feat: bump version to 0.3.31 (#1584)

Co-authored-by: jyong <jyong@dify.ai>

.devcontainer/Dockerfile

@@ -1,11 +1,8 @@
-FROM mcr.microsoft.com/devcontainers/anaconda:0-3
+FROM mcr.microsoft.com/devcontainers/python:3.10
+
+COPY . .
 
-# Copy environment.yml (if found) to a temp location so we update the environment. Also
-# copy "noop.txt" so the COPY instruction does not fail if no environment.yml exists.
-COPY environment.yml* .devcontainer/noop.txt /tmp/conda-tmp/
-RUN if [ -f "/tmp/conda-tmp/environment.yml" ]; then umask 0002 && /opt/conda/bin/conda env update -n base -f /tmp/conda-tmp/environment.yml; fi \
-    && rm -rf /tmp/conda-tmp
 
 # [Optional] Uncomment this section to install additional OS packages.
 # RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
-#     && apt-get -y install --no-install-recommends <your-package-list-here>
+#     && apt-get -y install --no-install-recommends <your-package-list-here>

.devcontainer/devcontainer.json

@@ -1,13 +1,12 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the
 // README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
 {
-	"name": "Anaconda (Python 3)",
+	"name": "Python 3.10",
 	"build": { 
 		"context": "..",
 		"dockerfile": "Dockerfile"
 	},
 	"features": {
-		"ghcr.io/dhoeric/features/act:1": {},
 		"ghcr.io/devcontainers/features/node:1": {
 			"nodeGypDependencies": true,
 			"version": "lts"

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,43 @@
+# Dify Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Language Policy
+
+To facilitate clear and effective communication, all discussions, comments, documentation, and pull requests in this project should be conducted in English. This ensures that all contributors can participate and collaborate effectively.
+
+

.github/ISSUE_TEMPLATE/bug_report.yml

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

.github/ISSUE_TEMPLATE/config.yml

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

.github/ISSUE_TEMPLATE/document_issue.yml

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

.github/ISSUE_TEMPLATE/feature_request.yml

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

.github/ISSUE_TEMPLATE/help_wanted.yml

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

.github/ISSUE_TEMPLATE/translation_issue.yml

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

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

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

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

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

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

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

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

@@ -31,7 +31,7 @@ jobs:
       with:
         images: langgenius/dify-api
         tags: |
-          type=raw,value=latest,enable={{is_default_branch}}
+          type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
           type=ref,event=branch
           type=sha,enable=true,priority=100,prefix=,suffix=,format=long
           type=semver,pattern={{major}}.{{minor}}.{{patch}}

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

@@ -31,7 +31,7 @@ jobs:
       with:
         images: langgenius/dify-web
         tags: |
-          type=raw,value=latest,enable={{is_default_branch}}
+          type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
           type=ref,event=branch
           type=sha,enable=true,priority=100,prefix=,suffix=,format=long
           type=semver,pattern={{major}}.{{minor}}.{{patch}}

.github/workflows/check_no_chinese_comments.py

@@ -1,36 +0,0 @@
-import os
-import re
-from zhon.hanzi import punctuation
-
-def has_chinese_characters(text):
-    for char in text:
-        if '\u4e00' <= char <= '\u9fff' or char in punctuation:
-            return True
-    return False
-
-def check_file_for_chinese_comments(file_path):
-    with open(file_path, 'r', encoding='utf-8') as file:
-        for line_number, line in enumerate(file, start=1):
-            if has_chinese_characters(line):
-                print(f"Found Chinese characters in {file_path} on line {line_number}:")
-                print(line.strip())
-                return True
-    return False
-
-def main():
-    has_chinese = False
-    excluded_files = ["model_template.py", 'stopwords.py', 'commands.py',
-                      'indexing_runner.py', 'web_reader_tool.py', 'spark_provider.py']
-
-    for root, _, files in os.walk("."):
-        for file in files:
-            if file.endswith(".py") and file not in excluded_files:
-                file_path = os.path.join(root, file)
-                if check_file_for_chinese_comments(file_path):
-                    has_chinese = True
-
-    if has_chinese:
-        raise Exception("Found Chinese characters in Python files. Please remove them.")
-
-if __name__ == "__main__":
-    main()

.github/workflows/check_no_chinese_comments.yml

@@ -1,31 +0,0 @@
-name: Check for Chinese comments
-
-on:
-  push:
-    branches:
-      - 'main'
-  pull_request:
-    branches:
-      - main
-
-jobs:
-  check-chinese-comments:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Check out repository
-      uses: actions/checkout@v2
-
-    - name: Set up Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: 3.9
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install zhon
-
-    - name: Run script to check for Chinese comments
-      run: |
-        python .github/workflows/check_no_chinese_comments.py

.github/workflows/stale.yml

@@ -20,11 +20,11 @@ jobs:
     steps:
     - uses: actions/stale@v5
       with:
-        days-before-issue-stale: 30
+        days-before-issue-stale: 15
         days-before-issue-close: 3
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         stale-issue-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
         stale-pr-message: "Close due to it's no longer active, if you have any questions, you can reopen it."
         stale-issue-label: 'no-issue-activity'
         stale-pr-label: 'no-pr-activity'
-        any-of-labels: 'duplicate,question,invalid,wontfix,no-issue-activity,no-pr-activity,enhancement'
+        any-of-labels: 'duplicate,question,invalid,wontfix,no-issue-activity,no-pr-activity,enhancement,cant-reproduce,help-wanted'

.gitignore

@@ -144,9 +144,11 @@ docker/volumes/app/storage/*
 docker/volumes/db/data/*
 docker/volumes/redis/data/*
 docker/volumes/weaviate/*
+docker/volumes/qdrant/*
 
 sdks/python-client/build
 sdks/python-client/dist
 sdks/python-client/dify_client.egg-info
 
-.vscode/
+.vscode/*
+!.vscode/launch.json

CONTRIBUTING.md

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

CONTRIBUTING_CN.md

@@ -16,15 +16,15 @@
 
 ## 本地开发
 
-要设置一个可工作的开发环境，只需 fork 项目的 git 存储库，并使用适当的软件包管理器安装后端和前端依赖项，然后创建并运行 docker-compose 堆栈。
+要设置一个可工作的开发环境，只需 fork 项目的 git 存储库，并使用适当的软件包管理器安装后端和前端依赖项，然后创建并运行 docker-compose。
 
 ### Fork存储库
 
-您需要 fork [存储库](https://github.com/langgenius/dify)。
+您需要 fork [Git 仓库](https://github.com/langgenius/dify)。
 
 ### 克隆存储库
 
-克隆您在 GitHub 上 fork 的存储库：
+克隆您在 GitHub 上 fork 的仓库：
 
 ```
 git clone git@github.com:<github_username>/dify.git

CONTRIBUTING_JA.md

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

README.md

@@ -1,62 +1,67 @@
-![](./images/describe-en.png)
+[![](./images/describe.png)](https://dify.ai)
 <p align="center">
   <a href="./README.md">English</a> |
   <a href="./README_CN.md">简体中文</a> |
   <a href="./README_JA.md">日本語</a> |
-  <a href="./README_ES.md">Español</a>
+  <a href="./README_ES.md">Español</a> |
+  <a href="./README_KL.md">Klingon</a>
 </p>
 
-#### [Website](https://dify.ai) • [Docs](https://docs.dify.ai) • [Deployment Docs](https://docs.dify.ai/getting-started/install-self-hosted) •  [FAQ](https://docs.dify.ai/getting-started/faq) • [Twitter](https://twitter.com/dify_ai) • [Discord](https://discord.gg/FngNHpbcY7)
+<p align="center">
+    <a href="https://dify.ai" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/AI-Dify?logo=AI&logoColor=%20%23f5f5f5&label=Dify&labelColor=%20%23155EEF&color=%23EAECF0"></a>
+    <a href="https://discord.gg/FngNHpbcY7" target="_blank">
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+            alt="chat on Discord"></a>
+    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
+        <img src="https://img.shields.io/twitter/follow/dify_ai?style=social&logo=X"
+            alt="follow on Twitter"></a>
+    <a href="https://hub.docker.com/u/langgenius" target="_blank">
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web"></a>
+</p>
 
-**Dify** is an easy-to-use LLMOps platform designed to empower more people to create sustainable, AI-native applications. With visual orchestration for various application types, Dify offers out-of-the-box, ready-to-use applications that can also serve as Backend-as-a-Service APIs. Unify your development process with one API for plugins and datasets integration, and streamline your operations using a single interface for prompt engineering, visual analytics, and continuous improvement.
+**Dify** is an LLM application development platform that has already seen over **100,000** applications built on Dify.AI. It integrates the concepts of Backend as a Service and LLMOps, covering the core tech stack required for building generative AI-native applications, including a built-in RAG engine. With Dify, **you can self-deploy capabilities similar to Assistants API and GPTs based on any LLMs.**
 
-Applications created with Dify include:
-
-Out-of-the-box web sites supporting form mode and chat conversation mode
-A single API encompassing plugin capabilities, context enhancement, and more, saving you backend coding effort
-Visual data analysis, log review, and annotation for applications
-
-## Highlighted Features
-**1. LLMs support:** Choose capabilities based on different models when building your Dify AI apps. Dify is compatible with Langchain, meaning it will support various LLMs. Currently supported:
-
-- [x] **OpenAI**: GPT4, GPT3.5-turbo, GPT3.5-turbo-16k, text-davinci-003 
-- [x] **Azure OpenAI Service**
-- [x] **Anthropic**: Claude2, Claude-instant
-- [x] **Replicate**
-- [x] **Hugging Face Hub**
-- [x] **ChatGLM**
-- [x] **Llama2**
-- [x] **MiniMax**
-- [x] **Spark**
-- [x] **Wenxin**
-- [x] **Tongyi**
-
-
-We provide the following free resources for registered Dify cloud users (sign up at [dify.ai](https://dify.ai)):
-* 600,000 free Claude model tokens to build Claude-powered apps
-* 200 free OpenAI queries to build OpenAI-based apps
-
-  
-**2. Visual orchestration:** Build an AI app in minutes by writing and debugging prompts visually.
-
-**3. Text embedding:** Fully automated text preprocessing embeds your data as context without complex concepts. Supports PDF, TXT, and syncing data from Notion, webpages, APIs.
-
-**4. API-based:**  Backend-as-a-service. Access web apps directly or integrate via APIs without complex backend setup.
-
-**5. Plugins:** Dify "Smart Chat" now supports first-party plugins like web browsing, Google search, Wikipedia to enable online lookup, analyzing web content, and explaining the AI's reasoning process conversationally.
-
-**6. Team workspaces:** Team members can join workspaces to collaboratively edit, manage, and use team AI apps.
-
-**7. Data labeling and improvement:**  Visually inspect AI app logs and improve data via labeling. Observe the AI's reasoning process to continuously enhance performance. (Coming soon)
-
-## Use cases
-* [Create an AI ChatBot with Business Data in Minutes.](https://docs.dify.ai/use-cases/create-an-ai-chatbot-with-business-data-in-minutes)
-* [How to Build an Notion AI Assistant Based on Your Own Notes?](https://docs.dify.ai/use-cases/build-an-notion-ai-assistant)
-* [Create a Midjoureny Prompt Bot Without Code in Just a Few Minutes.](https://docs.dify.ai/use-cases/create-a-midjoureny-prompt-bot-with-dify)
+![](./images/demo.png)
 
 ## Use Cloud Services
 
-Visit [Dify.ai](https://dify.ai)
+Using [Dify.AI Cloud](https://dify.ai) provides all the capabilities of the open-source version, and includes a complimentary 200 GPT trial credits.
+
+## Why Dify
+
+Dify features model neutrality and is a complete, engineered tech stack compared to hardcoded development libraries like LangChain. Unlike OpenAI's Assistants API, Dify allows for full local deployment of services.
+
+| Feature | Dify.AI | Assistants API | LangChain |
+|---------|---------|----------------|-----------|
+| **Programming Approach** | API-oriented | API-oriented | Python Code-oriented |
+| **Ecosystem Strategy** | Open Source | Closed and Commercial | Open Source |
+| **RAG Engine** | Supported | Supported | Not Supported |
+| **Prompt IDE** | Included | Included | None |
+| **Supported LLMs** | Rich Variety | Only GPT | Rich Variety |
+| **Local Deployment** | Supported | Not Supported | Not Applicable |
+
+## Features
+
+![](./images/models.png)
+
+**1. LLM Support**: Integration with OpenAI's GPT family of models, or the open-source Llama2 family models. In fact, Dify supports mainstream commercial models and open-source models (locally deployed or based on MaaS).
+
+**2. Prompt IDE**: Visual orchestration of applications and services based on LLMs with your team.
+
+**3. RAG Engine**: Includes various RAG capabilities based on full-text indexing or vector database embeddings, allowing direct upload of PDFs, TXTs, and other text formats.
+
+**4. Agents**: A Function Calling based Agent framework that allows users to configure what they see is what they get. Dify includes basic plugin capabilities like Google Search.
+
+**5. Continuous Operations**: Monitor and analyze application logs and performance, continuously improving Prompts, datasets, or models using production data.
+
+## Before You Start
+
+- [Website](https://dify.ai)
+- [Docs](https://docs.dify.ai)
+- [Deployment Docs](https://docs.dify.ai/getting-started/install-self-hosted)
+- [FAQ](https://docs.dify.ai/getting-started/faq) 
+
 
 ## Install the Community Edition
 
@@ -85,88 +90,28 @@ You can go to https://github.com/BorisPolonsky/dify-helm for deployment informat
 
 ### Configuration
 
-If you need to customize the configuration, please refer to the comments in our [docker-compose.yml](docker/docker-compose.yaml) file and manually set the environment configuration. After making the changes, please run 'docker-compose up -d' again.
+If you need to customize the configuration, please refer to the comments in our [docker-compose.yml](docker/docker-compose.yaml) file and manually set the environment configuration. After making the changes, please run `docker-compose up -d` again. You can see the full list of environment variables in our [docs](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
-## Roadmap
-
-Features under development:
-
-- **Datasets**, supporting more datasets, e.g. syncing content from Notion or webpages
-We will support more datasets, including text, webpages, and even Notion content. Users can build AI applications based on their own data sources.
-- **Plugins**, introducing ChatGPT Plugin-standard plugins for applications, or using Dify-produced plugins
-We will release plugins complying with ChatGPT standard, or Dify's own plugins to enable more capabilities in applications. 
-
-
-## Q&A
-
-**Q: What can I do with Dify?**
-
-A: Dify is a simple yet powerful LLM development and operations tool. You can use it to build commercial-grade applications, personal assistants. If you want to develop your own applications, LangDifyGenius can save you backend work in integrating with OpenAI and offer visual operations capabilities, allowing you to continuously improve and train your GPT model.
-
-**Q: How do I use Dify to "train" my own model?**
-
-A: A valuable application consists of Prompt Engineering, context enhancement, and Fine-tuning. We've created a hybrid programming approach combining Prompts with programming languages (similar to a template engine), making it easy to accomplish long-text embedding or capturing subtitles from a user-input Youtube video - all of which will be submitted as context for LLMs to process. We place great emphasis on application operability, with data generated by users during App usage available for analysis, annotation, and continuous training. Without the right tools, these steps can be time-consuming.
-
-**Q: What do I need to prepare if I want to create my own application?**
-
-A: We assume you already have an OpenAI API Key; if not, please register for one. If you already have some content that can serve as training context, that's great!
-
-**Q: What interface languages are available?**
-
-A: English and Chinese are currently supported, and you can contribute language packs to us.
 
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
 
-## Contributing 
+## Community & Support
 
-We welcome you to contribute to Dify to help make Dify better. We welcome contributions in various ways, submitting code, issues, new ideas, or sharing the interesting and useful AI applications you have created based on Dify. At the same time, we also welcome you to share Dify at different events, conferences, and social media.
+We welcome you to contribute to Dify to help make Dify better in various ways, submitting code, issues, new ideas, or sharing the interesting and useful AI applications you have created based on Dify. At the same time, we also welcome you to share Dify at different events, conferences, and social media.
 
-### Submit a Pull Request 
+- [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs and errors you encounter using Dify.AI, see the [Contribution Guide](CONTRIBUTING.md).
+- [Email Support](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify). Best for: questions you have about using Dify.AI.
+- [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
+- [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
+- [Business License](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). Best for: business inquiries of licensing Dify.AI for commercial use.
 
-To ensure proper review, all code contributions, including from contributors with direct commit access, must be submitted as PR requests and approved by core developers before merging branches. 
-We welcome PRs from everyone! If you're willing to help out, you can learn more about how to contribute code to the project in the [Contribution Guide](CONTRIBUTING.md).  
-
-### Submit issues or ideas  
-
-You can submit your issues or ideas by adding issues to the Dify repository. If you encounter issues, please describe the steps you took to encounter the issue as much as possible so we can better discover it. If you have any new ideas for our product, we also welcome your feedback. Please share your insights as much as possible so we can get more feedback and further discussion in the community.  
-
-### Share your applications
-
-We encourage all community members to share their AI applications built on Dify, which can be applied to different scenarios or different users. This will provide powerful inspiration for people who want to create AI capabilities! You can share your experience by [submitting an issue in the Dify-user-case repository](https://github.com/langgenius/dify-user-case/issues).  
-
-### Share Dify with others
-
-We encourage community contributors to actively demonstrate different aspects of using Dify. You can talk or share any feature of using Dify at  meetups and conferences, blogs or social media. We believe your unique sharing will be of great help to others!  Mention @Dify.AI on Twitter and/or communicate on [Discord](https://discord.gg/FngNHpbcY7) so we can give pointers and tips and help you spread the word by promoting your content on the different Dify communication channels.
-
-### Help others 
-You can also help people in need of help on Discord, GitHub issues or other social platforms, guide others to solve problems encountered during use and share usage experiences. This is also a great contribution! If you want to become a maintainer of the Dify community, please contact the official team via [Discord](https://discord.gg/FngNHpbcY7) or email us at support@dify.ai. 
-
-
-## Contact Us
-
-If you have any questions, suggestions, or partnership inquiries, feel free to contact us through the following channels:
-
-- Submit an Issue or PR on our GitHub Repo
-- Join the discussion in our [Discord](https://discord.gg/FngNHpbcY7) Community
-- Send an email to hello@dify.ai
-
-We're eager to assist you and together create more fun and useful AI applications!
-
-## Security
+## Security Disclosure
 
 To protect your privacy, please avoid posting security issues on GitHub. Instead, send your questions to security@dify.ai and we will provide you with a more detailed answer.
 
-## Citation
-
-This software uses the following open-source software:
-
-- Chase, H. (2022). LangChain [Computer software]. https://github.com/hwchase17/langchain
-
-For more information, please refer to the official website or license text of the respective software.
-
 ## License
 
-This repository is available under the [Dify Open Source License](LICENSE).
+This repository is available under the [Dify Open Source License](LICENSE), which is essentially Apache 2.0 with a few additional restrictions.

README_CN.md

@@ -1,61 +1,63 @@
-![](./images/describe-cn.jpg)
+[![](./images/describe.png)](https://dify.ai)
 <p align="center">
   <a href="./README.md">English</a> |
   <a href="./README_CN.md">简体中文</a> |
   <a href="./README_JA.md">日本語</a> |
-  <a href="./README_ES.md">Español</a>
+  <a href="./README_ES.md">Español</a> |
+  <a href="./README_KL.md">Klingon</a>
 </p>
 
+<p align="center">
+    <a href="https://dify.ai" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/AI-Dify?logo=AI&logoColor=%20%23f5f5f5&label=Dify&labelColor=%20%23155EEF&color=%23EAECF0"></a>
+    <a href="https://discord.gg/FngNHpbcY7" target="_blank">
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+            alt="chat on Discord"></a>
+    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
+        <img src="https://img.shields.io/twitter/follow/dify_ai?style=social&logo=X"
+            alt="follow on Twitter"></a>
+    <a href="https://hub.docker.com/u/langgenius" target="_blank">
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web"></a>
+</p>
 
-####  [官方网站](https://dify.ai) •  [使用文档](https://docs.dify.ai/v/zh-hans)  · [部署文档](https://docs.dify.ai/v/zh-hans/getting-started/install-self-hosted)  ·  [FAQ](https://docs.dify.ai/v/zh-hans/getting-started/faq) • [Twitter](https://twitter.com/dify_ai) •  [Discord](https://discord.gg/FngNHpbcY7)
+Dify 是一个 LLM 应用开发平台，已经有超过 10 万个应用基于 Dify.AI 构建。它融合了 Backend as Service 和 LLMOps 的理念，涵盖了构建生成式 AI 原生应用所需的核心技术栈，包括一个内置 RAG 引擎。使用 Dify，你可以基于任何模型自部署类似 Assistants API 和 GPTs 的能力。
 
-**Dify** 是一个易用的 LLMOps 平台，基于不同的大型语言模型能力，让更多人可以简易地创建可持续运营的原生 AI 应用。Dify 提供多种类型应用的可视化编排，应用可开箱即用，也能以“后端即服务”的 API 提供服务。
+![](./images/demo.png)
 
-通过 Dify 创建的应用包含了：
+## 为什么选择 Dify
 
-- 开箱即用的的 Web 站点，支持表单模式和聊天对话模式
-- 一套 API 即可包含插件、上下文增强等能力，替你省下了后端代码的编写工作
-- 可视化的对应用进行数据分析，查阅日志或进行标注
+Dify 具有模型中立性，相较 LangChain 等硬编码开发库 Dify 是一个完整的、工程化的技术栈，而相较于 OpenAI 的 Assistants API 你可以完全将服务部署在本地。
+
+| 功能 | Dify.AI | Assistants API | LangChain |
+| --- | --- | --- | --- |
+| 编程方式 | 面向 API | 面向 API | 面向 Python 代码 |
+| 生态策略 | 开源 | 封闭且商用 | 开源 |
+| RAG 引擎 | 支持 | 支持 | 不支持 |
+| Prompt IDE | 包含 | 包含 | 没有 |
+| 支持的 LLMs | 丰富 | 仅 GPT | 丰富 |
+| 本地部署 | 支持 | 不支持 | 不适用 |
 
 
+## 特点
 
-## 核心能力
-1. **模型支持：** 你可以在 Dify 上选择基于不同模型的能力来开发你的 AI 应用。Dify 兼容 Langchain，这意味着我们将逐步支持多种 LLMs ，目前支持的模型供应商：
+![](./images/models.png)
 
-- [x] **OpenAI**：GPT4、GPT3.5-turbo、GPT3.5-turbo-16k、text-davinci-003 
-- [x] **Azure OpenAI Service**
-- [x] **Anthropic**：Claude2、Claude-instant
-- [x] **Replicate**
-- [x] **Hugging Face Hub**
-- [x] **ChatGLM**
-- [x] **Llama2**
-- [x] **MiniMax**
-- [x] **讯飞星火大模型**
-- [x] **文心一言**
-- [x] **通义千问**
+**1. LLM支持**：与 OpenAI 的 GPT 系列模型集成,或者与开源的 Llama2 系列模型集成。事实上，Dify支持主流的商业模型和开源模型(本地部署或基于 MaaS)。
 
+**2. Prompt IDE**：和团队一起在 Dify 协作，通过可视化的 Prompt 和应用编排工具开发 AI 应用。 支持无缝切换多种大型语言模型。
 
-我们为所有注册云端版的用户免费提供以下资源（登录 [dify.ai](https://cloud.dify.ai) 即可使用）：
-* 60 万 Tokens Claude 模型的消息调用额度，用于创建基于 Claude 模型的 AI 应用
-* 200 次 OpenAI 模型的消息调用额度，用于创建基于 OpenAI 模型的 AI 应用
-* 300 万 讯飞星火大模型 Token 的调用额度，用于创建基于讯飞星火大模型的 AI 应用
-* 100 万 MiniMax Token 的调用额度，用于创建基于 MiniMax 模型的 AI 应用
-2. **可视化编排 Prompt：** 通过界面化编写 prompt 并调试，只需几分钟即可发布一个 AI 应用。
-3. **文本 Embedding 处理（数据集）**：全自动完成文本预处理，使用你的数据作为上下文，无需理解晦涩的概念和技术处理。支持 PDF、txt 等文件格式，支持从 Notion、网页、API 同步数据。
-4. **基于 API 开发：** 后端即服务。您可以直接访问网页应用，也可以接入 API 集成到您的应用中，无需关注复杂的后端架构和部署过程。
-5. **插件能力：** Dify 「智聊」平台已支持网页浏览、Google 搜索、Wikipedia 查询等第一方插件，可在对话中实现联网搜索、分析网页内容、展示 AI 的推理过程。
-6. **团队 Workspace：** 团队成员可加入 Workspace 编辑、管理和使用团队内的 AI 应用。
-6. **数据标注与改进：** 可视化查阅 AI 应用日志并对数据进行改进标注，观测 AI 的推理过程，不断提高其性能。（Coming soon）
- -----------------------------
- ## Use cases
- * [几分钟创建一个带有业务数据的官网 AI 智能客服](https://docs.dify.ai/v/zh-hans/use-cases/create-an-ai-chatbot-with-business-data-in-minutes)
- * [构建一个 Notion AI 助手](https://docs.dify.ai/v/zh-hans/use-cases/build-an-notion-ai-assistant)
- * [创建 Midjoureny 提示词机器人](https://docs.dify.ai/v/zh-hans/use-cases/create-a-midjoureny-prompt-word-robot-with-zero-code)
+**3. RAG引擎**：包括各种基于全文索引或向量数据库嵌入的 RAG 能力，允许直接上传 PDF、TXT 等各种文本格式。
 
+**4. Agent**：基于函数调用的 Agent框架，允许用户自定义配置，所见即所得。Dify 提供了基本的插件能力，如谷歌搜索。
 
-## 使用云服务
+**5. 持续运营**：监控和分析应用日志和性能，使用生产数据持续改进 Prompt、数据集或模型。
 
-访问 [Dify.ai](https://cloud.dify.ai) 使用云端版。
+## 在开始之前
+
+- [网站](https://dify.ai)
+- [文档](https://docs.dify.ai)
+- [部署文档](https://docs.dify.ai/getting-started/install-self-hosted)
+- [常见问题](https://docs.dify.ai/getting-started/faq)
 
 ## 安装社区版
 
@@ -84,80 +86,29 @@ docker compose up -d
 
 ### 配置
 
-需要自定义配置，请参考我们的 [docker-compose.yml](docker/docker-compose.yaml) 文件中的注释，并手动设置环境配置，修改完毕后，请再次执行 `docker-compose up -d`。
-
-## Roadmap
-
-我们正在开发中的功能：
-
-- **数据集**，支持更多的数据集，通过网页、API 同步内容。用户可以根据自己的数据源构建 AI 应用程序。
-- **插件**，我们将发布符合 ChatGPT 标准的插件，支持更多 Dify 自己的插件，支持用户自定义插件能力，以在应用程序中启用更多功能，例如以支持以目标为导向的分解推理任务。
-
-## Q&A
-
-**Q: 我能用 Dify 做什么？**
-
-A: Dify 是一个简单且能力丰富的 LLM 开发和运营工具。你可以用它搭建商用级应用，个人助理。如果你想自己开发应用，Dify 也能为你省下接入 OpenAI 的后端工作，使用我们逐步提供的可视化运营能力，你可以持续的改进和训练你的 GPT 模型。
-
-**Q: 如何使用 Dify “训练”自己的模型？**
-
-A: 一个有价值的应用由 Prompt Engineering、上下文增强和 Fine-tune 三个环节组成。我们创造了一种 Prompt 结合编程语言的 Hybrid 编程方式（类似一个模版引擎），你可以轻松的完成长文本嵌入，或抓取用户输入的一个 Youtube 视频的字幕——这些都将作为上下文提交给 LLMs 进行计算。我们十分注重应用的可运营性，你的用户在使用 App 期间产生的数据，可进行分析、标记和持续训练。以上环节如果没有好的工具支持，可能会消耗你大量的时间。
-
-**Q: 如果要创建一个自己的应用，我需要准备什么？**
-
-A: 我们假定你已经有了 OpenAI 或 Claude 等模型的 API Key，如果没有请去注册一个。如果你已经有了一些内容可以作为训练上下文，就太好了。
-
-**Q: 提供哪些界面语言？**
-
-A:  支持英文、中文，你可以为我们贡献语言包并提供维护支持。
+如果您需要自定义配置，请参考我们的 [docker-compose.yml](docker/docker-compose.yaml) 文件中的注释，并手动设置环境配置。更改后，请再次运行 `docker-compose up -d`。您可以在我们的[文档](https://docs.dify.ai/getting-started/install-self-hosted/environments)中查看所有环境变量的完整列表。
 
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
 
-## 贡献
+## 社区与支持
 
-我们欢迎你为 Dify 作出贡献帮助 Dify 变得更好。我们欢迎各种方式的贡献，提交代码、问题、新想法、或者分享你基于 Dify 创建出的各种有趣有用的 AI 应用。同时，我们也欢迎你在不同的活动、研讨会、社交媒体上分享 Dify。
+我们欢迎您为 Dify 做出贡献，以帮助改善 Dify。包括：提交代码、问题、新想法，或分享您基于 Dify 创建的有趣且有用的 AI 应用程序。同时，我们也欢迎您在不同的活动、会议和社交媒体上分享 Dify。
 
-### 贡献代码
-为了确保正确审查，所有代码贡献 - 包括来自具有直接提交更改权限的贡献者 - 都必须提交 PR 请求并在合并分支之前得到核心开发人员的批准。
+- [GitHub Issues](https://github.com/langgenius/dify/issues)。👉：使用 Dify.AI 时遇到的错误和问题，请参阅[贡献指南](CONTRIBUTING.md)。
+- [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉：关于使用 Dify.AI 的问题。
+- [Discord](https://discord.gg/FngNHpbcY7)。👉：分享您的应用程序并与社区交流。
+- [Twitter](https://twitter.com/dify_ai)。👉：分享您的应用程序并与社区交流。
+- [商业许可](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)。👉：有关商业用途许可 Dify.AI 的商业咨询。
+ - [微信]() 👉：扫描下方二维码，添加微信好友，备注 Dify，我们将邀请您加入 Dify 社区。  
+<img src="./images/wechat.png" alt="wechat" width="100"/>
 
-我们欢迎所有人提交 PR！如果您愿意提供帮助，可以在 [贡献指南](CONTRIBUTING_CN.md) 中了解有关如何为项目做出代码贡献的更多信息。
-
-### 提交问题或想法
-你可以通过 Dify 代码仓库新增 issues 来提交你的问题或想法。如遇到问题，请尽可能描述你遇到问题的操作步骤，以便我们更好地发现它。如果你对我们的产品有任何新想法，也欢迎向我们反馈，请尽可能多地分享你的见解，以便我们在社区中获得更多反馈和进一步讨论。
-
-### 分享你的应用
-我们鼓励所有社区成员分享他们基于 Dify 创造出的 AI 应用，它们可以是应用于不同情景或不同用户，这将有助于为希望基于 AI 能力创造的人们提供强大灵感！你可以通过 [Dify-user-case 仓库项目提交 issue](https://github.com/langgenius/dify-user-case) 来分享你的应用案例。
-
-### 向别人分享 Dify
-我们鼓励社区贡献者们积极展示你使用 Dify 的不同角度。你可以通过线下研讨会、博客或社交媒体上谈论或分享你使用 Dify 的任意功能，相信你独特的使用分享会给别人带来非常大的帮助！如果你需要任何指导帮助，欢迎联系我们 support@dify.ai ,你也可以在 twitter @Dify.AI 或在 [Discord 社区](https://discord.gg/FngNHpbcY7)交流来帮助你传播信息。
-
-### 帮助别人
-你还可以在 Discord、GitHub issues或其他社交平台上帮助需要帮助的人，指导别人解决使用过程中遇到的问题和分享使用经验。这也是个非常了不起的贡献！如果你希望成为 Dify 社区的维护者，请通过[Discord 社区](https://discord.gg/FngNHpbcY7) 联系官方团队或邮件联系我们 support@dify.ai.
-
-
-## 联系我们
-
-如果您有任何问题、建议或合作意向，欢迎通过以下方式联系我们：
-
-- 在我们的 [GitHub Repo](https://github.com/langgenius/dify) 上提交 Issue 或 PR
-- 在我们的 [Discord 社区](https://discord.gg/FngNHpbcY7) 上加入讨论
-- 发送邮件至 hello@dify.ai
-
-## 安全
+## 安全问题
 
 为了保护您的隐私，请避免在 GitHub 上发布安全问题。发送问题至 security@dify.ai，我们将为您做更细致的解答。
 
-## Citation
-
-本软件使用了以下开源软件：
-
-- Chase, H. (2022). LangChain [Computer software]. https://github.com/hwchase17/langchain
-
-更多信息，请参考相应软件的官方网站或许可证文本。
-
 ## License
 
 本仓库遵循 [Dify Open Source License](LICENSE) 开源协议。

README_ES.md

@@ -1,4 +1,4 @@
-![](./images/describe-en.png)
+[![](./images/describe.png)](https://dify.ai)
 <p align="center">
   <a href="./README.md">English</a> |
   <a href="./README_CN.md">简体中文</a> |
@@ -6,36 +6,71 @@
   <a href="./README_ES.md">Español</a>
 </p>
 
-[Sitio web](https://dify.ai) • [Documentación](https://docs.dify.ai) • [Twitter](https://twitter.com/dify_ai) • [Discord](https://discord.gg/FngNHpbcY7)
+<p align="center">
+    <a href="https://dify.ai" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/AI-Dify?logo=AI&logoColor=%20%23f5f5f5&label=Dify&labelColor=%20%23155EEF&color=%23EAECF0"></a>
+    <a href="https://discord.gg/FngNHpbcY7" target="_blank">
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+            alt="chat on Discord"></a>
+    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
+        <img src="https://img.shields.io/twitter/follow/dify_ai?style=social&logo=X"
+            alt="follow on Twitter"></a>
+    <a href="https://hub.docker.com/u/langgenius" target="_blank">
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web"></a>
+</p>
 
-**Dify** es una plataforma LLMOps fácil de usar diseñada para capacitar a más personas para que creen aplicaciones sostenibles basadas en IA. Con orquestación visual para varios tipos de aplicaciones, Dify ofrece aplicaciones listas para usar que también pueden funcionar como APIs de Backend-as-a-Service. Unifica tu proceso de desarrollo con una API para la integración de complementos y conjuntos de datos, y agiliza tus operaciones utilizando una interfaz única para la ingeniería de indicaciones, análisis visual y mejora continua.
+**Dify** es una plataforma de desarrollo de aplicaciones para modelos de lenguaje de gran tamaño (LLM) que ya ha visto la creación de más de **100,000** aplicaciones basadas en Dify.AI. Integra los conceptos de Backend como Servicio y LLMOps, cubriendo el conjunto de tecnologías esenciales requerido para construir aplicaciones nativas de inteligencia artificial generativa, incluyendo un motor RAG incorporado. Con Dify, **puedes auto-desplegar capacidades similares a las de Assistants API y GPTs basadas en cualquier LLM.**
 
-Las aplicaciones creadas con Dify incluyen:
+![](./images/demo.png)
 
-- Sitios web listos para usar que admiten el modo de formulario y el modo de conversación por chat.
-- Una API única que abarca capacidades de complementos, mejora de contexto y más, lo que te ahorra esfuerzo de programación en el backend.
-- Análisis visual de datos, revisión de registros y anotación para aplicaciones.
+## Utilizar Servicios en la Nube
 
-Dify es compatible con Langchain, lo que significa que gradualmente admitiremos múltiples LLMs, actualmente compatibles con:
+Usar [Dify.AI Cloud](https://dify.ai) proporciona todas las capacidades de la versión de código abierto, e incluye un complemento de 200 créditos de prueba para GPT.
 
-- GPT 3 (text-davinci-003)
-- GPT 3.5 Turbo (ChatGPT)
-- GPT-4
+## Por qué Dify
 
-## Usar servicios en la nube
+Dify se caracteriza por su neutralidad de modelo y es un conjunto tecnológico completo e ingenierizado, en comparación con las bibliotecas de desarrollo codificadas como LangChain. A diferencia de la API de Assistants de OpenAI, Dify permite el despliegue local completo de los servicios.
 
-Visita [Dify.ai](https://dify.ai)
+| Característica | Dify.AI | API de Assistants | LangChain |
+|----------------|---------|------------------|-----------|
+| **Enfoque de Programación** | Orientado a API | Orientado a API | Orientado a Código en Python |
+| **Estrategia del Ecosistema** | Código Abierto | Cerrado y Comercial | Código Abierto |
+| **Motor RAG** | Soportado | Soportado | No Soportado |
+| **IDE de Prompts** | Incluido | Incluido | Ninguno |
+| **LLMs Soportados** | Gran Variedad | Solo GPT | Gran Variedad |
+| **Despliegue Local** | Soportado | No Soportado | No Aplicable |
+
+## Características
+
+![](./images/models.png)
+
+**1. Soporte LLM**: Integración con la familia de modelos GPT de OpenAI, o los modelos de la familia Llama2 de código abierto. De hecho, Dify soporta modelos comerciales convencionales y modelos de código abierto (desplegados localmente o basados en MaaS).
+
+**2. IDE de Prompts**: Orquestación visual de aplicaciones y servicios basados en LLMs con tu equipo.
+
+**3. Motor RAG**: Incluye varias capacidades RAG basadas en indexación de texto completo o incrustaciones de base de datos vectoriales, permitiendo la carga directa de PDFs, TXTs y otros formatos de texto.
+
+**4. Agentes**: Un marco de Agentes basado en Llamadas de Función que permite a los usuarios configurar lo que ven es lo que obtienen. Dify incluye capacidades básicas de plugins como la Búsqueda de Google.
+
+**5. Operaciones Continuas**: Monitorear y analizar registros de aplicaciones y rendimiento, mejorando continuamente Prompts, conjuntos de datos o modelos usando datos de producción.
+
+## Antes de Empezar
+
+- [Sitio web](https://dify.ai)
+- [Documentación](https://docs.dify.ai)
+- [Documentación de Implementación](https://docs.dify.ai/getting-started/install-self-hosted)
+- [Preguntas Frecuentes](https://docs.dify.ai/getting-started/faq)
 
 ## Instalar la Edición Comunitaria
 
-### Requisitos del sistema
+### Requisitos del Sistema
 
-Antes de instalar Dify, asegúrate de que tu máquina cumple con los siguientes requisitos mínimos del sistema:
+Antes de instalar Dify, asegúrate de que tu máquina cumpla con los siguientes requisitos mínimos del sistema:
 
-- CPU >= 2 Core
+- CPU >= 2 núcleos
 - RAM >= 4GB
 
-### Inicio rápido
+### Inicio Rápido
 
 La forma más sencilla de iniciar el servidor de Dify es ejecutar nuestro archivo [docker-compose.yml](docker/docker-compose.yaml). Antes de ejecutar el comando de instalación, asegúrate de que [Docker](https://docs.docker.com/get-docker/) y [Docker Compose](https://docs.docker.com/compose/install/) estén instalados en tu máquina:
 
@@ -44,80 +79,34 @@ cd docker
 docker compose up -d
 ```
 
