bump version to 0.4.9 (#2103 )

delete document cache embedding (#2101 )
Co-authored-by: jyong <jyong@dify.ai>
2026-01-29 00:06:00 +08:00 · 2024-01-19 22:25:23 +08:00 · 2024-01-19 21:37:54 +08:00 · 2024-01-19 21:06:26 +08:00 · 2024-01-19 20:30:36 +08:00 · 2024-01-19 20:12:04 +08:00
56 changed files with 884 additions and 508 deletions
--- a/.github/ISSUE_TEMPLATE/feature_request.yml
+++ b/.github/ISSUE_TEMPLATE/feature_request.yml
@ -14,22 +14,35 @@ body:
          required: true
  - type: textarea
    attributes:
-      label: Description of the new feature / enhancement
-      placeholder: What is the expected behavior of the proposed feature?
+      label: 1. Is this request related to a challenge you're experiencing?
+      placeholder: Please describe the specific scenario or problem you're facing as clearly as possible. For instance "I was trying to use [feature] for [specific task], and [what happened]... It was frustrating because...."
    validations:
      required: true
  - type: textarea
    attributes:
-      label: Scenario when this would be used?
-      placeholder: What is the scenario this would be used? Why is this important to your workflow as a dify user?
+      label: 2. Describe the feature you'd like to see
+      placeholder: Think about what you want to achieve and how this feature will help you. Sketches, flow diagrams, or any visual representation will be a major plus.
    validations:
      required: true
  - type: textarea
    attributes:
-      label: Supporting information
-      placeholder: "Having additional evidence, data, tweets, blog posts, research, ... anything is extremely helpful. This information provides context to the scenario that may otherwise be lost."
+      label: 3. How will this feature improve your workflow or experience?
+      placeholder: Tell us how this change will benefit your work. This helps us prioritize based on user impact.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: 4. Additional context or comments
+      placeholder: (Any other information, comments, documentations, links, or screenshots that would provide more clarity. This is the place to add anything else not covered above.)
    validations:
      required: false
+  - type: checkboxes
+    attributes:
+      label: 5. Can you help us with this feature?
+      description: Let us know! This is not a commitment, but a starting point for collaboration.
+      options:
+        - label: I am interested in contributing to this feature.
+          required: false
  - type: markdown
    attributes:
      value: Please limit one request per issue.
--- a/.github/workflows/api-model-runtime-tests.yml
+++ b/.github/workflows/api-model-runtime-tests.yml
@ -4,10 +4,6 @@ on:
  pull_request:
    branches:
      - main
-  push:
-    branches:
-      - deploy/dev
-      - feat/model-runtime

 jobs:
  test:
--- a/.github/workflows/style.yml
+++ b/.github/workflows/style.yml
@ -4,9 +4,6 @@ on:
  pull_request:
    branches:
      - main
-  push:
-    branches:
-      - deploy/dev

 concurrency:
  group: dep-${{ github.head_ref || github.run_id }}
@ -24,7 +21,7 @@ jobs:
      - name: Setup NodeJS
        uses: actions/setup-node@v4
        with:
-          node-version: 18
+          node-version: 20
          cache: yarn
          cache-dependency-path: ./web/package.json

--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@ -1,66 +1,156 @@
-# Contributing
+So you're looking to contribute to Dify - that's awesome, we can't wait to see what you do. As a startup with limited headcount and funding, we have grand ambitions to design the most intuitive workflow for building and managing LLM applications. Any help from the community counts, truly.

-Thanks for your interest in [Dify](https://dify.ai) and for wanting to contribute! Before you begin, read the
-[code of conduct](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md) and check out the
-[existing issues](https://github.com/langgenius/langgenius-gateway/issues).
-This document describes how to set up your development environment to build and test [Dify](https://dify.ai).
+We need to be nimble and ship fast given where we are, but we also want to make sure that contributors like you get as smooth an experience at contributing as possible. We've assembled this contribution guide for that purpose, aiming at getting you familiarized with the codebase & how we work with contributors, so you could quickly jump to the fun part. 

-### Install dependencies
+This guide, like Dify itself, is a constant work in progress. We highly appreciate your understanding if at times it lags behind the actual project, and welcome any feedback for us to improve.

-You need to install and configure the following dependencies on your machine to build [Dify](https://dify.ai):
+In terms of licensing, please take a minute to read our short [License and Contributor Agreement](./license). The community also adheres to the [code of conduct](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+
+## Before you jump in
+
+[Find](https://github.com/langgenius/dify/issues?q=is:issue+is:closed) an existing issue, or [open](https://github.com/langgenius/dify/issues/new/choose) a new one. We categorize issues into 2 types:
+
+### Feature requests:
+
+* If you're opening a new feature request, we'd like you to explain what the proposed feature achieves, and include as much context as possible. [@perzeusss](https://github.com/perzeuss) has made a solid [Feature Request Copilot](https://udify.app/chat/MK2kVSnw1gakVwMX) that helps you draft out your needs. Feel free to give it a try.
+
+* If you want to pick one up from the existing issues, simply drop a comment below it saying so.
+
+  
+
+  A team member working in the related direction will be looped in. If all looks good, they will give the go-ahead for you to start coding. We ask that you hold off working on the feature until then, so none of your work goes to waste should we propose changes.
+
+  Depending on whichever area the proposed feature falls under, you might talk to different team members. Here's rundown of the areas each our team members are working on at the moment:
+
+  | Member                                                       | Scope                                                |
+  | ------------------------------------------------------------ | ---------------------------------------------------- |
+  | [@yeuoly](https://github.com/Yeuoly)                         | Architecting Agents                                  |
+  | [@jyong](https://github.com/JohnJyong)                       | RAG pipeline design                                  |
+  | [@GarfieldDai](https://github.com/GarfieldDai)               | Building workflow orchestrations                     |
+  | [@iamjoel](https://github.com/iamjoel) & [@zxhlyh](https://github.com/zxhlyh) | Making our frontend a breeze to use                  |
+  | [@guchenhe](https://github.com/guchenhe) & [@crazywoola](https://github.com/crazywoola) | Developer experience, points of contact for anything |
+  | [@takatost](https://github.com/takatost)                     | Overall product direction and architecture           |
+
+  How we prioritize:
+
+  | Feature Type                                                 | Priority        |
+  | ------------------------------------------------------------ | --------------- |
+  | High-Priority Features as being labeled by a team member     | High Priority   |
+  | Popular feature requests from our [community feedback board](https://feedback.dify.ai/) | Medium Priority |
+  | Non-core features and minor enhancements                     | Low Priority    |
+  | Valuable but not immediate                                   | Future-Feature  |
+
+### Anything else (e.g. bug report, performance optimization, typo correction):
+
+* Start coding right away.
+
+  How we prioritize:
+
+  | Issue Type                                                   | Priority        |
+  | ------------------------------------------------------------ | --------------- |
+  | Bugs in core functions (cannot login, applications not working, security loopholes) | Critical        |
+  | Non-critical bugs, performance boosts                        | Medium Priority |
+  | Minor fixes (typos, confusing but working UI)                | Low Priority    |
+
+
+## Installing
+
+Here are the steps to set up Dify for development:
+
+### 1. Fork this repository
+
+### 2. Clone the repo
+
+ Clone the forked repository from your terminal:
+
+```
+git clone git@github.com:<github_username>/dify.git
+```
+
+### 3. Verify dependencies
+
+Dify requires the following dependencies to build, make sure they're installed on your system:

- [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/) version 8.x.x or [Yarn](https://yarnpkg.com/)
 - [Python](https://www.python.org/) version 3.10.x

-## Local development
+### 4. Installations

-To set up a working development environment, just fork the project git repository and install the backend and frontend dependencies using the proper package manager and create run the docker-compose stack.
+Dify is composed of a backend and a frontend. Navigate to the backend directory by `cd api/`, then follow the [Backend README](api/README.md) to install it. In a separate terminal, navigate to the frontend directory by `cd web/`, then follow the [Frontend README](web/README.md) to install.

-### Fork the repository
+Check the [installation FAQ](https://docs.dify.ai/getting-started/faq/install-faq) for a list of common issues and steps to troubleshoot.

-you need to fork the [repository](https://github.com/langgenius/dify).
+### 5. Visit dify in your browser

-### Clone the repo
+To validate your set up, head over to [http://localhost:3000](http://localhost:3000) (the default, or your self-configured URL and port) in your browser. You should now see Dify up and running. 

-Clone your GitHub forked repository:
+## Developing
+
+If you are adding a model provider, [this guide](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md) is for you.
+
+To help you quickly navigate where your contribution fits, a brief, annotated outline of Dify's backend & frontend is as follows:
+
+### Backend
+
+Dify’s backend is written in Python using [Flask](https://flask.palletsprojects.com/en/3.0.x/). It uses [SQLAlchemy](https://www.sqlalchemy.org/) for ORM and [Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html) for task queueing. Authorization logic goes via Flask-login. 

 ```
-git clone git@github.com:<github_username>/dify.git
+[api/]
+├── constants             // Constant settings used throughout code base.
+├── controllers           // API route definitions and request handling logic.           
+├── core                  // Core application orchestration, model integrations, and tools.
+├── docker                // Docker & containerization related configurations.
+├── events                // Event handling and processing
+├── extensions            // Extensions with 3rd party frameworks/platforms.
+├── fields                // field definitions for serialization/marshalling.
+├── libs                  // Reusable libraries and helpers.
+├── migrations            // Scripts for database migration.
+├── models                // Database models & schema definitions.
+├── services              // Specifies business logic.
+├── storage               // Private key storage.      
+├── tasks                 // Handling of async tasks and background jobs.
+└── tests
 ```

-### Install backend
+### Frontend

-To learn how to install the backend application, please refer to the [Backend README](api/README.md).
+The website is bootstrapped on [Next.js](https://nextjs.org/) boilerplate in Typescript and uses [Tailwind CSS](https://tailwindcss.com/) for styling. [React-i18next](https://react.i18next.com/) is used for internationalization.

-### Install frontend
+```
+[web/]
+├── app                   // layouts, pages, and components
+│   ├── (commonLayout)    // common layout used throughout the app
+│   ├── (shareLayout)     // layouts specifically shared across token-specific sessions 
+│   ├── activate          // activate page
+│   ├── components        // shared by pages and layouts
+│   ├── install           // install page
+│   ├── signin            // signin page
+│   └── styles            // globally shared styles
+├── assets                // Static assets
+├── bin                   // scripts ran at build step
+├── config                // adjustable settings and options 
+├── context               // shared contexts used by different portions of the app
+├── dictionaries          // Language-specific translate files 
+├── docker                // container configurations
+├── hooks                 // Reusable hooks
+├── i18n                  // Internationalization configuration
+├── models                // describes data models & shapes of API responses
+├── public                // meta assets like favicon
+├── service               // specifies shapes of API actions
+├── test                  
+├── types                 // descriptions of function params and return values
+└── utils                 // Shared utility functions
+```

-To learn how to install the frontend application, please refer to the [Frontend README](web/README.md).
+## Submitting your PR

-### Visit dify in your browser
+At last, time to open a pull request (PR) to our repo. For major features, we first merge them into the `deploy/dev` branch for testing, before they go into the `main` branch. If you run into issues like merge conflicts or don't know how to open a pull request, check out [GitHub's pull request tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests). 

-Finally, you can now visit [http://localhost:3000](http://localhost:3000) to view the [Dify](https://dify.ai) in local environment.
+And that's it! Once your PR is merged, you will be featured as a contributor in our [README](https://github.com/langgenius/dify/blob/main/README.md).

+## Getting Help

-## Create a pull request
-
-After making your changes, open a pull request (PR). Once you submit your pull request, others from the Dify team/community will review it with you.
-
-Did you have an issue, like a merge conflict, or don't know how to open a pull request? Check out [GitHub's pull request tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests) on how to resolve merge conflicts and other issues. Once your PR has been merged, you will be proudly listed as a contributor in the [contributor chart](https://github.com/langgenius/langgenius-gateway/graphs/contributors).
-
-## Community channels
-
-Stuck somewhere? Have any questions? Join the [Discord Community Server](https://discord.gg/j3XRWSPBf7). We are here to help!
-
-
-### Provider Integrations
-If you see a model provider not yet supported by Dify that you'd like to use, follow these [steps](api/core/model_runtime/README.md) to submit a PR.
-
-
-### 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.
+If you ever get stuck or got a burning question while contributing, simply shoot your queries our way via the related GitHub issue, or hop onto our [Discord](https://discord.gg/AhzKf7dNgk) for a quick chat. 
--- a/README.md
+++ b/README.md
@ -26,23 +26,25 @@

 ![](./images/demo.png)

-## Use Cloud Services

-[Dify.AI Cloud](https://dify.ai) provides all the capabilities of the open-source version, and includes 200 free requests to OpenAI GPT-3.5.

-## Why Dify
+## Using our Cloud Services

-Dify is model-agnostic and boasts a comprehensive tech stack compared to hardcoded development libraries like LangChain. Unlike OpenAI's Assistants API, Dify allows for full local deployment of services.
+You can try out [Dify.AI Cloud](https://dify.ai) now. It provides all the capabilities of the self-deployed version, and includes 200 free requests to OpenAI GPT-3.5.
+
+## Dify vs. LangChain vs. Assistants API

 | Feature | Dify.AI | Assistants API | LangChain |
 |---------|---------|----------------|-----------|
 | **Programming Approach** | API-oriented | API-oriented | Python Code-oriented |
-| **Ecosystem Strategy** | Open Source | Closed and Commercial | Open Source |
+| **Ecosystem Strategy** | Open Source | Close Source | Open Source |
 | **RAG Engine** | Supported | Supported | Not Supported |
 | **Prompt IDE** | Included | Included | None |
-| **Supported LLMs** | Rich Variety | Only GPT | Rich Variety |
+| **Supported LLMs** | Rich Variety | OpenAI-only | Rich Variety |
 | **Local Deployment** | Supported | Not Supported | Not Applicable |

+
+
 ## Features

 ![](./images/models.png)
@ -59,7 +61,7 @@ Dify is model-agnostic and boasts a comprehensive tech stack compared to hardcod

 ## Before You Start

-**Star us, and you'll get instant notifications for all new releases on GitHub!**
+**Star us on GitHub, and be instantly notified for new releases!**

 ![star-us](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)

@ -103,17 +105,39 @@ If you need to customize the configuration, please refer to the comments in our

 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)

+## Contributing
+
+For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
+
+At the same time, please consider supporting Dify by sharing it on social media and at events and conferences.
+
+### Contributors
+
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
+### Translations
+
+We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README_EN.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/AhzKf7dNgk).

