fix: typos (#16385)

Co-authored-by: Novice <novice12185727@gmail.com>

.github/DISCUSSION_TEMPLATE/general.yml

@@ -9,7 +9,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true

.github/DISCUSSION_TEMPLATE/help.yml

@@ -9,7 +9,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true

.github/DISCUSSION_TEMPLATE/suggestion.yml

@@ -9,7 +9,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -14,7 +14,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true

.github/ISSUE_TEMPLATE/document_issue.yml

@@ -12,7 +12,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -12,7 +12,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true

.github/ISSUE_TEMPLATE/tracker.yml

@@ -1,5 +1,5 @@
 name: "👾 Tracker"
-description: For inner usages, please donot use this template.
+description: For inner usages, please do not use this template.
 title: "[Tracker] "
 labels:
   - tracker

.github/ISSUE_TEMPLATE/translation_issue.yml

@@ -1,5 +1,5 @@
 name: "🌐 Localization/Translation issue"
-description: Report incorrect translations. [please use English :）]
+description: Report incorrect translations. [please use English :)]
 labels:
   - translation
 body:
@@ -12,7 +12,7 @@ body:
           required: true
         - label: I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)).
           required: true
-        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）"
+        - label: "[FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)"
           required: true
         - label: "Please do not modify this template :) and fill in all the required fields."
           required: true

.github/workflows/build-push.yml

@@ -5,6 +5,7 @@ on:
     branches:
       - "main"
       - "deploy/dev"
+      - "deploy/enterprise"
   release:
     types: [published]
 

.github/workflows/deploy-enterprise.yml

@@ -0,0 +1,29 @@
+name: Deploy Enterprise
+
+permissions:
+  contents: read
+
+on:
+  workflow_run:
+    workflows: ["Build and Push API & Web"]
+    branches:
+      - "deploy/enterprise"
+    types:
+      - completed
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    if: |
+      github.event.workflow_run.conclusion == 'success' &&
+      github.event.workflow_run.head_branch == 'deploy/enterprise'
+
+    steps:
+      - name: Deploy to server
+        uses: appleboy/ssh-action@v0.1.8
+        with:
+          host: ${{ secrets.ENTERPRISE_SSH_HOST }}
+          username: ${{ secrets.ENTERPRISE_SSH_USER }}
+          password: ${{ secrets.ENTERPRISE_SSH_PASSWORD }}
+          script: |
+            ${{ vars.ENTERPRISE_SSH_SCRIPT || secrets.ENTERPRISE_SSH_SCRIPT }}

.github/workflows/expose_service_ports.sh

@@ -10,5 +10,6 @@ yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-com
 yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
 yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/tidb/docker-compose.yaml
+yq eval '.services.opengauss.ports += ["6600:6600"]' -i docker/docker-compose.yaml
 
-echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"
+echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase, opengauss"

.github/workflows/vdb-tests.yml

@@ -76,6 +76,7 @@ jobs:
             milvus-standalone
             pgvecto-rs
             pgvector
+            opengauss
             chroma
             elasticsearch
 

.gitignore

@@ -202,3 +202,6 @@ api/.vscode
 
 # plugin migrate
 plugins.jsonl
+
+# mise
+mise.toml

CONTRIBUTING.md

@@ -10,28 +10,47 @@ In terms of licensing, please take a minute to read our short [License and Contr
 
 ## Before you jump in
 
-[Find](https://github.com/langgenius/dify/issues?q=is:issue+is:open) an existing issue, or [open](https://github.com/langgenius/dify/issues/new/choose) a new one. We categorize issues into 2 types:
+Looking for something to tackle? Browse our [good first issues](https://github.com/langgenius/dify/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22good%20first%20issue%22) and pick one to get started!
+
+Got a cool new model runtime or tool to add? Open a PR in our [plugin repo](https://github.com/langgenius/dify-plugins) and show us what you've built.
+
+Need to update an existing model runtime, tool, or squash some bugs? Head over to our [official plugin repo](https://github.com/langgenius/dify-official-plugins) and make your magic happen!
+
+Join the fun, contribute, and let's build something awesome together! 💡✨
+
+Don't forget to link an existing issue or open an new issue in the PR's description.
+
+### Bug reports
+
+> [!IMPORTANT]
+> Please make sure to include the following information when submitting a bug report:
+
+- A clear and descriptive title
+- A detailed description of the bug, including any error messages
+- Steps to reproduce the bug
+- Expected behavior
+- **Logs**, if available, for backend issues, this is really important, you can find them in docker-compose logs
+- Screenshots or videos, if applicable
+
+How we prioritize:
+
+  | Issue Type                                                   | Priority        |
+  | ------------------------------------------------------------ | --------------- |
+  | Bugs in core functions (cloud service, cannot login, applications not working, security loopholes) | Critical        |
+  | Non-critical bugs, performance boosts                        | Medium Priority |
+  | Minor fixes (typos, confusing but working UI)                | Low Priority    |
 
 ### 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.
+> [!NOTE]
+> Please make sure to include the following information when submitting a feature request:
 
-* If you want to pick one up from the existing issues, simply drop a comment below it saying so.
+- A clear and descriptive title
+- A detailed description of the feature
+- A use case for the feature
+- Any other context or screenshots about the feature request
 
-  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:
+How we prioritize:
 
   | Feature Type                                                 | Priority        |
   | ------------------------------------------------------------ | --------------- |
@@ -39,119 +58,36 @@ In terms of licensing, please take a minute to read our short [License and Contr
   | Popular feature requests from our [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | 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:
-
-```shell
-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:
-
-* [Docker](https://www.docker.com/)
-* [Docker Compose](https://docs.docker.com/compose/install/)
-* [Node.js v18.x (LTS)](http://nodejs.org)
-* [pnpm](https://pnpm.io/)
-* [Python](https://www.python.org/) version 3.11.x or 3.12.x
-
-### 4. Installations
-
-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.
-
-Check the [installation FAQ](https://docs.dify.ai/learn-more/faq/install-faq) for a list of common issues and steps to troubleshoot.
-
-### 5. Visit dify in your browser
-
-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.
-
-## 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.
-
-If you are adding a tool provider to Agent or Workflow, [this guide](./api/core/tools/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.
-
-```text
-[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
-```
-
-### Frontend
-
-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.
-
-```text
-[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
-```
-
 ## Submitting your PR
 
-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).
+### Pull Request Process
 
-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).
+1. Fork the repository
+2. Before you draft a PR, please create an issue to discuss the changes you want to make
+3. Create a new branch for your changes
+4. Please add tests for your changes accordingly
+5. Ensure your code passes the existing tests
+6. Please link the issue in the PR description, `fixes #<issue_number>`
+7. Get merrged! 
+### Setup the project
 
+#### Frontend
+
+For setting up the frontend service, please refer to our comprehensive [guide](https://github.com/langgenius/dify/blob/main/web/README.md) in the `web/README.md` file. This document provides detailed instructions to help you set up the frontend environment properly.
+
+#### Backend
+
+For setting up the backend service, kindly refer to our detailed [instructions](https://github.com/langgenius/dify/blob/main/api/README.md) in the `api/README.md` file. This document contains step-by-step guidance to help you get the backend up and running smoothly.
+
+#### Other things to note
+
+We recommend reviewing this document carefully before proceeding with the setup, as it contains essential information about:
+- Prerequisites and dependencies
+- Installation steps
+- Configuration details
+- Common troubleshooting tips
+
+Feel free to reach out if you encounter any issues during the setup process.
 ## Getting Help
 
 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/8Tpq4AcN9c) for a quick chat.

CONTRIBUTING_CN.md

@@ -1,154 +1,97 @@
-所以你想为 Dify 做贡献 - 这太棒了，我们迫不及待地想看到你的贡献。作为一家人员和资金有限的初创公司，我们有着雄心勃勃的目标，希望设计出最直观的工作流程来构建和管理 LLM 应用程序。社区的任何帮助都是宝贵的。
+# 贡献指南
 
-考虑到我们的现状，我们需要灵活快速地交付，但我们也希望确保像你这样的贡献者在贡献过程中获得尽可能顺畅的体验。我们为此编写了这份贡献指南，旨在让你熟悉代码库和我们与贡献者的合作方式，以便你能快速进入有趣的部分。
+非常感谢你考虑为 Dify 做出贡献！作为一家资源有限的创业公司，我们希望打造最直观的 LLM 应用开发和管理工作流程。社区的每一份贡献对我们来说都弥足珍贵。
 
-这份指南，就像 Dify 本身一样，是一个不断改进的工作。如果有时它落后于实际项目，我们非常感谢你的理解，并欢迎提供任何反馈以供我们改进。
+我们需要保持敏捷和快速迭代，同时也希望确保贡献者能获得尽可能流畅的参与体验。这份贡献指南旨在帮助你熟悉代码库和我们的工作方式，让你可以尽快进入有趣的开发环节。
 
-在许可方面，请花一分钟阅读我们简短的 [许可证和贡献者协议](./LICENSE)。社区还遵守 [行为准则](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
+本指南和 Dify 一样在不断完善中。如果有任何滞后于项目实际情况的地方，恳请谅解，我们也欢迎任何改进建议。
 
-## 在开始之前
+关于许可证，请花一分钟阅读我们简短的[许可和贡献者协议](./LICENSE)。社区同时也遵循[行为准则](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
 
-[查找](https://github.com/langgenius/dify/issues?q=is:issue+is:open)现有问题，或 [创建](https://github.com/langgenius/dify/issues/new/choose) 一个新问题。我们将问题分为两类：
+## 开始之前
 
-### 功能请求：
+想寻找可以着手的任务？浏览我们的[新手友好议题](https://github.com/langgenius/dify/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22good%20first%20issue%22)并选择一个开始！
 
-* 如果您要提出新的功能请求，请解释所提议的功能的目标，并尽可能提供详细的上下文。[@perzeusss](https://github.com/perzeuss) 制作了一个很好的 [功能请求助手](https://udify.app/chat/MK2kVSnw1gakVwMX)，可以帮助您起草需求。随时尝试一下。
+有酷炫的新模型运行时或工具要添加？在我们的[插件仓库](https://github.com/langgenius/dify-plugins)开启 PR，展示你的作品。
 
-* 如果您想从现有问题中选择一个，请在其下方留下评论表示您的意愿。
+需要更新现有模型运行时、工具或修复 bug？前往我们的[官方插件仓库](https://github.com/langgenius/dify-official-plugins)大展身手！
 
-相关方向的团队成员将参与其中。如果一切顺利，他们将批准您开始编码。在此之前，请不要开始工作，以免我们提出更改导致您的工作付诸东流。
+加入我们，一起贡献，共同打造精彩项目！💡✨
 
-根据所提议的功能所属的领域不同，您可能需要与不同的团队成员交流。以下是我们团队成员目前正在从事的各个领域的概述：
+请记得在 PR 描述中关联现有 issue 或创建新的 issue。
 
-  | 团队成员                                                       | 工作范围                                                |
-  | ------------------------------------------------------------ | ---------------------------------------------------- |
-  | [@yeuoly](https://github.com/Yeuoly)                         | 架构 Agents                                  |
-  | [@jyong](https://github.com/JohnJyong)                       | RAG 流水线设计                                  |
-  | [@GarfieldDai](https://github.com/GarfieldDai)               | 构建 workflow 编排                     |
-  | [@iamjoel](https://github.com/iamjoel) & [@zxhlyh](https://github.com/zxhlyh) | 让我们的前端更易用                  |
-  | [@guchenhe](https://github.com/guchenhe) & [@crazywoola](https://github.com/crazywoola) | 开发人员体验, 综合事项联系人 |
-  | [@takatost](https://github.com/takatost)                     | 产品整体方向和架构           |
+### Bug 报告
 
-  事项优先级：
+> [!IMPORTANT]
+> 提交 bug 报告时请务必包含以下信息：
 
-  | 功能类型                                                 | 优先级        |
-  | ------------------------------------------------------------ | --------------- |
-  | 被团队成员标记为高优先级的功能    | 高优先级   |
-  | 在 [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) 内反馈的常见功能请求 | 中等优先级 |
-  | 非核心功能和小幅改进                     | 低优先级    |
-  | 有价值但不紧急                                   | 未来功能  |
+- 清晰描述性的标题
+- 详细的 bug 描述，包括任何错误信息
+- 复现步骤
+- 预期行为
+- **日志**，如果是后端问题，这点很重要，可以在 docker-compose 日志中找到
+- 截图或视频（如果适用）
 
-### 其他任何事情（例如 bug 报告、性能优化、拼写错误更正）：
-* 立即开始编码。
+优先级划分：
 
-  事项优先级：
+  | 问题类型                                           | 优先级     |
+  | -------------------------------------------------- | ---------- |
+  | 核心功能 bug（云服务、登录失败、应用无法使用、安全漏洞） | 紧急       |
+  | 非关键 bug、性能优化                                | 中等优先级 |
+  | 小修复（拼写错误、界面混乱但可用）                  | 低优先级   |
 
-  | Issue 类型                                                   | 优先级        |
-  | ------------------------------------------------------------ | --------------- |
-  | 核心功能的 Bugs（例如无法登录、应用无法工作、安全漏洞） | 紧急        |
-  | 非紧急 bugs, 性能提升                        | 中等优先级 |
-  | 小幅修复(错别字, 能正常工作但存在误导的 UI)                | 低优先级    |
 
-## 安装
+### 功能请求
 
-以下是设置 Dify 进行开发的步骤：
+> [!NOTE]
+> 提交功能请求时请务必包含以下信息：
 
-### 1. Fork 该仓库
+- 清晰描述性的标题
+- 详细的功能描述
+- 功能使用场景
+- 其他相关上下文或截图
 
-### 2. 克隆仓库
+优先级划分：
 
-从终端克隆代码仓库：
+  | 功能类型                                           | 优先级     |
+  | -------------------------------------------------- | ---------- |
+  | 被团队成员标记为高优先级的功能                      | 高优先级   |
+  | 来自[社区反馈板](https://github.com/langgenius/dify/discussions/categories/feedbacks)的热门功能请求 | 中等优先级 |
+  | 非核心功能和小改进                                  | 低优先级   |
+  | 有价值但非紧急的功能                                | 未来特性   |
 
-```
-git clone git@github.com:<github_username>/dify.git
-```
+## 提交 PR
 
-### 3. 验证依赖项
+### 项目设置
 
-Dify 依赖以下工具和库：
+### PR 提交流程
 
-- [Docker](https://www.docker.com/)
-- [Docker Compose](https://docs.docker.com/compose/install/)
-- [Node.js v18.x (LTS)](http://nodejs.org)
-- [pnpm](https://pnpm.io/)
-- [Python](https://www.python.org/) version 3.11.x or 3.12.x
+1. Fork 本仓库
+2. 在提交 PR 之前，请先创建 issue 讨论你想要做的修改
+3. 为你的修改创建一个新的分支
+4. 请为你的修改添加相应的测试
+5. 确保你的代码能通过现有的测试
+6. 请在 PR 描述中关联相关 issue，格式为 `fixes #<issue编号>`
+7. 等待合并！
 
-### 4. 安装
+#### 前端
 
-Dify 由后端和前端组成。通过 `cd api/` 导航到后端目录，然后按照 [后端 README](api/README.md) 进行安装。在另一个终端中，通过 `cd web/` 导航到前端目录，然后按照 [前端 README](web/README.md) 进行安装。
+关于前端服务的设置，请参考 `web/README.md` 文件中的[详细指南](https://github.com/langgenius/dify/blob/main/web/README.md)。该文档提供了帮助你正确配置前端环境的详细说明。
 
-查看 [安装常见问题解答](https://docs.dify.ai/v/zh-hans/learn-more/faq/install-faq) 以获取常见问题列表和故障排除步骤。
+#### 后端
 
-### 5. 在浏览器中访问 Dify
+关于后端服务的设置，请参考 `api/README.md` 文件中的[详细说明](https://github.com/langgenius/dify/blob/main/api/README.md)。该文档包含了帮助你顺利运行后端的步骤说明。
 
-为了验证您的设置，打开浏览器并访问 [http://localhost:3000](http://localhost:3000)（默认或您自定义的 URL 和端口）。现在您应该看到 Dify 正在运行。
+#### 其他注意事项
 
-## 开发
+我们建议在开始设置之前仔细阅读本文档，因为它包含以下重要信息：
+- 前置条件和依赖项
+- 安装步骤
+- 配置细节
+- 常见问题解决方案
 
-如果您要添加模型提供程序，请参考 [此指南](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md)。
-
-如果您要向 Agent 或 Workflow 添加工具提供程序，请参考 [此指南](./api/core/tools/README.md)。
-
-为了帮助您快速了解您的贡献在哪个部分，以下是 Dify 后端和前端的简要注释大纲：
-
-### 后端
-
-Dify 的后端使用 Python 编写，使用 [Flask](https://flask.palletsprojects.com/en/3.0.x/) 框架。它使用 [SQLAlchemy](https://www.sqlalchemy.org/) 作为 ORM，使用 [Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html) 作为任务队列。授权逻辑通过 Flask-login 进行处理。
-
-```
-[api/]
-├── constants             // 用于整个代码库的常量设置。
-├── controllers           // API 路由定义和请求处理逻辑。
-├── core                  // 核心应用编排、模型集成和工具。
-├── docker                // Docker 和容器化相关配置。
-├── events                // 事件处理和处理。
-├── extensions            // 与第三方框架/平台的扩展。
-├── fields                // 用于序列化/封装的字段定义。
-├── libs                  // 可重用的库和助手。
-├── migrations            // 数据库迁移脚本。
-├── models                // 数据库模型和架构定义。
-├── services              // 指定业务逻辑。
-├── storage               // 私钥存储。
-├── tasks                 // 异步任务和后台作业的处理。
-└── tests
-```
-
-### 前端
-
-该网站使用基于 Typescript 的 [Next.js](https://nextjs.org/) 模板进行引导，并使用 [Tailwind CSS](https://tailwindcss.com/) 进行样式设计。[React-i18next](https://react.i18next.com/) 用于国际化。
-
-```
-[web/]
-├── app                   // 布局、页面和组件
-│   ├── (commonLayout)    // 整个应用通用的布局
-│   ├── (shareLayout)     // 在特定会话中共享的布局
-│   ├── activate          // 激活页面
-│   ├── components        // 页面和布局共享的组件
-│   ├── install           // 安装页面
-│   ├── signin            // 登录页面
-│   └── styles            // 全局共享的样式
-├── assets                // 静态资源
-├── bin                   // 构建步骤运行的脚本
-├── config                // 可调整的设置和选项
-├── context               // 应用中不同部分使用的共享上下文
-├── dictionaries          // 语言特定的翻译文件
-├── docker                // 容器配置
-├── hooks                 // 可重用的钩子
-├── i18n                  // 国际化配置
-├── models                // 描述数据模型和 API 响应的形状
-├── public                // 如 favicon 等元资源
-├── service               // 定义 API 操作的形状
-├── test
-├── types                 // 函数参数和返回值的描述
-└── utils                 // 共享的实用函数
-```
-
-## 提交你的 PR
-
-最后，是时候向我们的仓库提交一个拉取请求（PR）了。对于重要的功能，我们首先将它们合并到 `deploy/dev` 分支进行测试，然后再合并到 `main` 分支。如果你遇到合并冲突或者不知道如何提交拉取请求的问题，请查看 [GitHub 的拉取请求教程](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests)。
-
-就是这样！一旦你的 PR 被合并，你将成为我们 [README](https://github.com/langgenius/dify/blob/main/README.md) 中的贡献者。
+如果在设置过程中遇到任何问题，请随时联系我们。
 
 ## 获取帮助
 
-如果你在贡献过程中遇到困难或者有任何问题，可以通过相关的 GitHub 问题提出你的疑问，或者加入我们的 [Discord](https://discord.gg/8Tpq4AcN9c) 进行快速交流。
+如果你在贡献过程中遇到困难或有紧急问题，可以通过相关 GitHub issue 向我们提问，或加入我们的 [Discord](https://discord.gg/8Tpq4AcN9c) 进行快速交流。

CONTRIBUTING_DE.md

@@ -1,155 +1,95 @@
 # MITWIRKEN
 
-So, du möchtest zu Dify beitragen – das ist großartig, wir können es kaum erwarten, zu sehen, was du beisteuern wirst. Als ein Startup mit begrenzter Mitarbeiterzahl und Finanzierung haben wir große Ambitionen, den intuitivsten Workflow zum Aufbau und zur Verwaltung von LLM-Anwendungen zu entwickeln. Jede Unterstützung aus der Community zählt wirklich.
+Sie möchten also zu Dify beitragen - das ist großartig, wir können es kaum erwarten zu sehen, was Sie entwickeln. Als Startup mit begrenztem Personal und Finanzierung haben wir große Ambitionen, den intuitivsten Workflow für die Entwicklung und Verwaltung von LLM-Anwendungen zu gestalten. Jede Hilfe aus der Community zählt wirklich.
 
-Dieser Leitfaden, ebenso wie Dify selbst, ist ein ständig in Entwicklung befindliches Projekt. Wir schätzen Ihr Verständnis, falls er zeitweise hinter dem tatsächlichen Projekt zurückbleibt, und freuen uns über jegliches Feedback, das uns hilft, ihn zu verbessern.
+Wir müssen wendig sein und schnell liefern, aber wir möchten auch sicherstellen, dass Mitwirkende wie Sie eine möglichst reibungslose Erfahrung beim Beitragen haben. Wir haben diesen Leitfaden zusammengestellt, damit Sie sich schnell mit der Codebasis und unserer Arbeitsweise mit Mitwirkenden vertraut machen können.
 