-Después de ejecutarlo, puedes acceder al panel de control de Dify en tu navegador desde [http://localhost/install](http://localhost/install) y comenzar el proceso de instalación de inicialización.
+Después de ejecutarlo, puedes acceder al panel de control de Dify en tu navegador en [http://localhost/install](http://localhost/install) y comenzar el proceso de instalación de inicialización.
 
-### Helm Chart
+### Gráfico Helm
 
-Un gran agradecimiento a @BorisPolonsky por proporcionarnos una versión de [Helm Chart](https://helm.sh/), que permite desplegar Dify en Kubernetes.
-Puede ir a https://github.com/BorisPolonsky/dify-helm para obtener información de despliegue.
+Un gran agradecimiento a @BorisPolonsky por proporcionarnos una versión del [Gráfico Helm](https://helm.sh/), que permite implementar Dify en Kubernetes. Puedes visitar https://github.com/BorisPolonsky/dify-helm para obtener información sobre la implementación.
 
 ### Configuración
 
-Si necesitas personalizar la configuración, consulta los comentarios en nuestro archivo [docker-compose.yml](docker/docker-compose.yaml) y configura manualmente la configuración del entorno. Después de realizar los cambios, ejecuta nuevamente 'docker-compose up -d'.
+Si necesitas personalizar la configuración, consulta los comentarios en nuestro archivo [docker-compose.yml](docker/docker-compose.yaml) y configura manualmente la configuración del entorno. Después de realizar los cambios, ejecuta nuevamente `docker-compose up -d`. Puedes ver la lista completa de variables de entorno en nuestra [documentación](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
-## Hoja de ruta
+## Historial de Estrellas
 
-Funciones en desarrollo:
+[![Gráfico de Historial de Estrellas](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
-- **Conjuntos de datos**, admitiendo más conjuntos de datos, por ejemplo, sincronización de contenido desde Notion o páginas web.
-Admitiremos más conjuntos de datos, incluidos texto, páginas web e incluso contenido de Notion. Los usuarios pueden construir aplicaciones de IA basadas en sus propias fuentes de datos
-- **Complementos**, introduciendo complementos estándar de ChatGPT para aplicaciones, o utilizando complementos producidos por Dify.
-Lanzaremos complementos que cumplan con el estándar de ChatGPT, o nuestros propios complementos de Dify para habilitar más capacidades en las aplicaciones.
-- **Modelos de código abierto**, por ejemplo, adoptar Llama como proveedor de modelos o para un ajuste adicional.
-Trabajaremos con excelentes modelos de código abierto como Llama, proporcionándolos como opciones de modelos en nuestra plataforma o utilizándolos para un ajuste adicional.
+## Comunidad y Soporte
 
-## Preguntas y respuestas
+Te damos la bienvenida a contribuir a Dify para ayudar a hacer que Dify sea mejor de diversas maneras, enviando código, informando problemas, proponiendo nuevas ideas o compartiendo las aplicaciones de inteligencia artificial interesantes y útiles que hayas creado basadas en Dify. Al mismo tiempo, también te invitamos a compartir Dify en diferentes eventos, conferencias y redes sociales.
 
-**P: ¿Qué puedo hacer con Dify?**
+- [Problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores y problemas que encuentres al usar Dify.AI, consulta la [Guía de Contribución](CONTRIBUTING.md).
+- [Soporte por Correo Electrónico](mailto:hello@dify.ai?subject=[GitHub]Preguntas%20sobre%20Dify). Lo mejor para: preguntas que tengas sobre el uso de Dify.AI.
+- [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y socializar con la comunidad.
+- [Twitter](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y socializar con la comunidad.
+- [Licencia Comercial](mailto:business@dify.ai?subject=[GitHub]Consulta%20de%20Licencia%20Comercial). Lo mejor para: consultas comerciales sobre la licencia de Dify.AI para uso comercial.
 
-R: Dify es una herramienta de desarrollo y operaciones de LLM, simple pero poderosa. Puedes usarla para construir aplicaciones de calidad comercial y asistentes personales. Si deseas desarrollar tus propias aplicaciones, LangDifyGenius puede ahorrarte trabajo en el backend al integrar con OpenAI y ofrecer capacidades de operaciones visuales, lo que te permite mejorar y entrenar continuamente tu modelo GPT.
-
-**P: ¿Cómo uso Dify para "entrenar" mi propio modelo?**
-
-R: Una aplicación valiosa consta de Ingeniería de indicaciones, mejora de contexto y ajuste fino. Hemos creado un enfoque de programación híbrida que combina las indicaciones con lenguajes de programación (similar a un motor de plantillas), lo que facilita la incorporación de texto largo o la captura de subtítulos de un video de YouTube ingresado por el usuario, todo lo cual se enviará como contexto para que los LLM lo procesen. Damos gran importancia a la operabilidad de la aplicación, con los datos generados por los usuarios durante el uso de la aplicación disponibles para análisis, anotación y entrenamiento continuo. Sin las herramientas adecuadas, estos pasos pueden llevar mucho tiempo.
-
-**P: ¿Qué necesito preparar si quiero crear mi propia aplicación?**
-
-R: Suponemos que ya tienes una clave de API de OpenAI; si no la tienes, por favor regístrate. ¡Si ya tienes contenido que pueda servir como contexto de entrenamiento, eso es genial!
-
-**P: ¿Qué idiomas de interfaz están disponibles?**
-
-R: Actualmente se admiten inglés y chino, y puedes contribuir con paquetes de idiomas.
-
-## Historial de estrellas
-
-[![Gráfico de historial de estrellas](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
-
-## Contáctanos
-
-Si tienes alguna pregunta, sugerencia o consulta sobre asociación, no dudes en contactarnos a través de los siguientes canales:
-
-- Presentar un problema o una solicitud de extracción en nuestro repositorio de GitHub.
-- Únete a la discusión en nuestra comunidad de [Discord](https://discord.gg/FngNHpbcY7).
-- Envía un correo electrónico a hello@dify.ai.
-
-¡Estamos ansiosos por ayudarte y crear juntos aplicaciones de IA más divertidas y útiles!
-
-## Contribuciones
-
-Para garantizar una revisión adecuada, todas las contribuciones de código, incluidas las de los colaboradores con acceso directo a los compromisos, deben enviarse mediante solicitudes de extracción y ser aprobadas por el equipo principal de
-
- desarrollo antes de fusionarse.
-
-¡Agradecemos todas las solicitudes de extracción! Si deseas ayudar, consulta la [Guía de Contribución](CONTRIBUTING.md) para obtener más información sobre cómo comenzar.
-
-## Seguridad
+## Divulgación de Seguridad
 
 Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada.
 
-## Citación
-
-Este software utiliza el siguiente software de código abierto:
-
-- Chase, H. (2022). LangChain [Software de computadora]. https://github.com/hwchase17/langchain
-
-Para obtener más información, consulta el sitio web oficial o el texto de la licencia del software correspondiente.
-
 ## Licencia
 
 Este repositorio está disponible bajo la [Licencia de código abierto de Dify](LICENSE).

README_JA.md

@@ -1,122 +1,103 @@
-![](./images/describe-en.png)
+[![](./images/describe.png)](https://dify.ai)
 <p align="center">
   <a href="./README.md">English</a> |
   <a href="./README_CN.md">简体中文</a> |
   <a href="./README_JA.md">日本語</a> |
-  <a href="./README_ES.md">Español</a>
+  <a href="./README_ES.md">Español</a> |
+  <a href="./README_KL.md">Klingon</a>
 </p>
 
-[Web サイト](https://dify.ai) • [ドキュメント](https://docs.dify.ai) • [Twitter](https://twitter.com/dify_ai) • [Discord](https://discord.gg/FngNHpbcY7)
+<p align="center">
+    <a href="https://dify.ai" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/AI-Dify?logo=AI&logoColor=%20%23f5f5f5&label=Dify&labelColor=%20%23155EEF&color=%23EAECF0"></a>
+    <a href="https://discord.gg/FngNHpbcY7" target="_blank">
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+            alt="chat on Discord"></a>
+    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
+        <img src="https://img.shields.io/twitter/follow/dify_ai?style=social&logo=X"
+            alt="follow on Twitter"></a>
+    <a href="https://hub.docker.com/u/langgenius" target="_blank">
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web"></a>
+</p>
 
+"Difyは、既にDify.AI上で10万以上のアプリケーションが構築されているLLMアプリケーション開発プラットフォームです。バックエンド・アズ・ア・サービスとLLMOpsの概念を統合し、組み込みのRAGエンジンを含む、生成AIネイティブアプリケーションを構築するためのコアテックスタックをカバーしています。Difyを使用すると、どのLLMに基づいても、Assistants APIやGPTのような機能を自己デプロイすることができます。"
 
-**Dify** は、より多くの人々が持続可能な AI ネイティブアプリケーションを作成できるように設計された、使いやすい LLMOps プラットフォームです。様々なアプリケーションタイプに対応したビジュアルオーケストレーションにより Dify は Backend-as-a-Service API としても機能する、すぐに使えるアプリケーションを提供します。プラグインやデータセットを統合するための1つの API で開発プロセスを統一し、プロンプトエンジニアリング、ビジュアル分析、継続的な改善のための1つのインターフェイスを使って業務を合理化します。
-
-Difyで作成したアプリケーションは以下の通りです:
-
-フォームモードとチャット会話モードをサポートする、すぐに使える Web サイト
-プラグイン機能、コンテキストの強化などを網羅する単一の API により、バックエンドのコーディングの手間を省きます。
-アプリケーションの視覚的なデータ分析、ログレビュー、アノテーションが可能です。
-Dify は LangChain と互換性があり、複数の LLM を徐々にサポートします:
-
-- GPT 3 (text-davinci-003)
-- GPT 3.5 Turbo(ChatGPT)
-- GPT-4
+Please note that translating complex technical terms can sometimes result in slight variations in meaning due to differences in language nuances.
 