 ## Community & Support

-We welcome you to contribute to Dify to help make Dify better 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.
+* [Canny](https://feedback.dify.ai/). Best for: sharing feedback and checking out our feature roadmap.
+* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
+* [Email Support](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify). Best for: questions you have about using Dify.AI.
+* [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
+* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
+* [Business Contact](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). Best for: business inquiries of licensing Dify.AI for commercial use.

- [Roadmap and Feedback](https://feedback.dify.ai/). Best for: sharing feedback and checking out our feature roadmap.
- [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs and errors you encounter using Dify.AI, see the [Contribution Guide](CONTRIBUTING.md).
- [Email Support](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify). Best for: questions you have about using Dify.AI.
- [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
- [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
- [Business License](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). Best for: business inquiries of licensing Dify.AI for commercial use.
+### Direct Meetings
+
+**Help us make Dify better. Reach out directly to us**.
+
+|                       Point of Contact                       |                           Purpose                            |
+| :----------------------------------------------------------: | :----------------------------------------------------------: |
+| <a href='https://cal.com/guchenhe/15min' target='_blank'><img src='https://i.postimg.cc/fWBqSmjP/Git-Hub-README-Button-3x.png' border='0' alt='Git-Hub-README-Button-3x' height="60" width="214"/></a> | Product design feedback, user experience discussions, feature planning and roadmaps. |
+| <a href='https://cal.com/pinkbanana' target='_blank'><img src='https://i.postimg.cc/LsRTh87D/Git-Hub-README-Button-2x.png' border='0' alt='Git-Hub-README-Button-2x' height="60" width="225"/></a> |        Technical support, issues, or feature requests        |

 ## Security Disclosure

--- a/api/.env.example
+++ b/api/.env.example
@ -15,7 +15,6 @@ CONSOLE_WEB_URL=http://127.0.0.1:3000
 SERVICE_API_URL=http://127.0.0.1:5001

 # Web APP base URL
-APP_API_URL=http://127.0.0.1:5001
 APP_WEB_URL=http://127.0.0.1:3000

 # Files URL
@ -102,10 +101,10 @@ NOTION_CLIENT_ID=you-client-id
 NOTION_INTERNAL_SECRET=you-internal-secret

 # Hosted Model Credentials
-HOSTED_OPENAI_ENABLED=false
 HOSTED_OPENAI_API_KEY=
 HOSTED_OPENAI_API_BASE=
 HOSTED_OPENAI_API_ORGANIZATION=
+HOSTED_OPENAI_TRIAL_ENABLED=false
 HOSTED_OPENAI_QUOTA_LIMIT=200
 HOSTED_OPENAI_PAID_ENABLED=false

@ -114,9 +113,9 @@ HOSTED_AZURE_OPENAI_API_KEY=
 HOSTED_AZURE_OPENAI_API_BASE=
 HOSTED_AZURE_OPENAI_QUOTA_LIMIT=200

-HOSTED_ANTHROPIC_ENABLED=false
 HOSTED_ANTHROPIC_API_BASE=
 HOSTED_ANTHROPIC_API_KEY=
+HOSTED_ANTHROPIC_TRIAL_ENABLED=false
 HOSTED_ANTHROPIC_QUOTA_LIMIT=600000
 HOSTED_ANTHROPIC_PAID_ENABLED=false

--- a/api/Dockerfile
+++ b/api/Dockerfile
@ -13,17 +13,20 @@ RUN pip install --prefix=/pkg -r requirements.txt
 # build stage
 FROM python:3.10-slim AS builder

+
 ENV FLASK_APP app.py
 ENV EDITION SELF_HOSTED
 ENV DEPLOY_ENV PRODUCTION
 ENV CONSOLE_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

+# set timezone
+ENV TZ UTC
+
 WORKDIR /app/api

 RUN apt-get update \
--- a/api/config.py
+++ b/api/config.py
@ -22,7 +22,6 @@ DEFAULTS = {
    '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',
    'FILES_URL': '',
    'STORAGE_TYPE': 'local',
    'STORAGE_LOCAL_PATH': 'storage',
@ -39,13 +38,19 @@ DEFAULTS = {
    'CELERY_BACKEND': 'database',
    'LOG_LEVEL': 'INFO',
    'HOSTED_OPENAI_QUOTA_LIMIT': 200,
-    'HOSTED_OPENAI_ENABLED': 'False',
+    'HOSTED_OPENAI_TRIAL_ENABLED': 'False',
    'HOSTED_OPENAI_PAID_ENABLED': 'False',
+    'HOSTED_OPENAI_PAID_INCREASE_QUOTA': 1,
+    'HOSTED_OPENAI_PAID_MIN_QUANTITY': 1,
+    'HOSTED_OPENAI_PAID_MAX_QUANTITY': 1,
    'HOSTED_AZURE_OPENAI_ENABLED': 'False',
    'HOSTED_AZURE_OPENAI_QUOTA_LIMIT': 200,
    'HOSTED_ANTHROPIC_QUOTA_LIMIT': 600000,
-    'HOSTED_ANTHROPIC_ENABLED': 'False',
+    'HOSTED_ANTHROPIC_TRIAL_ENABLED': 'False',
    'HOSTED_ANTHROPIC_PAID_ENABLED': 'False',
+    'HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA': 1,
+    'HOSTED_ANTHROPIC_PAID_MIN_QUANTITY': 1,
+    'HOSTED_ANTHROPIC_PAID_MAX_QUANTITY': 1,
    'HOSTED_MODERATION_ENABLED': 'False',
    'HOSTED_MODERATION_PROVIDERS': '',
    'CLEAN_DAY_SETTING': 30,
@ -66,7 +71,8 @@ def get_env(key):


 def get_bool_env(key):
-    return get_env(key).lower() == 'true'
+    value = get_env(key)
+    return value.lower() == 'true' if value is not None else False


 def get_cors_allow_origins(env, default):
@ -87,7 +93,7 @@ class Config:
        # ------------------------
        # General Configurations.
        # ------------------------
-        self.CURRENT_VERSION = "0.4.7"
+        self.CURRENT_VERSION = "0.4.9"
        self.COMMIT_SHA = get_env('COMMIT_SHA')
        self.EDITION = "SELF_HOSTED"
        self.DEPLOY_ENV = get_env('DEPLOY_ENV')
@ -96,35 +102,25 @@ class Config:

        # The backend URL prefix of the console API.
        # used to concatenate the login authorization callback or notion integration callback.
-        self.CONSOLE_API_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_API_URL')
+        self.CONSOLE_API_URL = get_env('CONSOLE_API_URL')

        # The front-end URL prefix of the console web.
        # used to concatenate some front-end addresses and for CORS configuration use.
-        self.CONSOLE_WEB_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_WEB_URL')
-
-        # WebApp API backend Url prefix.
-        # used to declare the back-end URL for the front-end API.
-        self.APP_API_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_API_URL')
+        self.CONSOLE_WEB_URL = get_env('CONSOLE_WEB_URL')

        # WebApp Url prefix.
        # used to display WebAPP API Base Url to the front-end.
-        self.APP_WEB_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_WEB_URL')
+        self.APP_WEB_URL = get_env('APP_WEB_URL')

        # Service API Url prefix.
        # used to display Service API Base Url to the front-end.
-        self.SERVICE_API_URL = get_env('API_URL') if get_env('API_URL') else get_env('SERVICE_API_URL')
+        self.SERVICE_API_URL = get_env('SERVICE_API_URL')

        # File preview or download Url prefix.
        # used to display File preview or download Url to the front-end or as Multi-model inputs;
        # Url is signed and has expiration time.
        self.FILES_URL = get_env('FILES_URL') if get_env('FILES_URL') else self.CONSOLE_API_URL

-        # Fallback Url prefix.
-        # Will be deprecated in the future.
-        self.CONSOLE_URL = get_env('CONSOLE_URL')
-        self.API_URL = get_env('API_URL')
-        self.APP_URL = get_env('APP_URL')
-
        # Your App secret key will be used for securely signing the session cookie
        # Make sure you are changing this key for your deployment with a strong key.
        # You can generate a strong key using `openssl rand -base64 42`.
@ -260,23 +256,35 @@ class Config:
        # ------------------------
        # Platform Configurations.
        # ------------------------
-        self.HOSTED_OPENAI_ENABLED = get_bool_env('HOSTED_OPENAI_ENABLED')
        self.HOSTED_OPENAI_API_KEY = get_env('HOSTED_OPENAI_API_KEY')
        self.HOSTED_OPENAI_API_BASE = get_env('HOSTED_OPENAI_API_BASE')
        self.HOSTED_OPENAI_API_ORGANIZATION = get_env('HOSTED_OPENAI_API_ORGANIZATION')
+        self.HOSTED_OPENAI_TRIAL_ENABLED = get_bool_env('HOSTED_OPENAI_TRIAL_ENABLED')
        self.HOSTED_OPENAI_QUOTA_LIMIT = int(get_env('HOSTED_OPENAI_QUOTA_LIMIT'))
        self.HOSTED_OPENAI_PAID_ENABLED = get_bool_env('HOSTED_OPENAI_PAID_ENABLED')
+        self.HOSTED_OPENAI_PAID_STRIPE_PRICE_ID = get_env('HOSTED_OPENAI_PAID_STRIPE_PRICE_ID')
+        self.HOSTED_OPENAI_PAID_INCREASE_QUOTA = int(get_env('HOSTED_OPENAI_PAID_INCREASE_QUOTA'))
+        self.HOSTED_OPENAI_PAID_MIN_QUANTITY = int(get_env('HOSTED_OPENAI_PAID_MIN_QUANTITY'))
+        self.HOSTED_OPENAI_PAID_MAX_QUANTITY = int(get_env('HOSTED_OPENAI_PAID_MAX_QUANTITY'))

        self.HOSTED_AZURE_OPENAI_ENABLED = get_bool_env('HOSTED_AZURE_OPENAI_ENABLED')
        self.HOSTED_AZURE_OPENAI_API_KEY = get_env('HOSTED_AZURE_OPENAI_API_KEY')
        self.HOSTED_AZURE_OPENAI_API_BASE = get_env('HOSTED_AZURE_OPENAI_API_BASE')
        self.HOSTED_AZURE_OPENAI_QUOTA_LIMIT = int(get_env('HOSTED_AZURE_OPENAI_QUOTA_LIMIT'))

-        self.HOSTED_ANTHROPIC_ENABLED = get_bool_env('HOSTED_ANTHROPIC_ENABLED')
        self.HOSTED_ANTHROPIC_API_BASE = get_env('HOSTED_ANTHROPIC_API_BASE')
        self.HOSTED_ANTHROPIC_API_KEY = get_env('HOSTED_ANTHROPIC_API_KEY')
+        self.HOSTED_ANTHROPIC_TRIAL_ENABLED = get_bool_env('HOSTED_ANTHROPIC_TRIAL_ENABLED')
        self.HOSTED_ANTHROPIC_QUOTA_LIMIT = int(get_env('HOSTED_ANTHROPIC_QUOTA_LIMIT'))
        self.HOSTED_ANTHROPIC_PAID_ENABLED = get_bool_env('HOSTED_ANTHROPIC_PAID_ENABLED')
+        self.HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID = get_env('HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID')
+        self.HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA = int(get_env('HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA'))
+        self.HOSTED_ANTHROPIC_PAID_MIN_QUANTITY = int(get_env('HOSTED_ANTHROPIC_PAID_MIN_QUANTITY'))
+        self.HOSTED_ANTHROPIC_PAID_MAX_QUANTITY = int(get_env('HOSTED_ANTHROPIC_PAID_MAX_QUANTITY'))
+
+        self.HOSTED_MINIMAX_ENABLED = get_bool_env('HOSTED_MINIMAX_ENABLED')
+        self.HOSTED_SPARK_ENABLED = get_bool_env('HOSTED_SPARK_ENABLED')
+        self.HOSTED_ZHIPUAI_ENABLED = get_bool_env('HOSTED_ZHIPUAI_ENABLED')

        self.HOSTED_MODERATION_ENABLED = get_bool_env('HOSTED_MODERATION_ENABLED')
        self.HOSTED_MODERATION_PROVIDERS = get_env('HOSTED_MODERATION_PROVIDERS')
--- a/api/controllers/console/app/completion.py
+++ b/api/controllers/console/app/completion.py
@ -163,29 +163,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/controllers/console/app/message.py
+++ b/api/controllers/console/app/message.py
@ -241,27 +241,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/controllers/console/datasets/datasets.py
+++ b/api/controllers/console/datasets/datasets.py
@ -19,7 +19,7 @@ from flask import current_app, request
 from flask_login import current_user
 from flask_restful import Resource, marshal, marshal_with, reqparse
 from libs.login import login_required
-from models.dataset import Document, DocumentSegment
+from models.dataset import Dataset, Document, DocumentSegment
 from models.model import ApiToken, UploadFile
 from services.dataset_service import DatasetService, DocumentService
 from werkzeug.exceptions import Forbidden, NotFound
@ -97,7 +97,8 @@ class DatasetListApi(Resource):
                            help='type is required. Name must be between 1 to 40 characters.',
                            type=_validate_name)
        parser.add_argument('indexing_technique', type=str, location='json',
-                            choices=('high_quality', 'economy'),
+                            choices=Dataset.INDEXING_TECHNIQUE_LIST,
+                            nullable=True,
                            help='Invalid indexing technique.')
        args = parser.parse_args()