-Bezüglich der Lizenzierung nehmen Sie sich bitte einen Moment Zeit, um unser kurzes [License and Contributor Agreement](./LICENSE) zu lesen. Die Community hält sich außerdem an den [Code of Conduct](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+Dieser Leitfaden ist, wie Dify selbst, in ständiger Entwicklung. Wir sind dankbar für Ihr Verständnis, falls er manchmal hinter dem eigentlichen Projekt zurückbleibt, und begrüßen jedes Feedback zur Verbesserung.
+
+Bitte nehmen Sie sich einen Moment Zeit, um unsere [Lizenz- und Mitwirkungsvereinbarung](./LICENSE) zu lesen. Die Community hält sich außerdem an den [Verhaltenskodex](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Bevor Sie loslegen
 
-[Finde](https://github.com/langgenius/dify/issues?q=is:issue+is:open) ein bestehendes Issue, oder [öffne](https://github.com/langgenius/dify/issues/new/choose) ein neues. Wir kategorisieren Issues in zwei Typen:
+Suchen Sie nach einer Aufgabe? Durchstöbern Sie unsere [Einsteiger-Issues](https://github.com/langgenius/dify/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22good%20first%20issue%22) und wählen Sie eines zum Einstieg!
+
+Haben Sie eine neue Modell-Runtime oder ein Tool hinzuzufügen? Öffnen Sie einen PR in unserem [Plugin-Repository](https://github.com/langgenius/dify-plugins).
+
+Möchten Sie eine bestehende Modell-Runtime oder ein Tool aktualisieren oder Bugs beheben? Besuchen Sie unser [offizielles Plugin-Repository](https://github.com/langgenius/dify-official-plugins)!
+
+Vergessen Sie nicht, in der PR-Beschreibung ein bestehendes Issue zu verlinken oder ein neues zu erstellen.
+
+### Fehlermeldungen
+
+> [!WICHTIG]
+> Bitte stellen Sie sicher, dass Sie folgende Informationen bei der Einreichung eines Fehlerberichts angeben:
+
+- Ein klarer und beschreibender Titel
+- Eine detaillierte Beschreibung des Fehlers, einschließlich Fehlermeldungen
+- Schritte zur Reproduktion des Fehlers
+- Erwartetes Verhalten
+- **Logs** bei Backend-Problemen (sehr wichtig, zu finden in docker-compose logs)
+- Screenshots oder Videos, falls zutreffend
+
+Unsere Priorisierung:
+
+  | Fehlertyp                                                    | Priorität       |
+  | ------------------------------------------------------------ | --------------- |
+  | Fehler in Kernfunktionen (Cloud-Service, Login nicht möglich, Anwendungen funktionieren nicht, Sicherheitslücken) | Kritisch        |
+  | Nicht-kritische Fehler, Leistungsverbesserungen              | Mittlere Priorität |
+  | Kleinere Korrekturen (Tippfehler, verwirrende aber funktionierende UI) | Niedrige Priorität |
 
 ### Feature-Anfragen
 
-* Wenn Sie eine neue Feature-Anfrage stellen, bitten wir Sie zu erklären, was das vorgeschlagene Feature bewirken soll und so viel Kontext wie möglich bereitzustellen. [@perzeusss](https://github.com/perzeuss) hat einen soliden [Feature Request Copilot](https://udify.app/chat/MK2kVSnw1gakVwMX) entwickelt, der Ihnen dabei hilft, Ihre Anforderungen zu formulieren. Probieren Sie ihn gerne aus.
+> [!HINWEIS]
+> Bitte stellen Sie sicher, dass Sie folgende Informationen bei der Einreichung einer Feature-Anfrage angeben:
 
-* Wenn Sie eines der bestehenden Issues übernehmen möchten, hinterlassen Sie einfach einen Kommentar darunter, in dem Sie uns dies mitteilen.
+- Ein klarer und beschreibender Titel
+- Eine detaillierte Beschreibung des Features
+- Ein Anwendungsfall für das Feature
+- Zusätzlicher Kontext oder Screenshots zur Feature-Anfrage
 
-  Ein Teammitglied, das in der entsprechenden Richtung arbeitet, wird hinzugezogen. Wenn alles in Ordnung ist, gibt es das Okay, mit der Codierung zu beginnen. Wir bitten Sie, mit der Umsetzung des Features zu warten, damit keine Ihrer Arbeiten verloren gehen sollte unsererseits Änderungen vorgeschlagen werden.
+Unsere Priorisierung:
 
-  Je nachdem, in welchen Bereich das vorgeschlagene Feature fällt, können Sie mit verschiedenen Teammitgliedern sprechen. Hier ist eine Übersicht der Bereiche, an denen unsere Teammitglieder derzeit arbeiten:
-
-  | 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           |
-
-  Wie wir Prioritäten setzen:
-
-  | Feature Type                                                 | Priority        |
+  | Feature-Typ                                                  | Priorität       |
   | ------------------------------------------------------------ | --------------- |
-  | Funktionen mit hoher Priorität, wie sie von einem Teammitglied gekennzeichnet wurden     | High Priority   |
-  | Beliebte Funktionsanfragen von unserem [Community-Feedback-Board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Medium Priority |
-  | Nicht-Kernfunktionen und kleinere Verbesserungen                    | Low Priority    |
-  | Wertvoll, aber nicht unmittelbar                                  | Future-Feature  |
+  | Hochprioritäre Features (durch Teammitglied gekennzeichnet)  | Hohe Priorität  |
+  | Beliebte Feature-Anfragen aus unserem [Community-Feedback-Board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Mittlere Priorität |
+  | Nicht-Kernfunktionen und kleinere Verbesserungen             | Niedrige Priorität |
+  | Wertvoll, aber nicht dringend                                | Zukunfts-Feature |
 
-### Sonstiges (e.g. bug report, performance optimization, typo correction)
+## Einreichen Ihres PRs
 
-* Fangen Sie sofort an zu programmieren..
+### Pull-Request-Prozess
 
-  Wie wir Prioritäten setzen:
+1. Repository forken
+2. Vor dem Erstellen eines PRs bitte ein Issue zur Diskussion der Änderungen erstellen
+3. Einen neuen Branch für Ihre Änderungen erstellen
+4. Tests für Ihre Änderungen hinzufügen
+5. Sicherstellen, dass Ihr Code die bestehenden Tests besteht
+6. Issue in der PR-Beschreibung verlinken (`fixes #<issue_number>`)
+7. Auf den Merge warten!
 
-  | Issue Type                                                   | Priority        |
-  | ------------------------------------------------------------ | --------------- |
-  | Fehler in Kernfunktionen (Anmeldung nicht möglich, Anwendungen funktionieren nicht, Sicherheitslücken) | Critical        |
-  | Nicht-kritische Fehler, Leistungsverbesserungen                     | Medium Priority |
-  | Kleinere Fehlerkorrekturen (Schreibfehler, verwirrende, aber funktionierende Benutzeroberfläche)                | Low Priority    |
+### Projekt einrichten
 
-## Installieren
+#### Frontend
 
-Hier sind die Schritte, um Dify für die Entwicklung einzurichten:
+Für die Einrichtung des Frontend-Service folgen Sie bitte unserer ausführlichen [Anleitung](https://github.com/langgenius/dify/blob/main/web/README.md) in der Datei `web/README.md`.
 
-### 1. Fork dieses Repository
+#### Backend
 
-### 2. Clone das Repo
+Für die Einrichtung des Backend-Service folgen Sie bitte unseren detaillierten [Anweisungen](https://github.com/langgenius/dify/blob/main/api/README.md) in der Datei `api/README.md`.
 
- Klonen Sie das geforkte Repository von Ihrem Terminal aus:
+#### Weitere Hinweise
 
-```shell
-git clone git@github.com:<github_username>/dify.git
-```
+Wir empfehlen, dieses Dokument sorgfältig zu lesen, da es wichtige Informationen enthält über:
+- Voraussetzungen und Abhängigkeiten
+- Installationsschritte
+- Konfigurationsdetails
+- Häufige Problemlösungen
 
-### 3. Abhängigkeiten prüfen
-
-Dify benötigt die folgenden Abhängigkeiten zum Bauen – stellen Sie sicher, dass sie auf Ihrem System installiert sind:
-
-* [Docker](https://www.docker.com/)
-* [Docker Compose](https://docs.docker.com/compose/install/)
-* [Node.js v18.x (LTS)](http://nodejs.org)
-* [pnpm](https://pnpm.io/)
-* [Python](https://www.python.org/) version 3.11.x or 3.12.x
-
-### 4. Installationen
-
-Dify setzt sich aus einem Backend und einem Frontend zusammen. Wechseln Sie in das Backend-Verzeichnis mit `cd api/` und folgen Sie der [Backend README](api/README.md) zur Installation. Öffnen Sie in einem separaten Terminal das Frontend-Verzeichnis mit `cd web/` und folgen Sie der [Frontend README](web/README.md) zur Installation.
-
-Überprüfen Sie die [Installation FAQ](https://docs.dify.ai/learn-more/faq/install-faq) für eine Liste bekannter Probleme und Schritte zur Fehlerbehebung.
-
-### 5. Besuchen Sie dify in Ihrem Browser
-
-Um Ihre Einrichtung zu validieren, öffnen Sie Ihren Browser und navigieren Sie zu [http://localhost:3000](http://localhost:3000) (Standardwert oder Ihre selbst konfigurierte URL und Port). Sie sollten nun Dify im laufenden Betrieb sehen.
-
-## Entwickeln
-
-Wenn Sie einen Modellanbieter hinzufügen, ist [dieser Leitfaden](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md) für Sie.
-
-Wenn Sie einen Tool-Anbieter für Agent oder Workflow hinzufügen möchten, ist [dieser Leitfaden](./api/core/tools/README.md) für Sie.
-
-Um Ihnen eine schnelle Orientierung zu bieten, wo Ihr Beitrag passt, folgt eine kurze, kommentierte Übersicht des Backends und Frontends von Dify:
-
-### Backend
-
-Dify’s Backend ist in Python geschrieben und nutzt [Flask](https://flask.palletsprojects.com/en/3.0.x/) als Web-Framework. Es verwendet [SQLAlchemy](https://www.sqlalchemy.org/) für ORM und [Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html) für Task-Queueing. Die Autorisierungslogik erfolgt über Flask-login.
-
-```text
-[api/]
-├── constants             // Konstante Einstellungen, die in der gesamten Codebasis verwendet werden.
-├── controllers           // API-Routendefinitionen und Logik zur Bearbeitung von Anfragen.
-├── core                  // Orchestrierung von Kernanwendungen, Modellintegrationen und Tools.
-├── docker                // Konfigurationen im Zusammenhang mit Docker und Containerisierung.
-├── events                // Ereignisbehandlung und -verarbeitung
-├── extensions            // Erweiterungen mit Frameworks/Plattformen von Drittanbietern.
-├── fields                // Felddefinitionen für die Serialisierung/Marshalling.
-├── libs                  // Wiederverwendbare Bibliotheken und Hilfsprogramme
-├── migrations            // Skripte für die Datenbankmigration.
-├── models                // Datenbankmodelle und Schemadefinitionen.
-├── services              // Gibt die Geschäftslogik an.
-├── storage               // Speicherung privater Schlüssel.   
-├── tasks                 // Handhabung von asynchronen Aufgaben und Hintergrundaufträgen.
-└── tests
-```
-
-### Frontend
-
-Die Website basiert auf einem [Next.js](https://nextjs.org/)-Boilerplate in TypeScript und verwendet [Tailwind CSS](https://tailwindcss.com/) für das Styling. [React-i18next](https://react.i18next.com/) wird für die Internationalisierung genutzt.
-
-```text
-[web/]
-├── app                   // Layouts, Seiten und Komponenten
-│   ├── (commonLayout)    // gemeinsames Layout für die gesamte Anwendung
-│   ├── (shareLayout)     // Layouts, die speziell für tokenspezifische Sitzungen gemeinsam genutzt werden 
-│   ├── activate          // Seite aufrufen
-│   ├── components        // gemeinsam genutzt von Seiten und Layouts
-│   ├── install           // Seite installieren
-│   ├── signin            // Anmeldeseite
-│   └── styles            // global geteilte Stile
-├── assets                // Statische Vermögenswerte
-├── bin                   // Skripte, die beim Build-Schritt ausgeführt werden
-├── config                // einstellbare Einstellungen und Optionen 
-├── context               // gemeinsame Kontexte, die von verschiedenen Teilen der Anwendung verwendet werden
-├── dictionaries          // Sprachspezifische Übersetzungsdateien 
-├── docker                // Container-Konfigurationen
-├── hooks                 // Wiederverwendbare Haken
-├── i18n                  // Konfiguration der Internationalisierung
-├── models                // beschreibt Datenmodelle und Formen von API-Antworten
-├── public                // Meta-Assets wie Favicon
-├── service               // legt Formen von API-Aktionen fest
-├── test                  
-├── types                 // Beschreibungen von Funktionsparametern und Rückgabewerten
-└── utils                 // Gemeinsame Nutzenfunktionen
-```
-
-## Einreichung Ihrer PR
-
-Am Ende ist es Zeit, einen Pull Request (PR) in unserem Repository zu eröffnen. Für wesentliche Features mergen wir diese zunächst in den `deploy/dev`-Branch zum Testen, bevor sie in den `main`-Branch übernommen werden. Falls Sie auf Probleme wie Merge-Konflikte stoßen oder nicht wissen, wie man einen Pull Request erstellt, schauen Sie sich [GitHub's Pull Request Tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests) an.
-
-Und das war's! Sobald Ihr PR gemerged wurde, werden Sie als Mitwirkender in unserem [README](https://github.com/langgenius/dify/blob/main/README.md) aufgeführt.
+Bei Problemen während der Einrichtung können Sie sich gerne an uns wenden.
 
 ## Hilfe bekommen
 
-Wenn Sie beim Beitragen jemals nicht weiter wissen oder eine brennende Frage haben, richten Sie Ihre Anfrage einfach über das entsprechende GitHub-Issue an uns oder besuchen Sie unseren [Discord](https://discord.gg/8Tpq4AcN9c) für ein kurzes Gespräch.
+Wenn Sie beim Mitwirken Fragen haben oder nicht weiterkommen, stellen Sie Ihre Fragen einfach im entsprechenden GitHub Issue oder besuchen Sie unseren [Discord](https://discord.gg/8Tpq4AcN9c) für einen schnellen Austausch.
+

CONTRIBUTING_JA.md

@@ -1,160 +1,97 @@
-Dify にコントリビュートしたいとお考えなのですね。それは素晴らしいことです。
-私たちは、LLM アプリケーションの構築と管理のための最も直感的なワークフローを設計するという壮大な野望を持っています。人数も資金も限られている新興企業として、コミュニティからの支援は本当に重要です。
+# 貢献ガイド
 
-私たちは現状を鑑み、機敏かつ迅速に開発をする必要がありますが、同時にあなた様のようなコントリビューターの方々に、可能な限りスムーズな貢献体験をしていただきたいと思っています。そのためにこのコントリビュートガイドを作成しました。
-コードベースやコントリビュータの方々と私たちがどのように仕事をしているのかに慣れていただき、楽しいパートにすぐに飛び込めるようにすることが目的です。
+Difyに貢献しようとお考えですか？素晴らしいですね。私たちは、あなたがどのような貢献をしてくださるのか、とても楽しみにしています。スタートアップとして限られた人員と資金の中で、LLMアプリケーションの構築と管理のための最も直感的なワークフローを設計するという大きな目標を持っています。コミュニティからのあらゆる支援が、本当に重要な意味を持ちます。
 
-このガイドは Dify そのものと同様に、継続的に改善されています。実際のプロジェクトに遅れをとることがあるかもしれませんが、ご理解のほどよろしくお願いいたします。
+私たちは迅速に開発を進める必要がありますが、同時に貢献者の皆様にとってスムーズな経験を提供したいと考えています。このガイドは、コードベースと私たちの貢献者との協働方法を理解していただき、すぐに楽しい開発に取り掛かれるようにすることを目的としています。
 
-ライセンスに関しては、私たちの短い[ライセンスおよびコントリビューター規約](./LICENSE)をお読みください。また、コミュニティは[行動規範](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)を遵守しています。
+このガイドは、Dify自体と同様に、常に進化し続けています。実際のプロジェクトの進行状況と多少のずれが生じる場合もございますが、ご理解いただけますと幸いです。改善のためのフィードバックも歓迎いたします。
 
-## 飛び込む前に
+ライセンスについては、[ライセンスと貢献者同意書](./LICENSE)をご一読ください。また、コミュニティは[行動規範](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)に従っています。
 
-[既存の Issue](https://github.com/langgenius/dify/issues?q=is:issue+is:open) を探すか、[新しい Issue](https://github.com/langgenius/dify/issues/new/choose) を作成してください。私たちは Issue を 2 つのタイプに分類しています。
+## 始める前に
+
+取り組むべき課題をお探しですか？[初心者向けの課題](https://github.com/langgenius/dify/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22good%20first%20issue%22)から選んで始めてみましょう！
+
+新しいモデルランタイムやツールを追加したいですか？[プラグインリポジトリ](https://github.com/langgenius/dify-plugins)でPRを作成し、あなたの成果を見せてください。
+
+既存のモデルランタイムやツールの更新、バグ修正をしたいですか？[公式プラグインリポジトリ](https://github.com/langgenius/dify-official-plugins)で作業を進めてください。
+
+参加して、貢献して、一緒に素晴らしいものを作りましょう！💡✨
+
+PRの説明には、既存のイシューへのリンクを含めるか、新しいイシューを作成することを忘れないでください。
+
+### バグ報告
+
+> [!IMPORTANT]
+> バグ報告時には、以下の情報を必ず含めてください：
+
+- 明確で分かりやすいタイトル
+- エラーメッセージを含む詳細なバグの説明
+- バグの再現手順
+- 期待される動作
+- バックエンドの問題の場合は**ログ**（docker-composeのログで確認可能）が非常に重要です
+- 該当する場合はスクリーンショットや動画
+
+優先順位の付け方：
+
+  | 問題の種類                                                    | 優先度    |
+  | ------------------------------------------------------------ | --------- |
+  | コア機能のバグ（クラウドサービス、ログイン不可、アプリケーション不具合、セキュリティ脆弱性） | 最重要    |
+  | 重要度の低いバグ、パフォーマンス改善                         | 中程度    |
+  | 軽微な修正（タイプミス、分かりにくいが動作するUI）           | 低       |
 
 ### 機能リクエスト
 
-* 新しい機能要望を出す場合は、提案する機能が何を実現するものなのかを説明し、可能な限り多くのコンテキストを含めてください。[@perzeusss](https://github.com/perzeuss)は、あなた様の要望を書き出すのに役立つ [Feature Request Copilot](https://udify.app/chat/MK2kVSnw1gakVwMX) を作ってくれました。気軽に試してみてください。
+> [!NOTE]
+> 機能リクエスト時には、以下の情報を必ず含めてください：
 
-* 既存の課題から 1 つ選びたい場合は、その下にコメントを書いてください。
+- 明確で分かりやすいタイトル
+- 機能の詳細な説明
+- 使用事例
+- その他の文脈や画面のスクリーンショット
 
-  関連する方向で作業しているチームメンバーが参加します。すべてが良好であれば、コーディングを開始する許可が与えられます。私たちが変更を提案した場合にあなた様の作業が無駄になることがないよう、それまでこの機能の作業を控えていただくようお願いいたします。
+優先順位の付け方：
 
-  提案された機能がどの分野に属するかによって、あなた様は異なるチーム・メンバーと話をするかもしれません。以下は、各チームメンバーが現在取り組んでいる分野の概要です。
+  | 機能の種類                                                    | 優先度    |
+  | ------------------------------------------------------------ | --------- |
+  | チームメンバーによって高優先度とラベル付けされた機能         | 高       |
+  | [コミュニティフィードボード](https://github.com/langgenius/dify/discussions/categories/feedbacks)での人気の機能リクエスト | 中程度    |
+  | 非コア機能と軽微な改善                                       | 低       |
+  | 価値はあるが緊急性の低いもの                                 | 将来対応  |
 
-| Member                                                                                  | Scope                                |
-| --------------------------------------------------------------------------------------- | ------------------------------------ |
-| [@yeuoly](https://github.com/Yeuoly)                                                    | エージェントアーキテクチャ           |
-| [@jyong](https://github.com/JohnJyong)                                                  | RAG パイプライン設計                 |
-| [@GarfieldDai](https://github.com/GarfieldDai)                                          | workflow orchestrations の構築       |
-| [@iamjoel](https://github.com/iamjoel) & [@zxhlyh](https://github.com/zxhlyh)           | フロントエンドを使いやすくする       |
-| [@guchenhe](https://github.com/guchenhe) & [@crazywoola](https://github.com/crazywoola) | 開発者体験、何でも相談できる窓口     |
-| [@takatost](https://github.com/takatost)                                                | 全体的な製品の方向性とアーキテクチャ |
+## PRの提出
 
-優先順位の付け方:
+### プルリクエストのプロセス
 
-| Feature Type                                                                                                          | Priority        |
-| --------------------------------------------------------------------------------------------------------------------- | --------------- |
-| チームメンバーによってラベル付けされた優先度の高い機能                                                                | High Priority   |
-| [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks)の人気の機能リクエスト | Medium Priority |
-| 非コア機能とマイナーな機能強化                                                                                        | Low Priority    |
-| 価値はあるが即効性はない                                                                                              | Future-Feature  |
+1. リポジトリをフォークする
+2. PRを作成する前に、変更内容についてイシューで議論する
+3. 変更用の新しいブランチを作成する
+4. 変更に応じたテストを追加する
+5. 既存のテストをパスすることを確認する
+6. PRの説明文にイシューをリンクする（`fixes #<issue_number>`）
+7. マージ完了！
 
-### その他 (バグレポート、パフォーマンスの最適化、誤字の修正など)
+### プロジェクトのセットアップ
 
-* すぐにコーディングを始めてください
+#### フロントエンド
 
-優先順位の付け方:
+フロントエンドサービスのセットアップについては、`web/README.md`の[ガイド](https://github.com/langgenius/dify/blob/main/web/README.md)を参照してください。このドキュメントには、フロントエンド環境を適切にセットアップするための詳細な手順が記載されています。
 
-| Issue Type                                                                             | Priority        |
-| -------------------------------------------------------------------------------------- | --------------- |
-| コア機能のバグ（ログインできない、アプリケーションが動作しない、セキュリティの抜け穴） | Critical        |
-| 致命的でないバグ、パフォーマンス向上                                                   | Medium Priority |
-| 細かな修正（誤字脱字、機能はするが分かりにくい UI）                                  | Low Priority    |
+#### バックエンド
 
-## インストール
+バックエンドサービスのセットアップについては、`api/README.md`の[手順](https://github.com/langgenius/dify/blob/main/api/README.md)を参照してください。このドキュメントには、バックエンドを正しく動作させるためのステップバイステップのガイドが含まれています。
 
-以下の手順で 、Difyのセットアップをしてください。
+#### その他の注意点
 
-### 1. このリポジトリをフォークする
+セットアップを進める前に、以下の重要な情報が含まれているため、このドキュメントを注意深く確認することをお勧めします：
+- 前提条件と依存関係
+- インストール手順
+- 設定の詳細
+- 一般的なトラブルシューティングのヒント
 
-### 2. リポジトリをクローンする
+セットアップ中に問題が発生した場合は、お気軽にお問い合わせください。
 
-フォークしたリポジトリをターミナルからクローンします。
+## サポートを受ける
 
-```
-git clone git@github.com:<github_username>/dify.git
-```
+貢献中に行き詰まったり、緊急の質問がある場合は、関連するGitHubイシューで質問するか、[Discord](https://discord.gg/8Tpq4AcN9c)で気軽にチャットしてください。
 