 ## クラウドサービスの利用
 
-[Dify.ai](https://dify.ai) をご覧ください
+[Dify.AI Cloud](https://dify.ai) を使用すると、オープンソース版の全機能を利用でき、さらに200GPTのトライアルクレジットが無料で提供されます。
 
-## Community Edition のインストール
+## Difyの利点
+
+Difyはモデルニュートラルであり、LangChainのようなハードコードされた開発ライブラリと比較して、完全にエンジニアリングされた技術スタックを特徴としています。OpenAIのAssistants APIとは異なり、Difyではサービスの完全なローカルデプロイメントが可能です。
+
+| 機能 | Dify.AI | Assistants API | LangChain |
+|---------|---------|----------------|-----------|
+| **プログラミングアプローチ** | API指向 | API指向 | Pythonコード指向 |
+| **エコシステム戦略** | オープンソース | 閉鎖的かつ商業的 | オープンソース |
+| **RAGエンジン** | サポート済み | サポート済み | 非サポート |
+| **プロンプトIDE** | 含まれる | 含まれる | なし |
+| **サポートされるLLMs** | 豊富な種類 | GPTのみ | 豊富な種類 |
+| **ローカルデプロイメント** | サポート済み | 非サポート | 該当なし |
+
+
+## 開始する前に
+
+- [Website](https://dify.ai)
+- [Docs](https://docs.dify.ai)
+- [Deployment Docs](https://docs.dify.ai/getting-started/install-self-hosted)
+- [FAQ](https://docs.dify.ai/getting-started/faq) 
+
+
+## コミュニティエディションのインストール
 
 ### システム要件
 
-Dify をインストールする前に、お使いのマシンが以下の最低システム要件を満たしていることを確認してください:
+Difyをインストールする前に、以下の最低限のシステム要件を満たしていることを確認してください：
 
-- CPU >= 1 Core
+- CPU >= 2コア
 - RAM >= 4GB
 
 ### クイックスタート
 
-Dify サーバーを起動する最も簡単な方法は、[docker-compose.yml](docker/docker-compose.yaml) ファイルを実行することです。インストールコマンドを実行する前に、[Docker](https://docs.docker.com/get-docker/) と [Docker Compose](https://docs.docker.com/compose/install/) がお使いのマシンにインストールされていることを確認してください:
+Difyサーバーを始める最も簡単な方法は、[docker-compose.yml](docker/docker-compose.yaml) ファイルを実行することです。インストールコマンドを実行する前に、マシンに [Docker](https://docs.docker.com/get-docker/) と [Docker Compose](https://docs.docker.com/compose/install/) がインストールされていることを確認してください：
 
 ```bash
 cd docker
 docker compose up -d
 ```
 
-実行後、ブラウザで [http://localhost/install](http://localhost/install) にアクセスし、初期化インストール作業を開始することができます。
+実行後、ブラウザで [http://localhost/install](http://localhost/install) にアクセスし、初期化インストールプロセスを開始できます。
 
 ### Helm Chart
 
-@BorisPolonsky に大感謝します。彼は Dify を Kubernetes 上にデプロイするための [Helm Chart](https://helm.sh/) バージョンを提供してくれました。
+@BorisPolonskyによる[Helm Chart](https://helm.sh/) バージョンを提供してくれて、大変感謝しています。これにより、DifyはKubernetes上にデプロイすることができます。
 デプロイ情報については、https://github.com/BorisPolonsky/dify-helm をご覧ください。
 
-### 構成
+### 設定
 
-カスタマイズが必要な場合は、[docker-compose.yml](docker/docker-compose.yaml) ファイルのコメントを参照し、手動で環境設定をお願いします。変更後、再度 'docker-compose up -d' を実行してください。
-
-## ロードマップ
-
-開発中の機能:
-
-- **データセット**, Notionやウェブページからのコンテンツ同期など、より多くのデータセットをサポートします
-テキスト、ウェブページ、さらには Notion コンテンツなど、より多くのデータセットをサポートする予定です。ユーザーは、自分のデータソースをもとに AI アプリケーションを構築することができます。
-- **プラグイン**, アプリケーションに ChatGPT プラグイン標準のプラグインを導入する、または Dify 制作のプラグインを利用する
-今後、ChatGPT 規格に準拠したプラグインや、ディファイ独自のプラグインを公開し、より多くの機能をアプリケーションで実現できるようにします。
-- **オープンソースモデル**, 例えばモデルプロバイダーとして Llama を採用したり、さらにファインチューニングを行う
-Llama のような優れたオープンソースモデルを、私たちのプラットフォームのモデルオプションとして提供したり、さらなる微調整のために使用したりすることで、協力していきます。
+設定をカスタマイズする必要がある場合は、[docker-compose.yml](docker/docker-compose.yaml) ファイルのコメントを参照し、環境設定を手動で行ってください。変更を行った後は、もう一度 `docker-compose up -d` を実行してください。環境変数の完全なリストは、[ドキュメント](https://docs.dify.ai/getting-started/install-self-hosted/environments)で確認できます。
 
 
-## Q&A
-
-**Q: Dify で何ができるのか？**
-
-A: Dify はシンプルでパワフルな LLM 開発・運用ツールです。商用グレードのアプリケーション、パーソナルアシスタントを構築するために使用することができます。独自のアプリケーションを開発したい場合、LangDifyGenius は OpenAI と統合する際のバックエンド作業を省き、視覚的な操作機能を提供し、GPT モデルを継続的に改善・訓練することが可能です。
-
-**Q: Dify を使って、自分のモデルを「トレーニング」するにはどうすればいいのでしょうか？**
-
-A: プロンプトエンジニアリング、コンテキスト拡張、ファインチューニングからなる価値あるアプリケーションです。プロンプトとプログラミング言語を組み合わせたハイブリッドプログラミングアプローチ（テンプレートエンジンのようなもの）で、長文の埋め込みやユーザー入力の YouTube 動画からの字幕取り込みなどを簡単に実現し、これらはすべて LLM が処理するコンテキストとして提出される予定です。また、アプリケーションの操作性を重視し、ユーザーがアプリケーションを使用する際に生成したデータを分析、アノテーション、継続的なトレーニングに利用できるようにしました。適切なツールがなければ、これらのステップに時間がかかることがあります。
-
-**Q: 自分でアプリケーションを作りたい場合、何を準備すればよいですか？**
-
-A: すでに OpenAI API Key をお持ちだと思いますが、お持ちでない場合はご登録ください。もし、すでにトレーニングのコンテキストとなるコンテンツをお持ちでしたら、それは素晴らしいことです！
-
-**Q: インターフェイスにどの言語が使えますか？**
-
-A: 現在、英語と中国語に対応しており、言語パックを寄贈することも可能です。
-
-## Star ヒストリー
+## スターヒストリー
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
-## お問合せ
+## コミュニティとサポート
 
-ご質問、ご提案、パートナーシップに関するお問い合わせは、以下のチャンネルからお気軽にご連絡ください:
+Difyに貢献していただき、コードの提出、問題の報告、新しいアイデアの提供、またはDifyを基に作成した興味深く有用なAIアプリケーションの共有により、Difyをより良いものにするお手伝いを歓迎します。同時に、さまざまなイベント、会議、ソーシャルメディアでDifyを共有することも歓迎します。
 
-- GitHub Repo で Issue や PR を提出する
-- [Discord](https://discord.gg/FngNHpbcY7) コミュニティで議論に参加する。
-- hello@dify.ai にメールを送信します
-
-私たちは、皆様のお手伝いをさせていただき、より楽しく、より便利な AI アプリケーションを一緒に作っていきたいと思っています！
-
-## コントリビュート
-
-適切なレビューを行うため、コミットへの直接アクセスが可能なコントリビュータを含むすべてのコードコントリビュータは、プルリクエストで提出し、マージされる前にコア開発チームによって承認される必要があります。
-
-私たちはすべてのプルリクエストを歓迎します！協力したい方は、[コントリビューションガイド](CONTRIBUTING.md) をチェックしてみてください。
+- [GitHub Issues](https://github.com/langgenius/dify/issues)。最適な使用法：Dify.AIの使用中に遭遇するバグやエラー、[貢献ガイド](CONTRIBUTING.md)を参照。
+- [Email サポート](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。最適な使用法：Dify.AIの使用に関する質問。
+- [Discord](https://discord.gg/FngNHpbcY7)。最適な使用法：アプリケーションの共有とコミュニティとの交流。
+- [Twitter](https://twitter.com/dify_ai)。最適な使用法：アプリケーションの共有とコミュニティとの交流。
+- [ビジネスライセンス](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)。最適な使用法：Dify.AIを商業利用するためのビジネス関連の問い合わせ。
 
 ## セキュリティ
 
 プライバシー保護のため、GitHub へのセキュリティ問題の投稿は避けてください。代わりに、あなたの質問を security@dify.ai に送ってください。より詳細な回答を提供します。
 
-## 引用
-
-本ソフトウェアは、以下のオープンソースソフトウェアを使用しています:
-
-- Chase, H. (2022). LangChain [Computer software]. https://github.com/hwchase17/langchain
-
-詳しくは、各ソフトウェアの公式サイトまたはライセンス文をご参照ください。
-
 ## ライセンス
 
 このリポジトリは、[Dify Open Source License](LICENSE) のもとで利用できます。

README_KL.md

@@ -0,0 +1,114 @@
+[![](./images/describe.png)](https://dify.ai)
+<p align="center">
+  <a href="./README.md">English</a> |
+  <a href="./README_CN.md">简体中文</a> |
+  <a href="./README_JA.md">日本語</a> |
+  <a href="./README_ES.md">Español</a> |
+  <a href="./README_KL.md">Klingon</a>
+</p>
+
+<p align="center">
+    <a href="https://dify.ai" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/AI-Dify?logo=AI&logoColor=%20%23f5f5f5&label=Dify&labelColor=%20%23155EEF&color=%23EAECF0"></a>
+    <a href="https://discord.gg/FngNHpbcY7" target="_blank">
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+            alt="chat on Discord"></a>
+    <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
+        <img src="https://img.shields.io/twitter/follow/dify_ai?style=social&logo=X"
+            alt="follow on Twitter"></a>
+    <a href="https://hub.docker.com/u/langgenius" target="_blank">
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web"></a>
+</p>
+
+**Dify** Hoch LLM qorwI' pIqoDvam pagh laHta' je **100,000** pIqoDvamvam Dify.AI De'wI'. Dify leghpu' Backend chu' a Service teH LLMOps vItlhutlh, generative AI-native pIqoD teq wa'vam, vIyoD Built-in RAG engine. Dify, **'ej chenmoHmoH Hoch 'oHna' Assistant API 'ej GPTmey HoStaHbogh LLMmey.**
+
+![](./images/demo.png)
+
+## ngIl QaQ
+
+[Dify.AI ngIl](https://dify.ai) pIm neHlaH 'ej ghaH. cha'logh wa' DIvI' 200 GPT trial credits.
+
+## Dify WovmoH
+
+Dify Daq rIn neutrality 'ej Hoch, LangChain tInHar HubwI'. maH Daqbe'law' Qawqar, OpenAI's Assistant API Daq local neH deployment.
+
+| Qo'logh | Dify.AI | Assistants API | LangChain |
+|---------|---------|----------------|-----------|
+| **qet QaS** | API-oriented | API-oriented | Python Code-oriented |
+| **Ecosystem Strategy** | Open Source | Closed and Commercial | Open Source |
+| **RAG Engine** | Ha'qu' | Ha'qu' | ghoS Ha'qu' |
+| **Prompt IDE** | jaH Include | jaH Include | qeylIS qaq |
+| **qet LLMmey** | bo'Degh Hoch | GPTmey tIn | bo'Degh Hoch |
+| **local deployment** | Ha'qu' | tInHa'qu' | tInHa'qu' ghogh |
+
+## ruch
+
+![](./images/models.png)
+
+**1. LLM tIq**: OpenAI's GPT Hur nISmoHvam neH vIngeH, wa' Llama2 Hur nISmoHvam. Heghlu'lu'pu' Dify mIw 'oH choH qay'be'.Daq commercial Hurmey 'ej Open Source Hurmey (maqtaHvIS pagh locally neH neH deployment HoSvam).
+
+**2. Prompt IDE**: cha'logh wa' LLMmey Hoch janlu'pu' 'ej lughpu' choH qay'be'.
+
+**3. RAG Engine**: RAG vaD tIqpu' lo'taH indexing qor neH vector database wa' embeddings wIj, PDFs, TXTs, 'ej ghojmoHmoH HIq qorlIj je upload.
+
+**4. jenSuvpu'**: jenbe' SuDqang naQ moDwu' jenSuvpu' porgh cha'logh choHvam. Dify Google Search Hur vItlhutlh plugin choH.
+
+**5. QaS muDHa'wI': cha'logh wa' pIq mI' logs 'ej quv yIn, vItlhutlh tIq 'e'wIj lo'taHmoHmoH Prompts, vItlhutlh, Hurmey ghaH production data jatlh.
+
+## Do'wI' qabmey lo'taH
+
+- [Website](https://dify.ai)
+- [Docs](https://docs.dify.ai)
+- [lo'taHmoH Docs](https://docs.dify.ai/getting-started/install-self-hosted)
+- [FAQ](https://docs.dify.ai/getting-started/faq) 
+
+## Community Edition tu' yo'
+
+### System Qab
+
+Dify yo' yo' qaqmeH SuS chenmoH 'oH qech!
+
+- CPU >= 2 Cores
+- RAM >= 4GB
+
+### Quick Start
+
+Dify server luHoHtaHlu' vIngeH lo'laHbe'chugh vIyoD [docker-compose.yml](docker/docker-compose.yaml) QorwI'ghach. toH yItlhutlh chenmoH luH!chugh 'ay' vaj vIneHmeH, 'ej [Docker](https://docs.docker.com/get-docker/) 'ej [Docker Compose](https://docs.docker.com/compose/install/) vaj 'oH 'e' vIneHmeH:
+
+```bash
+cd docker
+docker compose up -d
+```
+
+luHoHtaHmeH HoHtaHvIS, Dify dashboard vIneHmeH vIngeH lI'wI' [http://localhost/install](http://localhost/install) 'ej 'oH initialization 'e' vIneHmeH.
+
+### Helm Chart
+
+@BorisPolonsky Dify wIq tIq ['ay'var (Helm Chart)](https://helm.sh/) version Hur yIn chu' Dify luHoHchu'. Heghlu'lu' vIneHmeH [https://github.com/BorisPolonsky/dify-helm](https://github.com/BorisPolonsky/dify-helm) 'ej vaj QaS deployment information.
+
+### veS config
+
+chenmoHDI' config lo'taH ghaH, vItlhutlh HIq wIgharghbe'lu'pu'. toH lo'taHvIS pagh vay' vIneHmeH, 'ej `docker-compose up -d` wa'DIch. tIqmoHmeH list full wa' lo'taHvo'lu'pu' ghaH [docs](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+
+## tIng qem
+
+[![tIng qem Hur Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+
+## choHmoH 'ej vItlhutlh
+
+Dify choHmoH je mIw Dify puqloD, Dify ghaHta'bogh vItlhutlh, HurDI' code, ghItlh, ghItlh qo'lu'pu'pu' qej. tIqmeH, Hurmey je, Dify Hur tIqDI' woDDaj, DuD QangmeH 'ej HInobDaq vItlhutlh HImej Dify'e'.
+
+- [GitHub vItlhutlh](https://github.com/langgenius/dify/issues). Hurmey: bugs 'ej errors Dify.AI tIqmeH. yImej [Contribution Guide](CONTRIBUTING.md).
+- [Email QaH](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify). Hurmey: questions vItlhutlh Dify.AI chaw'.
+- [Discord](https://discord.gg/FngNHpbcY7). Hurmey: jIpuv 'ej jImej mIw Dify vItlhutlh.
+- [Twitter](https://twitter.com/dify_ai). Hurmey: jIpuv 'ej jImej mIw Dify vItlhutlh.
+- [Business License](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). Hurmey: qurgh vItlhutlh Hurmey Dify.AI tIqbe'law'.
+
+## bIQDaqmey bom
+
+taghlI' vIngeH'a'? pong security 'oH posting GitHub. yItlhutlh, toH security@dify.ai 'ej vIngeH'a'.
+
+## License
+
+ghItlh puqloD chenmoH [Dify vItlhutlh Hur](LICENSE), ghaH nIvbogh Apache 2.0.
+

api/.env.example

@@ -18,6 +18,9 @@ SERVICE_API_URL=http://127.0.0.1:5001
 APP_API_URL=http://127.0.0.1:5001
 APP_WEB_URL=http://127.0.0.1:3000
 
+# Files URL
+FILES_URL=http://127.0.0.1:5001
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 
@@ -50,25 +53,7 @@ S3_REGION=your-region
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
-# Cookie configuration
-COOKIE_HTTPONLY=true
-COOKIE_SAMESITE=None
-COOKIE_SECURE=true
-
-# Session configuration
-SESSION_PERMANENT=true
-SESSION_USE_SIGNER=true
-
-## support redis, sqlalchemy
-SESSION_TYPE=redis
-
-# session redis configuration
-SESSION_REDIS_HOST=localhost
-SESSION_REDIS_PORT=6379
-SESSION_REDIS_PASSWORD=difyai123456
-SESSION_REDIS_DB=2
-
-# Vector database configuration, support: weaviate, qdrant
+# Vector database configuration, support: weaviate, qdrant, milvus
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -77,9 +62,24 @@ WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
 WEAVIATE_GRPC_ENABLED=false
 WEAVIATE_BATCH_SIZE=100
 
-# Qdrant configuration, use `path:` prefix for local mode or `https://your-qdrant-cluster-url.qdrant.io` for remote mode
-QDRANT_URL=path:storage/qdrant
-QDRANT_API_KEY=your-qdrant-api-key
+# Qdrant configuration, use `http://localhost:6333` for local mode or `https://your-qdrant-cluster-url.qdrant.io` for remote mode
+QDRANT_URL=http://localhost:6333
+QDRANT_API_KEY=difyai123456
+
+# Milvus configuration
+MILVUS_HOST=127.0.0.1
+MILVUS_PORT=19530
+MILVUS_USER=root
+MILVUS_PASSWORD=Milvus
+MILVUS_SECURE=false
+
+# Upload configuration
+UPLOAD_FILE_SIZE_LIMIT=15
+UPLOAD_FILE_BATCH_LIMIT=5
+UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
+
+# Model Configuration
+MULTIMODAL_SEND_IMAGE_FORMAT=base64
 
 # Mail configuration, support: resend
 MAIL_TYPE=

api/.vscode/launch.json

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

api/Dockerfile

@@ -1,7 +1,18 @@
-FROM python:3.10-slim
+# packages install stage
+FROM python:3.10-slim AS base
 
 LABEL maintainer="takatost@gmail.com"
 
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends gcc g++ python3-dev libc-dev libffi-dev
+
+COPY requirements.txt /requirements.txt
+
+RUN pip install --prefix=/pkg -r requirements.txt
+
+# build stage
+FROM python:3.10-slim AS builder
+
 ENV FLASK_APP app.py
 ENV EDITION SELF_HOSTED
 ENV DEPLOY_ENV PRODUCTION
@@ -15,15 +26,17 @@ EXPOSE 5001
 
 WORKDIR /app/api
 
-RUN apt-get update && \
-    apt-get install -y bash curl wget vim gcc g++ python3-dev libc-dev libffi-dev nodejs
-
-COPY requirements.txt /app/api/requirements.txt
-
-RUN pip install -r requirements.txt
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends bash curl wget vim nodejs \
+    && apt-get autoremove \
+    && rm -rf /var/lib/apt/lists/*
 
+COPY --from=base /pkg /usr/local
 COPY . /app/api/
 
+RUN python -c "from transformers import GPT2TokenizerFast; GPT2TokenizerFast.from_pretrained('gpt2')"
+ENV TRANSFORMERS_OFFLINE true
+
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh
 

api/README.md

@@ -52,11 +52,13 @@
    flask run --host 0.0.0.0 --port=5001 --debug
    ```
 7. Setup your application by visiting http://localhost:5001/console/api/setup or other apis...
-8. If you need to debug local async processing, you can run `celery -A app.celery worker -Q dataset,generation,mail`, celery can do dataset importing and other async tasks.
+8. If you need to debug local async processing, you can run `celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail`, celery can do dataset importing and other async tasks.
 
-8. Start frontend:
+8. Start frontend
+
+   You can start the frontend by running `npm install && npm run dev` in web/ folder, or you can use docker to start the frontend, for example:
 
    ```
-   docker run -it -d --platform linux/amd64 -p 3000:3000 -e EDITION=SELF_HOSTED -e CONSOLE_URL=http://127.0.0.1:5000 --name web-self-hosted langgenius/dify-web:latest
+   docker run -it -d --platform linux/amd64 -p 3000:3000 -e EDITION=SELF_HOSTED -e CONSOLE_URL=http://127.0.0.1:5001 --name web-self-hosted langgenius/dify-web:latest
    ```
    This will start a dify frontend, now you are all set, happy coding!

api/app.py

@@ -1,24 +1,26 @@
 # -*- coding:utf-8 -*-
 import os
-from datetime import datetime
 
-from werkzeug.exceptions import Forbidden
+from werkzeug.exceptions import Unauthorized
 
 if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
     from gevent import monkey
     monkey.patch_all()
+    if os.environ.get("VECTOR_STORE") == 'milvus':
+        import grpc.experimental.gevent
+        grpc.experimental.gevent.init_gevent()
 
+import time
 import logging
 import json
 import threading
 
-from flask import Flask, request, Response, session
-import flask_login
+from flask import Flask, request, Response
 from flask_cors import CORS
 
 from core.model_providers.providers import hosted
-from extensions import ext_session, ext_celery, ext_sentry, ext_redis, ext_login, ext_migrate, \
-    ext_database, ext_storage, ext_mail, ext_stripe
+from extensions import ext_celery, ext_sentry, ext_redis, ext_login, ext_migrate, \
+    ext_database, ext_storage, ext_mail, ext_stripe, ext_code_based_extension
 from extensions.ext_database import db
 from extensions.ext_login import login_manager
 
@@ -27,16 +29,21 @@ from models import model, account, dataset, web, task, source, tool
 from events import event_handlers
 # DO NOT REMOVE ABOVE
 
-import core
 from config import Config, CloudEditionConfig
 from commands import register_commands
-from models.account import TenantAccountJoin, AccountStatus
-from models.model import Account, EndUser, App
-from services.account_service import TenantService
+from services.account_service import AccountService
+from libs.passport import PassportService
 
 import warnings
 warnings.simplefilter("ignore", ResourceWarning)
 
+# fix windows platform
+if os.name == "nt":
+    os.system('tzutil /s "UTC"')    
+else:
+    os.environ['TZ'] = 'UTC'
+    time.tzset()
+
 
 class DifyApp(Flask):
     pass
@@ -80,82 +87,39 @@ def create_app(test_config=None) -> Flask:
 def initialize_extensions(app):
     # Since the application instance is now created, pass it to each Flask
     # extension instance to bind it to the Flask application instance (app)
+    ext_code_based_extension.init()
     ext_database.init_app(app)
     ext_migrate.init(app, db)
     ext_redis.init_app(app)
     ext_storage.init_app(app)
     ext_celery.init_app(app)
-    ext_session.init_app(app)
     ext_login.init_app(app)
     ext_mail.init_app(app)
     ext_sentry.init_app(app)
     ext_stripe.init_app(app)
 
 
-def _create_tenant_for_account(account):
-    tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
-
-    TenantService.create_tenant_member(tenant, account, role='owner')
-    account.current_tenant = tenant
-
-    return tenant
-
-
 # Flask-Login configuration
-@login_manager.user_loader
-def load_user(user_id):
-    """Load user based on the user_id."""
+@login_manager.request_loader
+def load_user_from_request(request_from_flask_login):
+    """Load user based on the request."""
     if request.blueprint == 'console':
         # Check if the user_id contains a dot, indicating the old format
-        if '.' in user_id:
-            tenant_id, account_id = user_id.split('.')
-        else:
-            account_id = user_id
+        auth_header = request.headers.get('Authorization', '')
+        if ' ' not in auth_header:
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+        auth_scheme, auth_token = auth_header.split(None, 1)
+        auth_scheme = auth_scheme.lower()
+        if auth_scheme != 'bearer':
+            raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
+        
+        decoded = PassportService().verify(auth_token)
+        user_id = decoded.get('user_id')
 
-        account = db.session.query(Account).filter(Account.id == account_id).first()
-
-        if account:
-            if account.status == AccountStatus.BANNED.value or account.status == AccountStatus.CLOSED.value:
-                raise Forbidden('Account is banned or closed.')
-
-            workspace_id = session.get('workspace_id')
-            if workspace_id:
-                tenant_account_join = db.session.query(TenantAccountJoin).filter(
-                    TenantAccountJoin.account_id == account.id,
-                    TenantAccountJoin.tenant_id == workspace_id
-                ).first()
-
-                if not tenant_account_join:
-                    tenant_account_join = db.session.query(TenantAccountJoin).filter(
-                        TenantAccountJoin.account_id == account.id).first()
-
-                    if tenant_account_join:
-                        account.current_tenant_id = tenant_account_join.tenant_id
-                    else:
-                        _create_tenant_for_account(account)
-                    session['workspace_id'] = account.current_tenant_id
-                else:
-                    account.current_tenant_id = workspace_id
-            else:
-                tenant_account_join = db.session.query(TenantAccountJoin).filter(
-                    TenantAccountJoin.account_id == account.id).first()
-                if tenant_account_join:
-                    account.current_tenant_id = tenant_account_join.tenant_id
-                else:
-                    _create_tenant_for_account(account)
-                session['workspace_id'] = account.current_tenant_id
-
-            account.last_active_at = datetime.utcnow()
-            db.session.commit()
-
-            # Log in the user with the updated user_id
-            flask_login.login_user(account, remember=True)
-
-        return account
+        return AccountService.load_user(user_id)
     else:
         return None
 
-
 @login_manager.unauthorized_handler
 def unauthorized_handler():
     """Handle unauthorized requests."""
@@ -170,6 +134,7 @@ def register_blueprints(app):
     from controllers.service_api import bp as service_api_bp
     from controllers.web import bp as web_bp
     from controllers.console import bp as console_app_bp
+    from controllers.files import bp as files_bp
 
     CORS(service_api_bp,
          allow_headers=['Content-Type', 'Authorization', 'X-App-Code'],
@@ -199,6 +164,12 @@ def register_blueprints(app):
 
     app.register_blueprint(console_app_bp)
 
+    CORS(files_bp,
+         allow_headers=['Content-Type'],
+         methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH']
+         )
+    app.register_blueprint(files_bp)
+
 
 # create app
 app = create_app()
@@ -212,6 +183,7 @@ if app.config['TESTING']:
 @app.after_request
 def after_request(response):
     """Add Version headers to the response."""
+    response.set_cookie('remember_token', '', expires=0)
     response.headers.add('X-Version', app.config['CURRENT_VERSION'])
     response.headers.add('X-Env', app.config['DEPLOY_ENV'])
     return response

api/commands.py

@@ -1,22 +1,34 @@
 import datetime
+import json
 import math
 import random
 import string
+import threading
 import time
+import uuid
 
 import click
-from flask import current_app
+import qdrant_client
+from qdrant_client.http.models import TextIndexParams, TextIndexType, TokenizerType
+from tqdm import tqdm
+from flask import current_app, Flask
+from langchain.embeddings import OpenAIEmbeddings
 from werkzeug.exceptions import NotFound
 
+from core.embedding.cached_embedding import CacheEmbedding
 from core.index.index import IndexBuilder
+from core.model_providers.model_factory import ModelFactory
+from core.model_providers.models.embedding.openai_embedding import OpenAIEmbedding
+from core.model_providers.models.entity.model_params import ModelType
 from core.model_providers.providers.hosted import hosted_model_providers
+from core.model_providers.providers.openai_provider import OpenAIProvider
 from libs.password import password_pattern, valid_password, hash_password
 from libs.helper import email as email_validate
 from extensions.ext_database import db
 from libs.rsa import generate_key_pair
-from models.account import InvitationCode, Tenant
-from models.dataset import Dataset, DatasetQuery, Document
-from models.model import Account
+from models.account import InvitationCode, Tenant, TenantAccountJoin
+from models.dataset import Dataset, DatasetQuery, Document, DatasetCollectionBinding
+from models.model import Account, AppModelConfig, App
 import secrets
 import base64
 
@@ -231,7 +243,13 @@ def clean_unused_dataset_indexes():
                         kw_index = IndexBuilder.get_index(dataset, 'economy')
                         # delete from vector index
                         if vector_index:
-                            vector_index.delete()
+                            if dataset.collection_binding_id:
+                                vector_index.delete_by_group_id(dataset.id)
+                            else:
+                                if dataset.collection_binding_id:
+                                    vector_index.delete_by_group_id(dataset.id)
+                                else:
+                                    vector_index.delete()
                         kw_index.delete()
                         # update document
                         update_params = {
@@ -296,6 +314,444 @@ def sync_anthropic_hosted_providers():
     click.echo(click.style('Congratulations! Synced {} anthropic hosted providers.'.format(count), fg='green'))
 