@ -177,8 +178,9 @@ class DatasetApi(Resource):
                            location='json', store_missing=False,
                            type=_validate_description_length)
        parser.add_argument('indexing_technique', type=str, location='json',
-                            choices=('high_quality', 'economy'),
-                            help='Invalid indexing technique.')
+                    choices=Dataset.INDEXING_TECHNIQUE_LIST,
+                    nullable=True,
+                    help='Invalid indexing technique.')
        parser.add_argument('permission', type=str, location='json', choices=(
            'only_me', 'all_team_members'), help='Invalid permission.')
        parser.add_argument('retrieval_model', type=dict, location='json', help='Invalid retrieval model.')
@ -256,7 +258,9 @@ class DatasetIndexingEstimateApi(Resource):
        parser = reqparse.RequestParser()
        parser.add_argument('info_list', type=dict, required=True, nullable=True, location='json')
        parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
-        parser.add_argument('indexing_technique', type=str, required=True, nullable=True, location='json')
+        parser.add_argument('indexing_technique', type=str, required=True, 
+                            choices=Dataset.INDEXING_TECHNIQUE_LIST,
+                            nullable=True, location='json')
        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
        parser.add_argument('dataset_id', type=str, required=False, nullable=False, location='json')
        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
--- a/api/controllers/console/explore/completion.py
+++ b/api/controllers/console/explore/completion.py
@ -158,29 +158,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/controllers/console/explore/message.py
+++ b/api/controllers/console/explore/message.py
@ -117,26 +117,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/controllers/console/universal_chat/chat.py
+++ b/api/controllers/console/universal_chat/chat.py
@ -109,29 +109,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/controllers/service_api/init.py
+++ b/api/controllers/service_api/init.py
@ -6,5 +6,6 @@ bp = Blueprint('service_api', __name__, url_prefix='/v1')
 api = ExternalApi(bp)


+from . import index
 from .app import app, audio, completion, conversation, file, message
 from .dataset import dataset, document, segment
--- a/api/controllers/service_api/app/completion.py
+++ b/api/controllers/service_api/app/completion.py
@ -79,7 +79,12 @@ class CompletionStopApi(AppApiResource):
        if app_model.mode != 'completion':
            raise AppUnavailableError()

-        end_user_id = request.get_json().get('user')
+        parser = reqparse.RequestParser()
+        parser.add_argument('user', required=True, nullable=False, type=str, location='json')
+
+        args = parser.parse_args()
+
+        end_user_id = args.get('user')

        ApplicationQueueManager.set_stop_flag(task_id, InvokeFrom.SERVICE_API, end_user_id)

@ -157,29 +162,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/controllers/service_api/app/conversation.py
+++ b/api/controllers/service_api/app/conversation.py
@ -86,5 +86,4 @@ 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')
--- a/api/controllers/service_api/dataset/dataset.py
+++ b/api/controllers/service_api/dataset/dataset.py
@ -1,3 +1,4 @@
+from models.dataset import Dataset
 import services.dataset_service
 from controllers.service_api import api
 from controllers.service_api.dataset.error import DatasetNameDuplicateError
@ -68,7 +69,7 @@ class DatasetApi(DatasetApiResource):
                            help='type is required. Name must be between 1 to 40 characters.',
                            type=_validate_name)
        parser.add_argument('indexing_technique', type=str, location='json',
-                            choices=('high_quality', 'economy'),
+                            choices=Dataset.INDEXING_TECHNIQUE_LIST,
                            help='Invalid indexing technique.')
        args = parser.parse_args()

--- a/api/controllers/service_api/index.py
+++ b/api/controllers/service_api/index.py
@ -0,0 +1,16 @@
+from flask import current_app
+from flask_restful import Resource
+
+from controllers.service_api import api
+
+
+class IndexApi(Resource):
+    def get(self):
+        return {
+            "welcome": "Dify OpenAPI",
+            "api_version": "v1",
+            "server_version": current_app.config['CURRENT_VERSION']
+        }
+
+
+api.add_resource(IndexApi, '/')
--- a/api/controllers/service_api/wraps.py
+++ b/api/controllers/service_api/wraps.py
@ -75,7 +75,7 @@ def validate_dataset_token(view=None):
            tenant_account_join = db.session.query(Tenant, TenantAccountJoin) \
                .filter(Tenant.id == api_token.tenant_id) \
                .filter(TenantAccountJoin.tenant_id == Tenant.id) \
-                .filter(TenantAccountJoin.role == 'owner') \
+                .filter(TenantAccountJoin.role.in_(['owner', 'admin'])) \
                .one_or_none()
            if tenant_account_join:
                tenant, ta = tenant_account_join
--- a/api/controllers/web/completion.py
+++ b/api/controllers/web/completion.py
@ -146,29 +146,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/controllers/web/message.py
+++ b/api/controllers/web/message.py
@ -151,26 +151,8 @@ def compact_response(response: Union[dict, Generator]) -> Response:
        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 InvokeError as e:
-                yield "data: " + json.dumps(api.handle_error(CompletionRequestError(e.description)).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"
+            for chunk in response:
+                yield chunk

        return Response(stream_with_context(generate()), status=200,
                        mimetype='text/event-stream')
--- a/api/core/app_runner/generate_task_pipeline.py
+++ b/api/core/app_runner/generate_task_pipeline.py
@ -5,16 +5,18 @@ from typing import Generator, Optional, Union, cast

 from core.app_runner.moderation_handler import ModerationRule, OutputModerationHandler
 from core.application_queue_manager import ApplicationQueueManager, PublishFrom
-from core.entities.application_entities import ApplicationGenerateEntity
+from core.entities.application_entities import ApplicationGenerateEntity, InvokeFrom
 from core.entities.queue_entities import (AnnotationReplyEvent, QueueAgentThoughtEvent, QueueErrorEvent,
                                          QueueMessageEndEvent, QueueMessageEvent, QueueMessageReplaceEvent,
                                          QueuePingEvent, QueueRetrieverResourcesEvent, QueueStopEvent)
+from core.errors.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (AssistantPromptMessage, ImagePromptMessageContent,
                                                          PromptMessage, PromptMessageContentType, PromptMessageRole,
                                                          TextPromptMessageContent)
 from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
+from core.model_runtime.utils.encoders import jsonable_encoder
 from core.prompt.prompt_template import PromptTemplateParser
 from events.message_event import message_was_created
 from extensions.ext_database import db
@ -135,6 +137,8 @@ class GenerateTaskPipeline:
                        completion_tokens
                    )

+                self._task_state.metadata['usage'] = jsonable_encoder(self._task_state.llm_result.usage)
+
                # response moderation
                if self._output_moderation_handler:
                    self._output_moderation_handler.stop_thread()
@ -145,12 +149,13 @@ class GenerateTaskPipeline:
                    )

                # Save message
-                self._save_message(event.llm_result)
+                self._save_message(self._task_state.llm_result)

                response = {
                    'event': 'message',
                    'task_id': self._application_generate_entity.task_id,
                    'id': self._message.id,
+                    'message_id': self._message.id,
                    'mode': self._conversation.mode,
                    'answer': event.llm_result.message.content,
                    'metadata': {},
@ -161,7 +166,7 @@ class GenerateTaskPipeline:
                    response['conversation_id'] = self._conversation.id

                if self._task_state.metadata:
-                    response['metadata'] = self._task_state.metadata
+                    response['metadata'] = self._get_response_metadata()

                return response
            else:
@ -176,7 +181,9 @@ class GenerateTaskPipeline:
            event = message.event

            if isinstance(event, QueueErrorEvent):
-                raise self._handle_error(event)
+                data = self._error_to_stream_response_data(self._handle_error(event))
+                yield self._yield_response(data)
+                break
            elif isinstance(event, (QueueStopEvent, QueueMessageEndEvent)):
                if isinstance(event, QueueMessageEndEvent):
                    self._task_state.llm_result = event.llm_result
@ -213,6 +220,8 @@ class GenerateTaskPipeline:
                        completion_tokens
                    )

+                self._task_state.metadata['usage'] = jsonable_encoder(self._task_state.llm_result.usage)
+
                # response moderation
                if self._output_moderation_handler:
                    self._output_moderation_handler.stop_thread()
@ -244,13 +253,14 @@ class GenerateTaskPipeline:
                    'event': 'message_end',
                    'task_id': self._application_generate_entity.task_id,
                    'id': self._message.id,
+                    'message_id': self._message.id,
                }

                if self._conversation.mode == 'chat':
                    response['conversation_id'] = self._conversation.id

                if self._task_state.metadata:
-                    response['metadata'] = self._task_state.metadata
+                    response['metadata'] = self._get_response_metadata()

                yield self._yield_response(response)
            elif isinstance(event, QueueRetrieverResourcesEvent):
@ -410,6 +420,86 @@ class GenerateTaskPipeline:
        else:
            return Exception(e.description if getattr(e, 'description', None) is not None else str(e))

+    def _error_to_stream_response_data(self, e: Exception) -> dict:
+        """
+        Error to stream response.
+        :param e: exception
+        :return:
+        """
+        if isinstance(e, ValueError):
+            data = {
+                'code': 'invalid_param',
+                'message': str(e),
+                'status': 400
+            }
+        elif isinstance(e, ProviderTokenNotInitError):
+            data = {
+                'code': 'provider_not_initialize',
+                'message': e.description,
+                'status': 400
+            }
+        elif isinstance(e, QuotaExceededError):
+            data = {
+                'code': 'provider_quota_exceeded',
+                'message': "Your quota for Dify Hosted Model Provider has been exhausted. "
+                           "Please go to Settings -> Model Provider to complete your own provider credentials.",
+                'status': 400
+            }
+        elif isinstance(e, ModelCurrentlyNotSupportError):
+            data = {
+                'code': 'model_currently_not_support',
+                'message': e.description,
+                'status': 400
+            }
+        elif isinstance(e, InvokeError):
+            data = {
+                'code': 'completion_request_error',
+                'message': e.description,
+                'status': 400
+            }
+        else:
+            logging.error(e)
+            data = {
+                'code': 'internal_server_error',
+                'message': 'Internal Server Error, please contact support.',
+                'status': 500
+            }
+
+        return {
+            'event': 'error',
+            'task_id': self._application_generate_entity.task_id,
+            'message_id': self._message.id,
+            **data
+        }
+
+    def _get_response_metadata(self) -> dict:
+        """
+        Get response metadata by invoke from.
+        :return:
+        """
+        metadata = {}
+
+        # show_retrieve_source
+        if 'retriever_resources' in self._task_state.metadata:
+            if self._application_generate_entity.invoke_from in [InvokeFrom.DEBUGGER, InvokeFrom.SERVICE_API]:
+                metadata['retriever_resources'] = self._task_state.metadata['retriever_resources']
+            else:
+                metadata['retriever_resources'] = []
+                for resource in self._task_state.metadata['retriever_resources']:
+                    metadata['retriever_resources'].append({
+                        'segment_id': resource['segment_id'],
+                        'position': resource['position'],
+                        'document_name': resource['document_name'],
+                        'score': resource['score'],
+                        'content': resource['content'],
+                    })
+
+        # show usage
+        if self._application_generate_entity.invoke_from in [InvokeFrom.DEBUGGER, InvokeFrom.SERVICE_API]:
+            metadata['usage'] = self._task_state.metadata['usage']
+
+        return metadata
+
    def _yield_response(self, response: dict) -> str:
        """
        Yield response.
--- a/api/core/embedding/cached_embedding.py
+++ b/api/core/embedding/cached_embedding.py
@ -1,10 +1,16 @@
+import base64
+import json
 import logging
-from typing import List, Optional
+from typing import List, Optional, cast

 import numpy as np
 from core.model_manager import ModelInstance
+from core.model_runtime.entities.model_entities import ModelPropertyKey
+from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
 from extensions.ext_database import db
 from langchain.embeddings.base import Embeddings
+
+from extensions.ext_redis import redis_client
 from libs import helper
 from models.dataset import Embedding
 from sqlalchemy.exc import IntegrityError
@ -18,47 +24,33 @@ class CacheEmbedding(Embeddings):
        self._user = user

    def embed_documents(self, texts: List[str]) -> List[List[float]]:
-        """Embed search docs."""
-        # use doc embedding cache or store if not exists
-        text_embeddings = [None for _ in range(len(texts))]
-        embedding_queue_indices = []
-        for i, text in enumerate(texts):
-            hash = helper.generate_text_hash(text)
-            embedding = db.session.query(Embedding).filter_by(model_name=self._model_instance.model, hash=hash).first()
-            if embedding:
-                text_embeddings[i] = embedding.get_embedding()
-            else:
-                embedding_queue_indices.append(i)
+        """Embed search docs in batches of 10."""
+        text_embeddings = []
+        try:
+            model_type_instance = cast(TextEmbeddingModel, self._model_instance.model_type_instance)
+            model_schema = model_type_instance.get_model_schema(self._model_instance.model, self._model_instance.credentials)
+            max_chunks = model_schema.model_properties[ModelPropertyKey.MAX_CHUNKS] \
+                if model_schema and ModelPropertyKey.MAX_CHUNKS in model_schema.model_properties else 1
+            for i in range(0, len(texts), max_chunks):
+                batch_texts = texts[i:i + max_chunks]

-        if embedding_queue_indices:
-            try:
                embedding_result = self._model_instance.invoke_text_embedding(
-                    texts=[texts[i] for i in embedding_queue_indices],
+                    texts=batch_texts,
                    user=self._user
                )

-                embedding_results = embedding_result.embeddings
-            except Exception as ex:
-                logger.error('Failed to embed documents: ', ex)
-                raise ex
+                for vector in embedding_result.embeddings:
+                    try:
+                        normalized_embedding = (vector / np.linalg.norm(vector)).tolist()
+                        text_embeddings.append(normalized_embedding)
+                    except IntegrityError:
+                        db.session.rollback()
+                    except Exception as e:
+                        logging.exception('Failed to add embedding to redis')