-### 3. 依存関係の確認
-
-Dify を構築するには次の依存関係が必要です。それらがシステムにインストールされていることを確認してください。
-
-- [Docker](https://www.docker.com/)
-- [Docker Compose](https://docs.docker.com/compose/install/)
-- [Node.js v18.x (LTS)](http://nodejs.org)
-- [pnpm](https://pnpm.io/)
-- [Python](https://www.python.org/) version 3.11.x or 3.12.x
-
-### 4. インストール
-
-Dify はバックエンドとフロントエンドから構成されています。
-まず`cd api/`でバックエンドのディレクトリに移動し、[Backend README](api/README.md)に従ってインストールします。
-次に別のターミナルで、`cd web/`でフロントエンドのディレクトリに移動し、[Frontend README](web/README.md)に従ってインストールしてください。
-
-よくある問題とトラブルシューティングの手順については、[installation FAQ](https://docs.dify.ai/v/japanese/learn-more/faq/install-faq) を確認してください。
-
-### 5. ブラウザで dify にアクセスする
-
-設定を確認するために、ブラウザで[http://localhost:3000](http://localhost:3000)(デフォルト、または自分で設定した URL とポート)にアクセスしてください。Dify が起動して実行中であることが確認できるはずです。
-
-## 開発中
-
-モデルプロバイダーを追加する場合は、[このガイド](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md)が役立ちます。
-
-Agent や Workflow にツールプロバイダーを追加する場合は、[このガイド](./api/core/tools/README.md)が役立ちます。
-
-Dify のバックエンドとフロントエンドの概要を簡単に説明します。
-
-### バックエンド
-
-Dify のバックエンドは[Flask](https://flask.palletsprojects.com/en/3.0.x/)を使って Python で書かれています。ORM には[SQLAlchemy](https://www.sqlalchemy.org/)を、タスクキューには[Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html)を使っています。認証ロジックは Flask-login 経由で行われます。
-
-```
-[api/]
-├── constants             // コードベース全体で使用される定数設定
-├── controllers           // APIルート定義とリクエスト処理ロジック
-├── core                  // アプリケーションの中核的な管理、モデル統合、およびツール
-├── docker                // Dockerおよびコンテナ関連の設定
-├── events                // イベントのハンドリングと処理
-├── extensions            // 第三者のフレームワーク/プラットフォームとの拡張
-├── fields                // シリアライゼーション/マーシャリング用のフィールド定義
-├── libs                  // 再利用可能なライブラリとヘルパー
-├── migrations            // データベースマイグレーションスクリプト
-├── models                // データベースモデルとスキーマ定義
-├── services              // ビジネスロジックの定義
-├── storage               // 秘密鍵の保存
-├── tasks                 // 非同期タスクとバックグラウンドジョブの処理
-└── tests                 // テスト関連のファイル
-```
-
-### フロントエンド
-
-このウェブサイトは、Typescriptベースの[Next.js](https://nextjs.org/)テンプレートを使ってブートストラップされ、[Tailwind CSS](https://tailwindcss.com/)を使ってスタイリングされています。国際化には[React-i18next](https://react.i18next.com/)を使用しています。
-
-```
-[web/]
-├── app                   // レイアウト、ページ、コンポーネント
-│   ├── (commonLayout)    // アプリ全体で共通のレイアウト
-│   ├── (shareLayout)     // トークン特有のセッションで共有されるレイアウト
-│   ├── activate          // アクティベートページ
-│   ├── components        // ページやレイアウトで共有されるコンポーネント
-│   ├── install           // インストールページ
-│   ├── signin            // サインインページ
-│   └── styles            // グローバルに共有されるスタイル
-├── assets                // 静的アセット
-├── bin                   // ビルドステップで実行されるスクリプト
-├── config                // 調整可能な設定とオプション
-├── context               // アプリの異なる部分で使用される共有コンテキスト
-├── dictionaries          // 言語別の翻訳ファイル
-├── docker                // コンテナ設定
-├── hooks                 // 再利用可能なフック
-├── i18n                  // 国際化設定
-├── models                // データモデルとAPIレスポンスの形状を記述
-├── public                // ファビコンなどのメタアセット
-├── service               // APIアクションの形状を指定
-├── test
-├── types                 // 関数のパラメータと戻り値の記述
-└── utils                 // 共有ユーティリティ関数
-```
-
-## PR を投稿する
-
-いよいよ、私たちのリポジトリにプルリクエスト (PR) を提出する時が来ました。主要な機能については、まず `deploy/dev` ブランチにマージしてテストしてから `main` ブランチにマージします。
-マージ競合などの問題が発生した場合、またはプル リクエストを開く方法がわからない場合は、[GitHub's pull request tutorial](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests) をチェックしてみてください。
-
-これで完了です！あなた様の PR がマージされると、[README](https://github.com/langgenius/dify/blob/main/README.md) にコントリビューターとして紹介されます。
-
-## ヘルプを得る
-
-コントリビュート中に行き詰まったり、疑問が生じたりした場合は、GitHub の関連する issue から質問していただくか、[Discord](https://discord.gg/8Tpq4AcN9c)でチャットしてください。

CONTRIBUTING_TW.md

@@ -1,153 +1,97 @@
-# 貢獻指南
+# 參與貢獻
 
-您想為 Dify 做出貢獻 - 這太棒了，我們迫不及待地想看看您的成果。作為一家人力和資金有限的初創公司，我們有宏大的抱負，希望設計出最直觀的工作流程來構建和管理 LLM 應用程式。來自社群的任何幫助都非常珍貴，真的。
+我們很高興你想要為 Dify 做出貢獻！作為一個資源有限的新創團隊，我們期望打造最直觀的 LLM 應用開發與管理工作流程。社群中的每一份貢獻對我們來說都非常重要。
 
-鑑於我們的現狀，我們需要靈活且快速地發展，但同時也希望確保像您這樣的貢獻者能夠獲得盡可能順暢的貢獻體驗。我們編寫了這份貢獻指南，目的是幫助您熟悉代碼庫以及我們如何與貢獻者合作，讓您可以更快地進入有趣的部分。
+作為一個快速發展的專案，我們需要保持敏捷並快速迭代，同時也希望能為貢獻者提供順暢的參與體驗。我們準備了這份貢獻指南，幫助你了解程式碼庫和我們與貢獻者合作的方式，讓你能夠盡快投入有趣的開發工作。
 
-這份指南，就像 Dify 本身一樣，是不斷發展的。如果有時它落後於實際項目，我們非常感謝您的理解，也歡迎任何改進的反饋。
+這份指南與 Dify 一樣，都在持續完善中。如果指南內容有落後於實際專案的情況，還請見諒，也歡迎提供改進建議。
 
-關於授權，請花一分鐘閱讀我們簡短的[授權和貢獻者協議](./LICENSE)。社群也遵守[行為準則](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
+關於授權部分，請花點時間閱讀我們簡短的[授權和貢獻者協議](./LICENSE)。社群也需遵守[行為準則](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md)。
 
-## 在開始之前
+## 開始之前
 
-[尋找](https://github.com/langgenius/dify/issues?q=is:issue+is:open)現有的 issue，或[創建](https://github.com/langgenius/dify/issues/new/choose)一個新的。我們將 issues 分為 2 種類型：
+想找點事做？瀏覽我們的[新手友善議題](https://github.com/langgenius/dify/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22good%20first%20issue%22)並挑選一個開始！
+
+有酷炫的模型執行時期或工具要新增？在我們的[外掛倉庫](https://github.com/langgenius/dify-plugins)開啟 PR 展示你的作品。
+
+需要更新現有的模型執行時期、工具或修復錯誤？前往我們的[官方外掛倉庫](https://github.com/langgenius/dify-official-plugins)開始你的魔法之旅！
+
+加入我們，一起貢獻並打造令人驚艷的作品吧！💡✨
+
+別忘了在 PR 描述中連結現有議題或開啟新議題。
+
+### 錯誤回報
+
+> [!IMPORTANT]  
+> 提交錯誤回報時，請務必包含以下資訊：
+
+- 清晰明確的標題
+- 詳細的錯誤描述，包含任何錯誤訊息
+- 重現錯誤的步驟
+- 預期行為
+- **日誌**，如果有的話。對後端問題來說這點很重要，你可以在 docker-compose logs 中找到
+- 截圖或影片（如適用）
+
+優先順序評估：
+
+  | 議題類型 | 優先級 |
+  | -------- | ------ |
+  | 核心功能錯誤（雲端服務、無法登入、應用程式無法運作、安全漏洞） | 緊急 |
+  | 非緊急錯誤、效能優化 | 中等 |
+  | 次要修正（拼字錯誤、介面混淆但可運作） | 低 |
 
 ### 功能請求
 
-- 如果您要開啟新的功能請求，我們希望您能解釋所提議的功能要達成什麼目標，並且盡可能包含更多的相關背景資訊。[@perzeusss](https://github.com/perzeuss) 已經製作了一個實用的[功能請求輔助工具](https://udify.app/chat/MK2kVSnw1gakVwMX)，能幫助您草擬您的需求。歡迎試用。
+> [!NOTE]  
+> 提交功能請求時，請務必包含以下資訊：
 
-- 如果您想從現有問題中選擇一個來處理，只需在其下方留言表示即可。
+- 清晰明確的標題
+- 詳細的功能描述
+- 功能的使用情境
+- 其他相關背景說明或截圖
 
-  相關方向的團隊成員會加入討論。如果一切順利，他們會同意您開始編寫代碼。我們要求您在得到許可前先不要開始處理該功能，以免我們提出變更時您的工作成果被浪費。
+優先順序評估：
 
-  根據所提議功能的領域不同，您可能會與不同的團隊成員討論。以下是目前每位團隊成員所負責的領域概述：
+  | 功能類型 | 優先級 |
+  | -------- | ------ |
+  | 團隊成員標記為高優先級的功能 | 高 |
+  | 來自[社群回饋板](https://github.com/langgenius/dify/discussions/categories/feedbacks)的熱門功能請求 | 中 |
+  | 非核心功能和小幅改進 | 低 |
+  | 有價值但非急迫的功能 | 未來功能 |
 
-  | 成員                                                                                    | 負責領域                       |
-  | --------------------------------------------------------------------------------------- | ------------------------------ |
-  | [@yeuoly](https://github.com/Yeuoly)                                                    | 設計 Agents 架構               |
-  | [@jyong](https://github.com/JohnJyong)                                                  | RAG 管道設計                   |
-  | [@GarfieldDai](https://github.com/GarfieldDai)                                          | 建構工作流程編排               |
-  | [@iamjoel](https://github.com/iamjoel) & [@zxhlyh](https://github.com/zxhlyh)           | 打造易用的前端界面             |
-  | [@guchenhe](https://github.com/guchenhe) & [@crazywoola](https://github.com/crazywoola) | 開發者體驗，各類問題的聯絡窗口 |
-  | [@takatost](https://github.com/takatost)                                                | 整體產品方向與架構             |
+## 提交 PR
 
-  我們如何排定優先順序：
+### PR 流程
 
-  | 功能類型                                                                                                | 優先級   |
-  | ------------------------------------------------------------------------------------------------------- | -------- |
-  | 被團隊成員標記為高優先級的功能                                                                          | 高優先級 |
-  | 來自我們[社群回饋版](https://github.com/langgenius/dify/discussions/categories/feedbacks)的熱門功能請求 | 中優先級 |
-  | 非核心功能和次要增強                                                                                    | 低優先級 |
-  | 有價值但非急迫的功能                                                                                    | 未來功能 |
+1. Fork 專案
+2. 在開始撰寫 PR 前，請先建立議題討論你想做的更改
+3. 為你的更改建立新分支
+4. 請為你的更改新增相應的測試
+5. 確保你的程式碼通過現有測試
+6. 請在 PR 描述中連結相關議題，使用 `fixes #<issue_number>`
+7. 等待合併！
 
-### 其他事項 (例如錯誤回報、效能優化、錯字更正)
+### 專案設定
 
-- 可以直接開始編寫程式碼。
+#### 前端
 
-  我們如何排定優先順序：
+關於前端服務的設定，請參考 `web/README.md` 中的完整[指南](https://github.com/langgenius/dify/blob/main/web/README.md)。此文件提供詳細說明，幫助你正確設定前端環境。
 
-  | 問題類型                                              | 優先級   |
-  | ----------------------------------------------------- | -------- |
-  | 核心功能的錯誤 (無法登入、應用程式無法運行、安全漏洞) | 重要     |
-  | 非關鍵性錯誤、效能提升                                | 中優先級 |
-  | 小修正 (錯字、令人困惑但仍可運作的使用者界面)         | 低優先級 |
+#### 後端
 
-## 安裝
+關於後端服務的設定，請參考 `api/README.md` 中的詳細[說明](https://github.com/langgenius/dify/blob/main/api/README.md)。此文件包含逐步指引，幫助你順利啟動後端服務。
 
-以下是設置 Dify 開發環境的步驟：
+#### 其他注意事項
 
-### 1. 分叉此存儲庫
+我們建議在開始設定前仔細閱讀此文件，因為它包含以下重要資訊：
+- 前置需求和相依性
+- 安裝步驟
+- 設定細節
+- 常見問題排解
 
-### 2. 複製代碼庫
+如果在設定過程中遇到任何問題，歡迎隨時詢問。
 
-從您的終端機複製分叉的代碼庫：
+## 尋求協助
 
-```shell
-git clone git@github.com:<github_username>/dify.git
-```
+如果你在貢獻過程中遇到困難或有急切的問題，可以透過相關的 GitHub 議題詢問，或加入我們的 [Discord](https://discord.gg/8Tpq4AcN9c) 進行即時交流。
 
-- [Docker](https://www.docker.com/)
-- [Docker Compose](https://docs.docker.com/compose/install/)
-- [Node.js v18.x (LTS)](http://nodejs.org)
-- [pnpm](https://pnpm.io/)
-- [Python](https://www.python.org/) version 3.11.x or 3.12.x
-
-### 4. 安裝
-
-Dify 由後端和前端組成。透過 `cd api/` 導航至後端目錄，然後按照[後端 README](api/README.md)進行安裝。在另一個終端機視窗中，透過 `cd web/` 導航至前端目錄，然後按照[前端 README](web/README.md)進行安裝。
-
-查閱[安裝常見問題](https://docs.dify.ai/learn-more/faq/install-faq)了解常見問題和故障排除步驟的列表。
-
-### 5. 在瀏覽器中訪問 Dify
-
-要驗證您的設置，請在瀏覽器中訪問 [http://localhost:3000](http://localhost:3000)（預設值，或您自行設定的 URL 和埠號）。現在您應該能看到 Dify 已啟動並運行。
-
-## 開發
-
-如果您要添加模型提供者，請參考[此指南](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md)。
-
-如果您要為 Agent 或工作流程添加工具提供者，請參考[此指南](./api/core/tools/README.md)。
-
-為了幫助您快速找到您的貢獻適合的位置，以下是 Dify 後端和前端的簡要註解大綱：
-
-### 後端
-
-Dify 的後端使用 Python 的 [Flask](https://flask.palletsprojects.com/en/3.0.x/) 框架編寫。它使用 [SQLAlchemy](https://www.sqlalchemy.org/) 作為 ORM 工具，使用 [Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html) 進行任務佇列處理。授權邏輯則透過 Flask-login 實現。
-
-```text
-[api/]
-├── constants             // 整個專案中使用的常數與設定值
-├── controllers           // API 路由定義與請求處理邏輯
-├── core                  // 核心應用服務、模型整合與工具實現
-├── docker                // Docker 容器化相關設定檔案
-├── events                // 事件處理與流程管理機制
-├── extensions            // 與第三方框架或平台的整合擴充功能
-├── fields                // 資料序列化與結構定義欄位
-├── libs                  // 可重複使用的共用程式庫與輔助工具
-├── migrations            // 資料庫結構變更與遷移腳本
-├── models                // 資料庫模型與資料結構定義
-├── services              // 核心業務邏輯與功能實現
-├── storage               // 私鑰與敏感資訊儲存機制
-├── tasks                 // 非同步任務與背景作業處理器
-└── tests
-```
-
-### 前端
-
-網站基於 [Next.js](https://nextjs.org/) 的 Typescript 樣板，並使用 [Tailwind CSS](https://tailwindcss.com/) 進行樣式設計。[React-i18next](https://react.i18next.com/) 用於國際化。
-
-```text
-[web/]
-├── app                   // 頁面佈局與介面元件
-│   ├── (commonLayout)    // 應用程式共用佈局結構
-│   ├── (shareLayout)     // Token 會話專用共享佈局
-│   ├── activate          // 帳號啟用頁面
-│   ├── components        // 頁面與佈局共用元件
-│   ├── install           // 系統安裝頁面
-│   ├── signin            // 使用者登入頁面
-│   └── styles            // 全域共用樣式定義
-├── assets                // 靜態資源檔案庫
-├── bin                   // 建構流程執行腳本
-├── config                // 系統可調整設定與選項
-├── context               // 應用程式狀態共享上下文
-├── dictionaries          // 多語系翻譯詞彙庫
-├── docker                // Docker 容器設定檔
-├── hooks                 // 可重複使用的 React Hooks
-├── i18n                  // 國際化與本地化設定
-├── models                // 資料結構與 API 回應模型
-├── public                // 靜態資源與網站圖標
-├── service               // API 操作介面定義
-├── test                  // 測試用例與測試框架
-├── types                 // TypeScript 型別定義
-└── utils                 // 共用輔助功能函式庫
-```
-
-## 提交您的 PR
-
-最後，是時候向我們的存儲庫開啟拉取請求（PR）了。對於主要功能，我們會先將它們合併到 `deploy/dev` 分支進行測試，然後才會進入 `main` 分支。如果您遇到合併衝突或不知道如何開啟拉取請求等問題，請查看 [GitHub 的拉取請求教學](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests)。
-
-就是這樣！一旦您的 PR 被合併，您將作為貢獻者出現在我們的 [README](https://github.com/langgenius/dify/blob/main/README.md) 中。
-
-## 獲取幫助
-
-如果您在貢獻過程中遇到困難或有迫切的問題，只需通過相關的 GitHub issue 向我們提問，或加入我們的 [Discord](https://discord.gg/8Tpq4AcN9c) 進行快速交流。

CONTRIBUTING_VI.md

@@ -1,156 +1,97 @@
-Thật tuyệt vời khi bạn muốn đóng góp cho Dify! Chúng tôi rất mong chờ được thấy những gì bạn sẽ làm. Là một startup với nguồn nhân lực và tài chính hạn chế, chúng tôi có tham vọng lớn là thiết kế quy trình trực quan nhất để xây dựng và quản lý các ứng dụng LLM. Mọi sự giúp đỡ từ cộng đồng đều rất quý giá đối với chúng tôi.
+# ĐÓNG GÓP
 
-Chúng tôi cần linh hoạt và làm việc nhanh chóng, nhưng đồng thời cũng muốn đảm bảo các cộng tác viên như bạn có trải nghiệm đóng góp thuận lợi nhất có thể. Chúng tôi đã tạo ra hướng dẫn đóng góp này nhằm giúp bạn làm quen với codebase và cách chúng tôi làm việc với các cộng tác viên, để bạn có thể nhanh chóng bắt tay vào phần thú vị.
+Bạn đang muốn đóng góp cho Dify - thật tuyệt vời, chúng tôi rất mong được thấy những gì bạn sẽ làm. Là một startup với nguồn nhân lực và tài chính hạn chế, chúng tôi có tham vọng lớn trong việc thiết kế quy trình trực quan nhất để xây dựng và quản lý các ứng dụng LLM. Mọi sự giúp đỡ từ cộng đồng đều rất có ý nghĩa.
 
-Hướng dẫn này, cũng như bản thân Dify, đang trong quá trình cải tiến liên tục. Chúng tôi rất cảm kích sự thông cảm của bạn nếu đôi khi nó không theo kịp dự án thực tế, và chúng tôi luôn hoan nghênh mọi phản hồi để cải thiện.
+Chúng tôi cần phải nhanh nhẹn và triển khai nhanh chóng, nhưng cũng muốn đảm bảo những người đóng góp như bạn có trải nghiệm đóng góp thuận lợi nhất có thể. Chúng tôi đã tạo hướng dẫn đóng góp này nhằm giúp bạn làm quen với codebase và cách chúng tôi làm việc với người đóng góp, để bạn có thể nhanh chóng bắt đầu phần thú vị.
 
-Về vấn đề cấp phép, xin vui lòng dành chút thời gian đọc qua [Thỏa thuận Cấp phép và Đóng góp](./LICENSE) ngắn gọn của chúng tôi. Cộng đồng cũng tuân thủ [quy tắc ứng xử](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
+Hướng dẫn này, giống như Dify, đang được phát triển liên tục. Chúng tôi rất cảm kích sự thông cảm của bạn nếu đôi khi nó chưa theo kịp dự án thực tế, và hoan nghênh mọi phản hồi để cải thiện.
+
+Về giấy phép, vui lòng dành chút thời gian đọc [Thỏa thuận Cấp phép và Người đóng góp](./LICENSE) ngắn gọn của chúng tôi. Cộng đồng cũng tuân theo [quy tắc ứng xử](https://github.com/langgenius/.github/blob/main/CODE_OF_CONDUCT.md).
 
 ## Trước khi bắt đầu
 
-[Tìm kiếm](https://github.com/langgenius/dify/issues?q=is:issue+is:open) một vấn đề hiện có, hoặc [tạo mới](https://github.com/langgenius/dify/issues/new/choose) một vấn đề. Chúng tôi phân loại các vấn đề thành 2 loại:
+Đang tìm việc để thực hiện? Hãy xem qua [các issue dành cho người mới](https://github.com/langgenius/dify/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22good%20first%20issue%22) và chọn một để bắt đầu!
 
-### Yêu cầu tính năng:
+Bạn có một model runtime hoặc công cụ mới thú vị để thêm vào? Mở PR trong [repo plugin](https://github.com/langgenius/dify-plugins) của chúng tôi và cho chúng tôi thấy những gì bạn đã xây dựng.
 
-* Nếu bạn đang tạo một yêu cầu tính năng mới, chúng tôi muốn bạn giải thích tính năng đề xuất sẽ đạt được điều gì và cung cấp càng nhiều thông tin chi tiết càng tốt. [@perzeusss](https://github.com/perzeuss) đã tạo một [Trợ lý Yêu cầu Tính năng](https://udify.app/chat/MK2kVSnw1gakVwMX) rất hữu ích để giúp bạn soạn thảo nhu cầu của mình. Hãy thử dùng nó nhé.
+Cần cập nhật model runtime, công cụ hiện có hoặc sửa lỗi? Ghé thăm [repo plugin chính thức](https://github.com/langgenius/dify-official-plugins) và thực hiện phép màu của bạn!
 
