity/agent_loop.py

@@ -10,9 +10,9 @@ class AgentLoop(BaseModel):
     tool_output: str = None
 
     prompt: str = None
-    prompt_tokens: int = None
+    prompt_tokens: int = 0
     completion: str = None
-    completion_tokens: int = None
+    completion_tokens: int = 0
 
     latency: float = None