-            for i, indice in enumerate(embedding_queue_indices):
-                hash = helper.generate_text_hash(texts[indice])
-
-                try:
-                    embedding = Embedding(model_name=self._model_instance.model, hash=hash)
-                    vector = embedding_results[i]
-                    normalized_embedding = (vector / np.linalg.norm(vector)).tolist()
-                    text_embeddings[indice] = normalized_embedding
-                    embedding.set_embedding(normalized_embedding)
-                    db.session.add(embedding)
-                    db.session.commit()
-                except IntegrityError:
-                    db.session.rollback()
-                    continue
-                except:
-                    logging.exception('Failed to add embedding to db')
-                    continue
+        except Exception as ex:
+            logger.error('Failed to embed documents: ', ex)
+            raise ex

        return text_embeddings

@ -66,9 +58,12 @@ class CacheEmbedding(Embeddings):
        """Embed query text."""
        # use doc embedding cache or store if not exists
        hash = helper.generate_text_hash(text)
-        embedding = db.session.query(Embedding).filter_by(model_name=self._model_instance.model, hash=hash).first()
+        embedding_cache_key = f'{self._model_instance.provider}_{self._model_instance.model}_{hash}'
+        embedding = redis_client.get(embedding_cache_key)
        if embedding:
-            return embedding.get_embedding()
+            redis_client.expire(embedding_cache_key, 600)
+            return list(np.frombuffer(base64.b64decode(embedding), dtype="float"))
+

        try:
            embedding_result = self._model_instance.invoke_text_embedding(
@ -82,13 +77,18 @@ class CacheEmbedding(Embeddings):
            raise ex

        try:
-            embedding = Embedding(model_name=self._model_instance.model, hash=hash)
-            embedding.set_embedding(embedding_results)
-            db.session.add(embedding)
-            db.session.commit()
+            # encode embedding to base64
+            embedding_vector = np.array(embedding_results)
+            vector_bytes = embedding_vector.tobytes()
+            # Transform to Base64
+            encoded_vector = base64.b64encode(vector_bytes)
+            # Transform to string
+            encoded_str = encoded_vector.decode("utf-8")
+            redis_client.setex(embedding_cache_key, 600, encoded_str)
+
        except IntegrityError:
            db.session.rollback()
        except:
-            logging.exception('Failed to add embedding to db')
+            logging.exception('Failed to add embedding to redis')

        return embedding_results
--- a/api/core/features/dataset_retrieval.py
+++ b/api/core/features/dataset_retrieval.py
@ -166,8 +166,7 @@ class DatasetRetrievalFeature:
                dataset_ids=[dataset.id for dataset in available_datasets],
                tenant_id=tenant_id,
                top_k=retrieve_config.top_k or 2,
-                score_threshold=(retrieve_config.score_threshold or 0.5)
-                if retrieve_config.reranking_model.get('score_threshold_enabled', False) else None,
+                score_threshold=retrieve_config.score_threshold,
                hit_callbacks=[hit_callback],
                return_resource=return_resource,
                retriever_from=invoke_from.to_source(),
--- a/api/core/hosting_configuration.py
+++ b/api/core/hosting_configuration.py
@ -1,9 +1,8 @@
-import os
 from typing import Optional

 from core.entities.provider_entities import QuotaUnit, RestrictModel
 from core.model_runtime.entities.model_entities import ModelType
-from flask import Flask
+from flask import Flask, Config
 from models.provider import ProviderQuotaType
 from pydantic import BaseModel

@ -48,46 +47,47 @@ class HostingConfiguration:
    moderation_config: HostedModerationConfig = None

    def init_app(self, app: Flask) -> None:
-        if app.config.get('EDITION') != 'CLOUD':
+        config = app.config
+
+        if config.get('EDITION') != 'CLOUD':
            return

-        self.provider_map["azure_openai"] = self.init_azure_openai()
-        self.provider_map["openai"] = self.init_openai()
-        self.provider_map["anthropic"] = self.init_anthropic()
-        self.provider_map["minimax"] = self.init_minimax()
-        self.provider_map["spark"] = self.init_spark()
-        self.provider_map["zhipuai"] = self.init_zhipuai()
+        self.provider_map["azure_openai"] = self.init_azure_openai(config)
+        self.provider_map["openai"] = self.init_openai(config)
+        self.provider_map["anthropic"] = self.init_anthropic(config)
+        self.provider_map["minimax"] = self.init_minimax(config)
+        self.provider_map["spark"] = self.init_spark(config)
+        self.provider_map["zhipuai"] = self.init_zhipuai(config)

-        self.moderation_config = self.init_moderation_config()
+        self.moderation_config = self.init_moderation_config(config)

-    def init_azure_openai(self) -> HostingProvider:
+    def init_azure_openai(self, app_config: Config) -> HostingProvider:
        quota_unit = QuotaUnit.TIMES
-        if os.environ.get("HOSTED_AZURE_OPENAI_ENABLED") and os.environ.get("HOSTED_AZURE_OPENAI_ENABLED").lower() == 'true':
+        if app_config.get("HOSTED_AZURE_OPENAI_ENABLED"):
            credentials = {
-                "openai_api_key": os.environ.get("HOSTED_AZURE_OPENAI_API_KEY"),
-                "openai_api_base": os.environ.get("HOSTED_AZURE_OPENAI_API_BASE"),
+                "openai_api_key": app_config.get("HOSTED_AZURE_OPENAI_API_KEY"),
+                "openai_api_base": app_config.get("HOSTED_AZURE_OPENAI_API_BASE"),
                "base_model_name": "gpt-35-turbo"
            }

            quotas = []
-            hosted_quota_limit = int(os.environ.get("HOSTED_AZURE_OPENAI_QUOTA_LIMIT", "1000"))
-            if hosted_quota_limit != -1 or hosted_quota_limit > 0:
-                trial_quota = TrialHostingQuota(
-                    quota_limit=hosted_quota_limit,
-                    restrict_models=[
-                        RestrictModel(model="gpt-4", base_model_name="gpt-4", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-4-32k", base_model_name="gpt-4-32k", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-4-1106-preview", base_model_name="gpt-4-1106-preview", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-4-vision-preview", base_model_name="gpt-4-vision-preview", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-35-turbo", base_model_name="gpt-35-turbo", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-35-turbo-1106", base_model_name="gpt-35-turbo-1106", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-35-turbo-instruct", base_model_name="gpt-35-turbo-instruct", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-35-turbo-16k", base_model_name="gpt-35-turbo-16k", model_type=ModelType.LLM),
-                        RestrictModel(model="text-davinci-003", base_model_name="text-davinci-003", model_type=ModelType.LLM),
-                        RestrictModel(model="text-embedding-ada-002", base_model_name="text-embedding-ada-002", model_type=ModelType.TEXT_EMBEDDING),
-                    ]
-                )
-                quotas.append(trial_quota)
+            hosted_quota_limit = int(app_config.get("HOSTED_AZURE_OPENAI_QUOTA_LIMIT", "1000"))
+            trial_quota = TrialHostingQuota(
+                quota_limit=hosted_quota_limit,
+                restrict_models=[
+                    RestrictModel(model="gpt-4", base_model_name="gpt-4", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-4-32k", base_model_name="gpt-4-32k", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-4-1106-preview", base_model_name="gpt-4-1106-preview", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-4-vision-preview", base_model_name="gpt-4-vision-preview", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-35-turbo", base_model_name="gpt-35-turbo", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-35-turbo-1106", base_model_name="gpt-35-turbo-1106", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-35-turbo-instruct", base_model_name="gpt-35-turbo-instruct", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-35-turbo-16k", base_model_name="gpt-35-turbo-16k", model_type=ModelType.LLM),
+                    RestrictModel(model="text-davinci-003", base_model_name="text-davinci-003", model_type=ModelType.LLM),
+                    RestrictModel(model="text-embedding-ada-002", base_model_name="text-embedding-ada-002", model_type=ModelType.TEXT_EMBEDDING),
+                ]
+            )
+            quotas.append(trial_quota)

            return HostingProvider(
                enabled=True,
@ -101,43 +101,44 @@ class HostingConfiguration:
            quota_unit=quota_unit,
        )

-    def init_openai(self) -> HostingProvider:
+    def init_openai(self, app_config: Config) -> HostingProvider:
        quota_unit = QuotaUnit.TIMES
-        if os.environ.get("HOSTED_OPENAI_ENABLED") and os.environ.get("HOSTED_OPENAI_ENABLED").lower() == 'true':
+        quotas = []
+
+        if app_config.get("HOSTED_OPENAI_TRIAL_ENABLED"):
+            hosted_quota_limit = int(app_config.get("HOSTED_OPENAI_QUOTA_LIMIT", "200"))
+            trial_quota = TrialHostingQuota(
+                quota_limit=hosted_quota_limit,
+                restrict_models=[
+                    RestrictModel(model="gpt-3.5-turbo", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-3.5-turbo-1106", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-3.5-turbo-instruct", model_type=ModelType.LLM),
+                    RestrictModel(model="gpt-3.5-turbo-16k", model_type=ModelType.LLM),
+                    RestrictModel(model="text-davinci-003", model_type=ModelType.LLM),
+                    RestrictModel(model="whisper-1", model_type=ModelType.SPEECH2TEXT),
+                ]
+            )
+            quotas.append(trial_quota)
+
+        if app_config.get("HOSTED_OPENAI_PAID_ENABLED"):
+            paid_quota = PaidHostingQuota(
+                stripe_price_id=app_config.get("HOSTED_OPENAI_PAID_STRIPE_PRICE_ID"),
+                increase_quota=int(app_config.get("HOSTED_OPENAI_PAID_INCREASE_QUOTA", "1")),
+                min_quantity=int(app_config.get("HOSTED_OPENAI_PAID_MIN_QUANTITY", "1")),
+                max_quantity=int(app_config.get("HOSTED_OPENAI_PAID_MAX_QUANTITY", "1"))
+            )
+            quotas.append(paid_quota)
+
+        if len(quotas) > 0:
            credentials = {
-                "openai_api_key": os.environ.get("HOSTED_OPENAI_API_KEY"),
+                "openai_api_key": app_config.get("HOSTED_OPENAI_API_KEY"),
            }

-            if os.environ.get("HOSTED_OPENAI_API_BASE"):
-                credentials["openai_api_base"] = os.environ.get("HOSTED_OPENAI_API_BASE")
+            if app_config.get("HOSTED_OPENAI_API_BASE"):
+                credentials["openai_api_base"] = app_config.get("HOSTED_OPENAI_API_BASE")

-            if os.environ.get("HOSTED_OPENAI_API_ORGANIZATION"):
-                credentials["openai_organization"] = os.environ.get("HOSTED_OPENAI_API_ORGANIZATION")
-
-            quotas = []
-            hosted_quota_limit = int(os.environ.get("HOSTED_OPENAI_QUOTA_LIMIT", "200"))
-            if hosted_quota_limit != -1 or hosted_quota_limit > 0:
-                trial_quota = TrialHostingQuota(
-                    quota_limit=hosted_quota_limit,
-                    restrict_models=[
-                        RestrictModel(model="gpt-3.5-turbo", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-3.5-turbo-1106", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-3.5-turbo-instruct", model_type=ModelType.LLM),
-                        RestrictModel(model="gpt-3.5-turbo-16k", model_type=ModelType.LLM),
-                        RestrictModel(model="text-davinci-003", model_type=ModelType.LLM),
-                    ]
-                )
-                quotas.append(trial_quota)
-
-            if os.environ.get("HOSTED_OPENAI_PAID_ENABLED") and os.environ.get(
-                    "HOSTED_OPENAI_PAID_ENABLED").lower() == 'true':
-                paid_quota = PaidHostingQuota(
-                    stripe_price_id=os.environ.get("HOSTED_OPENAI_PAID_STRIPE_PRICE_ID"),
-                    increase_quota=int(os.environ.get("HOSTED_OPENAI_PAID_INCREASE_QUOTA", "1")),
-                    min_quantity=int(os.environ.get("HOSTED_OPENAI_PAID_MIN_QUANTITY", "1")),
-                    max_quantity=int(os.environ.get("HOSTED_OPENAI_PAID_MAX_QUANTITY", "1"))
-                )
-                quotas.append(paid_quota)
+            if app_config.get("HOSTED_OPENAI_API_ORGANIZATION"):
+                credentials["openai_organization"] = app_config.get("HOSTED_OPENAI_API_ORGANIZATION")

            return HostingProvider(
                enabled=True,
@ -151,33 +152,33 @@ class HostingConfiguration:
            quota_unit=quota_unit,
        )

-    def init_anthropic(self) -> HostingProvider:
+    def init_anthropic(self, app_config: Config) -> HostingProvider:
        quota_unit = QuotaUnit.TOKENS
-        if os.environ.get("HOSTED_ANTHROPIC_ENABLED") and os.environ.get("HOSTED_ANTHROPIC_ENABLED").lower() == 'true':
+        quotas = []
+
+        if app_config.get("HOSTED_ANTHROPIC_TRIAL_ENABLED"):
+            hosted_quota_limit = int(app_config.get("HOSTED_ANTHROPIC_QUOTA_LIMIT", "0"))
+            trial_quota = TrialHostingQuota(
+                quota_limit=hosted_quota_limit
+            )
+            quotas.append(trial_quota)
+
+        if app_config.get("HOSTED_ANTHROPIC_PAID_ENABLED"):
+            paid_quota = PaidHostingQuota(
+                stripe_price_id=app_config.get("HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID"),
+                increase_quota=int(app_config.get("HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA", "1000000")),
+                min_quantity=int(app_config.get("HOSTED_ANTHROPIC_PAID_MIN_QUANTITY", "20")),
+                max_quantity=int(app_config.get("HOSTED_ANTHROPIC_PAID_MAX_QUANTITY", "100"))
+            )
+            quotas.append(paid_quota)
+
+        if len(quotas) > 0:
            credentials = {
-                "anthropic_api_key": os.environ.get("HOSTED_ANTHROPIC_API_KEY"),
+                "anthropic_api_key": app_config.get("HOSTED_ANTHROPIC_API_KEY"),
            }