-* Nếu bạn muốn chọn một vấn đề từ danh sách hiện có, chỉ cần để lại bình luận dưới vấn đề đó nói rằng bạn sẽ làm.
+Hãy tham gia, đóng góp và cùng nhau xây dựng điều tuyệt vời! 💡✨
 
-  Một thành viên trong nhóm làm việc trong lĩnh vực liên quan sẽ được thông báo. Nếu mọi thứ ổn, họ sẽ cho phép bạn bắt đầu code. Chúng tôi yêu cầu bạn chờ đợi cho đến lúc đó trước khi bắt tay vào làm tính năng, để không lãng phí công sức của bạn nếu chúng tôi đề xuất thay đổi.
+Đừng quên liên kết đến issue hiện có hoặc mở issue mới trong mô tả PR.
 
-  Tùy thuộc vào lĩnh vực mà tính năng đề xuất thuộc về, bạn có thể nói chuyện với các thành viên khác nhau trong nhóm. Dưới đây là danh sách các lĩnh vực mà các thành viên trong nhóm chúng tôi đang làm việc hiện tại:
+### Báo cáo lỗi
 
-  | Thành viên                                                   | Phạm vi                                              |
-  | ------------------------------------------------------------ | ---------------------------------------------------- |
-  | [@yeuoly](https://github.com/Yeuoly)                         | Thiết kế kiến trúc Agents                            |
-  | [@jyong](https://github.com/JohnJyong)                       | Thiết kế quy trình RAG                               |
-  | [@GarfieldDai](https://github.com/GarfieldDai)               | Xây dựng quy trình làm việc                          |
-  | [@iamjoel](https://github.com/iamjoel) & [@zxhlyh](https://github.com/zxhlyh) | Làm cho giao diện người dùng dễ sử dụng              |
-  | [@guchenhe](https://github.com/guchenhe) & [@crazywoola](https://github.com/crazywoola) | Trải nghiệm nhà phát triển, đầu mối liên hệ cho mọi vấn đề |
-  | [@takatost](https://github.com/takatost)                     | Định hướng và kiến trúc tổng thể sản phẩm            |
+> [!QUAN TRỌNG]  
+> Vui lòng đảm bảo cung cấp các thông tin sau khi gửi báo cáo lỗi:
 
-  Cách chúng tôi ưu tiên:
+- Tiêu đề rõ ràng và mô tả
+- Mô tả chi tiết về lỗi, bao gồm các thông báo lỗi
+- Các bước để tái hiện lỗi
+- Hành vi mong đợi
+- **Log**, nếu có, cho các vấn đề backend, điều này rất quan trọng, bạn có thể tìm thấy chúng trong docker-compose logs
+- Ảnh chụp màn hình hoặc video, nếu có thể
 
-  | Loại tính năng                                               | Mức độ ưu tiên |
-  | ------------------------------------------------------------ | -------------- |
-  | Tính năng ưu tiên cao được gắn nhãn bởi thành viên trong nhóm | Ưu tiên cao    |
-  | Yêu cầu tính năng phổ biến từ [bảng phản hồi cộng đồng](https://github.com/langgenius/dify/discussions/categories/feedbacks) của chúng tôi | Ưu tiên trung bình |
-  | Tính năng không quan trọng và cải tiến nhỏ                   | Ưu tiên thấp   |
-  | Có giá trị nhưng không cấp bách                              | Tính năng tương lai |
+Cách chúng tôi ưu tiên:
 
-### Những vấn đề khác (ví dụ: báo cáo lỗi, tối ưu hiệu suất, sửa lỗi chính tả):
+  | Loại vấn đề | Mức độ ưu tiên |
+  | ----------- | -------------- |
+  | Lỗi trong các chức năng cốt lõi (dịch vụ đám mây, không thể đăng nhập, ứng dụng không hoạt động, lỗ hổng bảo mật) | Quan trọng |
+  | Lỗi không nghiêm trọng, cải thiện hiệu suất | Ưu tiên trung bình |
+  | Sửa lỗi nhỏ (lỗi chính tả, UI gây nhầm lẫn nhưng vẫn hoạt động) | Ưu tiên thấp |
 
-* Bắt đầu code ngay lập tức.
+### Yêu cầu tính năng
 
-  Cách chúng tôi ưu tiên:
+> [!LƯU Ý]
+> Vui lòng đảm bảo cung cấp các thông tin sau khi gửi yêu cầu tính năng:
 
-  | Loại vấn đề                                                  | Mức độ ưu tiên |
-  | ------------------------------------------------------------ | -------------- |
-  | Lỗi trong các chức năng chính (không thể đăng nhập, ứng dụng không hoạt động, lỗ hổng bảo mật) | Nghiêm trọng   |
-  | Lỗi không quan trọng, cải thiện hiệu suất                    | Ưu tiên trung bình |
-  | Sửa lỗi nhỏ (lỗi chính tả, giao diện người dùng gây nhầm lẫn nhưng vẫn hoạt động) | Ưu tiên thấp   |
+- Tiêu đề rõ ràng và mô tả
+- Mô tả chi tiết về tính năng
+- Trường hợp sử dụng cho tính năng
+- Bất kỳ ngữ cảnh hoặc ảnh chụp màn hình nào về yêu cầu tính năng
 
+Cách chúng tôi ưu tiên:
 
-## Cài đặt
-
-Dưới đây là các bước để thiết lập Dify cho việc phát triển:
-
-### 1. Fork repository này
-
-### 2. Clone repository
-
- Clone repository đã fork từ terminal của bạn:
-
-```
-git clone git@github.com:<tên_người_dùng_github>/dify.git
-```
-
-### 3. Kiểm tra các phụ thuộc
-
-Dify yêu cầu các phụ thuộc sau để build, hãy đảm bảo chúng đã được cài đặt trên hệ thống của bạn:
-
-- [Docker](https://www.docker.com/)
-- [Docker Compose](https://docs.docker.com/compose/install/)
-- [Node.js v18.x (LTS)](http://nodejs.org)
-- [pnpm](https://pnpm.io/)
-- [Python](https://www.python.org/) phiên bản 3.11.x hoặc 3.12.x
-
-### 4. Cài đặt
-
-Dify bao gồm một backend và một frontend. Đi đến thư mục backend bằng lệnh `cd api/`, sau đó làm theo hướng dẫn trong [README của Backend](api/README.md) để cài đặt. Trong một terminal khác, đi đến thư mục frontend bằng lệnh `cd web/`, sau đó làm theo hướng dẫn trong [README của Frontend](web/README.md) để cài đặt.
-
-Kiểm tra [FAQ về cài đặt](https://docs.dify.ai/learn-more/faq/install-faq) để xem danh sách các vấn đề thường gặp và các bước khắc phục.
-
-### 5. Truy cập Dify trong trình duyệt của bạn
-
-Để xác nhận cài đặt của bạn, hãy truy cập [http://localhost:3000](http://localhost:3000) (địa chỉ mặc định, hoặc URL và cổng bạn đã cấu hình) trong trình duyệt. Bạn sẽ thấy Dify đang chạy.
-
-## Phát triển
-
-Nếu bạn đang thêm một nhà cung cấp mô hình, [hướng dẫn này](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md) dành cho bạn.
-
-Nếu bạn đang thêm một nhà cung cấp công cụ cho Agent hoặc Workflow, [hướng dẫn này](./api/core/tools/README.md) dành cho bạn.
-
-Để giúp bạn nhanh chóng định hướng phần đóng góp của mình, dưới đây là một bản phác thảo ngắn gọn về cấu trúc backend & frontend của Dify:
-
-### Backend
-
-Backend của Dify được viết bằng Python sử dụng [Flask](https://flask.palletsprojects.com/en/3.0.x/). Nó sử dụng [SQLAlchemy](https://www.sqlalchemy.org/) cho ORM và [Celery](https://docs.celeryq.dev/en/stable/getting-started/introduction.html) cho hàng đợi tác vụ. Logic xác thực được thực hiện thông qua Flask-login.
-
-```
-[api/]
-├── constants             // Các cài đặt hằng số được sử dụng trong toàn bộ codebase.
-├── controllers           // Định nghĩa các route API và logic xử lý yêu cầu.           
-├── core                  // Điều phối ứng dụng cốt lõi, tích hợp mô hình và công cụ.
-├── docker                // Cấu hình liên quan đến Docker & containerization.
-├── events                // Xử lý và xử lý sự kiện
-├── extensions            // Mở rộng với các framework/nền tảng bên thứ 3.
-├── fields                // Định nghĩa trường cho serialization/marshalling.
-├── libs                  // Thư viện và tiện ích có thể tái sử dụng.
-├── migrations            // Script cho việc di chuyển cơ sở dữ liệu.
-├── models                // Mô hình cơ sở dữ liệu & định nghĩa schema.
-├── services              // Xác định logic nghiệp vụ.
-├── storage               // Lưu trữ khóa riêng tư.      
-├── tasks                 // Xử lý các tác vụ bất đồng bộ và công việc nền.
-└── tests
-```
-
-### Frontend
-
-Website được khởi tạo trên boilerplate [Next.js](https://nextjs.org/) bằng Typescript và sử dụng [Tailwind CSS](https://tailwindcss.com/) cho styling. [React-i18next](https://react.i18next.com/) được sử dụng cho việc quốc tế hóa.
-
-```
-[web/]
-├── app                   // layouts, pages và components
-│   ├── (commonLayout)    // layout chung được sử dụng trong toàn bộ ứng dụng
-│   ├── (shareLayout)     // layouts được chia sẻ cụ thể cho các phiên dựa trên token 
-│   ├── activate          // trang kích hoạt
-│   ├── components        // được chia sẻ bởi các trang và layouts
-│   ├── install           // trang cài đặt
-│   ├── signin            // trang đăng nhập
-│   └── styles            // styles được chia sẻ toàn cục
-├── assets                // Tài nguyên tĩnh
-├── bin                   // scripts chạy ở bước build
-├── config                // cài đặt và tùy chọn có thể điều chỉnh 
-├── context               // contexts được chia sẻ bởi các phần khác nhau của ứng dụng
-├── dictionaries          // File dịch cho từng ngôn ngữ 
-├── docker                // cấu hình container
-├── hooks                 // Hooks có thể tái sử dụng
-├── i18n                  // Cấu hình quốc tế hóa
-├── models                // mô tả các mô hình dữ liệu & hình dạng của phản hồi API
-├── public                // tài nguyên meta như favicon
-├── service               // xác định hình dạng của các hành động API
-├── test                  
-├── types                 // mô tả các tham số hàm và giá trị trả về
-└── utils                 // Các hàm tiện ích được chia sẻ
-```
+  | Loại tính năng | Mức độ ưu tiên |
+  | -------------- | -------------- |
+  | Tính năng ưu tiên cao được gắn nhãn bởi thành viên nhóm | Ưu tiên cao |
+  | Yêu cầu tính năng phổ biến từ [bảng phản hồi cộng đồng](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Ưu tiên trung bình |
+  | Tính năng không cốt lõi và cải tiến nhỏ | Ưu tiên thấp |
+  | Có giá trị nhưng không cấp bách | Tính năng tương lai |
 
 ## Gửi PR của bạn
 
-Cuối cùng, đã đến lúc mở một pull request (PR) đến repository của chúng tôi. Đối với các tính năng lớn, chúng tôi sẽ merge chúng vào nhánh `deploy/dev` để kiểm tra trước khi đưa vào nhánh `main`. Nếu bạn gặp vấn đề như xung đột merge hoặc không biết cách mở pull request, hãy xem [hướng dẫn về pull request của GitHub](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests).
+### Quy trình tạo Pull Request
 
-Và thế là xong! Khi PR của bạn được merge, bạn sẽ được giới thiệu là một người đóng góp trong [README](https://github.com/langgenius/dify/blob/main/README.md) của chúng tôi.
+1. Fork repository
+2. Trước khi soạn PR, vui lòng tạo issue để thảo luận về các thay đổi bạn muốn thực hiện
+3. Tạo nhánh mới cho các thay đổi của bạn
+4. Vui lòng thêm test cho các thay đổi tương ứng
+5. Đảm bảo code của bạn vượt qua các test hiện có
+6. Vui lòng liên kết issue trong mô tả PR, `fixes #<số_issue>`
+7. Được merge!
+
+### Thiết lập dự án
+
+#### Frontend
+
+Để thiết lập dịch vụ frontend, vui lòng tham khảo [hướng dẫn](https://github.com/langgenius/dify/blob/main/web/README.md) chi tiết của chúng tôi trong file `web/README.md`. Tài liệu này cung cấp hướng dẫn chi tiết để giúp bạn thiết lập môi trường frontend một cách đúng đắn.
+
+#### Backend
+
+Để thiết lập dịch vụ backend, vui lòng tham khảo [hướng dẫn](https://github.com/langgenius/dify/blob/main/api/README.md) chi tiết của chúng tôi trong file `api/README.md`. Tài liệu này chứa hướng dẫn từng bước để giúp bạn khởi chạy backend một cách suôn sẻ.
+
+#### Các điểm cần lưu ý khác
+
+Chúng tôi khuyến nghị xem xét kỹ tài liệu này trước khi tiến hành thiết lập, vì nó chứa thông tin thiết yếu về:
+- Điều kiện tiên quyết và dependencies
+- Các bước cài đặt
+- Chi tiết cấu hình
+- Các mẹo xử lý sự cố phổ biến
+
+Đừng ngần ngại liên hệ nếu bạn gặp bất kỳ vấn đề nào trong quá trình thiết lập.
 
 ## Nhận trợ giúp
 
-Nếu bạn gặp khó khăn hoặc có câu hỏi cấp bách trong quá trình đóng góp, hãy đặt câu hỏi của bạn trong vấn đề GitHub liên quan, hoặc tham gia [Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi để trò chuyện nhanh chóng.
+Nếu bạn bị mắc kẹt hoặc có câu hỏi cấp bách trong quá trình đóng góp, chỉ cần gửi câu hỏi của bạn thông qua issue GitHub liên quan, hoặc tham gia [Discord](https://discord.gg/8Tpq4AcN9c) của chúng tôi để trò chuyện nhanh.
+

README.md

@@ -204,7 +204,9 @@ If you'd like to configure a highly-available setup, there are community-contrib
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Using Terraform for Deployment
 

README_AR.md

@@ -187,7 +187,9 @@ docker compose up -d
 
 - [رسم بياني Helm من قبل @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [رسم بياني Helm من قبل @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [رسم بياني Helm من قبل @magicsong](https://github.com/magicsong/ai-charts)
 - [ملف YAML من قبل @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [ملف YAML من قبل @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### استخدام Terraform للتوزيع
 

README_BN.md

@@ -203,7 +203,9 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### টেরাফর্ম ব্যবহার করে ডিপ্লয়
 

README_CN.md

@@ -79,7 +79,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
   广泛的 RAG 功能，涵盖从文档摄入到检索的所有内容，支持从 PDF、PPT 和其他常见文档格式中提取文本的开箱即用的支持。
 
 **5. Agent 智能体**: 
-  您可以基于 LLM 函数调用或 ReAct 定义 Agent，并为 Agent 添加预构建或自定义工具。Dify 为 AI Agent 提供了50多种内置工具，如谷歌搜索、DALL·E、Stable Diffusion 和 WolframAlpha 等。
+  您可以基于 LLM 函数调用或 ReAct 定义 Agent，并为 Agent 添加预构建或自定义工具。Dify 为 AI Agent 提供了 50 多种内置工具，如谷歌搜索、DALL·E、Stable Diffusion 和 WolframAlpha 等。
 
 **6. LLMOps**: 
   随时间监视和分析应用程序日志和性能。您可以根据生产数据和标注持续改进提示、数据集和模型。
@@ -112,7 +112,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
     <td align="center">仅限 OpenAI</td>
   </tr>
   <tr>
-    <td align="center">RAG引擎</td>
+    <td align="center">RAG 引擎</td>
     <td align="center">✅</td>
     <td align="center">✅</td>
     <td align="center">✅</td>
@@ -205,7 +205,9 @@ docker compose up -d
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML 文件 by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### 使用 Terraform 部署
 
@@ -234,7 +236,7 @@ docker compose up -d
 对于那些想要贡献代码的人，请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
 同时，请考虑通过社交媒体、活动和会议来支持 Dify 的分享。
 
-> 我们正在寻找贡献者来帮助将Dify翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助，请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)获取更多信息，并在我们的[Discord社区服务器](https://discord.gg/8Tpq4AcN9c)的`global-users`频道中留言。
+> 我们正在寻找贡献者来帮助将 Dify 翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助，请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)获取更多信息，并在我们的[Discord 社区服务器](https://discord.gg/8Tpq4AcN9c)的`global-users`频道中留言。
 
 **Contributors**
 

README_DE.md

@@ -205,7 +205,9 @@ Falls Sie eine hochverfügbare Konfiguration einrichten möchten, gibt es von de
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Terraform für die Bereitstellung verwenden
 

README_ES.md

@@ -77,9 +77,7 @@ Dify es una plataforma de desarrollo de aplicaciones de LLM de código abierto.
   Amplias capacidades de RAG que cubren todo, desde la ingestión de documentos hasta la recuperación, con soporte listo para usar para la extracción de texto de PDF, PPT y otros formatos de documento comunes.
 
 **5. Capacidades de agente**: 
-  Puedes definir agent
-
-es basados en LLM Function Calling o ReAct, y agregar herramientas preconstruidas o personalizadas para el agente. Dify proporciona más de 50 herramientas integradas para agentes de IA, como Búsqueda de Google, DALL·E, Difusión Estable y WolframAlpha.
+  Puedes definir agentes basados en LLM Function Calling o ReAct, y agregar herramientas preconstruidas o personalizadas para el agente. Dify proporciona más de 50 herramientas integradas para agentes de IA, como Búsqueda de Google, DALL·E, Difusión Estable y WolframAlpha.
 
 **6. LLMOps**: 
   Supervisa y analiza registros de aplicaciones y rendimiento a lo largo del tiempo. Podrías mejorar continuamente prompts, conjuntos de datos y modelos basados en datos de producción y anotaciones.
@@ -207,7 +205,9 @@ Si desea configurar una configuración de alta disponibilidad, la comunidad prop
 
 - [Gráfico Helm por @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Gráfico Helm por @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Gráfico Helm por @magicsong](https://github.com/magicsong/ai-charts)
 - [Ficheros YAML por @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [Ficheros YAML por @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Uso de Terraform para el despliegue
 

README_FR.md

@@ -203,7 +203,9 @@ Si vous souhaitez configurer une configuration haute disponibilité, la communau
 
 - [Helm Chart par @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart par @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart par @magicsong](https://github.com/magicsong/ai-charts)
 - [Fichier YAML par @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [Fichier YAML par @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Utilisation de Terraform pour le déploiement
 

README_JA.md

@@ -204,7 +204,9 @@ docker compose up -d
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Terraformを使用したデプロイ
 

README_KL.md

@@ -203,7 +203,9 @@ If you'd like to configure a highly-available setup, there are community-contrib
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Terraform atorlugu pilersitsineq
 

README_KR.md

@@ -197,7 +197,9 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Helm Chart by @magicsong](https://github.com/magicsong/ai-charts)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Terraform을 사용한 배포
 

README_PT.md

@@ -203,7 +203,9 @@ Se deseja configurar uma instalação de alta disponibilidade, há [Helm Charts]
 
 - [Helm Chart de @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart de @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
-- [Arquivo YAML de @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [Helm Chart de @magicsong](https://github.com/magicsong/ai-charts)
+- [Arquivo YAML por @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [Arquivo YAML por @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Usando o Terraform para Implantação
 

README_SI.md

@@ -205,6 +205,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 - [YAML file by @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [YAML file by @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Uporaba Terraform za uvajanje
 

README_TR.md

@@ -198,6 +198,7 @@ Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify'
 - [@LeoQuote tarafından Helm Chart](https://github.com/douban/charts/tree/master/charts/dify)
 - [@BorisPolonsky tarafından Helm Chart](https://github.com/BorisPolonsky/dify-helm)
 - [@Winson-030 tarafından YAML dosyası](https://github.com/Winson-030/dify-kubernetes)
+- [@wyy-holding tarafından YAML dosyası](https://github.com/wyy-holding/dify-k8s)
 
 #### Dağıtım için Terraform Kullanımı
 

README_TW.md

@@ -204,6 +204,7 @@ Dify 的所有功能都提供相應的 API，因此您可以輕鬆地將 Dify
 - [由 @LeoQuote 提供的 Helm Chart](https://github.com/douban/charts/tree/master/charts/dify)
 - [由 @BorisPolonsky 提供的 Helm Chart](https://github.com/BorisPolonsky/dify-helm)
 - [由 @Winson-030 提供的 YAML 文件](https://github.com/Winson-030/dify-kubernetes)
+- [由 @wyy-holding 提供的 YAML 文件](https://github.com/wyy-holding/dify-k8s)
 
 ### 使用 Terraform 進行部署
 

README_VI.md

@@ -200,6 +200,7 @@ Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có
 - [Helm Chart bởi @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart bởi @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 - [Tệp YAML bởi @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+- [Tệp YAML bởi @wyy-holding](https://github.com/wyy-holding/dify-k8s)
 
 #### Sử dụng Terraform để Triển khai
 

api/.env.example

@@ -137,7 +137,7 @@ WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
 # Vector database configuration
-# support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase
+# support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase, opengauss
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -298,6 +298,14 @@ OCEANBASE_VECTOR_PASSWORD=difyai123456
 OCEANBASE_VECTOR_DATABASE=test
 OCEANBASE_MEMORY_LIMIT=6G
 
+# openGauss configuration
+OPENGAUSS_HOST=127.0.0.1
+OPENGAUSS_PORT=6600
+OPENGAUSS_USER=postgres
+OPENGAUSS_PASSWORD=Dify@123
+OPENGAUSS_DATABASE=dify
+OPENGAUSS_MIN_CONNECTION=1
+OPENGAUSS_MAX_CONNECTION=5
 
 # Upload configuration
 UPLOAD_FILE_SIZE_LIMIT=15
@@ -378,6 +386,7 @@ HTTP_REQUEST_MAX_READ_TIMEOUT=600
 HTTP_REQUEST_MAX_WRITE_TIMEOUT=600
 HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
 HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
+HTTP_REQUEST_NODE_SSL_VERIFY=True
 