 
+@click.command('create-qdrant-indexes', help='Create qdrant indexes.')
+def create_qdrant_indexes():
+    click.echo(click.style('Start create qdrant indexes.', fg='green'))
+    create_count = 0
+
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
+        except NotFound:
+            break
+
+        page += 1
+        for dataset in datasets:
+            if dataset.index_struct_dict:
+                if dataset.index_struct_dict['type'] != 'qdrant':
+                    try:
+                        click.echo('Create dataset qdrant index: {}'.format(dataset.id))
+                        try:
+                            embedding_model = ModelFactory.get_embedding_model(
+                                tenant_id=dataset.tenant_id,
+                                model_provider_name=dataset.embedding_model_provider,
+                                model_name=dataset.embedding_model
+                            )
+                        except Exception:
+                            try:
+                                embedding_model = ModelFactory.get_embedding_model(
+                                    tenant_id=dataset.tenant_id
+                                )
+                                dataset.embedding_model = embedding_model.name
+                                dataset.embedding_model_provider = embedding_model.model_provider.provider_name
+                            except Exception:
+                                provider = Provider(
+                                    id='provider_id',
+                                    tenant_id=dataset.tenant_id,
+                                    provider_name='openai',
+                                    provider_type=ProviderType.SYSTEM.value,
+                                    encrypted_config=json.dumps({'openai_api_key': 'TEST'}),
+                                    is_valid=True,
+                                )
+                                model_provider = OpenAIProvider(provider=provider)
+                                embedding_model = OpenAIEmbedding(name="text-embedding-ada-002",
+                                                                  model_provider=model_provider)
+                        embeddings = CacheEmbedding(embedding_model)
+
+                        from core.index.vector_index.qdrant_vector_index import QdrantVectorIndex, QdrantConfig
+
+                        index = QdrantVectorIndex(
+                            dataset=dataset,
+                            config=QdrantConfig(
+                                endpoint=current_app.config.get('QDRANT_URL'),
+                                api_key=current_app.config.get('QDRANT_API_KEY'),
+                                root_path=current_app.root_path
+                            ),
+                            embeddings=embeddings
+                        )
+                        if index:
+                            index.create_qdrant_dataset(dataset)
+                            index_struct = {
+                                "type": 'qdrant',
+                                "vector_store": {
+                                    "class_prefix": dataset.index_struct_dict['vector_store']['class_prefix']}
+                            }
+                            dataset.index_struct = json.dumps(index_struct)
+                            db.session.commit()
+                            create_count += 1
+                        else:
+                            click.echo('passed.')
+                    except Exception as e:
+                        click.echo(
+                            click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                        fg='red'))
+                        continue
+
+    click.echo(click.style('Congratulations! Create {} dataset indexes.'.format(create_count), fg='green'))
+
+
+@click.command('update-qdrant-indexes', help='Update qdrant indexes.')
+def update_qdrant_indexes():
+    click.echo(click.style('Start Update qdrant indexes.', fg='green'))
+    create_count = 0
+
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
+        except NotFound:
+            break
+
+        page += 1
+        for dataset in datasets:
+            if dataset.index_struct_dict:
+                if dataset.index_struct_dict['type'] != 'qdrant':
+                    try:
+                        click.echo('Update dataset qdrant index: {}'.format(dataset.id))
+                        try:
+                            embedding_model = ModelFactory.get_embedding_model(
+                                tenant_id=dataset.tenant_id,
+                                model_provider_name=dataset.embedding_model_provider,
+                                model_name=dataset.embedding_model
+                            )
+                        except Exception:
+                            provider = Provider(
+                                id='provider_id',
+                                tenant_id=dataset.tenant_id,
+                                provider_name='openai',
+                                provider_type=ProviderType.CUSTOM.value,
+                                encrypted_config=json.dumps({'openai_api_key': 'TEST'}),
+                                is_valid=True,
+                            )
+                            model_provider = OpenAIProvider(provider=provider)
+                            embedding_model = OpenAIEmbedding(name="text-embedding-ada-002",
+                                                              model_provider=model_provider)
+                        embeddings = CacheEmbedding(embedding_model)
+
+                        from core.index.vector_index.qdrant_vector_index import QdrantVectorIndex, QdrantConfig
+
+                        index = QdrantVectorIndex(
+                            dataset=dataset,
+                            config=QdrantConfig(
+                                endpoint=current_app.config.get('QDRANT_URL'),
+                                api_key=current_app.config.get('QDRANT_API_KEY'),
+                                root_path=current_app.root_path
+                            ),
+                            embeddings=embeddings
+                        )
+                        if index:
+                            index.update_qdrant_dataset(dataset)
+                            create_count += 1
+                        else:
+                            click.echo('passed.')
+                    except Exception as e:
+                        click.echo(
+                            click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                        fg='red'))
+                        continue
+
+    click.echo(click.style('Congratulations! Update {} dataset indexes.'.format(create_count), fg='green'))
+
+
+@click.command('normalization-collections', help='restore all collections in one')
+def normalization_collections():
+    click.echo(click.style('Start normalization collections.', fg='green'))
+    normalization_count = []
+    page = 1
+    while True:
+        try:
+            datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
+                .order_by(Dataset.created_at.desc()).paginate(page=page, per_page=100)
+        except NotFound:
+            break
+        datasets_result = datasets.items
+        page += 1
+        for i in range(0, len(datasets_result), 5):
+            threads = []
+            sub_datasets = datasets_result[i:i + 5]
+            for dataset in sub_datasets:
+                document_format_thread = threading.Thread(target=deal_dataset_vector, kwargs={
+                    'flask_app': current_app._get_current_object(),
+                    'dataset': dataset,
+                    'normalization_count': normalization_count
+                })
+                threads.append(document_format_thread)
+                document_format_thread.start()
+            for thread in threads:
+                thread.join()
+
+    click.echo(click.style('Congratulations! restore {} dataset indexes.'.format(len(normalization_count)), fg='green'))
+
+
+@click.command('add-qdrant-full-text-index', help='add qdrant full text index')
+def add_qdrant_full_text_index():
+    click.echo(click.style('Start add full text index.', fg='green'))
+    binds = db.session.query(DatasetCollectionBinding).all()
+    if binds and current_app.config['VECTOR_STORE'] == 'qdrant':
+        qdrant_url = current_app.config['QDRANT_URL']
+        qdrant_api_key = current_app.config['QDRANT_API_KEY']
+        client = qdrant_client.QdrantClient(
+            qdrant_url,
+            api_key=qdrant_api_key,  # For Qdrant Cloud, None for local instance
+        )
+        for bind in binds:
+            try:
+                text_index_params = TextIndexParams(
+                    type=TextIndexType.TEXT,
+                    tokenizer=TokenizerType.MULTILINGUAL,
+                    min_token_len=2,
+                    max_token_len=20,
+                    lowercase=True
+                )
+                client.create_payload_index(bind.collection_name, 'page_content',
+                                            field_schema=text_index_params)
+            except Exception as e:
+                click.echo(
+                    click.style('Create full text index error: {} {}'.format(e.__class__.__name__, str(e)),
+                                fg='red'))
+            click.echo(
+                click.style(
+                    'Congratulations! add collection {} full text index successful.'.format(bind.collection_name),
+                    fg='green'))
+
+
+def deal_dataset_vector(flask_app: Flask, dataset: Dataset, normalization_count: list):
+    with flask_app.app_context():
+        try:
+            click.echo('restore dataset index: {}'.format(dataset.id))
+            try:
+                embedding_model = ModelFactory.get_embedding_model(
+                    tenant_id=dataset.tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except Exception:
+                provider = Provider(
+                    id='provider_id',
+                    tenant_id=dataset.tenant_id,
+                    provider_name='openai',
+                    provider_type=ProviderType.CUSTOM.value,
+                    encrypted_config=json.dumps({'openai_api_key': 'TEST'}),
+                    is_valid=True,
+                )
+                model_provider = OpenAIProvider(provider=provider)
+                embedding_model = OpenAIEmbedding(name="text-embedding-ada-002",
+                                                  model_provider=model_provider)
+            embeddings = CacheEmbedding(embedding_model)
+            dataset_collection_binding = db.session.query(DatasetCollectionBinding). \
+                filter(DatasetCollectionBinding.provider_name == embedding_model.model_provider.provider_name,
+                       DatasetCollectionBinding.model_name == embedding_model.name). \
+                order_by(DatasetCollectionBinding.created_at). \
+                first()
+
+            if not dataset_collection_binding:
+                dataset_collection_binding = DatasetCollectionBinding(
+                    provider_name=embedding_model.model_provider.provider_name,
+                    model_name=embedding_model.name,
+                    collection_name="Vector_index_" + str(uuid.uuid4()).replace("-", "_") + '_Node'
+                )
+                db.session.add(dataset_collection_binding)
+                db.session.commit()
+
+            from core.index.vector_index.qdrant_vector_index import QdrantVectorIndex, QdrantConfig
+
+            index = QdrantVectorIndex(
+                dataset=dataset,
+                config=QdrantConfig(
+                    endpoint=current_app.config.get('QDRANT_URL'),
+                    api_key=current_app.config.get('QDRANT_API_KEY'),
+                    root_path=current_app.root_path
+                ),
+                embeddings=embeddings
+            )
+            if index:
+                # index.delete_by_group_id(dataset.id)
+                index.restore_dataset_in_one(dataset, dataset_collection_binding)
+            else:
+                click.echo('passed.')
+            normalization_count.append(1)
+        except Exception as e:
+            click.echo(
+                click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
+                            fg='red'))
+
+
+@click.command('update_app_model_configs', help='Migrate data to support paragraph variable.')
+@click.option("--batch-size", default=500, help="Number of records to migrate in each batch.")
+def update_app_model_configs(batch_size):
+    pre_prompt_template = '{{default_input}}'
+    user_input_form_template = {
+        "en-US": [
+            {
+                "paragraph": {
+                    "label": "Query",
+                    "variable": "default_input",
+                    "required": False,
+                    "default": ""
+                }
+            }
+        ],
+        "zh-Hans": [
+            {
+                "paragraph": {
+                    "label": "查询内容",
+                    "variable": "default_input",
+                    "required": False,
+                    "default": ""
+                }
+            }
+        ]
+    }
+
+    click.secho("Start migrate old data that the text generator can support paragraph variable.", fg='green')
+
+    total_records = db.session.query(AppModelConfig) \
+        .join(App, App.app_model_config_id == AppModelConfig.id) \
+        .filter(App.mode == 'completion') \
+        .count()
+
+    if total_records == 0:
+        click.secho("No data to migrate.", fg='green')
+        return
+
+    num_batches = (total_records + batch_size - 1) // batch_size
+
+    with tqdm(total=total_records, desc="Migrating Data") as pbar:
+        for i in range(num_batches):
+            offset = i * batch_size
+            limit = min(batch_size, total_records - offset)
+
+            click.secho(f"Fetching batch {i + 1}/{num_batches} from source database...", fg='green')
+
+            data_batch = db.session.query(AppModelConfig) \
+                .join(App, App.app_model_config_id == AppModelConfig.id) \
+                .filter(App.mode == 'completion') \
+                .order_by(App.created_at) \
+                .offset(offset).limit(limit).all()
+
+            if not data_batch:
+                click.secho("No more data to migrate.", fg='green')
+                break
+
+            try:
+                click.secho(f"Migrating {len(data_batch)} records...", fg='green')
+                for data in data_batch:
+                    # click.secho(f"Migrating data {data.id}, pre_prompt: {data.pre_prompt}, user_input_form: {data.user_input_form}", fg='green')
+
+                    if data.pre_prompt is None:
+                        data.pre_prompt = pre_prompt_template
+                    else:
+                        if pre_prompt_template in data.pre_prompt:
+                            continue
+                        data.pre_prompt += pre_prompt_template
+
+                    app_data = db.session.query(App) \
+                        .filter(App.id == data.app_id) \
+                        .one()
+
+                    account_data = db.session.query(Account) \
+                        .join(TenantAccountJoin, Account.id == TenantAccountJoin.account_id) \
+                        .filter(TenantAccountJoin.role == 'owner') \
+                        .filter(TenantAccountJoin.tenant_id == app_data.tenant_id) \
+                        .one_or_none()
+
+                    if not account_data:
+                        continue
+
+                    if data.user_input_form is None or data.user_input_form == 'null':
+                        data.user_input_form = json.dumps(user_input_form_template[account_data.interface_language])
+                    else:
+                        raw_json_data = json.loads(data.user_input_form)
+                        raw_json_data.append(user_input_form_template[account_data.interface_language][0])
+                        data.user_input_form = json.dumps(raw_json_data)
+
+                    # click.secho(f"Updated data {data.id}, pre_prompt: {data.pre_prompt}, user_input_form: {data.user_input_form}", fg='green')
+
+                db.session.commit()
+
+            except Exception as e:
+                click.secho(f"Error while migrating data: {e}, app_id: {data.app_id}, app_model_config_id: {data.id}",
+                            fg='red')
+                continue
+
+            click.secho(f"Successfully migrated batch {i + 1}/{num_batches}.", fg='green')
+
+            pbar.update(len(data_batch))
+
+
+@click.command('migrate_default_input_to_dataset_query_variable')
+@click.option("--batch-size", default=500, help="Number of records to migrate in each batch.")
+def migrate_default_input_to_dataset_query_variable(batch_size):
+    click.secho("Starting...", fg='green')
+
+    total_records = db.session.query(AppModelConfig) \
+        .join(App, App.app_model_config_id == AppModelConfig.id) \
+        .filter(App.mode == 'completion') \
+        .filter(AppModelConfig.dataset_query_variable == None) \
+        .count()
+
+    if total_records == 0:
+        click.secho("No data to migrate.", fg='green')
+        return
+
+    num_batches = (total_records + batch_size - 1) // batch_size
+
+    with tqdm(total=total_records, desc="Migrating Data") as pbar:
+        for i in range(num_batches):
+            offset = i * batch_size
+            limit = min(batch_size, total_records - offset)
+
+            click.secho(f"Fetching batch {i + 1}/{num_batches} from source database...", fg='green')
+
+            data_batch = db.session.query(AppModelConfig) \
+                .join(App, App.app_model_config_id == AppModelConfig.id) \
+                .filter(App.mode == 'completion') \
+                .filter(AppModelConfig.dataset_query_variable == None) \
+                .order_by(App.created_at) \
+                .offset(offset).limit(limit).all()
+
+            if not data_batch:
+                click.secho("No more data to migrate.", fg='green')
+                break
+
+            try:
+                click.secho(f"Migrating {len(data_batch)} records...", fg='green')
+                for data in data_batch:
+                    config = AppModelConfig.to_dict(data)
+
+                    tools = config["agent_mode"]["tools"]
+                    dataset_exists = "dataset" in str(tools)
+                    if not dataset_exists:
+                        continue
+
+                    user_input_form = config.get("user_input_form", [])
+                    for form in user_input_form:
+                        paragraph = form.get('paragraph')
+                        if paragraph \
+                                and paragraph.get('variable') == 'query':
+                            data.dataset_query_variable = 'query'
+                            break
+
+                        if paragraph \
+                                and paragraph.get('variable') == 'default_input':
+                            data.dataset_query_variable = 'default_input'
+                            break
+
+                db.session.commit()
+
+            except Exception as e:
+                click.secho(f"Error while migrating data: {e}, app_id: {data.app_id}, app_model_config_id: {data.id}",
+                            fg='red')
+                continue
+
+            click.secho(f"Successfully migrated batch {i + 1}/{num_batches}.", fg='green')
+
+            pbar.update(len(data_batch))
+
+
 def register_commands(app):
     app.cli.add_command(reset_password)
     app.cli.add_command(reset_email)
@@ -304,3 +760,9 @@ def register_commands(app):
     app.cli.add_command(recreate_all_dataset_indexes)
     app.cli.add_command(sync_anthropic_hosted_providers)
     app.cli.add_command(clean_unused_dataset_indexes)
+    app.cli.add_command(create_qdrant_indexes)
+    app.cli.add_command(update_qdrant_indexes)
+    app.cli.add_command(update_app_model_configs)
+    app.cli.add_command(normalization_collections)
+    app.cli.add_command(migrate_default_input_to_dataset_query_variable)
+    app.cli.add_command(add_qdrant_full_text_index)

api/config.py

@@ -10,9 +10,6 @@ from extensions.ext_redis import redis_client
 dotenv.load_dotenv()
 
 DEFAULTS = {
-    'COOKIE_HTTPONLY': 'True',
-    'COOKIE_SECURE': 'True',
-    'COOKIE_SAMESITE': 'None',
     'DB_USERNAME': 'postgres',
     'DB_PASSWORD': '',
     'DB_HOST': 'localhost',
@@ -22,10 +19,6 @@ DEFAULTS = {
     'REDIS_PORT': '6379',
     'REDIS_DB': '0',
     'REDIS_USE_SSL': 'False',
-    'SESSION_REDIS_HOST': 'localhost',
-    'SESSION_REDIS_PORT': '6379',
-    'SESSION_REDIS_DB': '2',
-    'SESSION_REDIS_USE_SSL': 'False',
     'OAUTH_REDIRECT_PATH': '/console/api/oauth/authorize',
     'OAUTH_REDIRECT_INDEX_PATH': '/',
     'CONSOLE_WEB_URL': 'https://cloud.dify.ai',
@@ -33,12 +26,10 @@ DEFAULTS = {
     'SERVICE_API_URL': 'https://api.dify.ai',
     'APP_WEB_URL': 'https://udify.app',
     'APP_API_URL': 'https://udify.app',
+    'FILES_URL': '',
     'STORAGE_TYPE': 'local',
     'STORAGE_LOCAL_PATH': 'storage',
     'CHECK_UPDATE_URL': 'https://updates.dify.ai',
-    'SESSION_TYPE': 'sqlalchemy',
-    'SESSION_PERMANENT': 'True',
-    'SESSION_USE_SIGNER': 'True',
     'DEPLOY_ENV': 'PRODUCTION',
     'SQLALCHEMY_POOL_SIZE': 30,
     'SQLALCHEMY_POOL_RECYCLE': 3600,
@@ -61,10 +52,16 @@ DEFAULTS = {
     'HOSTED_ANTHROPIC_PAID_INCREASE_QUOTA': 1000000,
     'HOSTED_ANTHROPIC_PAID_MIN_QUANTITY': 20,
     'HOSTED_ANTHROPIC_PAID_MAX_QUANTITY': 100,
+    'HOSTED_MODERATION_ENABLED': 'False',
+    'HOSTED_MODERATION_PROVIDERS': '',
     'TENANT_DOCUMENT_COUNT': 100,
     'CLEAN_DAY_SETTING': 30,
     'UPLOAD_FILE_SIZE_LIMIT': 15,
     'UPLOAD_FILE_BATCH_LIMIT': 5,
+    'UPLOAD_IMAGE_FILE_SIZE_LIMIT': 10,
+    'OUTPUT_MODERATION_BUFFER_SIZE': 300,
+    'MULTIMODAL_SEND_IMAGE_FORMAT': 'base64',
+    'INVITE_EXPIRY_HOURS': 72
 }
 
 
@@ -91,100 +88,65 @@ class Config:
     """Application configuration class."""
 
     def __init__(self):
-        # app settings
-        self.CONSOLE_API_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_API_URL')
-        self.CONSOLE_WEB_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_WEB_URL')
-        self.SERVICE_API_URL = get_env('API_URL') if get_env('API_URL') else get_env('SERVICE_API_URL')
-        self.APP_WEB_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_WEB_URL')
-        self.APP_API_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_API_URL')
-        self.CONSOLE_URL = get_env('CONSOLE_URL')
-        self.API_URL = get_env('API_URL')
-        self.APP_URL = get_env('APP_URL')
-        self.CURRENT_VERSION = "0.3.16"
+        # ------------------------
+        # General Configurations.
+        # ------------------------
+        self.CURRENT_VERSION = "0.3.31"
         self.COMMIT_SHA = get_env('COMMIT_SHA')
         self.EDITION = "SELF_HOSTED"
         self.DEPLOY_ENV = get_env('DEPLOY_ENV')
         self.TESTING = False
         self.LOG_LEVEL = get_env('LOG_LEVEL')
 
+        # The backend URL prefix of the console API.
+        # used to concatenate the login authorization callback or notion integration callback.
+        self.CONSOLE_API_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_API_URL')
+
+        # The front-end URL prefix of the console web.
+        # used to concatenate some front-end addresses and for CORS configuration use.
+        self.CONSOLE_WEB_URL = get_env('CONSOLE_URL') if get_env('CONSOLE_URL') else get_env('CONSOLE_WEB_URL')
+
+        # WebApp API backend Url prefix.
+        # used to declare the back-end URL for the front-end API.
+        self.APP_API_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_API_URL')
+
+        # WebApp Url prefix.
+        # used to display WebAPP API Base Url to the front-end.
+        self.APP_WEB_URL = get_env('APP_URL') if get_env('APP_URL') else get_env('APP_WEB_URL')
+
+        # Service API Url prefix.
+        # used to display Service API Base Url to the front-end.
+        self.SERVICE_API_URL = get_env('API_URL') if get_env('API_URL') else get_env('SERVICE_API_URL')
+
+        # File preview or download Url prefix.
+        # used to display File preview or download Url to the front-end or as Multi-model inputs;
+        # Url is signed and has expiration time.
+        self.FILES_URL = get_env('FILES_URL') if get_env('FILES_URL') else self.CONSOLE_API_URL
+
+        # Fallback Url prefix.
+        # Will be deprecated in the future.
+        self.CONSOLE_URL = get_env('CONSOLE_URL')
+        self.API_URL = get_env('API_URL')
+        self.APP_URL = get_env('APP_URL')
+
         # Your App secret key will be used for securely signing the session cookie
         # Make sure you are changing this key for your deployment with a strong key.
         # You can generate a strong key using `openssl rand -base64 42`.
         # Alternatively you can set it with `SECRET_KEY` environment variable.
         self.SECRET_KEY = get_env('SECRET_KEY')
 
-        # cookie settings
-        self.REMEMBER_COOKIE_HTTPONLY = get_bool_env('COOKIE_HTTPONLY')
-        self.SESSION_COOKIE_HTTPONLY = get_bool_env('COOKIE_HTTPONLY')
-        self.REMEMBER_COOKIE_SAMESITE = get_env('COOKIE_SAMESITE')
-        self.SESSION_COOKIE_SAMESITE = get_env('COOKIE_SAMESITE')
-        self.REMEMBER_COOKIE_SECURE = get_bool_env('COOKIE_SECURE')
-        self.SESSION_COOKIE_SECURE = get_bool_env('COOKIE_SECURE')
-        self.PERMANENT_SESSION_LIFETIME = timedelta(days=7)
-
-        # session settings, only support sqlalchemy, redis
-        self.SESSION_TYPE = get_env('SESSION_TYPE')
-        self.SESSION_PERMANENT = get_bool_env('SESSION_PERMANENT')
-        self.SESSION_USE_SIGNER = get_bool_env('SESSION_USE_SIGNER')
-
-        # redis settings
-        self.REDIS_HOST = get_env('REDIS_HOST')
-        self.REDIS_PORT = get_env('REDIS_PORT')
-        self.REDIS_USERNAME = get_env('REDIS_USERNAME')
-        self.REDIS_PASSWORD = get_env('REDIS_PASSWORD')
-        self.REDIS_DB = get_env('REDIS_DB')
-        self.REDIS_USE_SSL = get_bool_env('REDIS_USE_SSL')
-
-        # session redis settings
-        self.SESSION_REDIS_HOST = get_env('SESSION_REDIS_HOST')
-        self.SESSION_REDIS_PORT = get_env('SESSION_REDIS_PORT')
-        self.SESSION_REDIS_USERNAME = get_env('SESSION_REDIS_USERNAME')
-        self.SESSION_REDIS_PASSWORD = get_env('SESSION_REDIS_PASSWORD')
-        self.SESSION_REDIS_DB = get_env('SESSION_REDIS_DB')
-        self.SESSION_REDIS_USE_SSL = get_bool_env('SESSION_REDIS_USE_SSL')
-
-        # storage settings
-        self.STORAGE_TYPE = get_env('STORAGE_TYPE')
-        self.STORAGE_LOCAL_PATH = get_env('STORAGE_LOCAL_PATH')
-        self.S3_ENDPOINT = get_env('S3_ENDPOINT')
-        self.S3_BUCKET_NAME = get_env('S3_BUCKET_NAME')
-        self.S3_ACCESS_KEY = get_env('S3_ACCESS_KEY')
-        self.S3_SECRET_KEY = get_env('S3_SECRET_KEY')
-        self.S3_REGION = get_env('S3_REGION')
-
-        # vector store settings, only support weaviate, qdrant
-        self.VECTOR_STORE = get_env('VECTOR_STORE')
-
-        # weaviate settings
-        self.WEAVIATE_ENDPOINT = get_env('WEAVIATE_ENDPOINT')
-        self.WEAVIATE_API_KEY = get_env('WEAVIATE_API_KEY')
-        self.WEAVIATE_GRPC_ENABLED = get_bool_env('WEAVIATE_GRPC_ENABLED')
-        self.WEAVIATE_BATCH_SIZE = int(get_env('WEAVIATE_BATCH_SIZE'))
-
-        # qdrant settings
-        self.QDRANT_URL = get_env('QDRANT_URL')
-        self.QDRANT_API_KEY = get_env('QDRANT_API_KEY')
-
         # cors settings
         self.CONSOLE_CORS_ALLOW_ORIGINS = get_cors_allow_origins(
             'CONSOLE_CORS_ALLOW_ORIGINS', self.CONSOLE_WEB_URL)
         self.WEB_API_CORS_ALLOW_ORIGINS = get_cors_allow_origins(
             'WEB_API_CORS_ALLOW_ORIGINS', '*')
 
-        # mail settings
-        self.MAIL_TYPE = get_env('MAIL_TYPE')
-        self.MAIL_DEFAULT_SEND_FROM = get_env('MAIL_DEFAULT_SEND_FROM')
-        self.RESEND_API_KEY = get_env('RESEND_API_KEY')
-
-        # sentry settings
-        self.SENTRY_DSN = get_env('SENTRY_DSN')
-        self.SENTRY_TRACES_SAMPLE_RATE = float(get_env('SENTRY_TRACES_SAMPLE_RATE'))
-        self.SENTRY_PROFILES_SAMPLE_RATE = float(get_env('SENTRY_PROFILES_SAMPLE_RATE'))
-
         # check update url
         self.CHECK_UPDATE_URL = get_env('CHECK_UPDATE_URL')
 
-        # database settings
+        # ------------------------
+        # Database Configurations.
+        # ------------------------
         db_credentials = {
             key: get_env(key) for key in
             ['DB_USERNAME', 'DB_PASSWORD', 'DB_HOST', 'DB_PORT', 'DB_DATABASE']
@@ -198,14 +160,107 @@ class Config:
 
         self.SQLALCHEMY_ECHO = get_bool_env('SQLALCHEMY_ECHO')
 