-            if os.environ.get("HOSTED_ANTHROPIC_API_BASE"):
-                credentials["anthropic_api_url"] = os.environ.get("HOSTED_ANTHROPIC_API_BASE")
-
-            quotas = []
-            hosted_quota_limit = int(os.environ.get("HOSTED_ANTHROPIC_QUOTA_LIMIT", "0"))
-            if hosted_quota_limit != -1 or hosted_quota_limit > 0:
-                trial_quota = TrialHostingQuota(
-                    quota_limit=hosted_quota_limit
-                )
-                quotas.append(trial_quota)
-
-            if os.environ.get("HOSTED_ANTHROPIC_PAID_ENABLED") and os.environ.get(
-                    "HOSTED_ANTHROPIC_PAID_ENABLED").lower() == 'true':
-                paid_quota = PaidHostingQuota(
-                    stripe_price_id=os.environ.get("HOSTED_ANTHROPIC_PAID_STRIPE_PRICE_ID"),
-                    increase_quota=int(os.environ.get("HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA", "1000000")),
-                    min_quantity=int(os.environ.get("HOSTED_ANTHROPIC_PAID_MIN_QUANTITY", "20")),
-                    max_quantity=int(os.environ.get("HOSTED_ANTHROPIC_PAID_MAX_QUANTITY", "100"))
-                )
-                quotas.append(paid_quota)
+            if app_config.get("HOSTED_ANTHROPIC_API_BASE"):
+                credentials["anthropic_api_url"] = app_config.get("HOSTED_ANTHROPIC_API_BASE")

            return HostingProvider(
                enabled=True,
@ -191,9 +192,9 @@ class HostingConfiguration:
            quota_unit=quota_unit,
        )

-    def init_minimax(self) -> HostingProvider:
+    def init_minimax(self, app_config: Config) -> HostingProvider:
        quota_unit = QuotaUnit.TOKENS
-        if os.environ.get("HOSTED_MINIMAX_ENABLED") and os.environ.get("HOSTED_MINIMAX_ENABLED").lower() == 'true':
+        if app_config.get("HOSTED_MINIMAX_ENABLED"):
            quotas = [FreeHostingQuota()]

            return HostingProvider(
@ -208,9 +209,9 @@ class HostingConfiguration:
            quota_unit=quota_unit,
        )

-    def init_spark(self) -> HostingProvider:
+    def init_spark(self, app_config: Config) -> HostingProvider:
        quota_unit = QuotaUnit.TOKENS
-        if os.environ.get("HOSTED_SPARK_ENABLED") and os.environ.get("HOSTED_SPARK_ENABLED").lower() == 'true':
+        if app_config.get("HOSTED_SPARK_ENABLED"):
            quotas = [FreeHostingQuota()]

            return HostingProvider(
@ -225,9 +226,9 @@ class HostingConfiguration:
            quota_unit=quota_unit,
        )

-    def init_zhipuai(self) -> HostingProvider:
+    def init_zhipuai(self, app_config: Config) -> HostingProvider:
        quota_unit = QuotaUnit.TOKENS
-        if os.environ.get("HOSTED_ZHIPUAI_ENABLED") and os.environ.get("HOSTED_ZHIPUAI_ENABLED").lower() == 'true':
+        if app_config.get("HOSTED_ZHIPUAI_ENABLED"):
            quotas = [FreeHostingQuota()]

            return HostingProvider(
@ -242,12 +243,12 @@ class HostingConfiguration:
            quota_unit=quota_unit,
        )

-    def init_moderation_config(self) -> HostedModerationConfig:
-        if os.environ.get("HOSTED_MODERATION_ENABLED") and os.environ.get("HOSTED_MODERATION_ENABLED").lower() == 'true' \
-                and os.environ.get("HOSTED_MODERATION_PROVIDERS"):
+    def init_moderation_config(self, app_config: Config) -> HostedModerationConfig:
+        if app_config.get("HOSTED_MODERATION_ENABLED") \
+                and app_config.get("HOSTED_MODERATION_PROVIDERS"):
            return HostedModerationConfig(
                enabled=True,
-                providers=os.environ.get("HOSTED_MODERATION_PROVIDERS").split(',')
+                providers=app_config.get("HOSTED_MODERATION_PROVIDERS").split(',')
            )

        return HostedModerationConfig(
--- a/api/core/indexing_runner.py
+++ b/api/core/indexing_runner.py
@ -274,6 +274,8 @@ class IndexingRunner:
        tokens = 0
        preview_texts = []
        total_segments = 0
+        total_price = 0
+        currency = 'USD'
        for file_detail in file_details:

            processing_rule = DatasetProcessRule(
@ -344,11 +346,13 @@ class IndexingRunner:
                price_type=PriceType.INPUT,
                tokens=tokens
            )
+            total_price = '{:f}'.format(embedding_price_info.total_amount)
+            currency = embedding_price_info.currency
        return {
            "total_segments": total_segments,
            "tokens": tokens,
-            "total_price": '{:f}'.format(embedding_price_info.total_amount) if embedding_model_instance else 0,
-            "currency": embedding_price_info.currency if embedding_model_instance else 'USD',
+            "total_price": total_price,
+            "currency": currency,
            "preview": preview_texts
        }

@ -388,6 +392,8 @@ class IndexingRunner:
        tokens = 0
        preview_texts = []
        total_segments = 0
+        total_price = 0
+        currency = 'USD'
        for notion_info in notion_info_list:
            workspace_id = notion_info['workspace_id']
            data_source_binding = DataSourceBinding.query.filter(
@ -470,20 +476,22 @@ class IndexingRunner:
                    "qa_preview": document_qa_list,
                    "preview": preview_texts
                }
-
-        embedding_model_type_instance = embedding_model_instance.model_type_instance
-        embedding_model_type_instance = cast(TextEmbeddingModel, embedding_model_type_instance)
-        embedding_price_info = embedding_model_type_instance.get_price(
-            model=embedding_model_instance.model,
-            credentials=embedding_model_instance.credentials,
-            price_type=PriceType.INPUT,
-            tokens=tokens
-        )
+        if embedding_model_instance:
+            embedding_model_type_instance = embedding_model_instance.model_type_instance
+            embedding_model_type_instance = cast(TextEmbeddingModel, embedding_model_type_instance)
+            embedding_price_info = embedding_model_type_instance.get_price(
+                model=embedding_model_instance.model,
+                credentials=embedding_model_instance.credentials,
+                price_type=PriceType.INPUT,
+                tokens=tokens
+            )
+            total_price = '{:f}'.format(embedding_price_info.total_amount)
+            currency = embedding_price_info.currency
        return {
            "total_segments": total_segments,
            "tokens": tokens,
-            "total_price": '{:f}'.format(embedding_price_info.total_amount) if embedding_model_instance else 0,
-            "currency": embedding_price_info.currency if embedding_model_instance else 'USD',
+            "total_price": total_price,
+            "currency": currency,
            "preview": preview_texts
        }

--- a/api/core/model_runtime/model_providers/azure_openai/llm/llm.py
+++ b/api/core/model_runtime/model_providers/azure_openai/llm/llm.py
@ -1,3 +1,4 @@
+import copy
 import logging
 from typing import Generator, List, Optional, Union, cast

@ -625,9 +626,10 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
    def _get_ai_model_entity(base_model_name: str, model: str) -> AzureBaseModel:
        for ai_model_entity in LLM_BASE_MODELS:
            if ai_model_entity.base_model_name == base_model_name:
-                ai_model_entity.entity.model = model
-                ai_model_entity.entity.label.en_US = model
-                ai_model_entity.entity.label.zh_Hans = model
-                return ai_model_entity
+                ai_model_entity_copy = copy.deepcopy(ai_model_entity)
+                ai_model_entity_copy.entity.model = model
+                ai_model_entity_copy.entity.label.en_US = model
+                ai_model_entity_copy.entity.label.zh_Hans = model
+                return ai_model_entity_copy

        return None
--- a/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py
@ -1,4 +1,5 @@
 import base64
+import copy
 import time
 from typing import Optional, Tuple

@ -186,9 +187,10 @@ class AzureOpenAITextEmbeddingModel(_CommonAzureOpenAI, TextEmbeddingModel):
    def _get_ai_model_entity(base_model_name: str, model: str) -> AzureBaseModel:
        for ai_model_entity in EMBEDDING_BASE_MODELS:
            if ai_model_entity.base_model_name == base_model_name:
-                ai_model_entity.entity.model = model
-                ai_model_entity.entity.label.en_US = model
-                ai_model_entity.entity.label.zh_Hans = model
-                return ai_model_entity
+                ai_model_entity_copy = copy.deepcopy(ai_model_entity)
+                ai_model_entity_copy.entity.model = model
+                ai_model_entity_copy.entity.label.en_US = model
+                ai_model_entity_copy.entity.label.zh_Hans = model
+                return ai_model_entity_copy

        return None
--- a/api/core/model_runtime/model_providers/jina/text_embedding/jina-embeddings-v2-base-de.yaml
+++ b/api/core/model_runtime/model_providers/jina/text_embedding/jina-embeddings-v2-base-de.yaml
@ -0,0 +1,9 @@
+model: jina-embeddings-v2-base-de
+model_type: text-embedding
+model_properties:
+  context_size: 8192
+  max_chunks: 2048
+pricing:
+  input: '0.001'
+  unit: '0.001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/jina/text_embedding/jina-embeddings-v2-base-zh.yaml
+++ b/api/core/model_runtime/model_providers/jina/text_embedding/jina-embeddings-v2-base-zh.yaml
@ -0,0 +1,9 @@
+model: jina-embeddings-v2-base-zh
+model_type: text-embedding
+model_properties:
+  context_size: 8192
+  max_chunks: 2048
+pricing:
+  input: '0.001'
+  unit: '0.001'
+  currency: USD
--- a/api/core/model_runtime/model_providers/jina/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/jina/text_embedding/text_embedding.py
@ -17,7 +17,7 @@ class JinaTextEmbeddingModel(TextEmbeddingModel):
    Model class for Jina text embedding model.
    """
    api_base: str = 'https://api.jina.ai/v1/embeddings'
-    models: list[str] = ['jina-embeddings-v2-base-en', 'jina-embeddings-v2-small-en']
+    models: list[str] = ['jina-embeddings-v2-base-en', 'jina-embeddings-v2-small-en', 'jina-embeddings-v2-base-zh', 'jina-embeddings-v2-base-de']

    def _invoke(self, model: str, credentials: dict,
                texts: list[str], user: Optional[str] = None) \
--- a/api/core/model_runtime/model_providers/minimax/llm/abab5.5-chat.yaml
+++ b/api/core/model_runtime/model_providers/minimax/llm/abab5.5-chat.yaml
@ -10,8 +10,14 @@ model_properties:
 parameter_rules:
  - name: temperature
    use_template: temperature
+    min: 0.01
+    max: 1
+    default: 0.9
  - name: top_p
    use_template: top_p
+    min: 0.01
+    max: 1
+    default: 0.95
  - name: max_tokens
    use_template: max_tokens
    required: true
--- a/api/core/model_runtime/model_providers/minimax/llm/abab5.5s-chat.yaml
+++ b/api/core/model_runtime/model_providers/minimax/llm/abab5.5s-chat.yaml
@ -0,0 +1,35 @@
+model: abab5.5s-chat
+label:
+  en_US: Abab5.5s-Chat
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    min: 0.01
+    max: 1
+    default: 0.9
+  - name: top_p
+    use_template: top_p
+    min: 0.01
+    max: 1
+    default: 0.95
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 3072
+    min: 1
+    max: 8192
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+pricing:
+  input: '0.00'
+  output: '0.005'
+  unit: '0.001'
+  currency: RMB
--- a/api/core/model_runtime/model_providers/minimax/llm/chat_completion_pro.py
+++ b/api/core/model_runtime/model_providers/minimax/llm/chat_completion_pro.py
@ -22,7 +22,7 @@ class MinimaxChatCompletionPro(object):
        """
            generate chat completion
        """
-        if model != 'abab5.5-chat':
+        if model not in ['abab5.5-chat', 'abab5.5s-chat']:
            raise BadRequestError(f'Invalid model: {model}')
        
        if not api_key or not group_id:
--- a/api/core/model_runtime/model_providers/minimax/llm/llm.py
+++ b/api/core/model_runtime/model_providers/minimax/llm/llm.py
@ -18,6 +18,7 @@ from core.model_runtime.model_providers.minimax.llm.types import MinimaxMessage

 class MinimaxLargeLanguageModel(LargeLanguageModel):
    model_apis = {
+        'abab5.5s-chat': MinimaxChatCompletionPro,
        'abab5.5-chat': MinimaxChatCompletionPro,
        'abab5-chat': MinimaxChatCompletion
    }
--- a/api/core/model_runtime/utils/encoders.py
+++ b/api/core/model_runtime/utils/encoders.py
@ -151,6 +151,8 @@ def jsonable_encoder(
        return str(obj)
    if isinstance(obj, (str, int, float, type(None))):
        return obj
+    if isinstance(obj, Decimal):
+        return format(obj, 'f')
    if isinstance(obj, dict):
        encoded_dict = {}
        allowed_keys = set(obj.keys())
--- a/api/core/provider_manager.py
+++ b/api/core/provider_manager.py
@ -597,18 +597,28 @@ class ProviderManager:
        quota_configurations = []
        for provider_quota in provider_hosting_configuration.quotas:
            if provider_quota.quota_type not in quota_type_to_provider_records_dict:
-                continue
+                if provider_quota.quota_type == ProviderQuotaType.FREE:
+                    quota_configuration = QuotaConfiguration(
+                        quota_type=provider_quota.quota_type,
+                        quota_unit=provider_hosting_configuration.quota_unit,
+                        quota_used=0,
+                        quota_limit=0,
+                        is_valid=False,
+                        restrict_models=provider_quota.restrict_models
+                    )
+                else:
+                    continue
+            else:
+                provider_record = quota_type_to_provider_records_dict[provider_quota.quota_type]