 # Respect X-* headers to redirect clients
 RESPECT_XFORWARD_HEADERS_ENABLED=false
@@ -444,4 +453,4 @@ CREATE_TIDB_SERVICE_JOB_ENABLED=false
 # Maximum number of submitted thread count in a ThreadPool for parallel node execution
 MAX_SUBMIT_COUNT=100
 # Lockout duration in seconds
-LOGIN_LOCKOUT_DURATION=86400
+LOGIN_LOCKOUT_DURATION=86400

api/Dockerfile

@@ -56,8 +56,6 @@ RUN \
         curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
         # For Security
         expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
-        # install a chinese font to support the use of tools like matplotlib
-        fonts-noto-cjk \
         # install a package to improve the accuracy of guessing mime type and file extension
         media-types \
         # install libmagic to support the use of python-magic guess MIMETYPE

api/commands.py

@@ -12,6 +12,7 @@ from configs import dify_config
 from constants.languages import languages
 from core.rag.datasource.vdb.vector_factory import Vector
 from core.rag.datasource.vdb.vector_type import VectorType
+from core.rag.index_processor.constant.built_in_field import BuiltInField
 from core.rag.models.document import Document
 from events.app_event import app_was_created
 from extensions.ext_database import db
@@ -20,7 +21,7 @@ from libs.helper import email as email_validate
 from libs.password import hash_password, password_pattern, valid_password
 from libs.rsa import generate_key_pair
 from models import Tenant
-from models.dataset import Dataset, DatasetCollectionBinding, DocumentSegment
+from models.dataset import Dataset, DatasetCollectionBinding, DatasetMetadata, DatasetMetadataBinding, DocumentSegment
 from models.dataset import Document as DatasetDocument
 from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
 from models.provider import Provider, ProviderModel
@@ -160,11 +161,17 @@ def migrate_annotation_vector_database():
     while True:
         try:
             # get apps info
+            per_page = 50
             apps = (
-                App.query.filter(App.status == "normal")
+                db.session.query(App)
+                .filter(App.status == "normal")
                 .order_by(App.created_at.desc())
-                .paginate(page=page, per_page=50)
+                .limit(per_page)
+                .offset((page - 1) * per_page)
+                .all()
             )
+            if not apps:
+                break
         except NotFound:
             break
 
@@ -267,6 +274,7 @@ def migrate_knowledge_vector_database():
         VectorType.WEAVIATE,
         VectorType.ORACLE,
         VectorType.ELASTICSEARCH,
+        VectorType.OPENGAUSS,
     }
     lower_collection_vector_types = {
         VectorType.ANALYTICDB,
@@ -476,14 +484,11 @@ def convert_to_agent_apps():
     click.echo(click.style("Conversion complete. Converted {} agent apps.".format(len(proceeded_app_ids)), fg="green"))
 
 
-@click.command("add-qdrant-doc-id-index", help="Add Qdrant doc_id index.")
+@click.command("add-qdrant-index", help="Add Qdrant index.")
 @click.option("--field", default="metadata.doc_id", prompt=False, help="Index field , default is metadata.doc_id.")
-def add_qdrant_doc_id_index(field: str):
-    click.echo(click.style("Starting Qdrant doc_id index creation.", fg="green"))
-    vector_type = dify_config.VECTOR_STORE
-    if vector_type != "qdrant":
-        click.echo(click.style("This command only supports Qdrant vector store.", fg="red"))
-        return
+def add_qdrant_index(field: str):
+    click.echo(click.style("Starting Qdrant index creation.", fg="green"))
+
     create_count = 0
 
     try:
@@ -532,6 +537,76 @@ def add_qdrant_doc_id_index(field: str):
     click.echo(click.style(f"Index creation complete. Created {create_count} collection indexes.", fg="green"))
 
 
+@click.command("old-metadata-migration", help="Old metadata migration.")
+def old_metadata_migration():
+    """
+    Old metadata migration.
+    """
+    click.echo(click.style("Starting old metadata migration.", fg="green"))
+
+    page = 1
+    while True:
+        try:
+            documents = (
+                DatasetDocument.query.filter(DatasetDocument.doc_metadata is not None)
+                .order_by(DatasetDocument.created_at.desc())
+                .paginate(page=page, per_page=50)
+            )
+        except NotFound:
+            break
+        if not documents:
+            break
+        for document in documents:
+            if document.doc_metadata:
+                doc_metadata = document.doc_metadata
+                for key, value in doc_metadata.items():
+                    for field in BuiltInField:
+                        if field.value == key:
+                            break
+                    else:
+                        dataset_metadata = (
+                            db.session.query(DatasetMetadata)
+                            .filter(DatasetMetadata.dataset_id == document.dataset_id, DatasetMetadata.name == key)
+                            .first()
+                        )
+                        if not dataset_metadata:
+                            dataset_metadata = DatasetMetadata(
+                                tenant_id=document.tenant_id,
+                                dataset_id=document.dataset_id,
+                                name=key,
+                                type="string",
+                                created_by=document.created_by,
+                            )
+                            db.session.add(dataset_metadata)
+                            db.session.flush()
+                            dataset_metadata_binding = DatasetMetadataBinding(
+                                tenant_id=document.tenant_id,
+                                dataset_id=document.dataset_id,
+                                metadata_id=dataset_metadata.id,
+                                document_id=document.id,
+                                created_by=document.created_by,
+                            )
+                            db.session.add(dataset_metadata_binding)
+                        else:
+                            dataset_metadata_binding = DatasetMetadataBinding.query.filter(
+                                DatasetMetadataBinding.dataset_id == document.dataset_id,
+                                DatasetMetadataBinding.document_id == document.id,
+                                DatasetMetadataBinding.metadata_id == dataset_metadata.id,
+                            ).first()
+                            if not dataset_metadata_binding:
+                                dataset_metadata_binding = DatasetMetadataBinding(
+                                    tenant_id=document.tenant_id,
+                                    dataset_id=document.dataset_id,
+                                    metadata_id=dataset_metadata.id,
+                                    document_id=document.id,
+                                    created_by=document.created_by,
+                                )
+                                db.session.add(dataset_metadata_binding)
+                        db.session.commit()
+        page += 1
+    click.echo(click.style("Old metadata migration completed.", fg="green"))
+
+
 @click.command("create-tenant", help="Create account and tenant.")
 @click.option("--email", prompt=True, help="Tenant account email.")
 @click.option("--name", prompt=True, help="Workspace name.")

api/configs/feature/__init__.py

@@ -61,6 +61,10 @@ class AppExecutionConfig(BaseSettings):
         description="Maximum number of concurrent active requests per app (0 for unlimited)",
         default=0,
     )
+    APP_DAILY_RATE_LIMIT: NonNegativeInt = Field(
+        description="Maximum number of requests per app per day",
+        default=5000,
+    )
 
 
 class CodeExecutionSandboxConfig(BaseSettings):
@@ -332,6 +336,11 @@ class HttpConfig(BaseSettings):
         default=1 * 1024 * 1024,
     )
 
+    HTTP_REQUEST_NODE_SSL_VERIFY: bool = Field(
+        description="Enable or disable SSL verification for HTTP requests",
+        default=True,
+    )
+
     SSRF_DEFAULT_MAX_RETRIES: PositiveInt = Field(
         description="Maximum number of retries for network requests (SSRF)",
         default=3,

api/configs/middleware/__init__.py

@@ -26,6 +26,7 @@ from .vdb.lindorm_config import LindormConfig
 from .vdb.milvus_config import MilvusConfig
 from .vdb.myscale_config import MyScaleConfig
 from .vdb.oceanbase_config import OceanBaseVectorConfig
+from .vdb.opengauss_config import OpenGaussConfig
 from .vdb.opensearch_config import OpenSearchConfig
 from .vdb.oracle_config import OracleConfig
 from .vdb.pgvector_config import PGVectorConfig
@@ -281,5 +282,6 @@ class MiddlewareConfig(
     LindormConfig,
     OceanBaseVectorConfig,
     BaiduVectorDBConfig,
+    OpenGaussConfig,
 ):
     pass

api/configs/middleware/vdb/opengauss_config.py

@@ -0,0 +1,45 @@
+from typing import Optional
+
+from pydantic import Field, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class OpenGaussConfig(BaseSettings):
+    """
+    Configuration settings for OpenGauss
+    """
+
+    OPENGAUSS_HOST: Optional[str] = Field(
+        description="Hostname or IP address of the OpenGauss server(e.g., 'localhost')",
+        default=None,
+    )
+
+    OPENGAUSS_PORT: PositiveInt = Field(
+        description="Port number on which the OpenGauss server is listening (default is 6600)",
+        default=6600,
+    )
+
+    OPENGAUSS_USER: Optional[str] = Field(
+        description="Username for authenticating with the OpenGauss database",
+        default=None,
+    )
+
+    OPENGAUSS_PASSWORD: Optional[str] = Field(
+        description="Password for authenticating with the OpenGauss database",
+        default=None,
+    )
+
+    OPENGAUSS_DATABASE: Optional[str] = Field(
+        description="Name of the OpenGauss database to connect to",
+        default=None,
+    )
+
+    OPENGAUSS_MIN_CONNECTION: PositiveInt = Field(
+        description="Min connection of the OpenGauss database",
+        default=1,
+    )
+
+    OPENGAUSS_MAX_CONNECTION: PositiveInt = Field(
+        description="Max connection of the OpenGauss database",
+        default=5,
+    )

api/configs/middleware/vdb/pgvector_config.py

@@ -43,3 +43,8 @@ class PGVectorConfig(BaseSettings):
         description="Max connection of the PostgreSQL database",
         default=5,
     )
+
+    PGVECTOR_PG_BIGM: bool = Field(
+        description="Whether to use pg_bigm module for full text search",
+        default=False,
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="1.0.1",
+        default="1.1.1",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/console/__init__.py

@@ -81,6 +81,7 @@ from .datasets import (
     datasets_segments,
     external,
     hit_testing,
+    metadata,
     website,
 )
 

api/controllers/console/app/app.py

@@ -316,7 +316,7 @@ class AppTraceApi(Resource):
     @account_initialization_required
     def post(self, app_id):
         # add app trace
-        if not current_user.is_editing_role:
+        if not current_user.is_editor:
             raise Forbidden()
         parser = reqparse.RequestParser()
         parser.add_argument("enabled", type=bool, required=True, location="json")

api/controllers/console/app/workflow.py

@@ -10,9 +10,14 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 import services
 from configs import dify_config
 from controllers.console import api
-from controllers.console.app.error import ConversationCompletedError, DraftWorkflowNotExist, DraftWorkflowNotSync
+from controllers.console.app.error import (
+    ConversationCompletedError,
+    DraftWorkflowNotExist,
+    DraftWorkflowNotSync,
+)
 from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import account_initialization_required, setup_required
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
@@ -27,6 +32,7 @@ from models.account import Account
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
 from services.errors.app import WorkflowHashNotEqualError
+from services.errors.llm import InvokeRateLimitError
 from services.workflow_service import DraftWorkflowDeletionError, WorkflowInUseError, WorkflowService
 
 logger = logging.getLogger(__name__)
@@ -168,6 +174,8 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
             raise NotFound("Conversation Not Exists.")
         except services.errors.conversation.ConversationCompletedError:
             raise ConversationCompletedError()
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except ValueError as e:
             raise e
         except Exception:
@@ -344,15 +352,18 @@ class DraftWorkflowRunApi(Resource):
         parser.add_argument("files", type=list, required=False, location="json")
         args = parser.parse_args()
 
-        response = AppGenerateService.generate(
-            app_model=app_model,
-            user=current_user,
-            args=args,
-            invoke_from=InvokeFrom.DEBUGGER,
-            streaming=True,
-        )
+        try:
+            response = AppGenerateService.generate(
+                app_model=app_model,
+                user=current_user,
+                args=args,
+                invoke_from=InvokeFrom.DEBUGGER,
+                streaming=True,
+            )
 
-        return helper.compact_generate_response(response)
+            return helper.compact_generate_response(response)
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
 
 
 class WorkflowTaskStopApi(Resource):

api/controllers/console/datasets/datasets.py

@@ -79,7 +79,7 @@ class DatasetListApi(Resource):
         data = marshal(datasets, dataset_detail_fields)
         for item in data:
             # convert embedding_model_provider to plugin standard format
-            if item["indexing_technique"] == "high_quality":
+            if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
                 item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"]))
                 item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
                 if item_model in model_names:
@@ -184,6 +184,10 @@ class DatasetApi(Resource):
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
         data = marshal(dataset, dataset_detail_fields)
+        if dataset.indexing_technique == "high_quality":
+            if dataset.embedding_model_provider:
+                provider_id = ModelProviderID(dataset.embedding_model_provider)
+                data["embedding_model_provider"] = str(provider_id)
         if data.get("permission") == "partial_members":
             part_users_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
             data.update({"partial_member_list": part_users_list})
@@ -659,6 +663,7 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.LINDORM
                 | VectorType.COUCHBASE
                 | VectorType.MILVUS
+                | VectorType.OPENGAUSS
             ):
                 return {
                     "retrieval_method": [
@@ -702,6 +707,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.COUCHBASE
                 | VectorType.PGVECTOR
                 | VectorType.LINDORM
+                | VectorType.OPENGAUSS
             ):
                 return {
                     "retrieval_method": [

api/controllers/console/datasets/datasets_document.py

@@ -325,8 +325,8 @@ class DatasetInitApi(Resource):
     @cloud_edition_billing_resource_check("vector_space")
     @cloud_edition_billing_rate_limit_check("knowledge")
     def post(self):
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
 
         parser = reqparse.RequestParser()
@@ -621,7 +621,7 @@ class DocumentDetailApi(DocumentResource):
             raise InvalidMetadataError(f"Invalid metadata value: {metadata}")
 
         if metadata == "only":
-            response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata}
+            response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details}
         elif metadata == "without":
             dataset_process_rules = DatasetService.get_process_rules(dataset_id)
             document_process_rules = document.dataset_process_rule.to_dict()
@@ -682,7 +682,7 @@ class DocumentDetailApi(DocumentResource):
                 "disabled_by": document.disabled_by,
                 "archived": document.archived,
                 "doc_type": document.doc_type,
-                "doc_metadata": document.doc_metadata,
+                "doc_metadata": document.doc_metadata_details,
                 "segment_count": document.segment_count,
                 "average_segment_length": document.average_segment_length,
                 "hit_count": document.hit_count,
@@ -704,8 +704,8 @@ class DocumentProcessingApi(DocumentResource):
         document_id = str(document_id)
         document = self.get_document(dataset_id, document_id)
 
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
 
         if action == "pause":
@@ -769,8 +769,8 @@ class DocumentMetadataApi(DocumentResource):
         doc_type = req_data.get("doc_type")
         doc_metadata = req_data.get("doc_metadata")
 
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
 
         if doc_type is None or doc_metadata is None:

api/controllers/console/datasets/datasets_segments.py

@@ -123,8 +123,8 @@ class DatasetDocumentSegmentListApi(Resource):
             raise NotFound("Document not found.")
         segment_ids = request.args.getlist("segment_id")
 
-        # The role of the current user in the ta table must be admin or owner
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         try:
             DatasetService.check_dataset_permission(dataset, current_user)
@@ -151,8 +151,8 @@ class DatasetDocumentSegmentApi(Resource):
             raise NotFound("Document not found.")
         # check user's model setting
         DatasetService.check_dataset_model_setting(dataset)
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
 
         try:
@@ -206,7 +206,7 @@ class DatasetDocumentSegmentAddApi(Resource):
         document = DocumentService.get_document(dataset_id, document_id)
         if not document:
             raise NotFound("Document not found.")
-        if not current_user.is_editor:
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         # check embedding model setting
         if dataset.indexing_technique == "high_quality":
@@ -281,8 +281,8 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         ).first()
         if not segment:
             raise NotFound("Segment not found.")
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         try:
             DatasetService.check_dataset_permission(dataset, current_user)
@@ -325,8 +325,8 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         ).first()
         if not segment:
             raise NotFound("Segment not found.")
-        # The role of the current user in the ta table must be admin or owner
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         try:
             DatasetService.check_dataset_permission(dataset, current_user)
@@ -428,7 +428,7 @@ class ChildChunkAddApi(Resource):
         ).first()
         if not segment:
             raise NotFound("Segment not found.")
-        if not current_user.is_editor:
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         # check embedding model setting
         if dataset.indexing_technique == "high_quality":
@@ -528,8 +528,8 @@ class ChildChunkAddApi(Resource):
         ).first()
         if not segment:
             raise NotFound("Segment not found.")
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         try:
             DatasetService.check_dataset_permission(dataset, current_user)
@@ -579,8 +579,8 @@ class ChildChunkUpdateApi(Resource):
         ).first()
         if not child_chunk:
             raise NotFound("Child chunk not found.")
-        # The role of the current user in the ta table must be admin or owner
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         try:
             DatasetService.check_dataset_permission(dataset, current_user)
@@ -624,8 +624,8 @@ class ChildChunkUpdateApi(Resource):
         ).first()
         if not child_chunk:
             raise NotFound("Child chunk not found.")
-        # The role of the current user in the ta table must be admin or owner
-        if not current_user.is_editor:
+        # The role of the current user in the ta table must be admin, owner, dataset_operator, or editor
+        if not current_user.is_dataset_editor:
             raise Forbidden()
         try:
             DatasetService.check_dataset_permission(dataset, current_user)

api/controllers/console/datasets/metadata.py

@@ -0,0 +1,155 @@
+from flask_login import current_user  # type: ignore  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from werkzeug.exceptions import NotFound
+
+from controllers.console import api
+from controllers.console.wraps import account_initialization_required, enterprise_license_required, setup_required
+from fields.dataset_fields import dataset_metadata_fields
+from libs.login import login_required
+from services.dataset_service import DatasetService
+from services.entities.knowledge_entities.knowledge_entities import (
+    MetadataArgs,
+    MetadataOperationData,
+)
+from services.metadata_service import MetadataService
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 40:
+        raise ValueError("Name must be between 1 to 40 characters.")
+    return name
+
+
+def _validate_description_length(description):
+    if len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description
+
+
+class DatasetMetadataCreateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    @marshal_with(dataset_metadata_fields)
+    def post(self, dataset_id):
+        parser = reqparse.RequestParser()
+        parser.add_argument("type", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        args = parser.parse_args()
+        metadata_args = MetadataArgs(**args)
+
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        metadata = MetadataService.create_metadata(dataset_id_str, metadata_args)
+        return metadata, 201
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        return MetadataService.get_dataset_metadatas(dataset), 200
+
+
+class DatasetMetadataApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    @marshal_with(dataset_metadata_fields)
+    def patch(self, dataset_id, metadata_id):
+        parser = reqparse.RequestParser()
+        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        args = parser.parse_args()
+
+        dataset_id_str = str(dataset_id)
+        metadata_id_str = str(metadata_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args.get("name"))
+        return metadata, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def delete(self, dataset_id, metadata_id):
+        dataset_id_str = str(dataset_id)
+        metadata_id_str = str(metadata_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        MetadataService.delete_metadata(dataset_id_str, metadata_id_str)
+        return 200
+
+
+class DatasetMetadataBuiltInFieldApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def get(self):
+        built_in_fields = MetadataService.get_built_in_fields()
+        return {"fields": built_in_fields}, 200
+
+
+class DatasetMetadataBuiltInFieldActionApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def post(self, dataset_id, action):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        if action == "enable":
+            MetadataService.enable_built_in_field(dataset)
+        elif action == "disable":
+            MetadataService.disable_built_in_field(dataset)
+        return 200
+
+
+class DocumentMetadataEditApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @enterprise_license_required
+    def post(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("operation_data", type=list, required=True, nullable=True, location="json")
+        args = parser.parse_args()
+        metadata_args = MetadataOperationData(**args)
+
+        MetadataService.update_documents_metadata(dataset, metadata_args)
+
+        return 200
+
+
+api.add_resource(DatasetMetadataCreateApi, "/datasets/<uuid:dataset_id>/metadata")
+api.add_resource(DatasetMetadataApi, "/datasets/<uuid:dataset_id>/metadata/<uuid:metadata_id>")
+api.add_resource(DatasetMetadataBuiltInFieldApi, "/datasets/metadata/built-in")
+api.add_resource(DatasetMetadataBuiltInFieldActionApi, "/datasets/<uuid:dataset_id>/metadata/built-in/<string:action>")
+api.add_resource(DocumentMetadataEditApi, "/datasets/<uuid:dataset_id>/documents/metadata")

api/controllers/console/explore/completion.py

@@ -16,6 +16,7 @@ from controllers.console.app.error import (
 )
 from controllers.console.explore.error import NotChatAppError, NotCompletionAppError
 from controllers.console.explore.wraps import InstalledAppResource
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
@@ -29,6 +30,7 @@ from libs import helper
 from libs.helper import uuid_value
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
+from services.errors.llm import InvokeRateLimitError
 
 
 # define completion api for user
@@ -75,7 +77,7 @@ class CompletionApi(InstalledAppResource):
             raise CompletionRequestError(e.description)
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 
@@ -133,9 +135,11 @@ class ChatApi(InstalledAppResource):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 

api/controllers/console/explore/workflow.py

@@ -11,6 +11,7 @@ from controllers.console.app.error import (
 )
 from controllers.console.explore.error import NotWorkflowAppError
 from controllers.console.explore.wraps import InstalledAppResource
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
@@ -23,6 +24,7 @@ from libs import helper
 from libs.login import current_user
 from models.model import AppMode, InstalledApp
 from services.app_generate_service import AppGenerateService
+from services.errors.llm import InvokeRateLimitError
 
 logger = logging.getLogger(__name__)
 
@@ -56,9 +58,11 @@ class InstalledAppWorkflowRunApi(InstalledAppResource):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 

api/controllers/console/workspace/workspace.py

@@ -88,28 +88,20 @@ class WorkspaceListApi(Resource):
         parser.add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
         args = parser.parse_args()
 
-        tenants = Tenant.query.order_by(Tenant.created_at.desc()).paginate(page=args["page"], per_page=args["limit"])
-
+        tenants = Tenant.query.order_by(Tenant.created_at.desc()).paginate(
+            page=args["page"], per_page=args["limit"], error_out=False
+        )
         has_more = False
-        if len(tenants.items) == args["limit"]:
-            current_page_first_tenant = tenants[-1]
-            rest_count = (
-                db.session.query(Tenant)
-                .filter(
-                    Tenant.created_at < current_page_first_tenant.created_at, Tenant.id != current_page_first_tenant.id
-                )
-                .count()
-            )
 
-            if rest_count > 0:
-                has_more = True
-        total = db.session.query(Tenant).count()
+        if tenants.has_next:
+            has_more = True
+
         return {
             "data": marshal(tenants.items, workspace_fields),
             "has_more": has_more,
             "limit": args["limit"],
             "page": args["page"],
-            "total": total,
+            "total": tenants.total,
         }, 200
 