-        # celery settings
+        # ------------------------
+        # Redis Configurations.
+        # ------------------------
+        self.REDIS_HOST = get_env('REDIS_HOST')
+        self.REDIS_PORT = get_env('REDIS_PORT')
+        self.REDIS_USERNAME = get_env('REDIS_USERNAME')
+        self.REDIS_PASSWORD = get_env('REDIS_PASSWORD')
+        self.REDIS_DB = get_env('REDIS_DB')
+        self.REDIS_USE_SSL = get_bool_env('REDIS_USE_SSL')
+
+        # ------------------------
+        # Celery worker Configurations.
+        # ------------------------
         self.CELERY_BROKER_URL = get_env('CELERY_BROKER_URL')
         self.CELERY_BACKEND = get_env('CELERY_BACKEND')
         self.CELERY_RESULT_BACKEND = 'db+{}'.format(self.SQLALCHEMY_DATABASE_URI) \
             if self.CELERY_BACKEND == 'database' else self.CELERY_BROKER_URL
         self.BROKER_USE_SSL = self.CELERY_BROKER_URL.startswith('rediss://')
 
-        # hosted provider credentials
+        # ------------------------
+        # File Storage Configurations.
+        # ------------------------
+        self.STORAGE_TYPE = get_env('STORAGE_TYPE')
+        self.STORAGE_LOCAL_PATH = get_env('STORAGE_LOCAL_PATH')
+        self.S3_ENDPOINT = get_env('S3_ENDPOINT')
+        self.S3_BUCKET_NAME = get_env('S3_BUCKET_NAME')
+        self.S3_ACCESS_KEY = get_env('S3_ACCESS_KEY')
+        self.S3_SECRET_KEY = get_env('S3_SECRET_KEY')
+        self.S3_REGION = get_env('S3_REGION')
+
+        # ------------------------
+        # Vector Store Configurations.
+        # Currently, only support: qdrant, milvus, zilliz, weaviate
+        # ------------------------
+        self.VECTOR_STORE = get_env('VECTOR_STORE')
+
+        # qdrant settings
+        self.QDRANT_URL = get_env('QDRANT_URL')
+        self.QDRANT_API_KEY = get_env('QDRANT_API_KEY')
+
+        # milvus / zilliz setting
+        self.MILVUS_HOST = get_env('MILVUS_HOST')
+        self.MILVUS_PORT = get_env('MILVUS_PORT')
+        self.MILVUS_USER = get_env('MILVUS_USER')
+        self.MILVUS_PASSWORD = get_env('MILVUS_PASSWORD')
+        self.MILVUS_SECURE = get_env('MILVUS_SECURE')
+
+        # weaviate settings
+        self.WEAVIATE_ENDPOINT = get_env('WEAVIATE_ENDPOINT')
+        self.WEAVIATE_API_KEY = get_env('WEAVIATE_API_KEY')
+        self.WEAVIATE_GRPC_ENABLED = get_bool_env('WEAVIATE_GRPC_ENABLED')
+        self.WEAVIATE_BATCH_SIZE = int(get_env('WEAVIATE_BATCH_SIZE'))
+
+        # ------------------------
+        # Mail Configurations.
+        # ------------------------
+        self.MAIL_TYPE = get_env('MAIL_TYPE')
+        self.MAIL_DEFAULT_SEND_FROM = get_env('MAIL_DEFAULT_SEND_FROM')
+        self.RESEND_API_KEY = get_env('RESEND_API_KEY')
+        
+        # ------------------------
+        # Workpace Configurations.
+        # ------------------------
+        self.INVITE_EXPIRY_HOURS = int(get_env('INVITE_EXPIRY_HOURS'))
+
+        # ------------------------
+        # Sentry Configurations.
+        # ------------------------
+        self.SENTRY_DSN = get_env('SENTRY_DSN')
+        self.SENTRY_TRACES_SAMPLE_RATE = float(get_env('SENTRY_TRACES_SAMPLE_RATE'))
+        self.SENTRY_PROFILES_SAMPLE_RATE = float(get_env('SENTRY_PROFILES_SAMPLE_RATE'))
+
+        # ------------------------
+        # Business Configurations.
+        # ------------------------
+
+        # multi model send image format, support base64, url, default is base64
+        self.MULTIMODAL_SEND_IMAGE_FORMAT = get_env('MULTIMODAL_SEND_IMAGE_FORMAT')
+
+        # Dataset Configurations.
+        self.TENANT_DOCUMENT_COUNT = get_env('TENANT_DOCUMENT_COUNT')
+        self.CLEAN_DAY_SETTING = get_env('CLEAN_DAY_SETTING')
+
+        # File upload Configurations.
+        self.UPLOAD_FILE_SIZE_LIMIT = int(get_env('UPLOAD_FILE_SIZE_LIMIT'))
+        self.UPLOAD_FILE_BATCH_LIMIT = int(get_env('UPLOAD_FILE_BATCH_LIMIT'))
+        self.UPLOAD_IMAGE_FILE_SIZE_LIMIT = int(get_env('UPLOAD_IMAGE_FILE_SIZE_LIMIT'))
+
+        # Moderation in app Configurations.
+        self.OUTPUT_MODERATION_BUFFER_SIZE = int(get_env('OUTPUT_MODERATION_BUFFER_SIZE'))
+
+        # Notion integration setting
+        self.NOTION_CLIENT_ID = get_env('NOTION_CLIENT_ID')
+        self.NOTION_CLIENT_SECRET = get_env('NOTION_CLIENT_SECRET')
+        self.NOTION_INTEGRATION_TYPE = get_env('NOTION_INTEGRATION_TYPE')
+        self.NOTION_INTERNAL_SECRET = get_env('NOTION_INTERNAL_SECRET')
+        self.NOTION_INTEGRATION_TOKEN = get_env('NOTION_INTEGRATION_TOKEN')
+
+        # ------------------------
+        # Platform Configurations.
+        # ------------------------
         self.HOSTED_OPENAI_ENABLED = get_bool_env('HOSTED_OPENAI_ENABLED')
         self.HOSTED_OPENAI_API_KEY = get_env('HOSTED_OPENAI_API_KEY')
         self.HOSTED_OPENAI_API_BASE = get_env('HOSTED_OPENAI_API_BASE')
@@ -230,22 +285,8 @@ class Config:
         self.HOSTED_ANTHROPIC_PAID_MIN_QUANTITY = int(get_env('HOSTED_ANTHROPIC_PAID_MIN_QUANTITY'))
         self.HOSTED_ANTHROPIC_PAID_MAX_QUANTITY = int(get_env('HOSTED_ANTHROPIC_PAID_MAX_QUANTITY'))
 
-        self.STRIPE_API_KEY = get_env('STRIPE_API_KEY')
-        self.STRIPE_WEBHOOK_SECRET = get_env('STRIPE_WEBHOOK_SECRET')
-
-        # notion import setting
-        self.NOTION_CLIENT_ID = get_env('NOTION_CLIENT_ID')
-        self.NOTION_CLIENT_SECRET = get_env('NOTION_CLIENT_SECRET')
-        self.NOTION_INTEGRATION_TYPE = get_env('NOTION_INTEGRATION_TYPE')
-        self.NOTION_INTERNAL_SECRET = get_env('NOTION_INTERNAL_SECRET')
-        self.NOTION_INTEGRATION_TOKEN = get_env('NOTION_INTEGRATION_TOKEN')
-
-        self.TENANT_DOCUMENT_COUNT = get_env('TENANT_DOCUMENT_COUNT')
-        self.CLEAN_DAY_SETTING = get_env('CLEAN_DAY_SETTING')
-
-        # uploading settings
-        self.UPLOAD_FILE_SIZE_LIMIT = int(get_env('UPLOAD_FILE_SIZE_LIMIT'))
-        self.UPLOAD_FILE_BATCH_LIMIT = int(get_env('UPLOAD_FILE_BATCH_LIMIT'))
+        self.HOSTED_MODERATION_ENABLED = get_bool_env('HOSTED_MODERATION_ENABLED')
+        self.HOSTED_MODERATION_PROVIDERS = get_env('HOSTED_MODERATION_PROVIDERS')
 
 
 class CloudEditionConfig(Config):
@@ -261,18 +302,5 @@ class CloudEditionConfig(Config):
         self.GOOGLE_CLIENT_SECRET = get_env('GOOGLE_CLIENT_SECRET')
         self.OAUTH_REDIRECT_PATH = get_env('OAUTH_REDIRECT_PATH')
 
-
-class TestConfig(Config):
-
-    def __init__(self):
-        super().__init__()
-
-        self.EDITION = "SELF_HOSTED"
-        self.TESTING = True
-
-        db_credentials = {
-            key: get_env(key) for key in ['DB_USERNAME', 'DB_PASSWORD', 'DB_HOST', 'DB_PORT']
-        }
-
-        # use a different database for testing: dify_test
-        self.SQLALCHEMY_DATABASE_URI = f"postgresql://{db_credentials['DB_USERNAME']}:{db_credentials['DB_PASSWORD']}@{db_credentials['DB_HOST']}:{db_credentials['DB_PORT']}/dify_test"
+        self.STRIPE_API_KEY = get_env('STRIPE_API_KEY')
+        self.STRIPE_WEBHOOK_SECRET = get_env('STRIPE_WEBHOOK_SECRET')

api/constants/model_template.py

@@ -16,7 +16,7 @@ model_templates = {
         },
         'model_config': {
             'provider': 'openai',
-            'model_id': 'text-davinci-003',
+            'model_id': 'gpt-3.5-turbo-instruct',
             'configs': {
                 'prompt_template': '',
                 'prompt_variables': [],
@@ -30,7 +30,8 @@ model_templates = {
             },
             'model': json.dumps({
                 "provider": "openai",
-                "name": "text-davinci-003",
+                "name": "gpt-3.5-turbo-instruct",
+                "mode": "completion",
                 "completion_params": {
                     "max_tokens": 512,
                     "temperature": 1,
@@ -38,7 +39,18 @@ model_templates = {
                     "presence_penalty": 0,
                     "frequency_penalty": 0
                 }
-            })
+            }),
+            'user_input_form': json.dumps([
+                {
+                    "paragraph": {
+                        "label": "Query",
+                        "variable": "query",
+                        "required": True,
+                        "default": ""
+                    }
+                }
+            ]),
+            'pre_prompt': '{{query}}'
         }
     },
 
@@ -70,6 +82,7 @@ model_templates = {
             'model': json.dumps({
                 "provider": "openai",
                 "name": "gpt-3.5-turbo",
+                "mode": "chat",
                 "completion_params": {
                     "max_tokens": 512,
                     "temperature": 1,
@@ -93,7 +106,7 @@ demo_model_templates = {
             'mode': 'completion',
             'model_config': AppModelConfig(
                 provider='openai',
-                model_id='text-davinci-003',
+                model_id='gpt-3.5-turbo-instruct',
                 configs={
                     'prompt_template': "Please translate the following text into {{target_language}}:\n",
                     'prompt_variables': [
@@ -126,10 +139,11 @@ demo_model_templates = {
                 },
                 opening_statement='',
                 suggested_questions=None,
-                pre_prompt="Please translate the following text into {{target_language}}:\n",
+                pre_prompt="Please translate the following text into {{target_language}}:\n{{query}}\ntranslate:",
                 model=json.dumps({
                     "provider": "openai",
-                    "name": "text-davinci-003",
+                    "name": "gpt-3.5-turbo-instruct",
+                    "mode": "completion",
                     "completion_params": {
                         "max_tokens": 1000,
                         "temperature": 0,
@@ -158,6 +172,13 @@ demo_model_templates = {
                                 'Italian',
                             ]
                         }
+                    },{
+                        "paragraph": {
+                            "label": "Query",
+                            "variable": "query",
+                            "required": True,
+                            "default": ""
+                        }
                     }
                 ])
             )
@@ -189,6 +210,7 @@ demo_model_templates = {
                 model=json.dumps({
                     "provider": "openai",
                     "name": "gpt-3.5-turbo",
+                    "mode": "chat",
                     "completion_params": {
                         "max_tokens": 300,
                         "temperature": 0.8,
@@ -211,7 +233,7 @@ demo_model_templates = {
             'mode': 'completion',
             'model_config': AppModelConfig(
                 provider='openai',
-                model_id='text-davinci-003',
+                model_id='gpt-3.5-turbo-instruct',
                 configs={
                     'prompt_template': "请将以下文本翻译为{{target_language}}:\n",
                     'prompt_variables': [
@@ -244,10 +266,11 @@ demo_model_templates = {
                 },
                 opening_statement='',
                 suggested_questions=None,
-                pre_prompt="请将以下文本翻译为{{target_language}}:\n",
+                pre_prompt="请将以下文本翻译为{{target_language}}:\n{{query}}\n翻译:",
                 model=json.dumps({
                     "provider": "openai",
-                    "name": "text-davinci-003",
+                    "name": "gpt-3.5-turbo-instruct",
+                    "mode": "completion",
                     "completion_params": {
                         "max_tokens": 1000,
                         "temperature": 0,
@@ -276,6 +299,13 @@ demo_model_templates = {
                                 "意大利语",
                             ]
                         }
+                    },{
+                        "paragraph": {
+                            "label": "文本内容",
+                            "variable": "query",
+                            "required": True,
+                            "default": ""
+                        }
                     }
                 ])
             )
@@ -307,6 +337,7 @@ demo_model_templates = {
                 model=json.dumps({
                     "provider": "openai",
                     "name": "gpt-3.5-turbo",
+                    "mode": "chat",
                     "completion_params": {
                         "max_tokens": 300,
                         "temperature": 0.8,

api/controllers/console/__init__.py

@@ -6,10 +6,10 @@ bp = Blueprint('console', __name__, url_prefix='/console/api')
 api = ExternalApi(bp)
 
 # Import other controllers
-from . import setup, version, apikey, admin
+from . import extension, setup, version, apikey, admin
 
 # Import app controllers
-from .app import app, site, completion, model_config, statistic, conversation, message, generator, audio
+from .app import advanced_prompt_template, app, site, completion, model_config, statistic, conversation, message, generator, audio
 
 # Import auth controllers
 from .auth import login, oauth, data_source_oauth, activate

api/controllers/console/apikey.py

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

api/controllers/console/app/advanced_prompt_template.py

@@ -0,0 +1,25 @@
+from flask_restful import Resource, reqparse
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from libs.login import login_required
+from services.advanced_prompt_template_service import AdvancedPromptTemplateService
+
+class AdvancedPromptTemplateList(Resource):
+    
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+         
+        parser = reqparse.RequestParser()
+        parser.add_argument('app_mode', type=str, required=True, location='args')
+        parser.add_argument('model_mode', type=str, required=True, location='args')
+        parser.add_argument('has_context', type=str, required=False, default='true', location='args')
+        parser.add_argument('model_name', type=str, required=True, location='args')
+        args = parser.parse_args()
+
+        return AdvancedPromptTemplateService.get_prompt(args)
+
+api.add_resource(AdvancedPromptTemplateList, '/app/prompt-templates')

api/controllers/console/app/app.py

@@ -3,10 +3,9 @@ import json
 import logging
 from datetime import datetime
 
-import flask
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, reqparse, fields, marshal_with, abort, inputs
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with, abort, inputs
 from werkzeug.exceptions import Forbidden
 
 from constants.model_template import model_templates, demo_model_templates
@@ -17,41 +16,13 @@ from controllers.console.wraps import account_initialization_required
 from core.model_providers.error import ProviderTokenNotInitError, LLMBadRequestError
 from core.model_providers.model_factory import ModelFactory
 from core.model_providers.model_provider_factory import ModelProviderFactory
-from core.model_providers.models.entity.model_params import ModelType
 from events.app_event import app_was_created, app_was_deleted
-from libs.helper import TimestampField
+from fields.app_fields import app_pagination_fields, app_detail_fields, template_list_fields, \
+    app_detail_fields_with_site
 from extensions.ext_database import db
 from models.model import App, AppModelConfig, Site
 from services.app_model_config_service import AppModelConfigService
 
-model_config_fields = {
-    'opening_statement': fields.String,
-    'suggested_questions': fields.Raw(attribute='suggested_questions_list'),
-    'suggested_questions_after_answer': fields.Raw(attribute='suggested_questions_after_answer_dict'),
-    'speech_to_text': fields.Raw(attribute='speech_to_text_dict'),
-    'more_like_this': fields.Raw(attribute='more_like_this_dict'),
-    'sensitive_word_avoidance': fields.Raw(attribute='sensitive_word_avoidance_dict'),
-    'model': fields.Raw(attribute='model_dict'),
-    'user_input_form': fields.Raw(attribute='user_input_form_list'),
-    'pre_prompt': fields.String,
-    'agent_mode': fields.Raw(attribute='agent_mode_dict'),
-}
-
-app_detail_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'mode': fields.String,
-    'icon': fields.String,
-    'icon_background': fields.String,
-    'enable_site': fields.Boolean,
-    'enable_api': fields.Boolean,
-    'api_rpm': fields.Integer,
-    'api_rph': fields.Integer,
-    'is_demo': fields.Boolean,
-    'model_config': fields.Nested(model_config_fields, attribute='app_model_config'),
-    'created_at': TimestampField
-}
-
 
 def _get_app(app_id, tenant_id):
     app = db.session.query(App).filter(App.id == app_id, App.tenant_id == tenant_id).first()
@@ -61,35 +32,6 @@ def _get_app(app_id, tenant_id):
 
 
 class AppListApi(Resource):
-    prompt_config_fields = {
-        'prompt_template': fields.String,
-    }
-
-    model_config_partial_fields = {
-        'model': fields.Raw(attribute='model_dict'),
-        'pre_prompt': fields.String,
-    }
-
-    app_partial_fields = {
-        'id': fields.String,
-        'name': fields.String,
-        'mode': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'enable_site': fields.Boolean,
-        'enable_api': fields.Boolean,
-        'is_demo': fields.Boolean,
-        'model_config': fields.Nested(model_config_partial_fields, attribute='app_model_config'),
-        'created_at': TimestampField
-    }
-
-    app_pagination_fields = {
-        'page': fields.Integer,
-        'limit': fields.Integer(attribute='per_page'),
-        'total': fields.Integer,
-        'has_more': fields.Boolean(attribute='has_next'),
-        'data': fields.List(fields.Nested(app_partial_fields), attribute='items')
-    }
 
     @setup_required
     @login_required
@@ -161,7 +103,8 @@ class AppListApi(Resource):
             model_configuration = AppModelConfigService.validate_configuration(
                 tenant_id=current_user.current_tenant_id,
                 account=current_user,
-                config=model_config_dict
+                config=model_config_dict,
+                mode=args['mode']
             )
 
             app = App(
@@ -235,18 +178,6 @@ class AppListApi(Resource):
 
 
 class AppTemplateApi(Resource):
-    template_fields = {
-        'name': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'description': fields.String,
-        'mode': fields.String,
-        'model_config': fields.Nested(model_config_fields),
-    }
-
-    template_list_fields = {
-        'data': fields.List(fields.Nested(template_fields)),
-    }
 
     @setup_required
     @login_required
@@ -265,38 +196,6 @@ class AppTemplateApi(Resource):
 
 
 class AppApi(Resource):
-    site_fields = {
-        'access_token': fields.String(attribute='code'),
-        'code': fields.String,
-        'title': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'description': fields.String,
-        'default_language': fields.String,
-        'customize_domain': fields.String,
-        'copyright': fields.String,
-        'privacy_policy': fields.String,
-        'customize_token_strategy': fields.String,
-        'prompt_public': fields.Boolean,
-        'app_base_url': fields.String,
-    }
-
-    app_detail_fields_with_site = {
-        'id': fields.String,
-        'name': fields.String,
-        'mode': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-        'enable_site': fields.Boolean,
-        'enable_api': fields.Boolean,
-        'api_rpm': fields.Integer,
-        'api_rph': fields.Integer,
-        'is_demo': fields.Boolean,
-        'model_config': fields.Nested(model_config_fields, attribute='app_model_config'),
-        'site': fields.Nested(site_fields),
-        'api_base_url': fields.String,
-        'created_at': TimestampField
-    }
 
     @setup_required
     @login_required

api/controllers/console/app/audio.py

@@ -2,8 +2,8 @@
 import logging
 
 from flask import request
-from core.login.login import login_required
-from werkzeug.exceptions import InternalServerError, NotFound
+from libs.login import login_required
+from werkzeug.exceptions import InternalServerError
 
 import services
 from controllers.console import api

api/controllers/console/app/completion.py

@@ -5,7 +5,7 @@ from typing import Generator, Union
 
 import flask_login
 from flask import Response, stream_with_context
-from core.login.login import login_required
+from libs.login import login_required
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services
@@ -39,12 +39,15 @@ class CompletionMessageApi(Resource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
-        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('query', type=str, location='json', default='')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('model_config', type=dict, required=True, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
         args = parser.parse_args()
 
         streaming = args['response_mode'] != 'blocking'
+        args['auto_generate_name'] = False
 
         account = flask_login.current_user
 
@@ -112,12 +115,15 @@ class ChatMessageApi(Resource):
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
         parser.add_argument('query', type=str, required=True, location='json')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('model_config', type=dict, required=True, location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
         args = parser.parse_args()
 
         streaming = args['response_mode'] != 'blocking'
+        args['auto_generate_name'] = False
 
         account = flask_login.current_user
 

api/controllers/console/app/conversation.py

@@ -2,8 +2,8 @@ from datetime import datetime
 
 import pytz
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, reqparse, fields, marshal_with
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with
 from flask_restful.inputs import int_range
 from sqlalchemy import or_, func
 from sqlalchemy.orm import joinedload
@@ -13,107 +13,14 @@ from controllers.console import api
 from controllers.console.app import _get_app
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from libs.helper import TimestampField, datetime_string, uuid_value
+from fields.conversation_fields import conversation_pagination_fields, conversation_detail_fields, \
+    conversation_message_detail_fields, conversation_with_summary_pagination_fields
+from libs.helper import datetime_string
 from extensions.ext_database import db
 from models.model import Message, MessageAnnotation, Conversation
 
-account_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'email': fields.String
-}
-
-feedback_fields = {
-    'rating': fields.String,
-    'content': fields.String,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account': fields.Nested(account_fields, allow_null=True),
-}
-
-annotation_fields = {
-    'content': fields.String,
-    'account': fields.Nested(account_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
-message_detail_fields = {
-    'id': fields.String,
-    'conversation_id': fields.String,
-    'inputs': fields.Raw,
-    'query': fields.String,
-    'message': fields.Raw,
-    'message_tokens': fields.Integer,
-    'answer': fields.String,
-    'answer_tokens': fields.Integer,
-    'provider_response_latency': fields.Float,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account_id': fields.String,
-    'feedbacks': fields.List(fields.Nested(feedback_fields)),
-    'annotation': fields.Nested(annotation_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
-feedback_stat_fields = {
-    'like': fields.Integer,
-    'dislike': fields.Integer
-}
-
-model_config_fields = {
-    'opening_statement': fields.String,
-    'suggested_questions': fields.Raw,
-    'model': fields.Raw,
-    'user_input_form': fields.Raw,
-    'pre_prompt': fields.String,
-    'agent_mode': fields.Raw,
-}
-
 
 class CompletionConversationApi(Resource):
-    class MessageTextField(fields.Raw):
-        def format(self, value):
-            return value[0]['text'] if value else ''
-
-    simple_configs_fields = {
-        'prompt_template': fields.String,
-    }
-
-    simple_model_config_fields = {
-        'model': fields.Raw(attribute='model_dict'),
-        'pre_prompt': fields.String,
-    }
-
-    simple_message_detail_fields = {
-        'inputs': fields.Raw,
-        'query': fields.String,
-        'message': MessageTextField,
-        'answer': fields.String,
-    }
-
-    conversation_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_end_user_session_id': fields.String(),
-        'from_account_id': fields.String,
-        'read_at': TimestampField,
-        'created_at': TimestampField,
-        'annotation': fields.Nested(annotation_fields, allow_null=True),
-        'model_config': fields.Nested(simple_model_config_fields),
-        'user_feedback_stats': fields.Nested(feedback_stat_fields),
-        'admin_feedback_stats': fields.Nested(feedback_stat_fields),
-        'message': fields.Nested(simple_message_detail_fields, attribute='first_message')
-    }
-
-    conversation_pagination_fields = {
-        'page': fields.Integer,
-        'limit': fields.Integer(attribute='per_page'),
-        'total': fields.Integer,
-        'has_more': fields.Boolean(attribute='has_next'),
-        'data': fields.List(fields.Nested(conversation_fields), attribute='items')
-    }
 
     @setup_required
     @login_required
@@ -191,27 +98,17 @@ class CompletionConversationApi(Resource):
 
 
 class CompletionConversationDetailApi(Resource):
-    conversation_detail_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_account_id': fields.String,
-        'created_at': TimestampField,
-        'model_config': fields.Nested(model_config_fields),
-        'message': fields.Nested(message_detail_fields, attribute='first_message'),
-    }
 
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(conversation_detail_fields)
+    @marshal_with(conversation_message_detail_fields)
     def get(self, app_id, conversation_id):
         app_id = str(app_id)
         conversation_id = str(conversation_id)
 
         return _get_conversation(app_id, conversation_id, 'completion')
-    
+
     @setup_required
     @login_required
     @account_initialization_required
@@ -234,44 +131,11 @@ class CompletionConversationDetailApi(Resource):
 
 
 class ChatConversationApi(Resource):
-    simple_configs_fields = {
-        'prompt_template': fields.String,
-    }
-
-    simple_model_config_fields = {
-        'model': fields.Raw(attribute='model_dict'),
-        'pre_prompt': fields.String,
-    }
-
-    conversation_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_end_user_session_id': fields.String,
-        'from_account_id': fields.String,
-        'summary': fields.String(attribute='summary_or_query'),
-        'read_at': TimestampField,
-        'created_at': TimestampField,
-        'annotated': fields.Boolean,
-        'model_config': fields.Nested(simple_model_config_fields),
-        'message_count': fields.Integer,
-        'user_feedback_stats': fields.Nested(feedback_stat_fields),
-        'admin_feedback_stats': fields.Nested(feedback_stat_fields)
-    }
-
-    conversation_pagination_fields = {
-        'page': fields.Integer,
-        'limit': fields.Integer(attribute='per_page'),
-        'total': fields.Integer,
-        'has_more': fields.Boolean(attribute='has_next'),
-        'data': fields.List(fields.Nested(conversation_fields), attribute='items')
-    }
 
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(conversation_pagination_fields)
+    @marshal_with(conversation_with_summary_pagination_fields)
     def get(self, app_id):
         app_id = str(app_id)
 