-            provider_record = quota_type_to_provider_records_dict[provider_quota.quota_type]
-
-            quota_configuration = QuotaConfiguration(
-                quota_type=provider_quota.quota_type,
-                quota_unit=provider_hosting_configuration.quota_unit,
-                quota_used=provider_record.quota_used,
-                quota_limit=provider_record.quota_limit,
-                is_valid=provider_record.quota_limit > provider_record.quota_used or provider_record.quota_limit == -1,
-                restrict_models=provider_quota.restrict_models
-            )
+                quota_configuration = QuotaConfiguration(
+                    quota_type=provider_quota.quota_type,
+                    quota_unit=provider_hosting_configuration.quota_unit,
+                    quota_used=provider_record.quota_used,
+                    quota_limit=provider_record.quota_limit,
+                    is_valid=provider_record.quota_limit > provider_record.quota_used or provider_record.quota_limit == -1,
+                    restrict_models=provider_quota.restrict_models
+                )

            quota_configurations.append(quota_configuration)

@ -670,6 +680,7 @@ class ProviderManager:
                    current_using_credentials = cached_provider_credentials
            else:
                current_using_credentials = {}
+                quota_configurations = []

        return SystemConfiguration(
            enabled=True,
--- a/api/core/vector_store/vector/qdrant.py
+++ b/api/core/vector_store/vector/qdrant.py
@ -1450,7 +1450,7 @@ class Qdrant(VectorStore):
                wal_config=wal_config,
                quantization_config=quantization_config,
                init_from=init_from,
-                timeout=timeout,  # type: ignore[arg-type]
+                timeout=int(timeout),  # type: ignore[arg-type]
            )
            is_new_collection = True
        if force_recreate:
--- a/api/events/event_handlers/deduct_quota_when_messaeg_created.py
+++ b/api/events/event_handlers/deduct_quota_when_messaeg_created.py
@ -23,12 +23,16 @@ def handle(sender, **kwargs):
    for quota_configuration in system_configuration.quota_configurations:
        if quota_configuration.quota_type == system_configuration.current_quota_type:
            quota_unit = quota_configuration.quota_unit
+
+            if quota_configuration.quota_limit == -1:
+                return
+
            break

    used_quota = None
    if quota_unit:
-        if quota_unit == QuotaUnit.TOKENS.value:
-            used_quota = message.message_tokens + message.prompt_tokens
+        if quota_unit == QuotaUnit.TOKENS:
+            used_quota = message.message_tokens + message.answer_tokens
        else:
            used_quota = 1

--- a/api/libs/external_api.py
+++ b/api/libs/external_api.py
@ -31,6 +31,10 @@ class ExternalApi(Api):
                'message': getattr(e, 'description', http_status_message(status_code)),
                'status': status_code
            }
+
+            if default_data['message'] and default_data['message'] == 'Failed to decode JSON object: Expecting value: line 1 column 1 (char 0)':
+                default_data['message'] = 'Invalid JSON payload received or JSON payload is empty.'
+
            headers = e.get_response().headers
        elif isinstance(e, ValueError):
            status_code = 400
--- a/api/models/dataset.py
+++ b/api/models/dataset.py
@ -17,7 +17,7 @@ class Dataset(db.Model):
        db.Index('retrieval_model_idx', "retrieval_model", postgresql_using='gin')
    )

-    INDEXING_TECHNIQUE_LIST = ['high_quality', 'economy']
+    INDEXING_TECHNIQUE_LIST = ['high_quality', 'economy', None]

    id = db.Column(UUID, server_default=db.text('uuid_generate_v4()'))
    tenant_id = db.Column(UUID, nullable=False)
--- a/api/services/completion_service.py
+++ b/api/services/completion_service.py
@ -27,10 +27,15 @@ class CompletionService:
        auto_generate_name = args['auto_generate_name'] \
            if 'auto_generate_name' in args else True

-        if app_model.mode != 'completion' and not query:
-            raise ValueError('query is required')
+        if app_model.mode != 'completion':
+            if not query:
+                raise ValueError('query is required')

-        query = query.replace('\x00', '')
+        if query:
+            if not isinstance(query, str):
+                raise ValueError('query must be a string')
+
+            query = query.replace('\x00', '')

        conversation_id = args['conversation_id'] if 'conversation_id' in args else None

@ -230,6 +235,10 @@ class CompletionService:

            value = user_inputs[variable]

+            if value:
+                if not isinstance(value, str):
+                    raise ValueError(f"{variable} in input form must be a string")
+
            if input_type == "select":
                options = input_config["options"] if "options" in input_config else []
                if value not in options:
@ -243,4 +252,3 @@ class CompletionService:
            filtered_inputs[variable] = value.replace('\x00', '') if value else None

        return filtered_inputs
-
--- a/docker/docker-compose.yaml
+++ b/docker/docker-compose.yaml
@ -2,7 +2,7 @@ version: '3.1'
 services:
  # API service
  api:
-    image: langgenius/dify-api:0.4.7
+    image: langgenius/dify-api:0.4.9
    restart: always
    environment:
      # Startup mode, 'api' starts the API server.
@ -23,10 +23,6 @@ services:
      # different from console domain.
      # example: http://api.dify.ai
      SERVICE_API_URL: ''
-      # The URL prefix for Web APP api server, refers to the Web App base URL of WEB service if web app domain is different from
-      # console or api domain.
-      # example: http://udify.app
-      APP_API_URL: ''
      # The URL prefix for Web APP frontend, refers to the Web App base URL of WEB service if web app domain is different from
      # console or api domain.
      # example: http://udify.app
@ -131,7 +127,7 @@ services:
  # worker service
  # The Celery worker for processing the queue.
  worker:
-    image: langgenius/dify-api:0.4.7
+    image: langgenius/dify-api:0.4.9
    restart: always
    environment:
      # Startup mode, 'worker' starts the Celery worker for processing the queue.
@ -202,7 +198,7 @@ services:

  # Frontend web application.
  web:
-    image: langgenius/dify-web:0.4.7
+    image: langgenius/dify-web:0.4.9
    restart: always
    environment:
      EDITION: SELF_HOSTED
@ -287,7 +283,7 @@ services:
  # (if uncommented, you need to comment out the weaviate service above,
  # and set VECTOR_STORE to qdrant in the api & worker service.)
  # qdrant:
-  #   image: langgenius/qdrant:1.7.3
+  #   image: langgenius/qdrant:v1.7.3
  #   restart: always
  #   volumes:
  #     - ./volumes/qdrant:/qdrant/storage
--- a/web/Dockerfile
+++ b/web/Dockerfile
@ -1,16 +1,19 @@
 # base image
-FROM node:18.17.0-alpine AS base
+FROM node:20.11.0-alpine AS base
+LABEL maintainer="takatost@gmail.com"
+
+RUN apk add --no-cache tzdata
+

 # install packages
 FROM base as packages
-LABEL maintainer="takatost@gmail.com"

 WORKDIR /app/web

 COPY package.json .
 COPY yarn.lock .

-RUN yarn --only=prod
+RUN yarn install --frozen-lockfile


 # build resources
@ -32,6 +35,10 @@ ENV CONSOLE_API_URL http://127.0.0.1:5001
 ENV APP_API_URL http://127.0.0.1:5001
 ENV PORT 3000

+# set timezone
+ENV TZ UTC
+RUN ln -s /usr/share/zoneinfo/${TZ} /etc/localtime \
+    && echo ${TZ} > /etc/timezone

 WORKDIR /app/web
 COPY --from=builder /app/web/public ./public
@ -40,10 +47,9 @@ COPY --from=builder /app/web/.next/static ./.next/static


 COPY docker/entrypoint.sh ./entrypoint.sh
-RUN chmod +x ./entrypoint.sh

 ARG COMMIT_SHA
 ENV COMMIT_SHA ${COMMIT_SHA}

 EXPOSE 3000
-ENTRYPOINT ["/bin/sh", "./entrypoint.sh"]
+ENTRYPOINT ["/bin/sh", "./entrypoint.sh"]
--- a/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx
+++ b/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx
@ -55,8 +55,8 @@ const LikedItem = ({
  isMobile,
 }: ILikedItemProps) => {
  return (
-    <Link className={classNames(s.itemWrapper, 'px-0 sm:px-3 justify-center sm:justify-start')} href={`/app/${detail?.id}/overview`}>
-      <div className={classNames(s.iconWrapper, 'mr-0 sm:mr-2')}>
+    <Link className={classNames(s.itemWrapper, 'px-0', isMobile && 'justify-center')} href={`/app/${detail?.id}/overview`}>
+      <div className={classNames(s.iconWrapper, 'mr-0')}>
        <AppIcon size='tiny' icon={detail?.icon} background={detail?.icon_background}/>
        {type === 'app' && (
          <div className={s.statusPoint}>
@ -64,7 +64,7 @@ const LikedItem = ({
          </div>
        )}
      </div>
-      {!isMobile && <div className={s.appInfo}>{detail?.name || '--'}</div>}
+      {!isMobile && <div className={classNames(s.appInfo, 'ml-2')}>{detail?.name || '--'}</div>}
    </Link>
  )
 }
@ -197,14 +197,14 @@ const DatasetDetailLayout: FC<IAppDetailLayoutProps> = (props) => {
    return <Loading />

  return (
-    <div className='flex overflow-hidden'>
+    <div className='grow flex overflow-hidden'>
      {!hideSideBar && <AppSideBar
        title={datasetRes?.name || '--'}
        icon={datasetRes?.icon || 'https://static.dify.ai/images/dataset-default-icon.png'}
        icon_background={datasetRes?.icon_background || '#F5F5F5'}
        desc={datasetRes?.description || '--'}
        navigation={navigation}
-        extraInfo={<ExtraInfo isMobile={isMobile} relatedApps={relatedApps} />}
+        extraInfo={mode => <ExtraInfo isMobile={mode === 'collapse'} relatedApps={relatedApps} />}
        iconType={datasetRes?.data_source_type === DataSourceType.NOTION ? 'notion' : 'dataset'}
      />}
      <DatasetDetailContext.Provider value={{
--- a/web/app/components/app-sidebar/index.tsx
+++ b/web/app/components/app-sidebar/index.tsx
@ -20,7 +20,7 @@ export type IAppDetailNavProps = {
    icon: NavIcon
    selectedIcon: NavIcon
  }>
-  extraInfo?: React.ReactNode
+  extraInfo?: (modeState: string) => React.ReactNode
 }

 const AppDetailNav = ({ title, desc, icon, icon_background, navigation, extraInfo, iconType = 'app' }: IAppDetailNavProps) => {
@ -72,7 +72,7 @@ const AppDetailNav = ({ title, desc, icon, icon_background, navigation, extraInf
            <NavLink key={index} mode={modeState} iconMap={{ selected: item.selectedIcon, normal: item.icon }} name={item.name} href={item.href} />
          )
        })}
-        {extraInfo ?? null}
+        {extraInfo && extraInfo(modeState)}
      </nav>
      {
        !isMobile && (
--- a/web/app/components/billing/pricing/plan-item.tsx
+++ b/web/app/components/billing/pricing/plan-item.tsx
@ -107,7 +107,6 @@ const PlanItem: FC<Props> = ({
            <div>{t('billing.plansCommon.supportItems.emailSupport')}</div>
            <div className='mt-3.5 flex items-center space-x-1'>
              <div>+ {t('billing.plansCommon.supportItems.logoChange')}</div>
-              <div>{comingSoon}</div>
            </div>
            <div className='mt-3.5 flex items-center space-x-1'>
              <div className='flex items-center'>
@ -135,7 +134,6 @@ const PlanItem: FC<Props> = ({
            <div>{t('billing.plansCommon.supportItems.priorityEmail')}</div>
            <div className='mt-3.5 flex items-center space-x-1'>
              <div>+ {t('billing.plansCommon.supportItems.logoChange')}</div>
-              <div>{comingSoon}</div>
            </div>
            <div className='mt-3.5 flex items-center space-x-1'>
              <div>+ {t('billing.plansCommon.supportItems.SSOAuthentication')}</div>
--- a/web/app/components/header/account-setting/model-provider-page/index.tsx
+++ b/web/app/components/header/account-setting/model-provider-page/index.tsx
@ -38,7 +38,13 @@ const ModelProviderPage = () => {
    const notConfigedProviders: ModelProvider[] = []

    providers.forEach((provider) => {
-      if (provider.custom_configuration.status === CustomConfigurationStatusEnum.active || provider.system_configuration.enabled === true)
+      if (
+        provider.custom_configuration.status === CustomConfigurationStatusEnum.active
+        || (
+          provider.system_configuration.enabled === true
+          && provider.system_configuration.quota_configurations.find(item => item.quota_type === provider.system_configuration.current_quota_type)
+        )
+      )
        configedProviders.push(provider)
      else
        notConfigedProviders.push(provider)
--- a/web/app/components/header/account-setting/model-provider-page/provider-added-card/index.tsx
+++ b/web/app/components/header/account-setting/model-provider-page/provider-added-card/index.tsx
@ -9,6 +9,8 @@ import type {
 import { ConfigurateMethodEnum } from '../declarations'
 import {
  DEFAULT_BACKGROUND_COLOR,
+  MODEL_PROVIDER_QUOTA_GET_FREE,
+  MODEL_PROVIDER_QUOTA_GET_PAID,
  modelTypeFormat,
 } from '../utils'
 import ProviderIcon from '../provider-icon'
@ -41,7 +43,7 @@ const ProviderAddedCard: FC<ProviderAddedCardProps> = ({
  const configurateMethods = provider.configurate_methods.filter(method => method !== ConfigurateMethodEnum.fetchFromRemote)
  const systemConfig = provider.system_configuration
  const hasModelList = fetched && !!modelList.length
-  const showQuota = systemConfig.enabled && ['minimax', 'spark', 'zhipuai', 'anthropic', 'openai'].includes(provider.provider) && !IS_CE_EDITION
+  const showQuota = systemConfig.enabled && [...MODEL_PROVIDER_QUOTA_GET_FREE, ...MODEL_PROVIDER_QUOTA_GET_PAID].includes(provider.provider) && !IS_CE_EDITION