 

api/controllers/service_api/__init__.py

@@ -7,4 +7,4 @@ api = ExternalApi(bp)
 
 from . import index
 from .app import app, audio, completion, conversation, file, message, workflow
-from .dataset import dataset, document, hit_testing, segment, upload_file
+from .dataset import dataset, document, hit_testing, metadata, segment, upload_file

api/controllers/service_api/app/completion.py

@@ -15,6 +15,7 @@ from controllers.service_api.app.error import (
     ProviderQuotaExceededError,
 )
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
@@ -27,6 +28,7 @@ from libs import helper
 from libs.helper import uuid_value
 from models.model import App, AppMode, EndUser
 from services.app_generate_service import AppGenerateService
+from services.errors.llm import InvokeRateLimitError
 
 
 class CompletionApi(Resource):
@@ -75,7 +77,7 @@ class CompletionApi(Resource):
             raise CompletionRequestError(e.description)
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 
@@ -130,11 +132,13 @@ class ChatApi(Resource):
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
             raise ProviderModelCurrentlyNotSupportError()
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except InvokeError as e:
             raise CompletionRequestError(e.description)
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 

api/controllers/service_api/app/message.py

@@ -10,7 +10,7 @@ from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from core.app.entities.app_invoke_entities import InvokeFrom
 from fields.conversation_fields import message_file_fields
-from fields.message_fields import feedback_fields, retriever_resource_fields
+from fields.message_fields import agent_thought_fields, feedback_fields, retriever_resource_fields
 from fields.raws import FilesContainedField
 from libs.helper import TimestampField, uuid_value
 from models.model import App, AppMode, EndUser
@@ -19,20 +19,6 @@ from services.message_service import MessageService
 
 
 class MessageListApi(Resource):
-    agent_thought_fields = {
-        "id": fields.String,
-        "chain_id": fields.String,
-        "message_id": fields.String,
-        "position": fields.Integer,
-        "thought": fields.String,
-        "tool": fields.String,
-        "tool_labels": fields.Raw,
-        "tool_input": fields.String,
-        "created_at": TimestampField,
-        "observation": fields.String,
-        "message_files": fields.List(fields.Nested(message_file_fields)),
-    }
-
     message_fields = {
         "id": fields.String,
         "conversation_id": fields.String,

api/controllers/service_api/app/workflow.py

@@ -15,6 +15,7 @@ from controllers.service_api.app.error import (
     ProviderQuotaExceededError,
 )
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
@@ -29,6 +30,7 @@ from libs import helper
 from models.model import App, AppMode, EndUser
 from models.workflow import WorkflowRun, WorkflowRunStatus
 from services.app_generate_service import AppGenerateService
+from services.errors.llm import InvokeRateLimitError
 from services.workflow_app_service import WorkflowAppService
 
 logger = logging.getLogger(__name__)
@@ -93,11 +95,13 @@ class WorkflowRunApi(Resource):
             raise ProviderQuotaExceededError()
         except ModelCurrentlyNotSupportError:
             raise ProviderModelCurrentlyNotSupportError()
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except InvokeError as e:
             raise CompletionRequestError(e.description)
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 

api/controllers/service_api/dataset/dataset.py

@@ -7,6 +7,7 @@ from controllers.service_api import api
 from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError
 from controllers.service_api.wraps import DatasetApiResource
 from core.model_runtime.entities.model_entities import ModelType
+from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 from fields.dataset_fields import dataset_detail_fields
 from libs.login import current_user
@@ -48,7 +49,8 @@ class DatasetListApi(DatasetApiResource):
 
         data = marshal(datasets, dataset_detail_fields)
         for item in data:
-            if item["indexing_technique"] == "high_quality":
+            if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
+                item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"]))
                 item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
                 if item_model in model_names:
                     item["embedding_available"] = True

api/controllers/service_api/dataset/document.py

@@ -18,7 +18,6 @@ from controllers.service_api.app.error import (
 from controllers.service_api.dataset.error import (
     ArchivedDocumentImmutableError,
     DocumentIndexingError,
-    InvalidMetadataError,
 )
 from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
 from core.errors.error import ProviderTokenNotInitError
@@ -51,8 +50,6 @@ class DocumentAddByTextApi(DatasetApiResource):
             "indexing_technique", type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False, location="json"
         )
         parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
-        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
 
         args = parser.parse_args()
         dataset_id = str(dataset_id)
@@ -65,28 +62,6 @@ class DocumentAddByTextApi(DatasetApiResource):
         if not dataset.indexing_technique and not args["indexing_technique"]:
             raise ValueError("indexing_technique is required.")
 
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
         text = args.get("text")
         name = args.get("name")
         if text is None or name is None:
@@ -133,8 +108,6 @@ class DocumentUpdateByTextApi(DatasetApiResource):
             "doc_language", type=str, default="English", required=False, nullable=False, location="json"
         )
         parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
-        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
         args = parser.parse_args()
         dataset_id = str(dataset_id)
         tenant_id = str(tenant_id)
@@ -146,29 +119,6 @@ class DocumentUpdateByTextApi(DatasetApiResource):
         # indexing_technique is already set in dataset since this is an update
         args["indexing_technique"] = dataset.indexing_technique
 
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
         if args["text"]:
             text = args.get("text")
             name = args.get("name")
@@ -216,29 +166,6 @@ class DocumentAddByFileApi(DatasetApiResource):
         if "doc_language" not in args:
             args["doc_language"] = "English"
 
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
         # get dataset info
         dataset_id = str(dataset_id)
         tenant_id = str(tenant_id)
@@ -306,29 +233,6 @@ class DocumentUpdateByFileApi(DatasetApiResource):
         if "doc_language" not in args:
             args["doc_language"] = "English"
 
-        # Validate metadata if provided
-        if args.get("doc_type") or args.get("doc_metadata"):
-            if not args.get("doc_type") or not args.get("doc_metadata"):
-                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
-
-            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-                raise InvalidMetadataError(
-                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
-                )
-
-            if not isinstance(args["doc_metadata"], dict):
-                raise InvalidMetadataError("doc_metadata must be a dictionary")
-
-            # Validate metadata schema based on doc_type
-            if args["doc_type"] != "others":
-                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
-                for key, value in args["doc_metadata"].items():
-                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
-                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
-
-            # set to MetaDataConfig
-            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
-
         # get dataset info
         dataset_id = str(dataset_id)
         tenant_id = str(tenant_id)

api/controllers/service_api/dataset/metadata.py

@@ -0,0 +1,126 @@
+from flask_login import current_user  # type: ignore  # type: ignore
+from flask_restful import marshal, reqparse  # type: ignore
+from werkzeug.exceptions import NotFound
+
+from controllers.service_api import api
+from controllers.service_api.wraps import DatasetApiResource
+from fields.dataset_fields import dataset_metadata_fields
+from services.dataset_service import DatasetService
+from services.entities.knowledge_entities.knowledge_entities import (
+    MetadataArgs,
+    MetadataOperationData,
+)
+from services.metadata_service import MetadataService
+
+
+def _validate_name(name):
+    if not name or len(name) < 1 or len(name) > 40:
+        raise ValueError("Name must be between 1 to 40 characters.")
+    return name
+
+
+def _validate_description_length(description):
+    if len(description) > 400:
+        raise ValueError("Description cannot exceed 400 characters.")
+    return description
+
+
+class DatasetMetadataCreateServiceApi(DatasetApiResource):
+    def post(self, tenant_id, dataset_id):
+        parser = reqparse.RequestParser()
+        parser.add_argument("type", type=str, required=True, nullable=True, location="json")
+        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        args = parser.parse_args()
+        metadata_args = MetadataArgs(**args)
+
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        metadata = MetadataService.create_metadata(dataset_id_str, metadata_args)
+        return marshal(metadata, dataset_metadata_fields), 201
+
+    def get(self, tenant_id, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        return MetadataService.get_dataset_metadatas(dataset), 200
+
+
+class DatasetMetadataServiceApi(DatasetApiResource):
+    def patch(self, tenant_id, dataset_id, metadata_id):
+        parser = reqparse.RequestParser()
+        parser.add_argument("name", type=str, required=True, nullable=True, location="json")
+        args = parser.parse_args()
+
+        dataset_id_str = str(dataset_id)
+        metadata_id_str = str(metadata_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args.get("name"))
+        return marshal(metadata, dataset_metadata_fields), 200
+
+    def delete(self, tenant_id, dataset_id, metadata_id):
+        dataset_id_str = str(dataset_id)
+        metadata_id_str = str(metadata_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        MetadataService.delete_metadata(dataset_id_str, metadata_id_str)
+        return 200
+
+
+class DatasetMetadataBuiltInFieldServiceApi(DatasetApiResource):
+    def get(self, tenant_id):
+        built_in_fields = MetadataService.get_built_in_fields()
+        return {"fields": built_in_fields}, 200
+
+
+class DatasetMetadataBuiltInFieldActionServiceApi(DatasetApiResource):
+    def post(self, tenant_id, dataset_id, action):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        if action == "enable":
+            MetadataService.enable_built_in_field(dataset)
+        elif action == "disable":
+            MetadataService.disable_built_in_field(dataset)
+        return 200
+
+
+class DocumentMetadataEditServiceApi(DatasetApiResource):
+    def post(self, tenant_id, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        DatasetService.check_dataset_permission(dataset, current_user)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("operation_data", type=list, required=True, nullable=True, location="json")
+        args = parser.parse_args()
+        metadata_args = MetadataOperationData(**args)
+
+        MetadataService.update_documents_metadata(dataset, metadata_args)
+
+        return 200
+
+
+api.add_resource(DatasetMetadataCreateServiceApi, "/datasets/<uuid:dataset_id>/metadata")
+api.add_resource(DatasetMetadataServiceApi, "/datasets/<uuid:dataset_id>/metadata/<uuid:metadata_id>")
+api.add_resource(DatasetMetadataBuiltInFieldServiceApi, "/datasets/metadata/built-in")
+api.add_resource(
+    DatasetMetadataBuiltInFieldActionServiceApi, "/datasets/<uuid:dataset_id>/metadata/built-in/<string:action>"
+)
+api.add_resource(DocumentMetadataEditServiceApi, "/datasets/<uuid:dataset_id>/documents/metadata")

api/controllers/web/workflow.py

@@ -11,6 +11,7 @@ from controllers.web.error import (
     ProviderNotInitializeError,
     ProviderQuotaExceededError,
 )
+from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from controllers.web.wraps import WebApiResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
@@ -23,6 +24,7 @@ from core.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from models.model import App, AppMode, EndUser
 from services.app_generate_service import AppGenerateService
+from services.errors.llm import InvokeRateLimitError
 
 logger = logging.getLogger(__name__)
 
@@ -55,9 +57,11 @@ class WorkflowRunApi(WebApiResource):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
+        except InvokeRateLimitError as ex:
+            raise InvokeRateLimitHttpError(ex.description)
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 

api/core/app/app_config/easy_ui_based_app/dataset/manager.py

@@ -1,7 +1,12 @@
 import uuid
 from typing import Optional
 
-from core.app.app_config.entities import DatasetEntity, DatasetRetrieveConfigEntity
+from core.app.app_config.entities import (
+    DatasetEntity,
+    DatasetRetrieveConfigEntity,
+    MetadataFilteringCondition,
+    ModelConfig,
+)
 from core.entities.agent_entities import PlanningStrategy
 from models.model import AppMode
 from services.dataset_service import DatasetService
@@ -78,6 +83,15 @@ class DatasetConfigManager:
                     retrieve_strategy=DatasetRetrieveConfigEntity.RetrieveStrategy.value_of(
                         dataset_configs["retrieval_model"]
                     ),
+                    metadata_filtering_mode=dataset_configs.get("metadata_filtering_mode", "disabled"),
+                    metadata_model_config=ModelConfig(**dataset_configs.get("metadata_model_config"))
+                    if dataset_configs.get("metadata_model_config")
+                    else None,
+                    metadata_filtering_conditions=MetadataFilteringCondition(
+                        **dataset_configs.get("metadata_filtering_conditions", {})
+                    )
+                    if dataset_configs.get("metadata_filtering_conditions")
+                    else None,
                 ),
             )
         else:
@@ -89,11 +103,22 @@ class DatasetConfigManager:
                         dataset_configs["retrieval_model"]
                     ),
                     top_k=dataset_configs.get("top_k", 4),
-                    score_threshold=dataset_configs.get("score_threshold"),
+                    score_threshold=dataset_configs.get("score_threshold")
+                    if dataset_configs.get("score_threshold_enabled", False)
+                    else None,
                     reranking_model=dataset_configs.get("reranking_model"),
                     weights=dataset_configs.get("weights"),
                     reranking_enabled=dataset_configs.get("reranking_enabled", True),
                     rerank_mode=dataset_configs.get("reranking_mode", "reranking_model"),
+                    metadata_filtering_mode=dataset_configs.get("metadata_filtering_mode", "disabled"),
+                    metadata_model_config=ModelConfig(**dataset_configs.get("metadata_model_config"))
+                    if dataset_configs.get("metadata_model_config")
+                    else None,
+                    metadata_filtering_conditions=MetadataFilteringCondition(
+                        **dataset_configs.get("metadata_filtering_conditions", {})
+                    )
+                    if dataset_configs.get("metadata_filtering_conditions")
+                    else None,
                 ),
             )
 

api/core/app/app_config/entities.py

@@ -1,10 +1,11 @@
 from collections.abc import Sequence
 from enum import Enum, StrEnum
-from typing import Any, Optional
+from typing import Any, Literal, Optional
 
 from pydantic import BaseModel, Field, field_validator
 
 from core.file import FileTransferMethod, FileType, FileUploadConfig
+from core.model_runtime.entities.llm_entities import LLMMode
 from core.model_runtime.entities.message_entities import PromptMessageRole
 from models.model import AppMode
 
@@ -135,6 +136,55 @@ class ExternalDataVariableEntity(BaseModel):
     config: dict[str, Any] = Field(default_factory=dict)
 
 
+SupportedComparisonOperator = Literal[
+    # for string or array
+    "contains",
+    "not contains",
+    "start with",
+    "end with",
+    "is",
+    "is not",
+    "empty",
+    "not empty",
+    # for number
+    "=",
+    "≠",
+    ">",
+    "<",
+    "≥",
+    "≤",
+    # for time
+    "before",
+    "after",
+]
+
+
+class ModelConfig(BaseModel):
+    provider: str
+    name: str
+    mode: LLMMode
+    completion_params: dict[str, Any] = {}
+
+
+class Condition(BaseModel):
+    """
+    Conditon detail
+    """
+
+    name: str
+    comparison_operator: SupportedComparisonOperator
+    value: str | Sequence[str] | None | int | float = None
+
+
+class MetadataFilteringCondition(BaseModel):
+    """
+    Metadata Filtering Condition.
+    """
+
+    logical_operator: Optional[Literal["and", "or"]] = "and"
+    conditions: Optional[list[Condition]] = Field(default=None, deprecated=True)
+
+
 class DatasetRetrieveConfigEntity(BaseModel):
     """
     Dataset Retrieve Config Entity.
@@ -171,6 +221,9 @@ class DatasetRetrieveConfigEntity(BaseModel):
     reranking_model: Optional[dict] = None
     weights: Optional[dict] = None
     reranking_enabled: Optional[bool] = True
+    metadata_filtering_mode: Optional[Literal["disabled", "automatic", "manual"]] = "disabled"
+    metadata_model_config: Optional[ModelConfig] = None
+    metadata_filtering_conditions: Optional[MetadataFilteringCondition] = None
 
 
 class DatasetEntity(BaseModel):

api/core/app/app_config/features/file_upload/manager.py

@@ -17,17 +17,15 @@ class FileUploadConfigManager:
         if file_upload_dict:
             if file_upload_dict.get("enabled"):
                 transform_methods = file_upload_dict.get("allowed_file_upload_methods", [])
-                data = {
-                    "image_config": {
-                        "number_limits": file_upload_dict["number_limits"],
-                        "transfer_methods": transform_methods,
-                    }
+                file_upload_dict["image_config"] = {
+                    "number_limits": file_upload_dict.get("number_limits", 1),
+                    "transfer_methods": transform_methods,
                 }
 
                 if is_vision:
-                    data["image_config"]["detail"] = file_upload_dict.get("image", {}).get("detail", "low")
+                    file_upload_dict["image_config"]["detail"] = file_upload_dict.get("image", {}).get("detail", "high")
 
-                return FileUploadConfig.model_validate(data)
+                return FileUploadConfig.model_validate(file_upload_dict)
 
     @classmethod
     def validate_and_set_defaults(cls, config: dict) -> tuple[dict, list[str]]:

api/core/app/apps/advanced_chat/app_generator.py

@@ -29,6 +29,7 @@ from factories import file_factory
 from models.account import Account
 from models.model import App, Conversation, EndUser, Message
 from models.workflow import Workflow
+from services.conversation_service import ConversationService
 from services.errors.message import MessageNotExistsError
 
 logger = logging.getLogger(__name__)
@@ -105,7 +106,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         conversation = None
         conversation_id = args.get("conversation_id")
         if conversation_id:
-            conversation = self._get_conversation_by_user(
+            conversation = ConversationService.get_conversation(
                 app_model=app_model, conversation_id=conversation_id, user=user
             )
 

api/core/app/apps/agent_chat/app_generator.py

@@ -24,6 +24,7 @@ from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
 from models import Account, App, EndUser
+from services.conversation_service import ConversationService
 from services.errors.message import MessageNotExistsError
 
 logger = logging.getLogger(__name__)
@@ -98,9 +99,11 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
 
         # get conversation
         conversation = None
-        if args.get("conversation_id"):
-            conversation = self._get_conversation_by_user(app_model, args.get("conversation_id", ""), user)
-
+        conversation_id = args.get("conversation_id")
+        if conversation_id:
+            conversation = ConversationService.get_conversation(
+                app_model=app_model, conversation_id=conversation_id, user=user
+            )
         # get app model config
         app_model_config = self._get_app_model_config(app_model=app_model, conversation=conversation)
 

api/core/app/apps/base_app_generator.py

@@ -151,7 +151,7 @@ class BaseAppGenerator:
 
             def gen():
                 for message in generator:
-                    if isinstance(message, (Mapping, dict)):
+                    if isinstance(message, Mapping | dict):
                         yield f"data: {json.dumps(message)}\n\n"
                     else:
                         yield f"event: {message}\n\n"

api/core/app/apps/base_app_runner.py

@@ -17,7 +17,11 @@ from core.external_data_tool.external_data_fetch import ExternalDataFetch
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
-from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    ImagePromptMessageContent,
+    PromptMessage,
+)
 from core.model_runtime.entities.model_entities import ModelPropertyKey
 from core.model_runtime.errors.invoke import InvokeBadRequestError
 from core.moderation.input_moderation import InputModeration
@@ -141,6 +145,7 @@ class AppRunner:
         query: Optional[str] = None,
         context: Optional[str] = None,
         memory: Optional[TokenBufferMemory] = None,
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
     ) -> tuple[list[PromptMessage], Optional[list[str]]]:
         """
         Organize prompt messages
@@ -167,6 +172,7 @@ class AppRunner:
                 context=context,
                 memory=memory,
                 model_config=model_config,
+                image_detail_config=image_detail_config,
             )
         else:
             memory_config = MemoryConfig(window=MemoryConfig.WindowConfig(enabled=False))
@@ -201,6 +207,7 @@ class AppRunner:
                 memory_config=memory_config,
                 memory=memory,
                 model_config=model_config,
+                image_detail_config=image_detail_config,
             )
             stop = model_config.stop
 

api/core/app/apps/chat/app_generator.py

@@ -24,6 +24,7 @@ from extensions.ext_database import db
 from factories import file_factory
 from models.account import Account
 from models.model import App, EndUser
+from services.conversation_service import ConversationService
 from services.errors.message import MessageNotExistsError
 
 logger = logging.getLogger(__name__)
@@ -91,9 +92,11 @@ class ChatAppGenerator(MessageBasedAppGenerator):
 
         # get conversation
         conversation = None
-        if args.get("conversation_id"):
-            conversation = self._get_conversation_by_user(app_model, args.get("conversation_id", ""), user)
-
+        conversation_id = args.get("conversation_id")
+        if conversation_id:
+            conversation = ConversationService.get_conversation(
+                app_model=app_model, conversation_id=conversation_id, user=user
+            )
         # get app model config
         app_model_config = self._get_app_model_config(app_model=app_model, conversation=conversation)
 

api/core/app/apps/chat/app_runner.py

@@ -11,6 +11,7 @@ from core.app.entities.queue_entities import QueueAnnotationReplyEvent
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
+from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.moderation.base import ModerationError
 from core.rag.retrieval.dataset_retrieval import DatasetRetrieval
 from extensions.ext_database import db
@@ -50,6 +51,16 @@ class ChatAppRunner(AppRunner):
         query = application_generate_entity.query
         files = application_generate_entity.files
 
+        image_detail_config = (
+            application_generate_entity.file_upload_config.image_config.detail
+            if (
+                application_generate_entity.file_upload_config
+                and application_generate_entity.file_upload_config.image_config
+            )
+            else None
+        )
+        image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
+
         # Pre-calculate the number of tokens of the prompt messages,
         # and return the rest number of tokens by model context token size limit and max token size limit.
         # If the rest number of tokens is not enough, raise exception.
@@ -85,6 +96,7 @@ class ChatAppRunner(AppRunner):
             files=files,
             query=query,
             memory=memory,
+            image_detail_config=image_detail_config,
         )
 
         # moderation
@@ -168,6 +180,7 @@ class ChatAppRunner(AppRunner):
                 hit_callback=hit_callback,
                 memory=memory,
                 message_id=message.id,
+                inputs=inputs,
             )
 
         # reorganize all inputs and template to prompt messages
@@ -182,6 +195,7 @@ class ChatAppRunner(AppRunner):
             query=query,
             context=context,
             memory=memory,
+            image_detail_config=image_detail_config,
         )
 
         # check hosting moderation

api/core/app/apps/completion/app_runner.py

@@ -9,6 +9,7 @@ from core.app.entities.app_invoke_entities import (
 )
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
 from core.model_manager import ModelInstance
+from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.moderation.base import ModerationError
 from core.rag.retrieval.dataset_retrieval import DatasetRetrieval
 from extensions.ext_database import db
@@ -43,6 +44,16 @@ class CompletionAppRunner(AppRunner):
         query = application_generate_entity.query
         files = application_generate_entity.files
 
+        image_detail_config = (
+            application_generate_entity.file_upload_config.image_config.detail
+            if (
+                application_generate_entity.file_upload_config
+                and application_generate_entity.file_upload_config.image_config
+            )
+            else None
+        )
+        image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
+
         # Pre-calculate the number of tokens of the prompt messages,
         # and return the rest number of tokens by model context token size limit and max token size limit.
         # If the rest number of tokens is not enough, raise exception.
@@ -66,6 +77,7 @@ class CompletionAppRunner(AppRunner):
             inputs=inputs,
             files=files,
             query=query,
+            image_detail_config=image_detail_config,
         )
 
         # moderation
@@ -127,6 +139,7 @@ class CompletionAppRunner(AppRunner):
                 show_retrieve_source=app_config.additional_features.show_retrieve_source,
                 hit_callback=hit_callback,
                 message_id=message.id,
+                inputs=inputs,
             )
 