@@ -356,19 +220,6 @@ class ChatConversationApi(Resource):
 
 
 class ChatConversationDetailApi(Resource):
-    conversation_detail_fields = {
-        'id': fields.String,
-        'status': fields.String,
-        'from_source': fields.String,
-        'from_end_user_id': fields.String,
-        'from_account_id': fields.String,
-        'created_at': TimestampField,
-        'annotated': fields.Boolean,
-        'model_config': fields.Nested(model_config_fields),
-        'message_count': fields.Integer,
-        'user_feedback_stats': fields.Nested(feedback_stat_fields),
-        'admin_feedback_stats': fields.Nested(feedback_stat_fields)
-    }
 
     @setup_required
     @login_required
@@ -379,7 +230,7 @@ class ChatConversationDetailApi(Resource):
         conversation_id = str(conversation_id)
 
         return _get_conversation(app_id, conversation_id, 'chat')
-    
+
     @setup_required
     @login_required
     @account_initialization_required
@@ -402,8 +253,6 @@ class ChatConversationDetailApi(Resource):
         return {'result': 'success'}, 204
 
 
-
-
 api.add_resource(CompletionConversationApi, '/apps/<uuid:app_id>/completion-conversations')
 api.add_resource(CompletionConversationDetailApi, '/apps/<uuid:app_id>/completion-conversations/<uuid:conversation_id>')
 api.add_resource(ChatConversationApi, '/apps/<uuid:app_id>/chat-conversations')

api/controllers/console/app/generator.py

@@ -1,5 +1,5 @@
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
@@ -12,35 +12,6 @@ from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededE
     LLMAPIUnavailableError, LLMRateLimitError, LLMAuthorizationError, ModelCurrentlyNotSupportError
 
 
-class IntroductionGenerateApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument('prompt_template', type=str, required=True, location='json')
-        args = parser.parse_args()
-
-        account = current_user
-
-        try:
-            answer = LLMGenerator.generate_introduction(
-                account.current_tenant_id,
-                args['prompt_template']
-            )
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        except QuotaExceededError:
-            raise ProviderQuotaExceededError()
-        except ModelCurrentlyNotSupportError:
-            raise ProviderModelCurrentlyNotSupportError()
-        except (LLMBadRequestError, LLMAPIConnectionError, LLMAPIUnavailableError,
-                LLMRateLimitError, LLMAuthorizationError) as e:
-            raise CompletionRequestError(str(e))
-
-        return {'introduction': answer}
-
-
 class RuleGenerateApi(Resource):
     @setup_required
     @login_required
@@ -72,5 +43,4 @@ class RuleGenerateApi(Resource):
         return rules
 
 
-api.add_resource(IntroductionGenerateApi, '/introduction-generate')
 api.add_resource(RuleGenerateApi, '/rule-generate')

api/controllers/console/app/message.py

@@ -16,8 +16,9 @@ from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
     ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
-from core.login.login import login_required
-from libs.helper import uuid_value, TimestampField
+from libs.login import login_required
+from fields.conversation_fields import message_detail_fields
+from libs.helper import uuid_value
 from libs.infinite_scroll_pagination import InfiniteScrollPagination
 from extensions.ext_database import db
 from models.model import MessageAnnotation, Conversation, Message, MessageFeedback
@@ -27,44 +28,6 @@ from services.errors.conversation import ConversationNotExistsError
 from services.errors.message import MessageNotExistsError
 from services.message_service import MessageService
 
-account_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'email': fields.String
-}
-
-feedback_fields = {
-    'rating': fields.String,
-    'content': fields.String,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account': fields.Nested(account_fields, allow_null=True),
-}
-
-annotation_fields = {
-    'content': fields.String,
-    'account': fields.Nested(account_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
-message_detail_fields = {
-    'id': fields.String,
-    'conversation_id': fields.String,
-    'inputs': fields.Raw,
-    'query': fields.String,
-    'message': fields.Raw,
-    'message_tokens': fields.Integer,
-    'answer': fields.String,
-    'answer_tokens': fields.Integer,
-    'provider_response_latency': fields.Float,
-    'from_source': fields.String,
-    'from_end_user_id': fields.String,
-    'from_account_id': fields.String,
-    'feedbacks': fields.List(fields.Nested(feedback_fields)),
-    'annotation': fields.Nested(annotation_fields, allow_null=True),
-    'created_at': TimestampField
-}
-
 
 class ChatMessageListApi(Resource):
     message_infinite_scroll_pagination_fields = {
@@ -332,8 +295,8 @@ class MessageSuggestedQuestionApi(Resource):
         try:
             questions = MessageService.get_suggested_questions_after_answer(
                 app_model=app_model,
-                user=current_user,
                 message_id=message_id,
+                user=current_user,
                 check_enabled=False
             )
         except MessageNotExistsError:
@@ -366,7 +329,7 @@ class MessageApi(Resource):
         message_id = str(message_id)
 
         # get app info
-        app_model = _get_app(app_id, 'chat')
+        app_model = _get_app(app_id)
 
         message = db.session.query(Message).filter(
             Message.id == message_id,

api/controllers/console/app/model_config.py

@@ -1,5 +1,4 @@
 # -*- coding:utf-8 -*-
-import json
 
 from flask import request
 from flask_restful import Resource
@@ -9,7 +8,7 @@ from controllers.console import api
 from controllers.console.app import _get_app
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.login.login import login_required
+from libs.login import login_required
 from events.app_event import app_model_config_was_updated
 from extensions.ext_database import db
 from models.model import AppModelConfig
@@ -31,7 +30,8 @@ class ModelConfigResource(Resource):
         model_configuration = AppModelConfigService.validate_configuration(
             tenant_id=current_user.current_tenant_id,
             account=current_user,
-            config=request.json
+            config=request.json,
+            mode=app_model.mode
         )
 
         new_app_model_config = AppModelConfig(

api/controllers/console/app/site.py

@@ -1,33 +1,18 @@
 # -*- coding:utf-8 -*-
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, reqparse, fields, marshal_with
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with
 from werkzeug.exceptions import NotFound, Forbidden
 
 from controllers.console import api
 from controllers.console.app import _get_app
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
+from fields.app_fields import app_site_fields
 from libs.helper import supported_language
 from extensions.ext_database import db
 from models.model import Site
 
-app_site_fields = {
-    'app_id': fields.String,
-    'access_token': fields.String(attribute='code'),
-    'code': fields.String,
-    'title': fields.String,
-    'icon': fields.String,
-    'icon_background': fields.String,
-    'description': fields.String,
-    'default_language': fields.String,
-    'customize_domain': fields.String,
-    'copyright': fields.String,
-    'privacy_policy': fields.String,
-    'customize_token_strategy': fields.String,
-    'prompt_public': fields.Boolean
-}
-
 
 def parse_app_site_args():
     parser = reqparse.RequestParser()

api/controllers/console/app/statistic.py

@@ -5,7 +5,7 @@ from datetime import datetime
 import pytz
 from flask import jsonify
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, reqparse
 
 from controllers.console import api

api/controllers/console/auth/activate.py

@@ -16,26 +16,25 @@ from services.account_service import RegisterService
 class ActivateCheckApi(Resource):
     def get(self):
         parser = reqparse.RequestParser()
-        parser.add_argument('workspace_id', type=str, required=True, nullable=False, location='args')
-        parser.add_argument('email', type=email, required=True, nullable=False, location='args')
+        parser.add_argument('workspace_id', type=str, required=False, nullable=True, location='args')
+        parser.add_argument('email', type=email, required=False, nullable=True, location='args')
         parser.add_argument('token', type=str, required=True, nullable=False, location='args')
         args = parser.parse_args()
 
-        account = RegisterService.get_account_if_token_valid(args['workspace_id'], args['email'], args['token'])
+        workspaceId = args['workspace_id']
+        reg_email = args['email']
+        token = args['token']
 
-        tenant = db.session.query(Tenant).filter(
-            Tenant.id == args['workspace_id'],
-            Tenant.status == 'normal'
-        ).first()
+        invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
 
-        return {'is_valid': account is not None, 'workspace_name': tenant.name}
+        return {'is_valid': invitation is not None, 'workspace_name': invitation['tenant'].name if invitation else None}
 
 
 class ActivateApi(Resource):
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument('workspace_id', type=str, required=True, nullable=False, location='json')
-        parser.add_argument('email', type=email, required=True, nullable=False, location='json')
+        parser.add_argument('workspace_id', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('email', type=email, required=False, nullable=True, location='json')
         parser.add_argument('token', type=str, required=True, nullable=False, location='json')
         parser.add_argument('name', type=str_len(30), required=True, nullable=False, location='json')
         parser.add_argument('password', type=valid_password, required=True, nullable=False, location='json')
@@ -44,12 +43,13 @@ class ActivateApi(Resource):
         parser.add_argument('timezone', type=timezone, required=True, nullable=False, location='json')
         args = parser.parse_args()
 
-        account = RegisterService.get_account_if_token_valid(args['workspace_id'], args['email'], args['token'])
-        if account is None:
+        invitation = RegisterService.get_invitation_if_token_valid(args['workspace_id'], args['email'], args['token'])
+        if invitation is None:
             raise AlreadyActivateError()
 
         RegisterService.revoke_token(args['workspace_id'], args['email'], args['token'])
 
+        account = invitation['account']
         account.name = args['name']
 
         # generate password salt

api/controllers/console/auth/data_source_oauth.py

@@ -1,16 +1,13 @@
 import logging
-from datetime import datetime
-from typing import Optional
 
-import flask_login
 import requests
-from flask import request, redirect, current_app, session
+from flask import request, redirect, current_app
 from flask_login import current_user
 
 from flask_restful import Resource
 from werkzeug.exceptions import Forbidden
 
-from core.login.login import login_required
+from libs.login import login_required
 from libs.oauth_data_source import NotionOAuth
 from controllers.console import api
 from ..setup import setup_required
@@ -45,15 +42,34 @@ class OAuthDataSource(Resource):
         if current_app.config.get('NOTION_INTEGRATION_TYPE') == 'internal':
             internal_secret = current_app.config.get('NOTION_INTERNAL_SECRET')
             oauth_provider.save_internal_access_token(internal_secret)
-            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source=success')
+            return { 'data': '' }
         else:
             auth_url = oauth_provider.get_authorization_url()
-            return redirect(auth_url)
+            return { 'data': auth_url }, 200
 
 
 
 
 class OAuthDataSourceCallback(Resource):
+    def get(self, provider: str):
+        OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
+        with current_app.app_context():
+            oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
+        if not oauth_provider:
+            return {'error': 'Invalid provider'}, 400
+        if 'code' in request.args:
+            code = request.args.get('code')
+
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?type=notion&code={code}')
+        elif 'error' in request.args:
+            error = request.args.get('error')
+
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?type=notion&error={error}')
+        else:
+            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?type=notion&error=Access denied')
+        
+
+class OAuthDataSourceBinding(Resource):
     def get(self, provider: str):
         OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
@@ -69,12 +85,7 @@ class OAuthDataSourceCallback(Resource):
                     f"An error occurred during the OAuthCallback process with {provider}: {e.response.text}")
                 return {'error': 'OAuth data source process failed'}, 400
 
-            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source=success')
-        elif 'error' in request.args:
-            error = request.args.get('error')
-            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source={error}')
-        else:
-            return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_data_source=access_denied')
+            return {'result': 'success'}, 200
 
 
 class OAuthDataSourceSync(Resource):
@@ -101,4 +112,5 @@ class OAuthDataSourceSync(Resource):
 
 api.add_resource(OAuthDataSource, '/oauth/data-source/<string:provider>')
 api.add_resource(OAuthDataSourceCallback, '/oauth/data-source/callback/<string:provider>')
+api.add_resource(OAuthDataSourceBinding, '/oauth/data-source/binding/<string:provider>')
 api.add_resource(OAuthDataSourceSync, '/oauth/data-source/<string:provider>/<uuid:binding_id>/sync')

api/controllers/console/auth/login.py

@@ -6,7 +6,6 @@ from flask_restful import Resource, reqparse
 
 import services
 from controllers.console import api
-from controllers.console.error import AccountNotLinkTenantError
 from controllers.console.setup import setup_required
 from libs.helper import email
 from libs.password import valid_password
@@ -37,12 +36,12 @@ class LoginApi(Resource):
         except Exception:
             pass
 
-        flask_login.login_user(account, remember=args['remember_me'])
         AccountService.update_last_login(account, request)
 
         # todo: return the user info
+        token = AccountService.get_account_jwt_token(account)
 
-        return {'result': 'success'}
+        return {'result': 'success', 'data': token}
 
 
 class LogoutApi(Resource):

api/controllers/console/auth/oauth.py

@@ -2,9 +2,8 @@ import logging
 from datetime import datetime
 from typing import Optional
 
-import flask_login
 import requests
-from flask import request, redirect, current_app, session
+from flask import request, redirect, current_app
 from flask_restful import Resource
 
 from libs.oauth import OAuthUserInfo, GitHubOAuth, GoogleOAuth
@@ -75,12 +74,11 @@ class OAuthCallback(Resource):
             account.initialized_at = datetime.utcnow()
             db.session.commit()
 
-        # login user
-        session.clear()
-        flask_login.login_user(account, remember=True)
         AccountService.update_last_login(account, request)
 
-        return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?oauth_login=success')
+        token = AccountService.get_account_jwt_token(account)
+
+        return redirect(f'{current_app.config.get("CONSOLE_WEB_URL")}?console_token={token}')
 
 
 def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:

api/controllers/console/datasets/data_source.py

@@ -1,11 +1,10 @@
 import datetime
 import json
 
-from cachetools import TTLCache
-from flask import request, current_app
+from flask import request
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, marshal_with, fields, reqparse, marshal
+from libs.login import login_required
+from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
@@ -14,47 +13,14 @@ from controllers.console.wraps import account_initialization_required
 from core.data_loader.loader.notion import NotionLoader
 from core.indexing_runner import IndexingRunner
 from extensions.ext_database import db
-from libs.helper import TimestampField
+from fields.data_source_fields import integrate_notion_info_list_fields, integrate_list_fields
 from models.dataset import Document
 from models.source import DataSourceBinding
 from services.dataset_service import DatasetService, DocumentService
 from tasks.document_indexing_sync_task import document_indexing_sync_task
 
-cache = TTLCache(maxsize=None, ttl=30)
-
 
 class DataSourceApi(Resource):
-    integrate_icon_fields = {
-        'type': fields.String,
-        'url': fields.String,
-        'emoji': fields.String
-    }
-    integrate_page_fields = {
-        'page_name': fields.String,
-        'page_id': fields.String,
-        'page_icon': fields.Nested(integrate_icon_fields, allow_null=True),
-        'parent_id': fields.String,
-        'type': fields.String
-    }
-    integrate_workspace_fields = {
-        'workspace_name': fields.String,
-        'workspace_id': fields.String,
-        'workspace_icon': fields.String,
-        'pages': fields.List(fields.Nested(integrate_page_fields)),
-        'total': fields.Integer
-    }
-    integrate_fields = {
-        'id': fields.String,
-        'provider': fields.String,
-        'created_at': TimestampField,
-        'is_bound': fields.Boolean,
-        'disabled': fields.Boolean,
-        'link': fields.String,
-        'source_info': fields.Nested(integrate_workspace_fields)
-    }
-    integrate_list_fields = {
-        'data': fields.List(fields.Nested(integrate_fields)),
-    }
 
     @setup_required
     @login_required
@@ -131,28 +97,6 @@ class DataSourceApi(Resource):
 
 
 class DataSourceNotionListApi(Resource):
-    integrate_icon_fields = {
-        'type': fields.String,
-        'url': fields.String,
-        'emoji': fields.String
-    }
-    integrate_page_fields = {
-        'page_name': fields.String,
-        'page_id': fields.String,
-        'page_icon': fields.Nested(integrate_icon_fields, allow_null=True),
-        'is_bound': fields.Boolean,
-        'parent_id': fields.String,
-        'type': fields.String
-    }
-    integrate_workspace_fields = {
-        'workspace_name': fields.String,
-        'workspace_id': fields.String,
-        'workspace_icon': fields.String,
-        'pages': fields.List(fields.Nested(integrate_page_fields))
-    }
-    integrate_notion_info_list_fields = {
-        'notion_info': fields.List(fields.Nested(integrate_workspace_fields)),
-    }
 
     @setup_required
     @login_required

api/controllers/console/datasets/datasets.py

@@ -1,8 +1,11 @@
 # -*- coding:utf-8 -*-
-from flask import request
+import flask_restful
+from flask import request, current_app
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, reqparse, fields, marshal, marshal_with
+
+from controllers.console.apikey import api_key_list, api_key_fields
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal, marshal_with
 from werkzeug.exceptions import NotFound, Forbidden
 import services
 from controllers.console import api
@@ -12,45 +15,16 @@ from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.indexing_runner import IndexingRunner
 from core.model_providers.error import LLMBadRequestError, ProviderTokenNotInitError
-from core.model_providers.model_factory import ModelFactory
 from core.model_providers.models.entity.model_params import ModelType
-from libs.helper import TimestampField
+from fields.app_fields import related_app_list
+from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
+from fields.document_fields import document_status_fields
 from extensions.ext_database import db
 from models.dataset import DocumentSegment, Document
-from models.model import UploadFile
+from models.model import UploadFile, ApiToken
 from services.dataset_service import DatasetService, DocumentService
 from services.provider_service import ProviderService
 
-dataset_detail_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'description': fields.String,
-    'provider': fields.String,
-    'permission': fields.String,
-    'data_source_type': fields.String,
-    'indexing_technique': fields.String,
-    'app_count': fields.Integer,
-    'document_count': fields.Integer,
-    'word_count': fields.Integer,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'updated_by': fields.String,
-    'updated_at': TimestampField,
-    'embedding_model': fields.String,
-    'embedding_model_provider': fields.String,
-    'embedding_available': fields.Boolean
-}
-
-dataset_query_detail_fields = {
-    "id": fields.String,
-    "content": fields.String,
-    "source": fields.String,
-    "source_app_id": fields.String,
-    "created_by_role": fields.String,
-    "created_by": fields.String,
-    "created_at": TimestampField
-}
-
 
 def _validate_name(name):
     if not name or len(name) < 1 or len(name) > 40:
@@ -82,18 +56,25 @@ class DatasetListApi(Resource):
 
         # check embedding setting
         provider_service = ProviderService()
-        valid_model_list = provider_service.get_valid_model_list(current_user.current_tenant_id, ModelType.EMBEDDINGS.value)
+        valid_model_list = provider_service.get_valid_model_list(current_user.current_tenant_id,
+                                                                 ModelType.EMBEDDINGS.value)
         # if len(valid_model_list) == 0:
         #     raise ProviderNotInitializeError(
         #         f"No Embedding Model available. Please configure a valid provider "
         #         f"in the Settings -> Model Provider.")
-        model_names = [item['model_name'] for item in valid_model_list]
+        model_names = []
+        for valid_model in valid_model_list:
+            model_names.append(f"{valid_model['model_name']}:{valid_model['model_provider']['provider_name']}")
         data = marshal(datasets, dataset_detail_fields)
         for item in data:
-            if item['embedding_model'] in model_names:
-                item['embedding_available'] = True
+            if item['indexing_technique'] == 'high_quality':
+                item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
+                if item_model in model_names:
+                    item['embedding_available'] = True
+                else:
+                    item['embedding_available'] = False
             else:
-                item['embedding_available'] = False
+                item['embedding_available'] = True
         response = {
             'data': data,
             'has_more': len(datasets) == limit,
@@ -119,14 +100,6 @@ class DatasetListApi(Resource):
         # The role of the current user in the ta table must be admin or owner
         if current_user.current_tenant.current_role not in ['admin', 'owner']:
             raise Forbidden()
-        try:
-            ModelFactory.get_embedding_model(
-                tenant_id=current_user.current_tenant_id
-            )
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
-                f"in the Settings -> Model Provider.")
 
         try:
             dataset = DatasetService.create_empty_dataset(
@@ -150,20 +123,40 @@ class DatasetApi(Resource):
         dataset = DatasetService.get_dataset(dataset_id_str)
         if dataset is None:
             raise NotFound("Dataset not found.")
-
         try:
             DatasetService.check_dataset_permission(
                 dataset, current_user)
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
-
-        return marshal(dataset, dataset_detail_fields), 200
+        data = marshal(dataset, dataset_detail_fields)
+        # check embedding setting
+        provider_service = ProviderService()
+        # get valid model list
+        valid_model_list = provider_service.get_valid_model_list(current_user.current_tenant_id,
+                                                                 ModelType.EMBEDDINGS.value)
+        model_names = []
+        for valid_model in valid_model_list:
+            model_names.append(f"{valid_model['model_name']}:{valid_model['model_provider']['provider_name']}")
+        if data['indexing_technique'] == 'high_quality':
+            item_model = f"{data['embedding_model']}:{data['embedding_model_provider']}"
+            if item_model in model_names:
+                data['embedding_available'] = True
+            else:
+                data['embedding_available'] = False
+        else:
+            data['embedding_available'] = True
+        return data, 200
 
     @setup_required
     @login_required
     @account_initialization_required
     def patch(self, dataset_id):
         dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
 
         parser = reqparse.RequestParser()
         parser.add_argument('name', nullable=False,
@@ -177,6 +170,7 @@ class DatasetApi(Resource):
                             help='Invalid indexing technique.')
         parser.add_argument('permission', type=str, location='json', choices=(
             'only_me', 'all_team_members'), help='Invalid permission.')
+        parser.add_argument('retrieval_model', type=dict, location='json', help='Invalid retrieval model.')
         args = parser.parse_args()
 
         # The role of the current user in the ta table must be admin or owner
@@ -251,9 +245,11 @@ class DatasetIndexingEstimateApi(Resource):
         parser = reqparse.RequestParser()
         parser.add_argument('info_list', type=dict, required=True, nullable=True, location='json')
         parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
+        parser.add_argument('indexing_technique', type=str, required=True, nullable=True, location='json')
         parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
         parser.add_argument('dataset_id', type=str, required=False, nullable=False, location='json')
-        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
         args = parser.parse_args()
         # validate args
         DocumentService.estimate_args_validate(args)
@@ -272,7 +268,8 @@ class DatasetIndexingEstimateApi(Resource):
             try:
                 response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, file_details,
                                                                   args['process_rule'], args['doc_form'],
-                                                                  args['doc_language'], args['dataset_id'])
+                                                                  args['doc_language'], args['dataset_id'],
+                                                                  args['indexing_technique'])
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
                     f"No Embedding Model available. Please configure a valid provider "
@@ -287,7 +284,8 @@ class DatasetIndexingEstimateApi(Resource):
                 response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id,
                                                                     args['info_list']['notion_info_list'],
                                                                     args['process_rule'], args['doc_form'],
-                                                                    args['doc_language'], args['dataset_id'])
+                                                                    args['doc_language'], args['dataset_id'],
+                                                                    args['indexing_technique'])
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
                     f"No Embedding Model available. Please configure a valid provider "
@@ -300,18 +298,6 @@ class DatasetIndexingEstimateApi(Resource):
 
 
 class DatasetRelatedAppListApi(Resource):
-    app_detail_kernel_fields = {
-        'id': fields.String,
-        'name': fields.String,
-        'mode': fields.String,
-        'icon': fields.String,
-        'icon_background': fields.String,
-    }
-
-    related_app_list = {
-        'data': fields.List(fields.Nested(app_detail_kernel_fields)),
-        'total': fields.Integer,
-    }
 
     @setup_required
     @login_required
@@ -343,24 +329,6 @@ class DatasetRelatedAppListApi(Resource):
 
 
 class DatasetIndexingStatusApi(Resource):
-    document_status_fields = {
-        'id': fields.String,
-        'indexing_status': fields.String,
-        'processing_started_at': TimestampField,
-        'parsing_completed_at': TimestampField,
-        'cleaning_completed_at': TimestampField,
-        'splitting_completed_at': TimestampField,
-        'completed_at': TimestampField,
-        'paused_at': TimestampField,
-        'error': fields.String,
-        'stopped_at': TimestampField,
-        'completed_segments': fields.Integer,
-        'total_segments': fields.Integer,
-    }
-
-    document_status_fields_list = {
-        'data': fields.List(fields.Nested(document_status_fields))
-    }
 
     @setup_required
     @login_required
@@ -380,16 +348,148 @@ class DatasetIndexingStatusApi(Resource):
                                                           DocumentSegment.status != 're_segment').count()
             document.completed_segments = completed_segments
             document.total_segments = total_segments
-            documents_status.append(marshal(document, self.document_status_fields))
+            documents_status.append(marshal(document, document_status_fields))
         data = {
             'data': documents_status
         }
         return data
 