  const getModelList = async (providerName: string) => {
    if (loading)
--- a/web/app/components/header/account-setting/model-provider-page/provider-added-card/quota-panel.tsx
+++ b/web/app/components/header/account-setting/model-provider-page/provider-added-card/quota-panel.tsx
@ -11,6 +11,10 @@ import {
  useFreeQuota,
  useUpdateModelProviders,
 } from '../hooks'
+import {
+  MODEL_PROVIDER_QUOTA_GET_FREE,
+  MODEL_PROVIDER_QUOTA_GET_PAID,
+} from '../utils'
 import PriorityUseTip from './priority-use-tip'
 import { InfoCircle } from '@/app/components/base/icons/src/vender/line/general'
 import Button from '@/app/components/base/button'
@ -34,7 +38,7 @@ const QuotaPanel: FC<QuotaPanelProps> = ({
  const priorityUseType = provider.preferred_provider_type
  const systemConfig = provider.system_configuration
  const currentQuota = systemConfig.enabled && systemConfig.quota_configurations.find(item => item.quota_type === systemConfig.current_quota_type)
-  const openaiOrAnthropic = ['openai', 'anthropic'].includes(provider.provider)
+  const openaiOrAnthropic = MODEL_PROVIDER_QUOTA_GET_PAID.includes(provider.provider)

  return (
    <div className='group relative shrink-0 min-w-[112px] px-3 py-2 rounded-lg bg-white/[0.3] border-[0.5px] border-black/5'>
@ -72,7 +76,7 @@ const QuotaPanel: FC<QuotaPanelProps> = ({
        )
      }
      {
-        !currentQuota && ['minimax', 'spark', 'zhipuai'].includes(provider.provider) && (
+        !currentQuota && MODEL_PROVIDER_QUOTA_GET_FREE.includes(provider.provider) && (
          <Button
            className='h-6 bg-white text-xs font-medium rounded-md'
            onClick={() => handleFreeQuota(provider.provider)}
--- a/web/app/components/header/account-setting/model-provider-page/provider-card/index.tsx
+++ b/web/app/components/header/account-setting/model-provider-page/provider-card/index.tsx
@ -7,6 +7,7 @@ import type {
 import { ConfigurateMethodEnum } from '../declarations'
 import {
  DEFAULT_BACKGROUND_COLOR,
+  MODEL_PROVIDER_QUOTA_GET_FREE,
  modelTypeFormat,
 } from '../utils'
 import {
@ -55,7 +56,7 @@ const ProviderCard: FC<ProviderCardProps> = ({
  }
  const handleFreeQuota = useFreeQuota(handleFreeQuotaSuccess)
  const configurateMethods = provider.configurate_methods.filter(method => method !== ConfigurateMethodEnum.fetchFromRemote)
-  const canGetFreeQuota = ['mininmax', 'spark', 'zhipuai'].includes(provider.provider) && !IS_CE_EDITION
+  const canGetFreeQuota = MODEL_PROVIDER_QUOTA_GET_FREE.includes(provider.provider) && !IS_CE_EDITION && provider.system_configuration.enabled

  return (
    <div
--- a/web/app/components/header/account-setting/model-provider-page/utils.ts
+++ b/web/app/components/header/account-setting/model-provider-page/utils.ts
@ -23,6 +23,9 @@ export const languageMaps = {
  'zh-Hans': 'zh_Hans'
 }

+export const MODEL_PROVIDER_QUOTA_GET_FREE = ['minimax', 'spark', 'zhipuai']
+export const MODEL_PROVIDER_QUOTA_GET_PAID = ['anthropic', 'openai']
+
 export const DEFAULT_BACKGROUND_COLOR = '#F3F4F6'

 export const isNullOrUndefined = (value: any) => {
--- a/web/docker/entrypoint.sh
+++ b/web/docker/entrypoint.sh
@ -4,18 +4,8 @@ set -e

 export NEXT_PUBLIC_DEPLOY_ENV=${DEPLOY_ENV}
 export NEXT_PUBLIC_EDITION=${EDITION}
-
-if [[ -z "$CONSOLE_URL" ]]; then
-  export NEXT_PUBLIC_API_PREFIX=${CONSOLE_API_URL}/console/api
-else
-  export NEXT_PUBLIC_API_PREFIX=${CONSOLE_URL}/console/api
-fi
-
-if [[ -z "$APP_URL" ]]; then
-  export NEXT_PUBLIC_PUBLIC_API_PREFIX=${APP_API_URL}/api
-else
-  export NEXT_PUBLIC_PUBLIC_API_PREFIX=${APP_URL}/api
-fi
+export NEXT_PUBLIC_API_PREFIX=${CONSOLE_API_URL}/console/api
+export NEXT_PUBLIC_PUBLIC_API_PREFIX=${APP_API_URL}/api

 export NEXT_PUBLIC_SENTRY_DSN=${SENTRY_DSN}
 export NEXT_PUBLIC_SITE_ABOUT=${SITE_ABOUT}
--- a/web/package.json
+++ b/web/package.json
@ -1,6 +1,6 @@
 {
  "name": "dify-web",
-  "version": "0.4.7",
+  "version": "0.4.9",
  "private": true,
  "scripts": {
    "dev": "next dev",
@ -74,6 +74,7 @@
    "remark-math": "^5.1.1",
    "scheduler": "^0.23.0",
    "server-only": "^0.0.1",
+    "sharp": "^0.33.2",
    "sortablejs": "^1.15.0",
    "swr": "^2.1.0",
    "use-context-selector": "^1.4.1"
--- a/web/yarn.lock
+++ b/web/yarn.lock
@ -112,6 +112,13 @@
  resolved "https://registry.npmjs.org/@braintree/sanitize-url/-/sanitize-url-6.0.4.tgz"
  integrity sha512-s3jaWicZd0pkP0jf5ysyHUI/RE7MHos6qlToFcGWXVp+ykHOy77OUMrfbgJ9it2C5bow7OIQwYYaHjk9XlBQ2A==

+"@emnapi/runtime@^0.45.0":
+  version "0.45.0"
+  resolved "https://registry.yarnpkg.com/@emnapi/runtime/-/runtime-0.45.0.tgz#e754de04c683263f34fd0c7f32adfe718bbe4ddd"
+  integrity sha512-Txumi3td7J4A/xTTwlssKieHKTGl3j4A1tglBx72auZ49YK7ePY6XZricgIg9mnZT4xPfA+UPCUdnhRuEFDL+w==
+  dependencies:
+    tslib "^2.4.0"
+
 "@emoji-mart/data@^1.1.2":
  version "1.1.2"
  resolved "https://registry.npmjs.org/@emoji-mart/data/-/data-1.1.2.tgz"
@ -235,6 +242,119 @@
  resolved "https://registry.npmjs.org/@humanwhocodes/object-schema/-/object-schema-1.2.1.tgz"
  integrity sha512-ZnQMnLV4e7hDlUvw8H+U8ASL02SS2Gn6+9Ac3wGGLIe7+je2AeAOxPY+izIPJDfFDb7eDjev0Us8MO1iFRN8hA==

+"@img/sharp-darwin-arm64@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-darwin-arm64/-/sharp-darwin-arm64-0.33.2.tgz#0a52a82c2169112794dac2c71bfba9e90f7c5bd1"
+  integrity sha512-itHBs1rPmsmGF9p4qRe++CzCgd+kFYktnsoR1sbIAfsRMrJZau0Tt1AH9KVnufc2/tU02Gf6Ibujx+15qRE03w==
+  optionalDependencies:
+    "@img/sharp-libvips-darwin-arm64" "1.0.1"
+
+"@img/sharp-darwin-x64@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-darwin-x64/-/sharp-darwin-x64-0.33.2.tgz#982e26bb9d38a81f75915c4032539aed621d1c21"
+  integrity sha512-/rK/69Rrp9x5kaWBjVN07KixZanRr+W1OiyKdXcbjQD6KbW+obaTeBBtLUAtbBsnlTTmWthw99xqoOS7SsySDg==
+  optionalDependencies:
+    "@img/sharp-libvips-darwin-x64" "1.0.1"
+
+"@img/sharp-libvips-darwin-arm64@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-darwin-arm64/-/sharp-libvips-darwin-arm64-1.0.1.tgz#81e83ffc2c497b3100e2f253766490f8fad479cd"
+  integrity sha512-kQyrSNd6lmBV7O0BUiyu/OEw9yeNGFbQhbxswS1i6rMDwBBSX+e+rPzu3S+MwAiGU3HdLze3PanQ4Xkfemgzcw==
+
+"@img/sharp-libvips-darwin-x64@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-darwin-x64/-/sharp-libvips-darwin-x64-1.0.1.tgz#fc1fcd9d78a178819eefe2c1a1662067a83ab1d6"
+  integrity sha512-eVU/JYLPVjhhrd8Tk6gosl5pVlvsqiFlt50wotCvdkFGf+mDNBJxMh+bvav+Wt3EBnNZWq8Sp2I7XfSjm8siog==
+
+"@img/sharp-libvips-linux-arm64@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-linux-arm64/-/sharp-libvips-linux-arm64-1.0.1.tgz#26eb8c556a9b0db95f343fc444abc3effb67ebcf"
+  integrity sha512-bnGG+MJjdX70mAQcSLxgeJco11G+MxTz+ebxlz8Y3dxyeb3Nkl7LgLI0mXupoO+u1wRNx/iRj5yHtzA4sde1yA==
+
+"@img/sharp-libvips-linux-arm@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-linux-arm/-/sharp-libvips-linux-arm-1.0.1.tgz#2a377b959ff7dd6528deee486c25461296a4fa8b"
+  integrity sha512-FtdMvR4R99FTsD53IA3LxYGghQ82t3yt0ZQ93WMZ2xV3dqrb0E8zq4VHaTOuLEAuA83oDawHV3fd+BsAPadHIQ==
+
+"@img/sharp-libvips-linux-s390x@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-linux-s390x/-/sharp-libvips-linux-s390x-1.0.1.tgz#af28ac9ba929204467ecdf843330d791e9421e10"
+  integrity sha512-3+rzfAR1YpMOeA2zZNp+aYEzGNWK4zF3+sdMxuCS3ey9HhDbJ66w6hDSHDMoap32DueFwhhs3vwooAB2MaK4XQ==
+
+"@img/sharp-libvips-linux-x64@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-linux-x64/-/sharp-libvips-linux-x64-1.0.1.tgz#4273d182aa51912e655e1214ea47983d7c1f7f8d"
+  integrity sha512-3NR1mxFsaSgMMzz1bAnnKbSAI+lHXVTqAHgc1bgzjHuXjo4hlscpUxc0vFSAPKI3yuzdzcZOkq7nDPrP2F8Jgw==
+
+"@img/sharp-libvips-linuxmusl-arm64@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-linuxmusl-arm64/-/sharp-libvips-linuxmusl-arm64-1.0.1.tgz#d150c92151cea2e8d120ad168b9c358d09c77ce8"
+  integrity sha512-5aBRcjHDG/T6jwC3Edl3lP8nl9U2Yo8+oTl5drd1dh9Z1EBfzUKAJFUDTDisDjUwc7N4AjnPGfCA3jl3hY8uDg==
+
+"@img/sharp-libvips-linuxmusl-x64@1.0.1":
+  version "1.0.1"
+  resolved "https://registry.yarnpkg.com/@img/sharp-libvips-linuxmusl-x64/-/sharp-libvips-linuxmusl-x64-1.0.1.tgz#e297c1a4252c670d93b0f9e51fca40a7a5b6acfd"
+  integrity sha512-dcT7inI9DBFK6ovfeWRe3hG30h51cBAP5JXlZfx6pzc/Mnf9HFCQDLtYf4MCBjxaaTfjCCjkBxcy3XzOAo5txw==
+
+"@img/sharp-linux-arm64@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-linux-arm64/-/sharp-linux-arm64-0.33.2.tgz#af3409f801a9bee1d11d0c7e971dcd6180f80022"
+  integrity sha512-pz0NNo882vVfqJ0yNInuG9YH71smP4gRSdeL09ukC2YLE6ZyZePAlWKEHgAzJGTiOh8Qkaov6mMIMlEhmLdKew==
+  optionalDependencies:
+    "@img/sharp-libvips-linux-arm64" "1.0.1"
+
+"@img/sharp-linux-arm@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-linux-arm/-/sharp-linux-arm-0.33.2.tgz#181f7466e6ac074042a38bfb679eb82505e17083"
+  integrity sha512-Fndk/4Zq3vAc4G/qyfXASbS3HBZbKrlnKZLEJzPLrXoJuipFNNwTes71+Ki1hwYW5lch26niRYoZFAtZVf3EGA==
+  optionalDependencies:
+    "@img/sharp-libvips-linux-arm" "1.0.1"
+
+"@img/sharp-linux-s390x@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-linux-s390x/-/sharp-linux-s390x-0.33.2.tgz#9c171f49211f96fba84410b3e237b301286fa00f"
+  integrity sha512-MBoInDXDppMfhSzbMmOQtGfloVAflS2rP1qPcUIiITMi36Mm5YR7r0ASND99razjQUpHTzjrU1flO76hKvP5RA==
+  optionalDependencies:
+    "@img/sharp-libvips-linux-s390x" "1.0.1"
+
+"@img/sharp-linux-x64@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-linux-x64/-/sharp-linux-x64-0.33.2.tgz#b956dfc092adc58c2bf0fae2077e6f01a8b2d5d7"
+  integrity sha512-xUT82H5IbXewKkeF5aiooajoO1tQV4PnKfS/OZtb5DDdxS/FCI/uXTVZ35GQ97RZXsycojz/AJ0asoz6p2/H/A==
+  optionalDependencies:
+    "@img/sharp-libvips-linux-x64" "1.0.1"
+
+"@img/sharp-linuxmusl-arm64@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-linuxmusl-arm64/-/sharp-linuxmusl-arm64-0.33.2.tgz#10e0ec5a79d1234c6a71df44c9f3b0bef0bc0f15"
+  integrity sha512-F+0z8JCu/UnMzg8IYW1TMeiViIWBVg7IWP6nE0p5S5EPQxlLd76c8jYemG21X99UzFwgkRo5yz2DS+zbrnxZeA==
+  optionalDependencies:
+    "@img/sharp-libvips-linuxmusl-arm64" "1.0.1"
+
+"@img/sharp-linuxmusl-x64@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-linuxmusl-x64/-/sharp-linuxmusl-x64-0.33.2.tgz#29e0030c24aa27c38201b1fc84e3d172899fcbe0"
+  integrity sha512-+ZLE3SQmSL+Fn1gmSaM8uFusW5Y3J9VOf+wMGNnTtJUMUxFhv+P4UPaYEYT8tqnyYVaOVGgMN/zsOxn9pSsO2A==
+  optionalDependencies:
+    "@img/sharp-libvips-linuxmusl-x64" "1.0.1"
+
+"@img/sharp-wasm32@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-wasm32/-/sharp-wasm32-0.33.2.tgz#38d7c740a22de83a60ad1e6bcfce17462b0d4230"
+  integrity sha512-fLbTaESVKuQcpm8ffgBD7jLb/CQLcATju/jxtTXR1XCLwbOQt+OL5zPHSDMmp2JZIeq82e18yE0Vv7zh6+6BfQ==
+  dependencies:
+    "@emnapi/runtime" "^0.45.0"
+
+"@img/sharp-win32-ia32@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-win32-ia32/-/sharp-win32-ia32-0.33.2.tgz#09456314e223f68e5417c283b45c399635c16202"
+  integrity sha512-okBpql96hIGuZ4lN3+nsAjGeggxKm7hIRu9zyec0lnfB8E7Z6p95BuRZzDDXZOl2e8UmR4RhYt631i7mfmKU8g==
+
+"@img/sharp-win32-x64@0.33.2":
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/@img/sharp-win32-x64/-/sharp-win32-x64-0.33.2.tgz#148e96dfd6e68747da41a311b9ee4559bb1b1471"
+  integrity sha512-E4magOks77DK47FwHUIGH0RYWSgRBfGdK56kIHSVeB9uIS4pPFr4N2kIVsXdQQo4LzOsENKV5KAhRlRL7eMAdg==
+
 "@jridgewell/gen-mapping@^0.3.2":
  version "0.3.3"
  resolved "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.3.tgz"
@ -1581,11 +1701,27 @@ color-name@1.1.3:
  resolved "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz"
  integrity sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw==