         # reorganize all inputs and template to prompt messages
@@ -140,6 +153,7 @@ class CompletionAppRunner(AppRunner):
             files=files,
             query=query,
             context=context,
+            image_detail_config=image_detail_config,
         )
 
         # check hosting moderation

api/core/app/apps/message_based_app_generator.py

@@ -4,8 +4,6 @@ from collections.abc import Generator
 from datetime import UTC, datetime
 from typing import Optional, Union, cast
 
-from sqlalchemy import and_
-
 from core.app.app_config.entities import EasyUIBasedAppConfig, EasyUIBasedAppModelConfigFrom
 from core.app.apps.base_app_generator import BaseAppGenerator
 from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedError
@@ -30,7 +28,7 @@ from models import Account
 from models.enums import CreatedByRole
 from models.model import App, AppMode, AppModelConfig, Conversation, EndUser, Message, MessageFile
 from services.errors.app_model_config import AppModelConfigBrokenError
-from services.errors.conversation import ConversationCompletedError, ConversationNotExistsError
+from services.errors.conversation import ConversationNotExistsError
 
 logger = logging.getLogger(__name__)
 
@@ -81,31 +79,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
                 logger.exception(f"Failed to handle response, conversation_id: {conversation.id}")
                 raise e
 
-    def _get_conversation_by_user(
-        self, app_model: App, conversation_id: str, user: Union[Account, EndUser]
-    ) -> Conversation:
-        conversation_filter = [
-            Conversation.id == conversation_id,
-            Conversation.app_id == app_model.id,
-            Conversation.status == "normal",
-            Conversation.is_deleted.is_(False),
-        ]
-
-        if isinstance(user, Account):
-            conversation_filter.append(Conversation.from_account_id == user.id)
-        else:
-            conversation_filter.append(Conversation.from_end_user_id == user.id if user else None)
-
-        conversation = db.session.query(Conversation).filter(and_(*conversation_filter)).first()
-
-        if not conversation:
-            raise ConversationNotExistsError()
-
-        if conversation.status != "normal":
-            raise ConversationCompletedError()
-
-        return conversation
-
     def _get_app_model_config(self, app_model: App, conversation: Optional[Conversation] = None) -> AppModelConfig:
         if conversation:
             app_model_config = (

api/core/app/features/rate_limiting/rate_limit.py

@@ -40,14 +40,10 @@ class RateLimit:
         self.last_recalculate_time = time.time()
         # flush max active requests
         if use_local_value or not redis_client.exists(self.max_active_requests_key):
-            with redis_client.pipeline() as pipe:
-                pipe.set(self.max_active_requests_key, self.max_active_requests)
-                pipe.expire(self.max_active_requests_key, timedelta(days=1))
-                pipe.execute()
+            redis_client.setex(self.max_active_requests_key, timedelta(days=1), self.max_active_requests)
         else:
-            with redis_client.pipeline() as pipe:
-                self.max_active_requests = int(redis_client.get(self.max_active_requests_key).decode("utf-8"))
-                redis_client.expire(self.max_active_requests_key, timedelta(days=1))
+            self.max_active_requests = int(redis_client.get(self.max_active_requests_key).decode("utf-8"))
+            redis_client.expire(self.max_active_requests_key, timedelta(days=1))
 
         # flush max active requests (in-transit request list)
         if not redis_client.exists(self.active_requests_key):

api/core/file/models.py

@@ -63,7 +63,9 @@ class File(BaseModel):
         extension: Optional[str] = None,
         mime_type: Optional[str] = None,
         size: int = -1,
-        storage_key: str,
+        storage_key: Optional[str] = None,
+        dify_model_identity: Optional[str] = FILE_MODEL_IDENTITY,
+        url: Optional[str] = None,
     ):
         super().__init__(
             id=id,
@@ -76,8 +78,10 @@ class File(BaseModel):
             extension=extension,
             mime_type=mime_type,
             size=size,
+            dify_model_identity=dify_model_identity,
+            url=url,
         )
-        self._storage_key = storage_key
+        self._storage_key = str(storage_key)
 
     def to_dict(self) -> Mapping[str, str | int | None]:
         data = self.model_dump(mode="json")

api/core/helper/ssrf_proxy.py

@@ -11,6 +11,19 @@ from configs import dify_config
 
 SSRF_DEFAULT_MAX_RETRIES = dify_config.SSRF_DEFAULT_MAX_RETRIES
 
+HTTP_REQUEST_NODE_SSL_VERIFY = True  # Default value for HTTP_REQUEST_NODE_SSL_VERIFY is True
+try:
+    HTTP_REQUEST_NODE_SSL_VERIFY = dify_config.HTTP_REQUEST_NODE_SSL_VERIFY
+    http_request_node_ssl_verify_lower = str(HTTP_REQUEST_NODE_SSL_VERIFY).lower()
+    if http_request_node_ssl_verify_lower == "true":
+        HTTP_REQUEST_NODE_SSL_VERIFY = True
+    elif http_request_node_ssl_verify_lower == "false":
+        HTTP_REQUEST_NODE_SSL_VERIFY = False
+    else:
+        raise ValueError("Invalid value. HTTP_REQUEST_NODE_SSL_VERIFY should be 'True' or 'False'")
+except NameError:
+    HTTP_REQUEST_NODE_SSL_VERIFY = True
+
 BACKOFF_FACTOR = 0.5
 STATUS_FORCELIST = [429, 500, 502, 503, 504]
 
@@ -39,17 +52,17 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
     while retries <= max_retries:
         try:
             if dify_config.SSRF_PROXY_ALL_URL:
-                with httpx.Client(proxy=dify_config.SSRF_PROXY_ALL_URL) as client:
+                with httpx.Client(proxy=dify_config.SSRF_PROXY_ALL_URL, verify=HTTP_REQUEST_NODE_SSL_VERIFY) as client:
                     response = client.request(method=method, url=url, **kwargs)
             elif dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL:
                 proxy_mounts = {
                     "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
                     "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
                 }
-                with httpx.Client(mounts=proxy_mounts) as client:
+                with httpx.Client(mounts=proxy_mounts, verify=HTTP_REQUEST_NODE_SSL_VERIFY) as client:
                     response = client.request(method=method, url=url, **kwargs)
             else:
-                with httpx.Client() as client:
+                with httpx.Client(verify=HTTP_REQUEST_NODE_SSL_VERIFY) as client:
                     response = client.request(method=method, url=url, **kwargs)
 
             if response.status_code not in STATUS_FORCELIST:

api/core/model_runtime/README_CN.md

@@ -10,7 +10,7 @@
 - 支持 5 种模型类型的能力调用
 
   - `LLM` - LLM 文本补全、对话，预计算 tokens 能力
-  - `Text Embedidng Model` - 文本 Embedding ，预计算 tokens 能力
+  - `Text Embedding Model` - 文本 Embedding ，预计算 tokens 能力
   - `Rerank Model` - 分段 Rerank 能力
   - `Speech-to-text Model` - 语音转文本能力
   - `Text-to-speech Model` - 文本转语音能力

api/core/model_runtime/docs/en_US/interfaces.md

@@ -493,7 +493,7 @@ If inputting a combination of text and images, the images need to be constructed
 The base class for all Role message bodies, used only for parameter declaration and cannot be initialized.
 
 ```python
-class PromptMessage(ABC, BaseModel):
+class PromptMessage(BaseModel):
     """
     Model class for prompt message.
     """

api/core/model_runtime/docs/zh_Hans/interfaces.md

@@ -533,7 +533,7 @@ class ImagePromptMessageContent(PromptMessageContent):
 所有 Role 消息体的基类，仅作为参数声明用，不可初始化。
 
 ```python
-class PromptMessage(ABC, BaseModel):
+class PromptMessage(BaseModel):
     """
     Model class for prompt message.
     """

api/core/model_runtime/entities/__init__.py

@@ -31,11 +31,9 @@ __all__ = [
     "ModelPropertyKey",
     "MultiModalPromptMessageContent",
     "PromptMessage",
-    "PromptMessage",
     "PromptMessageContent",
     "PromptMessageContentType",
     "PromptMessageRole",
-    "PromptMessageRole",
     "PromptMessageTool",
     "SystemPromptMessage",
     "TextPromptMessageContent",

api/core/model_runtime/entities/message_entities.py

@@ -1,4 +1,3 @@
-from abc import ABC
 from collections.abc import Sequence
 from enum import Enum, StrEnum
 from typing import Optional
@@ -119,7 +118,7 @@ class DocumentPromptMessageContent(MultiModalPromptMessageContent):
     type: PromptMessageContentType = PromptMessageContentType.DOCUMENT
 
 
-class PromptMessage(ABC, BaseModel):
+class PromptMessage(BaseModel):
     """
     Model class for prompt message.
     """

api/core/model_runtime/model_providers/__base/ai_model.py

@@ -80,7 +80,7 @@ class AIModel(BaseModel):
                         )
                     )
                 elif isinstance(invoke_error, InvokeError):
-                    return invoke_error(description=f"[{self.provider_name}] {invoke_error.description}, {str(error)}")
+                    return InvokeError(description=f"[{self.provider_name}] {invoke_error.description}, {str(error)}")
                 else:
                     return error
 

api/core/ops/ops_trace_manager.py

@@ -214,6 +214,8 @@ class OpsTraceManager:
                 provider_config_map[tracing_provider]["trace_instance"],
                 provider_config_map[tracing_provider]["config_class"],
             )
+            if not decrypt_trace_config:
+                return None
             tracing_instance = trace_instance(config_class(**decrypt_trace_config))
             return tracing_instance
 

api/core/plugin/backwards_invocation/model.py

@@ -3,7 +3,7 @@ from binascii import hexlify, unhexlify
 from collections.abc import Generator
 
 from core.model_manager import ModelManager
-from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
+from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.entities.message_entities import (
     PromptMessage,
     SystemPromptMessage,
@@ -46,7 +46,7 @@ class PluginModelBackwardsInvocation(BaseBackwardsInvocation):
             model_parameters=payload.completion_params,
             tools=payload.tools,
             stop=payload.stop,
-            stream=payload.stream or True,
+            stream=True if payload.stream is None else payload.stream,
             user=user_id,
         )
 
@@ -64,7 +64,21 @@ class PluginModelBackwardsInvocation(BaseBackwardsInvocation):
         else:
             if response.usage:
                 LLMNode.deduct_llm_quota(tenant_id=tenant.id, model_instance=model_instance, usage=response.usage)
-            return response
+
+            def handle_non_streaming(response: LLMResult) -> Generator[LLMResultChunk, None, None]:
+                yield LLMResultChunk(
+                    model=response.model,
+                    prompt_messages=response.prompt_messages,
+                    system_fingerprint=response.system_fingerprint,
+                    delta=LLMResultChunkDelta(
+                        index=0,
+                        message=response.message,
+                        usage=response.usage,
+                        finish_reason="",
+                    ),
+                )
+
+            return handle_non_streaming(response)
 
     @classmethod
     def invoke_text_embedding(cls, user_id: str, tenant: Tenant, payload: RequestInvokeTextEmbedding):

api/core/plugin/entities/parameters.py

@@ -147,7 +147,7 @@ def init_frontend_parameter(rule: PluginParameter, type: enum.StrEnum, value: An
     init frontend parameter by rule
     """
     parameter_value = value
-    if not parameter_value and parameter_value != 0:
+    if not parameter_value and parameter_value != 0 and type != PluginParameterType.TOOLS_SELECTOR:
         # get default value
         parameter_value = rule.default
         if not parameter_value and rule.required:

api/core/prompt/advanced_prompt_transform.py

@@ -46,6 +46,7 @@ class AdvancedPromptTransform(PromptTransform):
         memory_config: Optional[MemoryConfig],
         memory: Optional[TokenBufferMemory],
         model_config: ModelConfigWithCredentialsEntity,
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
     ) -> list[PromptMessage]:
         prompt_messages = []
 
@@ -59,6 +60,7 @@ class AdvancedPromptTransform(PromptTransform):
                 memory_config=memory_config,
                 memory=memory,
                 model_config=model_config,
+                image_detail_config=image_detail_config,
             )
         elif isinstance(prompt_template, list) and all(isinstance(item, ChatModelMessage) for item in prompt_template):
             prompt_messages = self._get_chat_model_prompt_messages(
@@ -70,6 +72,7 @@ class AdvancedPromptTransform(PromptTransform):
                 memory_config=memory_config,
                 memory=memory,
                 model_config=model_config,
+                image_detail_config=image_detail_config,
             )
 
         return prompt_messages
@@ -84,6 +87,7 @@ class AdvancedPromptTransform(PromptTransform):
         memory_config: Optional[MemoryConfig],
         memory: Optional[TokenBufferMemory],
         model_config: ModelConfigWithCredentialsEntity,
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
     ) -> list[PromptMessage]:
         """
         Get completion model prompt messages.
@@ -124,7 +128,9 @@ class AdvancedPromptTransform(PromptTransform):
             prompt_message_contents: list[PromptMessageContent] = []
             prompt_message_contents.append(TextPromptMessageContent(data=prompt))
             for file in files:
-                prompt_message_contents.append(file_manager.to_prompt_message_content(file))
+                prompt_message_contents.append(
+                    file_manager.to_prompt_message_content(file, image_detail_config=image_detail_config)
+                )
 
             prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
         else:
@@ -142,6 +148,7 @@ class AdvancedPromptTransform(PromptTransform):
         memory_config: Optional[MemoryConfig],
         memory: Optional[TokenBufferMemory],
         model_config: ModelConfigWithCredentialsEntity,
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
     ) -> list[PromptMessage]:
         """
         Get chat model prompt messages.
@@ -197,7 +204,9 @@ class AdvancedPromptTransform(PromptTransform):
                 prompt_message_contents: list[PromptMessageContent] = []
                 prompt_message_contents.append(TextPromptMessageContent(data=query))
                 for file in files:
-                    prompt_message_contents.append(file_manager.to_prompt_message_content(file))
+                    prompt_message_contents.append(
+                        file_manager.to_prompt_message_content(file, image_detail_config=image_detail_config)
+                    )
                 prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
             else:
                 prompt_messages.append(UserPromptMessage(content=query))
@@ -209,19 +218,25 @@ class AdvancedPromptTransform(PromptTransform):
                     # get last user message content and add files
                     prompt_message_contents = [TextPromptMessageContent(data=cast(str, last_message.content))]
                     for file in files:
-                        prompt_message_contents.append(file_manager.to_prompt_message_content(file))
+                        prompt_message_contents.append(
+                            file_manager.to_prompt_message_content(file, image_detail_config=image_detail_config)
+                        )
 
                     last_message.content = prompt_message_contents
                 else:
                     prompt_message_contents = [TextPromptMessageContent(data="")]  # not for query
                     for file in files:
-                        prompt_message_contents.append(file_manager.to_prompt_message_content(file))
+                        prompt_message_contents.append(
+                            file_manager.to_prompt_message_content(file, image_detail_config=image_detail_config)
+                        )
 
                     prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
             else:
                 prompt_message_contents = [TextPromptMessageContent(data=query)]
                 for file in files:
-                    prompt_message_contents.append(file_manager.to_prompt_message_content(file))
+                    prompt_message_contents.append(
+                        file_manager.to_prompt_message_content(file, image_detail_config=image_detail_config)
+                    )
 
                 prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
         elif query:

api/core/prompt/simple_prompt_transform.py

@@ -9,6 +9,7 @@ from core.app.entities.app_invoke_entities import ModelConfigWithCredentialsEnti
 from core.file import file_manager
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_runtime.entities.message_entities import (
+    ImagePromptMessageContent,
     PromptMessage,
     PromptMessageContent,
     SystemPromptMessage,
@@ -60,6 +61,7 @@ class SimplePromptTransform(PromptTransform):
         context: Optional[str],
         memory: Optional[TokenBufferMemory],
         model_config: ModelConfigWithCredentialsEntity,
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
     ) -> tuple[list[PromptMessage], Optional[list[str]]]:
         inputs = {key: str(value) for key, value in inputs.items()}
 
@@ -74,6 +76,7 @@ class SimplePromptTransform(PromptTransform):
                 context=context,
                 memory=memory,
                 model_config=model_config,
+                image_detail_config=image_detail_config,
             )
         else:
             prompt_messages, stops = self._get_completion_model_prompt_messages(
@@ -85,11 +88,12 @@ class SimplePromptTransform(PromptTransform):
                 context=context,
                 memory=memory,
                 model_config=model_config,
+                image_detail_config=image_detail_config,
             )
 
         return prompt_messages, stops
 
-    def get_prompt_str_and_rules(
+    def _get_prompt_str_and_rules(
         self,
         app_mode: AppMode,
         model_config: ModelConfigWithCredentialsEntity,
@@ -175,11 +179,12 @@ class SimplePromptTransform(PromptTransform):
         files: Sequence["File"],
         memory: Optional[TokenBufferMemory],
         model_config: ModelConfigWithCredentialsEntity,
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
     ) -> tuple[list[PromptMessage], Optional[list[str]]]:
         prompt_messages: list[PromptMessage] = []
 
         # get prompt
-        prompt, _ = self.get_prompt_str_and_rules(
+        prompt, _ = self._get_prompt_str_and_rules(
             app_mode=app_mode,
             model_config=model_config,
             pre_prompt=pre_prompt,
@@ -204,9 +209,9 @@ class SimplePromptTransform(PromptTransform):
             )
 
         if query:
-            prompt_messages.append(self.get_last_user_message(query, files))
+            prompt_messages.append(self._get_last_user_message(query, files, image_detail_config))
         else:
-            prompt_messages.append(self.get_last_user_message(prompt, files))
+            prompt_messages.append(self._get_last_user_message(prompt, files, image_detail_config))
 
         return prompt_messages, None
 
@@ -220,9 +225,10 @@ class SimplePromptTransform(PromptTransform):
         files: Sequence["File"],
         memory: Optional[TokenBufferMemory],
         model_config: ModelConfigWithCredentialsEntity,
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
     ) -> tuple[list[PromptMessage], Optional[list[str]]]:
         # get prompt
-        prompt, prompt_rules = self.get_prompt_str_and_rules(
+        prompt, prompt_rules = self._get_prompt_str_and_rules(
             app_mode=app_mode,
             model_config=model_config,
             pre_prompt=pre_prompt,
@@ -248,7 +254,7 @@ class SimplePromptTransform(PromptTransform):
             )
 
             # get prompt
-            prompt, prompt_rules = self.get_prompt_str_and_rules(
+            prompt, prompt_rules = self._get_prompt_str_and_rules(
                 app_mode=app_mode,
                 model_config=model_config,
                 pre_prompt=pre_prompt,
@@ -262,14 +268,21 @@ class SimplePromptTransform(PromptTransform):
         if stops is not None and len(stops) == 0:
             stops = None
 
-        return [self.get_last_user_message(prompt, files)], stops
+        return [self._get_last_user_message(prompt, files, image_detail_config)], stops
 
-    def get_last_user_message(self, prompt: str, files: Sequence["File"]) -> UserPromptMessage:
+    def _get_last_user_message(
+        self,
+        prompt: str,
+        files: Sequence["File"],
+        image_detail_config: Optional[ImagePromptMessageContent.DETAIL] = None,
+    ) -> UserPromptMessage:
         if files:
             prompt_message_contents: list[PromptMessageContent] = []
             prompt_message_contents.append(TextPromptMessageContent(data=prompt))
             for file in files:
-                prompt_message_contents.append(file_manager.to_prompt_message_content(file))
+                prompt_message_contents.append(
+                    file_manager.to_prompt_message_content(file, image_detail_config=image_detail_config)
+                )
 
             prompt_message = UserPromptMessage(content=prompt_message_contents)
         else:

api/core/provider_manager.py

@@ -149,6 +149,11 @@ class ProviderManager:
             provider_name = provider_entity.provider
             provider_records = provider_name_to_provider_records_dict.get(provider_entity.provider, [])
             provider_model_records = provider_name_to_provider_model_records_dict.get(provider_entity.provider, [])
+            provider_id_entity = ModelProviderID(provider_name)
+            if provider_id_entity.is_langgenius():
+                provider_model_records.extend(
+                    provider_name_to_provider_model_records_dict.get(provider_id_entity.provider_name, [])
+                )
 
             # Convert to custom configuration
             custom_configuration = self._to_custom_configuration(
@@ -190,6 +195,20 @@ class ProviderManager:
                 provider_name
             )
 
+            provider_id_entity = ModelProviderID(provider_name)
+
+            if provider_id_entity.is_langgenius():
+                if provider_model_settings is not None:
+                    provider_model_settings.extend(
+                        provider_name_to_provider_model_settings_dict.get(provider_id_entity.provider_name, [])
+                    )
+                if provider_load_balancing_configs is not None:
+                    provider_load_balancing_configs.extend(
+                        provider_name_to_provider_load_balancing_model_configs_dict.get(
+                            provider_id_entity.provider_name, []
+                        )
+                    )
+
             # Convert to model settings
             model_settings = self._to_model_settings(
                 provider_entity=provider_entity,
@@ -207,7 +226,7 @@ class ProviderManager:
                 model_settings=model_settings,
             )
 
-            provider_configurations[str(ModelProviderID(provider_name))] = provider_configuration
+            provider_configurations[str(provider_id_entity)] = provider_configuration
 
         # Return the encapsulated object
         return provider_configurations

api/core/rag/datasource/keyword/jieba/jieba.py

@@ -88,16 +88,17 @@ class Jieba(BaseKeyword):
         keyword_table = self._get_dataset_keyword_table()
 
         k = kwargs.get("top_k", 4)
-
+        document_ids_filter = kwargs.get("document_ids_filter")
         sorted_chunk_indices = self._retrieve_ids_by_query(keyword_table or {}, query, k)
 
         documents = []
         for chunk_index in sorted_chunk_indices:
-            segment = (
-                db.session.query(DocumentSegment)
-                .filter(DocumentSegment.dataset_id == self.dataset.id, DocumentSegment.index_node_id == chunk_index)
-                .first()
+            segment_query = db.session.query(DocumentSegment).filter(
+                DocumentSegment.dataset_id == self.dataset.id, DocumentSegment.index_node_id == chunk_index
             )
+            if document_ids_filter:
+                segment_query = segment_query.filter(DocumentSegment.document_id.in_(document_ids_filter))
+            segment = segment_query.first()
 
             if segment:
                 documents.append(

api/core/rag/datasource/retrieval_service.py

@@ -1,5 +1,4 @@
 import concurrent.futures
-import json
 from concurrent.futures import ThreadPoolExecutor
 from typing import Optional
 