 
+class DatasetApiKeyApi(Resource):
+    max_keys = 10
+    token_prefix = 'dataset-'
+    resource_type = 'dataset'
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_key_list)
+    def get(self):
+        keys = db.session.query(ApiToken). \
+            filter(ApiToken.type == self.resource_type, ApiToken.tenant_id == current_user.current_tenant_id). \
+            all()
+        return {"items": keys}
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_key_fields)
+    def post(self):
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        current_key_count = db.session.query(ApiToken). \
+            filter(ApiToken.type == self.resource_type, ApiToken.tenant_id == current_user.current_tenant_id). \
+            count()
+
+        if current_key_count >= self.max_keys:
+            flask_restful.abort(
+                400,
+                message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
+                code='max_keys_exceeded'
+            )
+
+        key = ApiToken.generate_api_key(self.token_prefix, 24)
+        api_token = ApiToken()
+        api_token.tenant_id = current_user.current_tenant_id
+        api_token.token = key
+        api_token.type = self.resource_type
+        db.session.add(api_token)
+        db.session.commit()
+        return api_token, 200
+
+
+class DatasetApiDeleteApi(Resource):
+    resource_type = 'dataset'
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, api_key_id):
+        api_key_id = str(api_key_id)
+
+        # The role of the current user in the ta table must be admin or owner
+        if current_user.current_tenant.current_role not in ['admin', 'owner']:
+            raise Forbidden()
+
+        key = db.session.query(ApiToken). \
+            filter(ApiToken.tenant_id == current_user.current_tenant_id, ApiToken.type == self.resource_type,
+                   ApiToken.id == api_key_id). \
+            first()
+
+        if key is None:
+            flask_restful.abort(404, message='API key not found')
+
+        db.session.query(ApiToken).filter(ApiToken.id == api_key_id).delete()
+        db.session.commit()
+
+        return {'result': 'success'}, 204
+
+
+class DatasetApiBaseUrlApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        return {
+            'api_base_url': (current_app.config['SERVICE_API_URL'] if current_app.config['SERVICE_API_URL']
+                             else request.host_url.rstrip('/')) + '/v1'
+        }
+
+
+class DatasetRetrievalSettingApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        vector_type = current_app.config['VECTOR_STORE']
+        if vector_type == 'milvus':
+            return {
+                'retrieval_method': [
+                    'semantic_search'
+                ]
+            }
+        elif vector_type == 'qdrant' or vector_type == 'weaviate':
+            return {
+                'retrieval_method': [
+                    'semantic_search', 'full_text_search', 'hybrid_search'
+                ]
+            }
+        else:
+            raise ValueError("Unsupported vector db type.")
+
+
+class DatasetRetrievalSettingMockApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, vector_type):
+
+        if vector_type == 'milvus':
+            return {
+                'retrieval_method': [
+                    'semantic_search'
+                ]
+            }
+        elif vector_type == 'qdrant' or vector_type == 'weaviate':
+            return {
+                'retrieval_method': [
+                    'semantic_search', 'full_text_search', 'hybrid_search'
+                ]
+            }
+        else:
+            raise ValueError("Unsupported vector db type.")
+
+
 api.add_resource(DatasetListApi, '/datasets')
 api.add_resource(DatasetApi, '/datasets/<uuid:dataset_id>')
 api.add_resource(DatasetQueryApi, '/datasets/<uuid:dataset_id>/queries')
 api.add_resource(DatasetIndexingEstimateApi, '/datasets/indexing-estimate')
 api.add_resource(DatasetRelatedAppListApi, '/datasets/<uuid:dataset_id>/related-apps')
 api.add_resource(DatasetIndexingStatusApi, '/datasets/<uuid:dataset_id>/indexing-status')
+api.add_resource(DatasetApiKeyApi, '/datasets/api-keys')
+api.add_resource(DatasetApiDeleteApi, '/datasets/api-keys/<uuid:api_key_id>')
+api.add_resource(DatasetApiBaseUrlApi, '/datasets/api-base-info')
+api.add_resource(DatasetRetrievalSettingApi, '/datasets/retrieval-setting')
+api.add_resource(DatasetRetrievalSettingMockApi, '/datasets/retrieval-setting/<string:vector_type>')

api/controllers/console/datasets/datasets_document.py

@@ -1,11 +1,10 @@
 # -*- coding:utf-8 -*-
-import random
 from datetime import datetime
 from typing import List
 
-from flask import request
+from flask import request, current_app
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, fields, marshal, marshal_with, reqparse
 from sqlalchemy import desc, asc
 from werkzeug.exceptions import NotFound, Forbidden
@@ -23,7 +22,8 @@ from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededE
     LLMBadRequestError
 from core.model_providers.model_factory import ModelFactory
 from extensions.ext_redis import redis_client
-from libs.helper import TimestampField
+from fields.document_fields import document_with_segments_fields, document_fields, \
+    dataset_and_document_fields, document_status_fields
 from extensions.ext_database import db
 from models.dataset import DatasetProcessRule, Dataset
 from models.dataset import Document, DocumentSegment
@@ -32,64 +32,6 @@ from services.dataset_service import DocumentService, DatasetService
 from tasks.add_document_to_index_task import add_document_to_index_task
 from tasks.remove_document_from_index_task import remove_document_from_index_task
 
-dataset_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'description': fields.String,
-    'permission': fields.String,
-    'data_source_type': fields.String,
-    'indexing_technique': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-}
-
-document_fields = {
-    'id': fields.String,
-    'position': fields.Integer,
-    'data_source_type': fields.String,
-    'data_source_info': fields.Raw(attribute='data_source_info_dict'),
-    'dataset_process_rule_id': fields.String,
-    'name': fields.String,
-    'created_from': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'tokens': fields.Integer,
-    'indexing_status': fields.String,
-    'error': fields.String,
-    'enabled': fields.Boolean,
-    'disabled_at': TimestampField,
-    'disabled_by': fields.String,
-    'archived': fields.Boolean,
-    'display_status': fields.String,
-    'word_count': fields.Integer,
-    'hit_count': fields.Integer,
-    'doc_form': fields.String,
-}
-
-document_with_segments_fields = {
-    'id': fields.String,
-    'position': fields.Integer,
-    'data_source_type': fields.String,
-    'data_source_info': fields.Raw(attribute='data_source_info_dict'),
-    'dataset_process_rule_id': fields.String,
-    'name': fields.String,
-    'created_from': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'tokens': fields.Integer,
-    'indexing_status': fields.String,
-    'error': fields.String,
-    'enabled': fields.Boolean,
-    'disabled_at': TimestampField,
-    'disabled_by': fields.String,
-    'archived': fields.Boolean,
-    'display_status': fields.String,
-    'word_count': fields.Integer,
-    'hit_count': fields.Integer,
-    'completed_segments': fields.Integer,
-    'total_segments': fields.Integer
-}
-
 
 class DocumentResource(Resource):
     def get_document(self, dataset_id: str, document_id: str) -> Document:
@@ -138,6 +80,10 @@ class GetProcessRuleApi(Resource):
         req_data = request.args
 
         document_id = req_data.get('document_id')
+        
+        # get default rules
+        mode = DocumentService.DEFAULT_RULES['mode']
+        rules = DocumentService.DEFAULT_RULES['rules']
         if document_id:
             # get the latest process rule
             document = Document.query.get_or_404(document_id)
@@ -158,11 +104,9 @@ class GetProcessRuleApi(Resource):
                 order_by(DatasetProcessRule.created_at.desc()). \
                 limit(1). \
                 one_or_none()
-            mode = dataset_process_rule.mode
-            rules = dataset_process_rule.rules_dict
-        else:
-            mode = DocumentService.DEFAULT_RULES['mode']
-            rules = DocumentService.DEFAULT_RULES['rules']
+            if dataset_process_rule:
+                mode = dataset_process_rule.mode
+                rules = dataset_process_rule.rules_dict
 
         return {
             'mode': mode,
@@ -275,7 +219,10 @@ class DatasetDocumentListApi(Resource):
         parser.add_argument('duplicate', type=bool, nullable=False, location='json')
         parser.add_argument('original_document_id', type=str, required=False, location='json')
         parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
-        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False, location='json')
+        parser.add_argument('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')
         args = parser.parse_args()
 
         if not dataset.indexing_technique and not args['indexing_technique']:
@@ -284,20 +231,6 @@ class DatasetDocumentListApi(Resource):
         # validate args
         DocumentService.document_create_args_validate(args)
 
-        # check embedding model setting
-        try:
-            ModelFactory.get_embedding_model(
-                tenant_id=current_user.current_tenant_id,
-                model_provider_name=dataset.embedding_model_provider,
-                model_name=dataset.embedding_model
-            )
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
-                f"in the Settings -> Model Provider.")
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-
         try:
             documents, batch = DocumentService.save_document_with_dataset_id(dataset, args, current_user)
         except ProviderTokenNotInitError as ex:
@@ -314,11 +247,6 @@ class DatasetDocumentListApi(Resource):
 
 
 class DatasetInitApi(Resource):
-    dataset_and_document_fields = {
-        'dataset': fields.Nested(dataset_fields),
-        'documents': fields.List(fields.Nested(document_fields)),
-        'batch': fields.String
-    }
 
     @setup_required
     @login_required
@@ -335,17 +263,22 @@ class DatasetInitApi(Resource):
         parser.add_argument('data_source', type=dict, required=True, nullable=True, location='json')
         parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
         parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
-        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False, location='json')
+        parser.add_argument('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')
         args = parser.parse_args()
-
-        try:
-            ModelFactory.get_embedding_model(
-                tenant_id=current_user.current_tenant_id
-            )
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
-                f"in the Settings -> Model Provider.")
+        if args['indexing_technique'] == 'high_quality':
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
 
         # validate args
         DocumentService.document_create_args_validate(args)
@@ -414,7 +347,8 @@ class DocumentIndexingEstimateApi(DocumentResource):
 
                 try:
                     response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, [file],
-                                                                      data_process_rule_dict, None, dataset_id)
+                                                                      data_process_rule_dict, None,
+                                                                      'English', dataset_id)
                 except LLMBadRequestError:
                     raise ProviderNotInitializeError(
                         f"No Embedding Model available. Please configure a valid provider "
@@ -483,7 +417,8 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
             indexing_runner = IndexingRunner()
             try:
                 response = indexing_runner.file_indexing_estimate(current_user.current_tenant_id, file_details,
-                                                                  data_process_rule_dict,  None, dataset_id)
+                                                                  data_process_rule_dict, None,
+                                                                  'English', dataset_id)
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
                     f"No Embedding Model available. Please configure a valid provider "
@@ -497,7 +432,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                 response = indexing_runner.notion_indexing_estimate(current_user.current_tenant_id,
                                                                     info_list,
                                                                     data_process_rule_dict,
-                                                                    None, dataset_id)
+                                                                    None, 'English', dataset_id)
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
                     f"No Embedding Model available. Please configure a valid provider "
@@ -510,24 +445,6 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
 
 
 class DocumentBatchIndexingStatusApi(DocumentResource):
-    document_status_fields = {
-        'id': fields.String,
-        'indexing_status': fields.String,
-        'processing_started_at': TimestampField,
-        'parsing_completed_at': TimestampField,
-        'cleaning_completed_at': TimestampField,
-        'splitting_completed_at': TimestampField,
-        'completed_at': TimestampField,
-        'paused_at': TimestampField,
-        'error': fields.String,
-        'stopped_at': TimestampField,
-        'completed_segments': fields.Integer,
-        'total_segments': fields.Integer,
-    }
-
-    document_status_fields_list = {
-        'data': fields.List(fields.Nested(document_status_fields))
-    }
 
     @setup_required
     @login_required
@@ -547,7 +464,7 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
             document.total_segments = total_segments
             if document.is_paused:
                 document.indexing_status = 'paused'
-            documents_status.append(marshal(document, self.document_status_fields))
+            documents_status.append(marshal(document, document_status_fields))
         data = {
             'data': documents_status
         }
@@ -555,20 +472,6 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
 
 
 class DocumentIndexingStatusApi(DocumentResource):
-    document_status_fields = {
-        'id': fields.String,
-        'indexing_status': fields.String,
-        'processing_started_at': TimestampField,
-        'parsing_completed_at': TimestampField,
-        'cleaning_completed_at': TimestampField,
-        'splitting_completed_at': TimestampField,
-        'completed_at': TimestampField,
-        'paused_at': TimestampField,
-        'error': fields.String,
-        'stopped_at': TimestampField,
-        'completed_segments': fields.Integer,
-        'total_segments': fields.Integer,
-    }
 
     @setup_required
     @login_required
@@ -592,7 +495,7 @@ class DocumentIndexingStatusApi(DocumentResource):
         document.total_segments = total_segments
         if document.is_paused:
             document.indexing_status = 'paused'
-        return marshal(document, self.document_status_fields)
+        return marshal(document, document_status_fields)
 
 
 class DocumentDetailApi(DocumentResource):
@@ -725,6 +628,12 @@ class DocumentDeleteApi(DocumentResource):
     def delete(self, dataset_id, document_id):
         dataset_id = str(dataset_id)
         document_id = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+
         document = self.get_document(dataset_id, document_id)
 
         try:
@@ -787,6 +696,12 @@ class DocumentStatusApi(DocumentResource):
     def patch(self, dataset_id, document_id, action):
         dataset_id = str(dataset_id)
         document_id = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+
         document = self.get_document(dataset_id, document_id)
 
         # The role of the current user in the ta table must be admin or owner
@@ -855,6 +770,14 @@ class DocumentStatusApi(DocumentResource):
             if not document.archived:
                 raise InvalidActionError('Document is not archived.')
 
+            # check document limit
+            if current_app.config['EDITION'] == 'CLOUD':
+                documents_count = DocumentService.get_tenant_documents_count()
+                total_count = documents_count + 1
+                tenant_document_count = int(current_app.config['TENANT_DOCUMENT_COUNT'])
+                if total_count > tenant_document_count:
+                    raise ValueError(f"All your documents have overed limit {tenant_document_count}.")
+
             document.archived = False
             document.archived_at = None
             document.archived_by = None
@@ -872,6 +795,10 @@ class DocumentStatusApi(DocumentResource):
 
 
 class DocumentPauseApi(DocumentResource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
     def patch(self, dataset_id, document_id):
         """pause document."""
         dataset_id = str(dataset_id)
@@ -901,6 +828,9 @@ class DocumentPauseApi(DocumentResource):
 
 
 class DocumentRecoverApi(DocumentResource):
+    @setup_required
+    @login_required
+    @account_initialization_required
     def patch(self, dataset_id, document_id):
         """recover document."""
         dataset_id = str(dataset_id)
@@ -926,6 +856,21 @@ class DocumentRecoverApi(DocumentResource):
         return {'result': 'success'}, 204
 
 
+class DocumentLimitApi(DocumentResource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        """get document limit"""
+        documents_count = DocumentService.get_tenant_documents_count()
+        tenant_document_count = int(current_app.config['TENANT_DOCUMENT_COUNT'])
+
+        return {
+            'documents_count': documents_count,
+            'documents_limit': tenant_document_count
+                }, 200
+
+
 api.add_resource(GetProcessRuleApi, '/datasets/process-rule')
 api.add_resource(DatasetDocumentListApi,
                  '/datasets/<uuid:dataset_id>/documents')
@@ -951,3 +896,4 @@ api.add_resource(DocumentStatusApi,
                  '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/status/<string:action>')
 api.add_resource(DocumentPauseApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/pause')
 api.add_resource(DocumentRecoverApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/resume')
+api.add_resource(DocumentLimitApi, '/datasets/limit')

api/controllers/console/datasets/datasets_segments.py

@@ -3,7 +3,7 @@ import uuid
 from datetime import datetime
 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, reqparse, fields, marshal
+from flask_restful import Resource, reqparse, marshal
 from werkzeug.exceptions import NotFound, Forbidden
 
 import services
@@ -14,48 +14,18 @@ from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.model_providers.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_providers.model_factory import ModelFactory
-from core.login.login import login_required
+from libs.login import login_required
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
+from fields.segment_fields import segment_fields
 from models.dataset import DocumentSegment
 
-from libs.helper import TimestampField
 from services.dataset_service import DatasetService, DocumentService, SegmentService
 from tasks.enable_segment_to_index_task import enable_segment_to_index_task
 from tasks.disable_segment_from_index_task import disable_segment_from_index_task
 from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
 import pandas as pd
 
-segment_fields = {
-    'id': fields.String,
-    'position': fields.Integer,
-    'document_id': fields.String,
-    'content': fields.String,
-    'answer': fields.String,
-    'word_count': fields.Integer,
-    'tokens': fields.Integer,
-    'keywords': fields.List(fields.String),
-    'index_node_id': fields.String,
-    'index_node_hash': fields.String,
-    'hit_count': fields.Integer,
-    'enabled': fields.Boolean,
-    'disabled_at': TimestampField,
-    'disabled_by': fields.String,
-    'status': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'indexing_at': TimestampField,
-    'completed_at': TimestampField,
-    'error': fields.String,
-    'stopped_at': TimestampField
-}
-
-segment_list_response = {
-    'data': fields.List(fields.Nested(segment_fields)),
-    'has_more': fields.Boolean,
-    'limit': fields.Integer
-}
-
 
 class DatasetDocumentSegmentListApi(Resource):
     @setup_required
@@ -149,7 +119,8 @@ class DatasetDocumentSegmentApi(Resource):
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
             raise NotFound('Dataset not found.')
-
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
         # The role of the current user in the ta table must be admin or owner
         if current_user.current_tenant.current_role not in ['admin', 'owner']:
             raise Forbidden()
@@ -158,20 +129,20 @@ class DatasetDocumentSegmentApi(Resource):
             DatasetService.check_dataset_permission(dataset, current_user)
         except services.errors.account.NoPermissionError as e:
             raise Forbidden(str(e))
-
-        # check embedding model setting
-        try:
-            ModelFactory.get_embedding_model(
-                tenant_id=current_user.current_tenant_id,
-                model_provider_name=dataset.embedding_model_provider,
-                model_name=dataset.embedding_model
-            )
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
-                f"in the Settings -> Model Provider.")
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
+        if dataset.indexing_technique == 'high_quality':
+            # check embedding model setting
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
 
         segment = DocumentSegment.query.filter(
             DocumentSegment.id == str(segment_id),
@@ -244,18 +215,19 @@ class DatasetDocumentSegmentAddApi(Resource):
         if current_user.current_tenant.current_role not in ['admin', 'owner']:
             raise Forbidden()
         # check embedding model setting
-        try:
-            ModelFactory.get_embedding_model(
-                tenant_id=current_user.current_tenant_id,
-                model_provider_name=dataset.embedding_model_provider,
-                model_name=dataset.embedding_model
-            )
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
-                f"in the Settings -> Model Provider.")
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
+        if dataset.indexing_technique == 'high_quality':
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
         try:
             DatasetService.check_dataset_permission(dataset, current_user)
         except services.errors.account.NoPermissionError as e:
@@ -284,25 +256,28 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
             raise NotFound('Dataset not found.')
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
         # check document
         document_id = str(document_id)
         document = DocumentService.get_document(dataset_id, document_id)
         if not document:
             raise NotFound('Document not found.')
-        # check embedding model setting
-        try:
-            ModelFactory.get_embedding_model(
-                tenant_id=current_user.current_tenant_id,
-                model_provider_name=dataset.embedding_model_provider,
-                model_name=dataset.embedding_model
-            )
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
-                f"in the Settings -> Model Provider.")
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
-        # check segment
+        if dataset.indexing_technique == 'high_quality':
+            # check embedding model setting
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+            # check segment
         segment_id = str(segment_id)
         segment = DocumentSegment.query.filter(
             DocumentSegment.id == str(segment_id),
@@ -339,6 +314,8 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
             raise NotFound('Dataset not found.')
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
         # check document
         document_id = str(document_id)
         document = DocumentService.get_document(dataset_id, document_id)
@@ -378,18 +355,6 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
         document = DocumentService.get_document(dataset_id, document_id)
         if not document:
             raise NotFound('Document not found.')
-        try:
-            ModelFactory.get_embedding_model(
-                tenant_id=current_user.current_tenant_id,
-                model_provider_name=dataset.embedding_model_provider,
-                model_name=dataset.embedding_model
-            )
-        except LLMBadRequestError:
-            raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
-                f"in the Settings -> Model Provider.")
-        except ProviderTokenNotInitError as ex:
-            raise ProviderNotInitializeError(ex.description)
         # get file from request
         file = request.files['file']
         # check file

api/controllers/console/datasets/file.py

@@ -1,40 +1,24 @@
-import datetime
-import hashlib
-import tempfile
-import chardet
-import time
-import uuid
-from pathlib import Path
-
-from cachetools import TTLCache
 from flask import request, current_app
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, marshal_with, fields
-from werkzeug.exceptions import NotFound
+
+import services
+from libs.login import login_required
+from flask_restful import Resource, marshal_with
 
 from controllers.console import api
 from controllers.console.datasets.error import NoFileUploadedError, TooManyFilesError, FileTooLargeError, \
     UnsupportedFileTypeError
+
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
-from core.data_loader.file_extractor import FileExtractor
-from extensions.ext_storage import storage
-from libs.helper import TimestampField
-from extensions.ext_database import db
-from models.model import UploadFile
+from fields.file_fields import upload_config_fields, file_fields
 
-cache = TTLCache(maxsize=None, ttl=30)
+from services.file_service import FileService
 
-ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx']
 PREVIEW_WORDS_LIMIT = 3000
 
 
 class FileApi(Resource):
-    upload_config_fields = {
-        'file_size_limit': fields.Integer,
-        'batch_count_limit': fields.Integer
-    }
 
     @setup_required
     @login_required
@@ -43,21 +27,13 @@ class FileApi(Resource):
     def get(self):
         file_size_limit = current_app.config.get("UPLOAD_FILE_SIZE_LIMIT")
         batch_count_limit = current_app.config.get("UPLOAD_FILE_BATCH_LIMIT")
+        image_file_size_limit = current_app.config.get("UPLOAD_IMAGE_FILE_SIZE_LIMIT")
         return {
             'file_size_limit': file_size_limit,
-            'batch_count_limit': batch_count_limit
+            'batch_count_limit': batch_count_limit,
+            'image_file_size_limit': image_file_size_limit
         }, 200
 
-    file_fields = {
-        'id': fields.String,
-        'name': fields.String,
-        'size': fields.Integer,
-        'extension': fields.String,
-        'mime_type': fields.String,
-        'created_by': fields.String,
-        'created_at': TimestampField,
-    }
-
     @setup_required
     @login_required
     @account_initialization_required
@@ -73,45 +49,13 @@ class FileApi(Resource):
 
         if len(request.files) > 1:
             raise TooManyFilesError()
-
-        file_content = file.read()
-        file_size = len(file_content)
-
-        file_size_limit = current_app.config.get("UPLOAD_FILE_SIZE_LIMIT") * 1024 * 1024
-        if file_size > file_size_limit:
-            message = "({file_size} > {file_size_limit})"
-            raise FileTooLargeError(message)
-
-        extension = file.filename.split('.')[-1]
-        if extension not in ALLOWED_EXTENSIONS:
+        try:
+            upload_file = FileService.upload_file(file, current_user)
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
             raise UnsupportedFileTypeError()
 
-        # user uuid as file name
-        file_uuid = str(uuid.uuid4())
-        file_key = 'upload_files/' + current_user.current_tenant_id + '/' + file_uuid + '.' + extension
-
-        # save file to storage
-        storage.save(file_key, file_content)
-
-        # save file to db
-        config = current_app.config
-        upload_file = UploadFile(
-            tenant_id=current_user.current_tenant_id,
-            storage_type=config['STORAGE_TYPE'],
-            key=file_key,
-            name=file.filename,
-            size=file_size,
-            extension=extension,
-            mime_type=file.mimetype,
-            created_by=current_user.id,
-            created_at=datetime.datetime.utcnow(),
-            used=False,
-            hash=hashlib.sha3_256(file_content).hexdigest()
-        )
-
-        db.session.add(upload_file)
-        db.session.commit()
-
         return upload_file, 201
 
 
@@ -121,26 +65,7 @@ class FilePreviewApi(Resource):
     @account_initialization_required
     def get(self, file_id):
         file_id = str(file_id)
-
-        key = file_id + request.path
-        cached_response = cache.get(key)
-        if cached_response and time.time() - cached_response['timestamp'] < cache.ttl:
-            return cached_response['response']
-
-        upload_file = db.session.query(UploadFile) \
-            .filter(UploadFile.id == file_id) \
-            .first()
-
-        if not upload_file:
-            raise NotFound("File not found")
-
-        # extract text from file
-        extension = upload_file.extension
-        if extension not in ALLOWED_EXTENSIONS:
-            raise UnsupportedFileTypeError()
-
-        text = FileExtractor.load(upload_file, return_text=True)
-        text = text[0:PREVIEW_WORDS_LIMIT] if text else ''
+        text = FileService.get_file_preview(file_id)
         return {'content': text}
 
 

api/controllers/console/datasets/hit_testing.py

@@ -1,8 +1,8 @@
 import logging
 
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, reqparse, marshal, fields
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal
 from werkzeug.exceptions import InternalServerError, NotFound, Forbidden
 
 import services
@@ -14,48 +14,10 @@ from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
 from core.model_providers.error import ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError, \
     LLMBadRequestError
-from libs.helper import TimestampField
+from fields.hit_testing_fields import hit_testing_record_fields
 from services.dataset_service import DatasetService
 from services.hit_testing_service import HitTestingService
 
-document_fields = {
-    'id': fields.String,
-    'data_source_type': fields.String,
-    'name': fields.String,
-    'doc_type': fields.String,
-}
-
-segment_fields = {
-    'id': fields.String,
-    'position': fields.Integer,
-    'document_id': fields.String,
-    'content': fields.String,
-    'answer': fields.String,
-    'word_count': fields.Integer,
-    'tokens': fields.Integer,
-    'keywords': fields.List(fields.String),
-    'index_node_id': fields.String,
-    'index_node_hash': fields.String,
-    'hit_count': fields.Integer,
-    'enabled': fields.Boolean,
-    'disabled_at': TimestampField,
-    'disabled_by': fields.String,
-    'status': fields.String,
-    'created_by': fields.String,
-    'created_at': TimestampField,
-    'indexing_at': TimestampField,
-    'completed_at': TimestampField,
-    'error': fields.String,
-    'stopped_at': TimestampField,
-    'document': fields.Nested(document_fields),
-}
-
-hit_testing_record_fields = {
-    'segment': fields.Nested(segment_fields),
-    'score': fields.Float,
-    'tsne_position': fields.Raw
-}
-
 
 class HitTestingApi(Resource):
 
@@ -80,19 +42,18 @@ class HitTestingApi(Resource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('query', type=str, location='json')
+        parser.add_argument('retrieval_model', type=dict, required=False, location='json')
         args = parser.parse_args()
 
-        query = args['query']
-
-        if not query or len(query) > 250:
-            raise ValueError('Query is required and cannot exceed 250 characters')
+        HitTestingService.hit_testing_args_check(args)
 
         try:
             response = HitTestingService.retrieve(
                 dataset=dataset,
-                query=query,
+                query=args['query'],
                 account=current_user,
-                limit=10,
+                retrieval_model=args['retrieval_model'],
+                limit=10
             )
 
             return {"query": response['query'], 'records': marshal(response['records'], hit_testing_record_fields)}
@@ -106,7 +67,7 @@ class HitTestingApi(Resource):
             raise ProviderModelCurrentlyNotSupportError()
         except LLMBadRequestError:
             raise ProviderNotInitializeError(
-                f"No Embedding Model available. Please configure a valid provider "
+                f"No Embedding Model or Reranking Model available. Please configure a valid provider "
                 f"in the Settings -> Model Provider.")
         except ValueError as e:
             raise ValueError(str(e))

api/controllers/console/explore/completion.py

@@ -1,6 +1,7 @@
 # -*- coding:utf-8 -*-
 import json
 import logging
+from datetime import datetime
 from typing import Generator, Union
 
 from flask import Response, stream_with_context
@@ -17,6 +18,7 @@ from controllers.console.explore.wraps import InstalledAppResource
 from core.conversation_message_task import PubHandler
 from core.model_providers.error import LLMBadRequestError, LLMAPIUnavailableError, LLMAuthorizationError, LLMAPIConnectionError, \
     LLMRateLimitError, ProviderTokenNotInitError, QuotaExceededError, ModelCurrentlyNotSupportError
+from extensions.ext_database import db
 from libs.helper import uuid_value
 from services.completion_service import CompletionService
 