-color-name@~1.1.4:
+color-name@^1.0.0, color-name@~1.1.4:
  version "1.1.4"
  resolved "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz"
  integrity sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==

+color-string@^1.9.0:
+  version "1.9.1"
+  resolved "https://registry.yarnpkg.com/color-string/-/color-string-1.9.1.tgz#4467f9146f036f855b764dfb5bf8582bf342c7a4"
+  integrity sha512-shrVawQFojnZv6xM40anx4CkoDP+fZsw/ZerEMsW/pyzsRbElpsL/DBVW7q3ExxwusdNXI3lXpuhEZkzs8p5Eg==
+  dependencies:
+    color-name "^1.0.0"
+    simple-swizzle "^0.2.2"
+
+color@^4.2.3:
+  version "4.2.3"
+  resolved "https://registry.yarnpkg.com/color/-/color-4.2.3.tgz#d781ecb5e57224ee43ea9627560107c0e0c6463a"
+  integrity sha512-1rXeuUUiGGrykh+CeBdu5Ie7OJwinCgQY0bc7GCRxy5xVHy+moaqkpL/jqQq0MtQOeYcrqEz4abc5f0KtU7W4A==
+  dependencies:
+    color-convert "^2.0.1"
+    color-string "^1.9.0"
+
 colorette@^2.0.19:
  version "2.0.20"
  resolved "https://registry.npmjs.org/colorette/-/colorette-2.0.20.tgz"
@ -2076,6 +2212,11 @@ dequal@^2.0.0, dequal@^2.0.3:
  resolved "https://registry.npmjs.org/dequal/-/dequal-2.0.3.tgz"
  integrity sha512-0je+qPKHEMohvfRTCEo3CrPG6cAzAYgmzKyxRiYSSDkS6eGJdyVJm7WaYA5ECaAD9wLB2T4EEeymA5aFVcYXCA==

+detect-libc@^2.0.2:
+  version "2.0.2"
+  resolved "https://registry.yarnpkg.com/detect-libc/-/detect-libc-2.0.2.tgz#8ccf2ba9315350e1241b88d0ac3b0e1fbd99605d"
+  integrity sha512-UX6sGumvvqSaXgdKGUsgZWqcUyIXZ/vZTrlRT/iobiKhGL0zL4d3osHj3uqllWJK+i+sixDS/3COVEOFbupFyw==
+
 didyoumean@^1.2.2:
  version "1.2.2"
  resolved "https://registry.npmjs.org/didyoumean/-/didyoumean-1.2.2.tgz"
@ -3521,6 +3662,11 @@ is-arrayish@^0.2.1:
  resolved "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.2.1.tgz"
  integrity sha512-zz06S8t0ozoDXMG+ube26zeCTNXcKIPJZJi8hBrF4idCLms4CG9QtK7qBl1boi5ODzFpjswb5JPmHCbMpjaYzg==

+is-arrayish@^0.3.1:
+  version "0.3.2"
+  resolved "https://registry.yarnpkg.com/is-arrayish/-/is-arrayish-0.3.2.tgz#4574a2ae56f7ab206896fb431eaeed066fdf8f03"
+  integrity sha512-eVRqCvVlZbuw3GrM63ovNSNAeA1K16kaR/LRY/92w0zxQ5/1YzwblUX652i4Xs9RwAGjW9d9y6X88t8OaAJfWQ==
+
 is-async-function@^2.0.0:
  version "2.0.0"
  resolved "https://registry.yarnpkg.com/is-async-function/-/is-async-function-2.0.0.tgz#8e4418efd3e5d3a6ebb0164c05ef5afb69aa9646"
@ -6072,6 +6218,35 @@ set-function-name@^2.0.0, set-function-name@^2.0.1:
    functions-have-names "^1.2.3"
    has-property-descriptors "^1.0.0"

+sharp@^0.33.2:
+  version "0.33.2"
+  resolved "https://registry.yarnpkg.com/sharp/-/sharp-0.33.2.tgz#fcd52f2c70effa8a02160b1bfd989a3de55f2dfb"
+  integrity sha512-WlYOPyyPDiiM07j/UO+E720ju6gtNtHjEGg5vovUk1Lgxyjm2LFO+37Nt/UI3MMh2l6hxTWQWi7qk3cXJTutcQ==
+  dependencies:
+    color "^4.2.3"
+    detect-libc "^2.0.2"
+    semver "^7.5.4"
+  optionalDependencies:
+    "@img/sharp-darwin-arm64" "0.33.2"
+    "@img/sharp-darwin-x64" "0.33.2"
+    "@img/sharp-libvips-darwin-arm64" "1.0.1"
+    "@img/sharp-libvips-darwin-x64" "1.0.1"
+    "@img/sharp-libvips-linux-arm" "1.0.1"
+    "@img/sharp-libvips-linux-arm64" "1.0.1"
+    "@img/sharp-libvips-linux-s390x" "1.0.1"
+    "@img/sharp-libvips-linux-x64" "1.0.1"
+    "@img/sharp-libvips-linuxmusl-arm64" "1.0.1"
+    "@img/sharp-libvips-linuxmusl-x64" "1.0.1"
+    "@img/sharp-linux-arm" "0.33.2"
+    "@img/sharp-linux-arm64" "0.33.2"
+    "@img/sharp-linux-s390x" "0.33.2"
+    "@img/sharp-linux-x64" "0.33.2"
+    "@img/sharp-linuxmusl-arm64" "0.33.2"
+    "@img/sharp-linuxmusl-x64" "0.33.2"
+    "@img/sharp-wasm32" "0.33.2"
+    "@img/sharp-win32-ia32" "0.33.2"
+    "@img/sharp-win32-x64" "0.33.2"
+
 shebang-command@^2.0.0:
  version "2.0.0"
  resolved "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz"
@ -6098,6 +6273,13 @@ signal-exit@^3.0.2, signal-exit@^3.0.3, signal-exit@^3.0.7:
  resolved "https://registry.npmjs.org/signal-exit/-/signal-exit-3.0.7.tgz"
  integrity sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ==

+simple-swizzle@^0.2.2:
+  version "0.2.2"
+  resolved "https://registry.yarnpkg.com/simple-swizzle/-/simple-swizzle-0.2.2.tgz#a4da6b635ffcccca33f70d17cb92592de95e557a"
+  integrity sha512-JA//kQgZtbuY83m+xT+tXJkmJncGMTFT+C+g2h2R9uxkYIrE2yy9sgmcLhCnw57/WSD+Eh3J97FPEDFnbXnDUg==
+  dependencies:
+    is-arrayish "^0.3.1"
+
 size-sensor@^1.0.1:
  version "1.0.1"
  resolved "https://registry.npmjs.org/size-sensor/-/size-sensor-1.0.1.tgz"
Author	SHA1	Message	Date
takatost	c7783dbd6c	bump version to 0.4.9 (#2103 )	2024-01-19 22:25:23 +08:00
Jyong	ee9c7e204f	delete document cache embedding (#2101 ) Co-authored-by: jyong <jyong@dify.ai>	2024-01-19 21:37:54 +08:00
Bowen Liang	483dcb6340	fix: skip linking /etc/localtime file first in api docker image (#2099 )	2024-01-19 21:06:26 +08:00
Bowen Liang	9ad7b65996	support setting timezone in docker images (#2091 )	2024-01-19 20:30:36 +08:00
crazywoola	ec1659cba0	fix: saving error in empty dataset (#2098 )	2024-01-19 20:12:04 +08:00
Joshua	09a8db10d4	Add jina-embeddings-v2-base-de model configuration (#2094 )	2024-01-19 18:11:55 +08:00
Bowen Liang	f3323beaca	fix: yarn install command in web Dockerfile (#2084 )	2024-01-19 18:11:47 +08:00
Chenhe Gu	275973da8c	add feature request copilot (#2095 )	2024-01-19 17:55:39 +08:00
Bowen Liang	e2c89a9487	fix: bypass admin users to use dataset api with API key (#2072 )	2024-01-19 17:23:05 +08:00
Jyong	869690c485	fix notion estimate (#2090 ) Co-authored-by: jyong <jyong@dify.ai>	2024-01-19 13:27:12 +08:00
Jyong	a3c7c07ecc	use redis to cache embeddings (#2085 ) Co-authored-by: jyong <jyong@dify.ai>	2024-01-18 21:39:12 +08:00
Bowen Liang	dc8a8af117	bump default NodeJS version to 20 LTS (#2061 )	2024-01-18 19:12:40 +08:00
takatost	6c28e1e69a	fix: version (#2083 )	2024-01-18 16:44:09 +08:00
takatost	0e1163f698	feat: remove deprecated envs (#2078 )	2024-01-18 14:44:37 +08:00
takatost	8654415f33	bump version to 0.4.8 (#2074 )	2024-01-17 22:51:02 +08:00
takatost	1a6ad05a23	feat: service api add llm usage (#2051 )	2024-01-17 22:39:47 +08:00
takatost	1d91535ba6	fix: azure customize model name duplicate (#2073 )	2024-01-17 21:17:59 +08:00
takatost	8799c888e3	fix: free quota type apply button missing (#2069 ) Co-authored-by: StyleZhang <jasonapring2015@outlook.com>	2024-01-17 15:02:27 +08:00
crazywoola	d7209d9057	feat: add abab5.5s-chat (#2063 )	2024-01-16 19:45:21 +08:00
Chenhe Gu	5960103cb8	Fix aspect ratio of buttons in readme (#2062 )	2024-01-16 19:25:57 +08:00
Bowen Liang	2ffea39a5c	fix: add sharp package to fix sharp-missing-in-production warning (#2060 )	2024-01-16 17:25:18 +08:00
crazywoola	1e76b1bf2d	Update README.md (#2058 )	2024-01-16 17:24:49 +08:00
Chenhe Gu	2022ca1d52	fix indentation & move contact into community section (#2055 )	2024-01-16 16:59:38 +08:00
Chenhe Gu	e1319d1a2d	Update contribution guide (#2053 )	2024-01-16 15:12:35 +08:00
Jyong	a61df6cb03	timeout parameter error (#2052 ) Co-authored-by: jyong <jyong@dify.ai>	2024-01-16 14:44:47 +08:00
Jyong	790b885d0a	fix multi-dataset retrieve score limit (#2050 ) Co-authored-by: jyong <jyong@dify.ai>	2024-01-16 14:14:34 +08:00
Ricky	1a2eacc5a6	Add jina-embeddings-v2-base-zh model configuration (#2049 )	2024-01-16 12:25:42 +08:00
zxhlyh	f7a2f7a727	fix: dataset sidebar (#2048 )	2024-01-16 12:14:09 +08:00
takatost	a4adca595a	fix qdrant tag in docker-compose.yaml (#2047 )	2024-01-16 10:24:06 +08:00