@@ -42,6 +41,7 @@ class RetrievalService:
         reranking_model: Optional[dict] = None,
         reranking_mode: str = "reranking_model",
         weights: Optional[dict] = None,
+        document_ids_filter: Optional[list[str]] = None,
     ):
         if not query:
             return []
@@ -65,6 +65,7 @@ class RetrievalService:
                         top_k=top_k,
                         all_documents=all_documents,
                         exceptions=exceptions,
+                        document_ids_filter=document_ids_filter,
                     )
                 )
             if RetrievalMethod.is_support_semantic_search(retrieval_method):
@@ -80,6 +81,7 @@ class RetrievalService:
                         all_documents=all_documents,
                         retrieval_method=retrieval_method,
                         exceptions=exceptions,
+                        document_ids_filter=document_ids_filter,
                     )
                 )
             if RetrievalMethod.is_support_fulltext_search(retrieval_method):
@@ -131,7 +133,14 @@ class RetrievalService:
 
     @classmethod
     def keyword_search(
-        cls, flask_app: Flask, dataset_id: str, query: str, top_k: int, all_documents: list, exceptions: list
+        cls,
+        flask_app: Flask,
+        dataset_id: str,
+        query: str,
+        top_k: int,
+        all_documents: list,
+        exceptions: list,
+        document_ids_filter: Optional[list[str]] = None,
     ):
         with flask_app.app_context():
             try:
@@ -140,7 +149,10 @@ class RetrievalService:
                     raise ValueError("dataset not found")
 
                 keyword = Keyword(dataset=dataset)
-                documents = keyword.search(cls.escape_query_for_search(query), top_k=top_k)
+
+                documents = keyword.search(
+                    cls.escape_query_for_search(query), top_k=top_k, document_ids_filter=document_ids_filter
+                )
                 all_documents.extend(documents)
             except Exception as e:
                 exceptions.append(str(e))
@@ -157,6 +169,7 @@ class RetrievalService:
         all_documents: list,
         retrieval_method: str,
         exceptions: list,
+        document_ids_filter: Optional[list[str]] = None,
     ):
         with flask_app.app_context():
             try:
@@ -171,6 +184,7 @@ class RetrievalService:
                     top_k=top_k,
                     score_threshold=score_threshold,
                     filter={"group_id": [dataset.id]},
+                    document_ids_filter=document_ids_filter,
                 )
 
                 if documents:
@@ -243,7 +257,7 @@ class RetrievalService:
 
     @staticmethod
     def escape_query_for_search(query: str) -> str:
-        return json.dumps(query).strip('"')
+        return query.replace('"', '\\"')
 
     @classmethod
     def format_retrieval_documents(cls, documents: list[Document]) -> list[RetrievalSegments]:
@@ -277,6 +291,8 @@ class RetrievalService:
                     continue
 
                 dataset_document = dataset_documents[document_id]
+                if not dataset_document:
+                    continue
 
                 if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
                     # Handle parent-child documents

api/core/rag/datasource/vdb/analyticdb/analyticdb_vector.py

@@ -53,7 +53,7 @@ class AnalyticdbVector(BaseVector):
         self.analyticdb_vector.delete_by_metadata_field(key, value)
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
-        return self.analyticdb_vector.search_by_vector(query_vector)
+        return self.analyticdb_vector.search_by_vector(query_vector, **kwargs)
 
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
         return self.analyticdb_vector.search_by_full_text(query, **kwargs)

api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py

@@ -194,6 +194,13 @@ class AnalyticdbVectorBySql:
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
         top_k = kwargs.get("top_k", 4)
+        if not isinstance(top_k, int) or top_k <= 0:
+            raise ValueError("top_k must be a positive integer")
+        document_ids_filter = kwargs.get("document_ids_filter")
+        where_clause = "WHERE 1=1"
+        if document_ids_filter:
+            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
+            where_clause += f"AND metadata_->>'document_id' IN ({document_ids})"
         score_threshold = float(kwargs.get("score_threshold") or 0.0)
         with self._get_cursor() as cur:
             query_vector_str = json.dumps(query_vector)
@@ -202,7 +209,7 @@ class AnalyticdbVectorBySql:
                 f"SELECT t.id AS id, t.vector AS vector, (1.0 - t.score) AS score, "
                 f"t.page_content as page_content, t.metadata_ AS metadata_ "
                 f"FROM (SELECT id, vector, page_content, metadata_, vector <=> %s AS score "
-                f"FROM {self.table_name} ORDER BY score LIMIT {top_k} ) t",
+                f"FROM {self.table_name} {where_clause} ORDER BY score LIMIT {top_k} ) t",
                 (query_vector_str,),
             )
             documents = []
@@ -220,12 +227,19 @@ class AnalyticdbVectorBySql:
 
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
         top_k = kwargs.get("top_k", 4)
+        if not isinstance(top_k, int) or top_k <= 0:
+            raise ValueError("top_k must be a positive integer")
+        document_ids_filter = kwargs.get("document_ids_filter")
+        where_clause = ""
+        if document_ids_filter:
+            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
+            where_clause += f"AND metadata_->>'document_id' IN ({document_ids})"
         with self._get_cursor() as cur:
             cur.execute(
                 f"""SELECT id, vector, page_content, metadata_, 
                 ts_rank(to_tsvector, to_tsquery_from_text(%s, 'zh_cn'), 32) AS score
                 FROM {self.table_name}
-                WHERE to_tsvector@@to_tsquery_from_text(%s, 'zh_cn')
+                WHERE to_tsvector@@to_tsquery_from_text(%s, 'zh_cn') {where_clause}
                 ORDER BY score DESC
                 LIMIT {top_k}""",
                 (f"'{query}'", f"'{query}'"),

api/core/rag/datasource/vdb/baidu/baidu_vector.py

@@ -123,11 +123,21 @@ class BaiduVector(BaseVector):
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
         query_vector = [float(val) if isinstance(val, np.float64) else val for val in query_vector]
-        anns = AnnSearch(
-            vector_field=self.field_vector,
-            vector_floats=query_vector,
-            params=HNSWSearchParams(ef=kwargs.get("ef", 10), limit=kwargs.get("top_k", 4)),
-        )
+        document_ids_filter = kwargs.get("document_ids_filter")
+        if document_ids_filter:
+            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
+            anns = AnnSearch(
+                vector_field=self.field_vector,
+                vector_floats=query_vector,
+                params=HNSWSearchParams(ef=kwargs.get("ef", 10), limit=kwargs.get("top_k", 4)),
+                filter=f"document_id IN ({document_ids})",
+            )
+        else:
+            anns = AnnSearch(
+                vector_field=self.field_vector,
+                vector_floats=query_vector,
+                params=HNSWSearchParams(ef=kwargs.get("ef", 10), limit=kwargs.get("top_k", 4)),
+            )
         res = self._db.table(self._collection_name).search(
             anns=anns,
             projections=[self.field_id, self.field_text, self.field_metadata],

api/core/rag/datasource/vdb/chroma/chroma_vector.py

@@ -95,7 +95,15 @@ class ChromaVector(BaseVector):
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
         collection = self._client.get_or_create_collection(self._collection_name)
-        results: QueryResult = collection.query(query_embeddings=query_vector, n_results=kwargs.get("top_k", 4))
+        document_ids_filter = kwargs.get("document_ids_filter")
+        if document_ids_filter:
+            results: QueryResult = collection.query(
+                query_embeddings=query_vector,
+                n_results=kwargs.get("top_k", 4),
+                where={"document_id": {"$in": document_ids_filter}},  # type: ignore
+            )
+        else:
+            results: QueryResult = collection.query(query_embeddings=query_vector, n_results=kwargs.get("top_k", 4))  # type: ignore
         score_threshold = float(kwargs.get("score_threshold") or 0.0)
 
         # Check if results contain data

api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py

@@ -117,6 +117,9 @@ class ElasticSearchVector(BaseVector):
         top_k = kwargs.get("top_k", 4)
         num_candidates = math.ceil(top_k * 1.5)
         knn = {"field": Field.VECTOR.value, "query_vector": query_vector, "k": top_k, "num_candidates": num_candidates}
+        document_ids_filter = kwargs.get("document_ids_filter")
+        if document_ids_filter:
+            knn["filter"] = {"terms": {"metadata.document_id": document_ids_filter}}
 
         results = self._client.search(index=self._collection_name, knn=knn, size=top_k)
 
@@ -145,6 +148,9 @@ class ElasticSearchVector(BaseVector):
 
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
         query_str = {"match": {Field.CONTENT_KEY.value: query}}
+        document_ids_filter = kwargs.get("document_ids_filter")
+        if document_ids_filter:
+            query_str["filter"] = {"terms": {"metadata.document_id": document_ids_filter}}  # type: ignore
         results = self._client.search(index=self._collection_name, query=query_str, size=kwargs.get("top_k", 4))
         docs = []
         for hit in results["hits"]["hits"]:
@@ -190,7 +196,8 @@ class ElasticSearchVector(BaseVector):
                         Field.METADATA_KEY.value: {
                             "type": "object",
                             "properties": {
-                                "doc_id": {"type": "keyword"}  # Map doc_id to keyword type
+                                "doc_id": {"type": "keyword"},  # Map doc_id to keyword type
+                                "document_id": {"type": "keyword"},  # Map doc_id to keyword type
                             },
                         },
                     }

api/core/rag/datasource/vdb/field.py

@@ -11,3 +11,4 @@ class Field(Enum):
     TEXT_KEY = "text"
     PRIMARY_KEY = "id"
     DOC_ID = "metadata.doc_id"
+    DOCUMENT_ID = "metadata.document_id"

api/core/rag/datasource/vdb/lindorm/lindorm_vector.py

@@ -168,7 +168,12 @@ class LindormVectorStore(BaseVector):
             raise ValueError("All elements in query_vector should be floats")
 
         top_k = kwargs.get("top_k", 10)
-        query = default_vector_search_query(query_vector=query_vector, k=top_k, **kwargs)
+        document_ids_filter = kwargs.get("document_ids_filter")
+        filters = []
+        if document_ids_filter:
+            filters.append({"terms": {"metadata.document_id": document_ids_filter}})
+        query = default_vector_search_query(query_vector=query_vector, k=top_k, filters=filters, **kwargs)
+
         try:
             params = {}
             if self._using_ugc:
@@ -206,7 +211,10 @@ class LindormVectorStore(BaseVector):
         should = kwargs.get("should")
         minimum_should_match = kwargs.get("minimum_should_match", 0)
         top_k = kwargs.get("top_k", 10)
-        filters = kwargs.get("filter")
+        filters = kwargs.get("filter", [])
+        document_ids_filter = kwargs.get("document_ids_filter")
+        if document_ids_filter:
+            filters.append({"terms": {"metadata.document_id": document_ids_filter}})
         routing = self._routing
         full_text_query = default_text_search_query(
             query_text=query,

api/core/rag/datasource/vdb/milvus/milvus_vector.py

@@ -228,12 +228,18 @@ class MilvusVector(BaseVector):
         """
         Search for documents by vector similarity.
         """
+        document_ids_filter = kwargs.get("document_ids_filter")
+        filter = ""
+        if document_ids_filter:
+            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
+            filter = f'metadata["document_id"] in ({document_ids})'
         results = self._client.search(
             collection_name=self._collection_name,
             data=[query_vector],
             anns_field=Field.VECTOR.value,
             limit=kwargs.get("top_k", 4),
             output_fields=[Field.CONTENT_KEY.value, Field.METADATA_KEY.value],
+            filter=filter,
         )
 
         return self._process_search_results(
@@ -249,6 +255,11 @@ class MilvusVector(BaseVector):
         if not self._hybrid_search_enabled or not self.field_exists(Field.SPARSE_VECTOR.value):
             logger.warning("Full-text search is not supported in current Milvus version (requires >= 2.5.0)")
             return []
+        document_ids_filter = kwargs.get("document_ids_filter")
+        filter = ""
+        if document_ids_filter:
+            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
+            filter = f'metadata["document_id"] in ({document_ids})'
 
         results = self._client.search(
             collection_name=self._collection_name,
@@ -256,6 +267,7 @@ class MilvusVector(BaseVector):
             anns_field=Field.SPARSE_VECTOR.value,
             limit=kwargs.get("top_k", 4),
             output_fields=[Field.CONTENT_KEY.value, Field.METADATA_KEY.value],
+            filter=filter,
         )
 
         return self._process_search_results(

api/core/rag/datasource/vdb/myscale/myscale_vector.py

@@ -125,12 +125,18 @@ class MyScaleVector(BaseVector):
 
     def _search(self, dist: str, order: SortOrder, **kwargs: Any) -> list[Document]:
         top_k = kwargs.get("top_k", 4)
+        if not isinstance(top_k, int) or top_k <= 0:
+            raise ValueError("top_k must be a positive integer")
         score_threshold = float(kwargs.get("score_threshold") or 0.0)
         where_str = (
             f"WHERE dist < {1 - score_threshold}"
             if self._metric.upper() == "COSINE" and order == SortOrder.ASC and score_threshold > 0.0
             else ""
         )
+        document_ids_filter = kwargs.get("document_ids_filter")
+        if document_ids_filter:
+            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
+            where_str = f"{where_str} AND metadata['document_id'] in ({document_ids})"
         sql = f"""
             SELECT text, vector, metadata, {dist} as dist FROM {self._config.database}.{self._collection_name}
             {where_str} ORDER BY dist {order.value} LIMIT {top_k}

api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py

@@ -154,6 +154,11 @@ class OceanBaseVector(BaseVector):
         return []
 
     def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
+        document_ids_filter = kwargs.get("document_ids_filter")
+        where_clause = None
+        if document_ids_filter:
+            document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
+            where_clause = f"metadata->>'$.document_id' in ({document_ids})"
         ef_search = kwargs.get("ef_search", self._hnsw_ef_search)
         if ef_search != self._hnsw_ef_search:
             self._client.set_ob_hnsw_ef_search(ef_search)
@@ -167,6 +172,7 @@ class OceanBaseVector(BaseVector):
             distance_func=func.l2_distance,
             output_column_names=["text", "metadata"],
             with_dist=True,
+            where_clause=where_clause,
         )
         docs = []
         for text, metadata, distance in cur:

api/core/rag/datasource/vdb/opengauss/opengauss.py

@@ -0,0 +1,240 @@
+import json
+import uuid
+from contextlib import contextmanager
+from typing import Any
+
+import psycopg2.extras  # type: ignore
+import psycopg2.pool  # type: ignore
+from pydantic import BaseModel, model_validator
+
+from configs import dify_config
+from core.rag.datasource.vdb.vector_base import BaseVector
+from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory
+from core.rag.datasource.vdb.vector_type import VectorType
+from core.rag.embedding.embedding_base import Embeddings
+from core.rag.models.document import Document
+from extensions.ext_redis import redis_client
+from models.dataset import Dataset
+
+
+class OpenGaussConfig(BaseModel):
+    host: str
+    port: int
+    user: str
+    password: str
+    database: str
+    min_connection: int
+    max_connection: int
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_config(cls, values: dict) -> dict:
+        if not values["host"]:
+            raise ValueError("config OPENGAUSS_HOST is required")
+        if not values["port"]:
+            raise ValueError("config OPENGAUSS_PORT is required")
+        if not values["user"]:
+            raise ValueError("config OPENGAUSS_USER is required")
+        if not values["password"]:
+            raise ValueError("config OPENGAUSS_PASSWORD is required")
+        if not values["database"]:
+            raise ValueError("config OPENGAUSS_DATABASE is required")
+        if not values["min_connection"]:
+            raise ValueError("config OPENGAUSS_MIN_CONNECTION is required")
+        if not values["max_connection"]:
+            raise ValueError("config OPENGAUSS_MAX_CONNECTION is required")
+        if values["min_connection"] > values["max_connection"]:
+            raise ValueError("config OPENGAUSS_MIN_CONNECTION should less than OPENGAUSS_MAX_CONNECTION")
+        return values
+
+
+SQL_CREATE_TABLE = """
+CREATE TABLE IF NOT EXISTS {table_name} (
+    id UUID PRIMARY KEY,
+    text TEXT NOT NULL,
+    meta JSONB NOT NULL,
+    embedding vector({dimension}) NOT NULL
+);
+"""
+
+SQL_CREATE_INDEX = """
+CREATE INDEX IF NOT EXISTS embedding_cosine_{table_name}_idx ON {table_name} 
+USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
+"""
+
+
+class OpenGauss(BaseVector):
+    def __init__(self, collection_name: str, config: OpenGaussConfig):
+        super().__init__(collection_name)
+        self.pool = self._create_connection_pool(config)
+        self.table_name = f"embedding_{collection_name}"
+
+    def get_type(self) -> str:
+        return VectorType.OPENGAUSS
+
+    def _create_connection_pool(self, config: OpenGaussConfig):
+        return psycopg2.pool.SimpleConnectionPool(
+            config.min_connection,
+            config.max_connection,
+            host=config.host,
+            port=config.port,
+            user=config.user,
+            password=config.password,
+            database=config.database,
+        )
+
+    @contextmanager
+    def _get_cursor(self):
+        conn = self.pool.getconn()
+        cur = conn.cursor()
+        try:
+            yield cur
+        finally:
+            cur.close()
+            conn.commit()
+            self.pool.putconn(conn)
+
+    def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs):
+        dimension = len(embeddings[0])
+        self._create_collection(dimension)
+        return self.add_texts(texts, embeddings)
+
+    def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs):
+        values = []
+        pks = []
+        for i, doc in enumerate(documents):
+            if doc.metadata is not None:
+                doc_id = doc.metadata.get("doc_id", str(uuid.uuid4()))
+                pks.append(doc_id)
+                values.append(
+                    (
+                        doc_id,
+                        doc.page_content,
+                        json.dumps(doc.metadata),
+                        embeddings[i],
+                    )
+                )
+        with self._get_cursor() as cur:
+            psycopg2.extras.execute_values(
+                cur, f"INSERT INTO {self.table_name} (id, text, meta, embedding) VALUES %s", values
+            )
+        return pks
+
+    def text_exists(self, id: str) -> bool:
+        with self._get_cursor() as cur:
+            cur.execute(f"SELECT id FROM {self.table_name} WHERE id = %s", (id,))
+            return cur.fetchone() is not None
+
+    def get_by_ids(self, ids: list[str]) -> list[Document]:
+        with self._get_cursor() as cur:
+            cur.execute(f"SELECT meta, text FROM {self.table_name} WHERE id IN %s", (tuple(ids),))
+            docs = []
+            for record in cur:
+                docs.append(Document(page_content=record[1], metadata=record[0]))
+        return docs
+
+    def delete_by_ids(self, ids: list[str]) -> None:
+        # Avoiding crashes caused by performing delete operations on empty lists in certain scenarios
+        # Scenario 1: extract a document fails, resulting in a table not being created.
+        # Then clicking the retry button triggers a delete operation on an empty list.
+        if not ids:
+            return
+        with self._get_cursor() as cur:
+            cur.execute(f"DELETE FROM {self.table_name} WHERE id IN %s", (tuple(ids),))
+
+    def delete_by_metadata_field(self, key: str, value: str) -> None:
+        with self._get_cursor() as cur:
+            cur.execute(f"DELETE FROM {self.table_name} WHERE meta->>%s = %s", (key, value))
+
+    def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]:
+        """
+        Search the nearest neighbors to a vector.
+
+        :param query_vector: The input vector to search for similar items.
+        :param top_k: The number of nearest neighbors to return, default is 5.
+        :return: List of Documents that are nearest to the query vector.
+        """
+        top_k = kwargs.get("top_k", 4)
+        if not isinstance(top_k, int) or top_k <= 0:
+            raise ValueError("top_k must be a positive integer")
+        with self._get_cursor() as cur:
+            cur.execute(
+                f"SELECT meta, text, embedding <=> %s AS distance FROM {self.table_name}"
+                f" ORDER BY distance LIMIT {top_k}",
+                (json.dumps(query_vector),),
+            )
+            docs = []
+            score_threshold = float(kwargs.get("score_threshold") or 0.0)
+            for record in cur:
+                metadata, text, distance = record
+                score = 1 - distance
+                metadata["score"] = score
+                if score > score_threshold:
+                    docs.append(Document(page_content=text, metadata=metadata))
+        return docs
+
+    def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
+        top_k = kwargs.get("top_k", 5)
+        if not isinstance(top_k, int) or top_k <= 0:
+            raise ValueError("top_k must be a positive integer")
+        with self._get_cursor() as cur:
+            cur.execute(
+                f"""SELECT meta, text, ts_rank(to_tsvector(coalesce(text, '')), plainto_tsquery(%s)) AS score
+                FROM {self.table_name}
+                WHERE to_tsvector(text) @@ plainto_tsquery(%s)
+                ORDER BY score DESC
+                LIMIT {top_k}""",
+                # f"'{query}'" is required in order to account for whitespace in query
+                (f"'{query}'", f"'{query}'"),
+            )
+
+            docs = []
+
+            for record in cur:
+                metadata, text, score = record
+                metadata["score"] = score
+                docs.append(Document(page_content=text, metadata=metadata))
+
+        return docs
+
+    def delete(self) -> None:
+        with self._get_cursor() as cur:
+            cur.execute(f"DROP TABLE IF EXISTS {self.table_name}")
+
+    def _create_collection(self, dimension: int):
+        cache_key = f"vector_indexing_{self._collection_name}"
+        lock_name = f"{cache_key}_lock"
+        with redis_client.lock(lock_name, timeout=20):
+            collection_exist_cache_key = f"vector_indexing_{self._collection_name}"
+            if redis_client.get(collection_exist_cache_key):
+                return
+
+            with self._get_cursor() as cur:
+                cur.execute(SQL_CREATE_TABLE.format(table_name=self.table_name, dimension=dimension))
+                if dimension <= 2000:
+                    cur.execute(SQL_CREATE_INDEX.format(table_name=self.table_name))
+            redis_client.set(collection_exist_cache_key, 1, ex=3600)
+
+
+class OpenGaussFactory(AbstractVectorFactory):
+    def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings) -> OpenGauss:
+        if dataset.index_struct_dict:
+            class_prefix: str = dataset.index_struct_dict["vector_store"]["class_prefix"]
+            collection_name = class_prefix
+        else:
+            dataset_id = dataset.id
+            collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+            dataset.index_struct = json.dumps(self.gen_index_struct_dict(VectorType.OPENGAUSS, collection_name))
+
+        return OpenGauss(
+            collection_name=collection_name,
+            config=OpenGaussConfig(
+                host=dify_config.OPENGAUSS_HOST or "localhost",
+                port=dify_config.OPENGAUSS_PORT,
+                user=dify_config.OPENGAUSS_USER or "postgres",
+                password=dify_config.OPENGAUSS_PASSWORD or "",
+                database=dify_config.OPENGAUSS_DATABASE or "dify",
+                min_connection=dify_config.OPENGAUSS_MIN_CONNECTION,
+                max_connection=dify_config.OPENGAUSS_MAX_CONNECTION,
+            ),
+        )