@@ -31,11 +33,17 @@ class CompletionApi(InstalledAppResource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
-        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('query', type=str, location='json', default='')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='explore_app', location='json')
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
+        args['auto_generate_name'] = False
+
+        installed_app.last_used_at = datetime.utcnow()
+        db.session.commit()
 
         try:
             response = CompletionService.completion(
@@ -90,11 +98,17 @@ class ChatApi(InstalledAppResource):
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
         parser.add_argument('query', type=str, required=True, location='json')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='explore_app', location='json')
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
+        args['auto_generate_name'] = False
+
+        installed_app.last_used_at = datetime.utcnow()
+        db.session.commit()
 
         try:
             response = CompletionService.completion(

api/controllers/console/explore/conversation.py

@@ -7,26 +7,12 @@ from werkzeug.exceptions import NotFound
 from controllers.console import api
 from controllers.console.explore.error import NotChatAppError
 from controllers.console.explore.wraps import InstalledAppResource
+from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import TimestampField, uuid_value
 from services.conversation_service import ConversationService
 from services.errors.conversation import LastConversationNotExistsError, ConversationNotExistsError
 from services.web_conversation_service import WebConversationService
 
-conversation_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'inputs': fields.Raw,
-    'status': fields.String,
-    'introduction': fields.String,
-    'created_at': TimestampField
-}
-
-conversation_infinite_scroll_pagination_fields = {
-    'limit': fields.Integer,
-    'has_more': fields.Boolean,
-    'data': fields.List(fields.Nested(conversation_fields))
-}
-
 
 class ConversationListApi(InstalledAppResource):
 
@@ -52,7 +38,8 @@ class ConversationListApi(InstalledAppResource):
                 user=current_user,
                 last_id=args['last_id'],
                 limit=args['limit'],
-                pinned=pinned
+                pinned=pinned,
+                exclude_debug_conversation=True
             )
         except LastConversationNotExistsError:
             raise NotFound("Last Conversation Not Exists.")
@@ -76,7 +63,7 @@ class ConversationApi(InstalledAppResource):
 
 class ConversationRenameApi(InstalledAppResource):
 
-    @marshal_with(conversation_fields)
+    @marshal_with(simple_conversation_fields)
     def post(self, installed_app, c_id):
         app_model = installed_app.app
         if app_model.mode != 'chat':
@@ -85,11 +72,18 @@ class ConversationRenameApi(InstalledAppResource):
         conversation_id = str(c_id)
 
         parser = reqparse.RequestParser()
-        parser.add_argument('name', type=str, required=True, location='json')
+        parser.add_argument('name', type=str, required=False, location='json')
+        parser.add_argument('auto_generate', type=bool, required=False, default='False', location='json')
         args = parser.parse_args()
 
         try:
-            return ConversationService.rename(app_model, conversation_id, current_user, args['name'])
+            return ConversationService.rename(
+                app_model,
+                conversation_id,
+                current_user,
+                args['name'],
+                args['auto_generate']
+            )
         except ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")
 

api/controllers/console/explore/installed_app.py

@@ -2,8 +2,8 @@
 from datetime import datetime
 
 from flask_login import current_user
-from core.login.login import login_required
-from flask_restful import Resource, reqparse, fields, marshal_with, inputs
+from libs.login import login_required
+from flask_restful import Resource, reqparse, marshal_with, inputs
 from sqlalchemy import and_
 from werkzeug.exceptions import NotFound, Forbidden, BadRequest
 
@@ -11,32 +11,10 @@ from controllers.console import api
 from controllers.console.explore.wraps import InstalledAppResource
 from controllers.console.wraps import account_initialization_required
 from extensions.ext_database import db
-from libs.helper import TimestampField
+from fields.installed_app_fields import installed_app_list_fields
 from models.model import App, InstalledApp, RecommendedApp
 from services.account_service import TenantService
 
-app_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'mode': fields.String,
-    'icon': fields.String,
-    'icon_background': fields.String
-}
-
-installed_app_fields = {
-    'id': fields.String,
-    'app': fields.Nested(app_fields),
-    'app_owner_tenant_id': fields.String,
-    'is_pinned': fields.Boolean,
-    'last_used_at': TimestampField,
-    'editable': fields.Boolean,
-    'uninstallable': fields.Boolean,
-}
-
-installed_app_list_fields = {
-    'installed_apps': fields.List(fields.Nested(installed_app_fields))
-}
-
 
 class InstalledAppsListApi(Resource):
     @login_required
@@ -61,8 +39,9 @@ class InstalledAppsListApi(Resource):
             }
             for installed_app in installed_apps
         ]
-        installed_apps.sort(key=lambda app: (-app['is_pinned'], app['last_used_at']
-                            if app['last_used_at'] is not None else datetime.min))
+        installed_apps.sort(key=lambda app: (-app['is_pinned'],
+                                             app['last_used_at'] is None,
+                                             -app['last_used_at'].timestamp() if app['last_used_at'] is not None else 0))
 
         return {'installed_apps': installed_apps}
 

api/controllers/console/explore/message.py

@@ -17,6 +17,7 @@ from controllers.console.explore.error import NotCompletionAppError, AppSuggeste
 from controllers.console.explore.wraps import InstalledAppResource
 from core.model_providers.error import LLMRateLimitError, LLMBadRequestError, LLMAuthorizationError, LLMAPIConnectionError, \
     ProviderTokenNotInitError, LLMAPIUnavailableError, QuotaExceededError, ModelCurrentlyNotSupportError
+from fields.message_fields import message_infinite_scroll_pagination_fields
 from libs.helper import uuid_value, TimestampField
 from services.completion_service import CompletionService
 from services.errors.app import MoreLikeThisDisabledError
@@ -26,25 +27,6 @@ from services.message_service import MessageService
 
 
 class MessageListApi(InstalledAppResource):
-    feedback_fields = {
-        'rating': fields.String
-    }
-
-    message_fields = {
-        'id': fields.String,
-        'conversation_id': fields.String,
-        'inputs': fields.Raw,
-        'query': fields.String,
-        'answer': fields.String,
-        'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
-        'created_at': TimestampField
-    }
-
-    message_infinite_scroll_pagination_fields = {
-        'limit': fields.Integer,
-        'has_more': fields.Boolean,
-        'data': fields.List(fields.Nested(message_fields))
-    }
 
     @marshal_with(message_infinite_scroll_pagination_fields)
     def get(self, installed_app):

api/controllers/console/explore/parameter.py

@@ -1,5 +1,6 @@
 # -*- coding:utf-8 -*-
 from flask_restful import marshal_with, fields
+from flask import current_app
 
 from controllers.console import api
 from controllers.console.explore.wraps import InstalledAppResource
@@ -19,13 +20,21 @@ class AppParameterApi(InstalledAppResource):
         'options': fields.List(fields.String)
     }
 
+    system_parameters_fields = {
+        'image_file_size_limit': fields.String
+    }
+
     parameters_fields = {
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
         'speech_to_text': fields.Raw,
+        'retriever_resource': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
+        'sensitive_word_avoidance': fields.Raw,
+        'file_upload': fields.Raw,
+        'system_parameters': fields.Nested(system_parameters_fields)
     }
 
     @marshal_with(parameters_fields)
@@ -39,8 +48,14 @@ class AppParameterApi(InstalledAppResource):
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
             'speech_to_text': app_model_config.speech_to_text_dict,
+            'retriever_resource': app_model_config.retriever_resource_dict,
             'more_like_this': app_model_config.more_like_this_dict,
-            'user_input_form': app_model_config.user_input_form_list
+            'user_input_form': app_model_config.user_input_form_list,
+            'sensitive_word_avoidance': app_model_config.sensitive_word_avoidance_dict,
+            'file_upload': app_model_config.file_upload_dict,
+            'system_parameters': {
+                'image_file_size_limit': current_app.config.get('UPLOAD_IMAGE_FILE_SIZE_LIMIT')
+            }
         }
 
 

api/controllers/console/explore/recommended_app.py

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

api/controllers/console/explore/saved_message.py

@@ -9,6 +9,7 @@ from controllers.console.explore.wraps import InstalledAppResource
 from libs.helper import uuid_value, TimestampField
 from services.errors.message import MessageNotExistsError
 from services.saved_message_service import SavedMessageService
+from fields.conversation_fields import message_file_fields
 
 feedback_fields = {
     'rating': fields.String
@@ -19,6 +20,7 @@ message_fields = {
     'inputs': fields.Raw,
     'query': fields.String,
     'answer': fields.String,
+    'message_files': fields.List(fields.Nested(message_file_fields), attribute='files'),
     'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
     'created_at': TimestampField
 }

api/controllers/console/explore/wraps.py

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

api/controllers/console/extension.py

@@ -0,0 +1,114 @@
+from flask_restful import Resource, reqparse, marshal_with
+from flask_login import current_user
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from libs.login import login_required
+from models.api_based_extension import APIBasedExtension
+from fields.api_based_extension_fields import api_based_extension_fields
+from services.code_based_extension_service import CodeBasedExtensionService
+from services.api_based_extension_service import APIBasedExtensionService
+
+
+class CodeBasedExtensionAPI(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('module', type=str, required=True, location='args')
+        args = parser.parse_args()
+
+        return {
+            'module': args['module'],
+            'data': CodeBasedExtensionService.get_code_based_extension(args['module'])
+        }
+
+
+class APIBasedExtensionAPI(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_based_extension_fields)
+    def get(self):
+        tenant_id = current_user.current_tenant_id
+        return APIBasedExtensionService.get_all_by_tenant_id(tenant_id)
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_based_extension_fields)
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', type=str, required=True, location='json')
+        parser.add_argument('api_endpoint', type=str, required=True, location='json')
+        parser.add_argument('api_key', type=str, required=True, location='json')
+        args = parser.parse_args()
+
+        extension_data = APIBasedExtension(
+            tenant_id=current_user.current_tenant_id,
+            name=args['name'],
+            api_endpoint=args['api_endpoint'],
+            api_key=args['api_key']
+        )
+
+        return APIBasedExtensionService.save(extension_data)
+
+
+class APIBasedExtensionDetailAPI(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_based_extension_fields)
+    def get(self, id):
+        api_based_extension_id = str(id)
+        tenant_id = current_user.current_tenant_id
+
+        return APIBasedExtensionService.get_with_tenant_id(tenant_id, api_based_extension_id)
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(api_based_extension_fields)
+    def post(self, id):
+        api_based_extension_id = str(id)
+        tenant_id = current_user.current_tenant_id
+
+        extension_data_from_db = APIBasedExtensionService.get_with_tenant_id(tenant_id, api_based_extension_id)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', type=str, required=True, location='json')
+        parser.add_argument('api_endpoint', type=str, required=True, location='json')
+        parser.add_argument('api_key', type=str, required=True, location='json')
+        args = parser.parse_args()
+
+        extension_data_from_db.name = args['name']
+        extension_data_from_db.api_endpoint = args['api_endpoint']
+
+        if args['api_key'] != '[__HIDDEN__]':
+            extension_data_from_db.api_key = args['api_key']
+
+        return APIBasedExtensionService.save(extension_data_from_db)
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, id):
+        api_based_extension_id = str(id)
+        tenant_id = current_user.current_tenant_id
+
+        extension_data_from_db = APIBasedExtensionService.get_with_tenant_id(tenant_id, api_based_extension_id)
+
+        APIBasedExtensionService.delete(extension_data_from_db)
+
+        return {'result': 'success'}
+
+
+api.add_resource(CodeBasedExtensionAPI, '/code-based-extension')
+
+api.add_resource(APIBasedExtensionAPI, '/api-based-extension')
+api.add_resource(APIBasedExtensionDetailAPI, '/api-based-extension/<uuid:id>')

api/controllers/console/setup.py

@@ -1,7 +1,6 @@
 # -*- coding:utf-8 -*-
 from functools import wraps
 
-import flask_login
 from flask import request, current_app
 from flask_restful import Resource, reqparse
 
@@ -58,9 +57,6 @@ class SetupApi(Resource):
         )
 
         setup()
-
-        # Login
-        flask_login.login_user(account)
         AccountService.update_last_login(account, request)
 
         return {'result': 'success'}, 201

api/controllers/console/universal_chat/chat.py

@@ -25,10 +25,12 @@ class UniversalChatApi(UniversalChatResource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('query', type=str, required=True, location='json')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
         parser.add_argument('provider', type=str, required=True, location='json')
         parser.add_argument('model', type=str, required=True, location='json')
         parser.add_argument('tools', type=list, required=True, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='universal_app', location='json')
         args = parser.parse_args()
 
         app_model_config = app_model.app_model_config
@@ -59,6 +61,8 @@ class UniversalChatApi(UniversalChatResource):
         del args['model']
         del args['tools']
 
+        args['auto_generate_name'] = False
+
         try:
             response = CompletionService.completion(
                 app_model=app_model,

api/controllers/console/universal_chat/conversation.py

@@ -6,31 +6,17 @@ from werkzeug.exceptions import NotFound
 
 from controllers.console import api
 from controllers.console.universal_chat.wraps import UniversalChatResource
+from fields.conversation_fields import conversation_with_model_config_infinite_scroll_pagination_fields, \
+    conversation_with_model_config_fields
 from libs.helper import TimestampField, uuid_value
 from services.conversation_service import ConversationService
 from services.errors.conversation import LastConversationNotExistsError, ConversationNotExistsError
 from services.web_conversation_service import WebConversationService
 
-conversation_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'inputs': fields.Raw,
-    'status': fields.String,
-    'introduction': fields.String,
-    'created_at': TimestampField,
-    'model_config': fields.Raw,
-}
-
-conversation_infinite_scroll_pagination_fields = {
-    'limit': fields.Integer,
-    'has_more': fields.Boolean,
-    'data': fields.List(fields.Nested(conversation_fields))
-}
-
 
 class UniversalChatConversationListApi(UniversalChatResource):
 
-    @marshal_with(conversation_infinite_scroll_pagination_fields)
+    @marshal_with(conversation_with_model_config_infinite_scroll_pagination_fields)
     def get(self, universal_app):
         app_model = universal_app
 
@@ -73,17 +59,24 @@ class UniversalChatConversationApi(UniversalChatResource):
 
 class UniversalChatConversationRenameApi(UniversalChatResource):
 
-    @marshal_with(conversation_fields)
+    @marshal_with(conversation_with_model_config_fields)
     def post(self, universal_app, c_id):
         app_model = universal_app
         conversation_id = str(c_id)
 
         parser = reqparse.RequestParser()
-        parser.add_argument('name', type=str, required=True, location='json')
+        parser.add_argument('name', type=str, required=False, location='json')
+        parser.add_argument('auto_generate', type=bool, required=False, default='False', location='json')
         args = parser.parse_args()
 
         try:
-            return ConversationService.rename(app_model, conversation_id, current_user, args['name'])
+            return ConversationService.rename(
+                app_model,
+                conversation_id,
+                current_user,
+                args['name'],
+                args['auto_generate']
+            )
         except ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")
 

api/controllers/console/universal_chat/message.py

@@ -36,6 +36,25 @@ class UniversalChatMessageListApi(UniversalChatResource):
         'created_at': TimestampField
     }
 
+    retriever_resource_fields = {
+        'id': fields.String,
+        'message_id': fields.String,
+        'position': fields.Integer,
+        'dataset_id': fields.String,
+        'dataset_name': fields.String,
+        'document_id': fields.String,
+        'document_name': fields.String,
+        'data_source_type': fields.String,
+        'segment_id': fields.String,
+        'score': fields.Float,
+        'hit_count': fields.Integer,
+        'word_count': fields.Integer,
+        'segment_position': fields.Integer,
+        'index_node_hash': fields.String,
+        'content': fields.String,
+        'created_at': TimestampField
+    }
+
     message_fields = {
         'id': fields.String,
         'conversation_id': fields.String,
@@ -43,6 +62,7 @@ class UniversalChatMessageListApi(UniversalChatResource):
         'query': fields.String,
         'answer': fields.String,
         'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
+        'retriever_resources': fields.List(fields.Nested(retriever_resource_fields)),
         'created_at': TimestampField,
         'agent_thoughts': fields.List(fields.Nested(agent_thought_fields))
     }

api/controllers/console/universal_chat/parameter.py

@@ -1,4 +1,6 @@
 # -*- coding:utf-8 -*-
+import json
+
 from flask_restful import marshal_with, fields
 
 from controllers.console import api
@@ -14,6 +16,7 @@ class UniversalChatParameterApi(UniversalChatResource):
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
         'speech_to_text': fields.Raw,
+        'retriever_resource': fields.Raw,
     }
 
     @marshal_with(parameters_fields)
@@ -21,12 +24,14 @@ class UniversalChatParameterApi(UniversalChatResource):
         """Retrieve app parameters."""
         app_model = universal_app
         app_model_config = app_model.app_model_config
+        app_model_config.retriever_resource = json.dumps({'enabled': True})
 
         return {
             'opening_statement': app_model_config.opening_statement,
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
             'speech_to_text': app_model_config.speech_to_text_dict,
+            'retriever_resource': app_model_config.retriever_resource_dict,
         }
 
 

api/controllers/console/universal_chat/wraps.py

@@ -2,7 +2,7 @@ import json
 from functools import wraps
 
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource
 from controllers.console.setup import setup_required
 from controllers.console.wraps import account_initialization_required
@@ -47,6 +47,7 @@ def universal_chat_app_required(view=None):
                     suggested_questions=json.dumps([]),
                     suggested_questions_after_answer=json.dumps({'enabled': True}),
                     speech_to_text=json.dumps({'enabled': True}),
+                    retriever_resource=json.dumps({'enabled': True}),
                     more_like_this=None,
                     sensitive_word_avoidance=None,
                     model=json.dumps({

api/controllers/console/workspace/account.py

@@ -4,7 +4,7 @@ from datetime import datetime
 import pytz
 from flask import current_app, request
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, reqparse, fields, marshal_with
 
 from services.errors.account import CurrentPasswordIncorrectError as ServiceCurrentPasswordIncorrectError

api/controllers/console/workspace/members.py

@@ -1,7 +1,7 @@
 # -*- coding:utf-8 -*-
 from flask import current_app
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, reqparse, marshal_with, abort, fields, marshal
 
 import services
@@ -49,46 +49,43 @@ class MemberInviteEmailApi(Resource):
     @account_initialization_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument('email', type=str, required=True, location='json')
+        parser.add_argument('emails', type=str, required=True, location='json', action='append')
         parser.add_argument('role', type=str, required=True, default='admin', location='json')
         args = parser.parse_args()
 
-        invitee_email = args['email']
+        invitee_emails = args['emails']
         invitee_role = args['role']
         if invitee_role not in ['admin', 'normal']:
             return {'code': 'invalid-role', 'message': 'Invalid role'}, 400
 
         inviter = current_user
-
-        try:
-            token = RegisterService.invite_new_member(inviter.current_tenant, invitee_email, role=invitee_role,
-                                                      inviter=inviter)
-            account = db.session.query(Account, TenantAccountJoin.role).join(
-                TenantAccountJoin, Account.id == TenantAccountJoin.account_id
-            ).filter(Account.email == args['email']).first()
-            account, role = account
-            account = marshal(account, account_fields)
-            account['role'] = role
-        except services.errors.account.CannotOperateSelfError as e:
-            return {'code': 'cannot-operate-self', 'message': str(e)}, 400
-        except services.errors.account.NoPermissionError as e:
-            return {'code': 'forbidden', 'message': str(e)}, 403
-        except services.errors.account.AccountAlreadyInTenantError as e:
-            return {'code': 'email-taken', 'message': str(e)}, 409
-        except Exception as e:
-            return {'code': 'unexpected-error', 'message': str(e)}, 500
-
-        # todo:413
+        invitation_results = []
+        console_web_url = current_app.config.get("CONSOLE_WEB_URL")
+        for invitee_email in invitee_emails:
+            try:
+                token = RegisterService.invite_new_member(inviter.current_tenant, invitee_email, role=invitee_role,
+                                                        inviter=inviter)
+                account = db.session.query(Account, TenantAccountJoin.role).join(
+                    TenantAccountJoin, Account.id == TenantAccountJoin.account_id
+                ).filter(Account.email == invitee_email).first()
+                account, role = account
+                invitation_results.append({
+                    'status': 'success',
+                    'email': invitee_email,
+                    'url': f'{console_web_url}/activate?email={invitee_email}&token={token}'
+                })
+                account = marshal(account, account_fields)
+                account['role'] = role
+            except Exception as e:
+                invitation_results.append({
+                    'status': 'failed',
+                    'email': invitee_email,
+                    'message': str(e)
+                })
 
         return {
             'result': 'success',
-            'account': account,
-            'invite_url': '{}/activate?workspace_id={}&email={}&token={}'.format(
-                current_app.config.get("CONSOLE_WEB_URL"),
-                str(current_user.current_tenant_id),
-                invitee_email,
-                token
-            )
+            'invitation_results': invitation_results,
         }, 201
 
 

api/controllers/console/workspace/model_providers.py

@@ -1,5 +1,5 @@
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
@@ -21,8 +21,12 @@ class ModelProviderListApi(Resource):
     def get(self):
         tenant_id = current_user.current_tenant_id
 
+        parser = reqparse.RequestParser()
+        parser.add_argument('model_type', type=str, required=False, nullable=True, location='args')
+        args = parser.parse_args()
+
         provider_service = ProviderService()
-        provider_list = provider_service.get_provider_list(tenant_id)
+        provider_list = provider_service.get_provider_list(tenant_id=tenant_id, model_type=args.get('model_type'))
 
         return provider_list
 
@@ -246,7 +250,8 @@ class ModelProviderModelParameterRuleApi(Resource):
                 'enabled': v.enabled,
                 'min': v.min,
                 'max': v.max,
-                'default': v.default
+                'default': v.default,
+                'precision': v.precision
             }
             for k, v in vars(parameter_rules).items()
         }
@@ -285,6 +290,25 @@ class ModelProviderFreeQuotaSubmitApi(Resource):
         return result
 
 
+class ModelProviderFreeQuotaQualificationVerifyApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, provider_name: str):
+        parser = reqparse.RequestParser()
+        parser.add_argument('token', type=str, required=False, nullable=True, location='args')
+        args = parser.parse_args()
+
+        provider_service = ProviderService()
+        result = provider_service.free_quota_qualification_verify(
+            tenant_id=current_user.current_tenant_id,
+            provider_name=provider_name,
+            token=args['token']
+        )
+
+        return result
+
+
 api.add_resource(ModelProviderListApi, '/workspaces/current/model-providers')
 api.add_resource(ModelProviderValidateApi, '/workspaces/current/model-providers/<string:provider_name>/validate')
 api.add_resource(ModelProviderUpdateApi, '/workspaces/current/model-providers/<string:provider_name>')
@@ -300,3 +324,5 @@ api.add_resource(ModelProviderPaymentCheckoutUrlApi,
                  '/workspaces/current/model-providers/<string:provider_name>/checkout-url')
 api.add_resource(ModelProviderFreeQuotaSubmitApi,
                  '/workspaces/current/model-providers/<string:provider_name>/free-quota-submit')
+api.add_resource(ModelProviderFreeQuotaQualificationVerifyApi,
+                 '/workspaces/current/model-providers/<string:provider_name>/free-quota-qualification-verify')

api/controllers/console/workspace/models.py

@@ -1,5 +1,7 @@
+import logging
+
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
@@ -19,7 +21,7 @@ class DefaultModelApi(Resource):
     def get(self):
         parser = reqparse.RequestParser()
         parser.add_argument('model_type', type=str, required=True, nullable=False,
-                            choices=['text-generation', 'embeddings', 'speech2text'], location='args')
+                            choices=['text-generation', 'embeddings', 'speech2text', 'reranking'], location='args')
         args = parser.parse_args()
 
         tenant_id = current_user.current_tenant_id
@@ -71,19 +73,21 @@ class DefaultModelApi(Resource):
     @account_initialization_required
     def post(self):
         parser = reqparse.RequestParser()
-        parser.add_argument('model_name', type=str, required=True, nullable=False, location='json')
-        parser.add_argument('model_type', type=str, required=True, nullable=False,
-                            choices=['text-generation', 'embeddings', 'speech2text'], location='json')
-        parser.add_argument('provider_name', type=str, required=True, nullable=False, location='json')
+        parser.add_argument('model_settings', type=list, required=True, nullable=False, location='json')
         args = parser.parse_args()
 
         provider_service = ProviderService()
-        provider_service.update_default_model_of_model_type(
-            tenant_id=current_user.current_tenant_id,
-            model_type=args['model_type'],
-            provider_name=args['provider_name'],
-            model_name=args['model_name']
-        )
+        model_settings = args['model_settings']
+        for model_setting in model_settings:
+            try:
+                provider_service.update_default_model_of_model_type(
+                    tenant_id=current_user.current_tenant_id,
+                    model_type=model_setting['model_type'],
+                    provider_name=model_setting['provider_name'],
+                    model_name=model_setting['model_name']
+                )
+            except Exception:
+                logging.warning(f"{model_setting['model_type']} save error")
 
         return {'result': 'success'}
 

api/controllers/console/workspace/providers.py

@@ -1,6 +1,6 @@
 # -*- coding:utf-8 -*-
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 

api/controllers/console/workspace/tool_providers.py

@@ -1,7 +1,7 @@
 import json
 
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, abort, reqparse
 from werkzeug.exceptions import Forbidden
 

api/controllers/console/workspace/workspace.py

@@ -3,9 +3,8 @@ import logging
 
 from flask import request
 from flask_login import current_user
-from core.login.login import login_required
+from libs.login import login_required
 from flask_restful import Resource, fields, marshal_with, reqparse, marshal, inputs
-from flask_restful.inputs import int_range
 
 from controllers.console import api
 from controllers.console.admin import admin_required

api/controllers/files/__init__.py

@@ -0,0 +1,10 @@
+# -*- coding:utf-8 -*-
+from flask import Blueprint
+
+from libs.external_api import ExternalApi
+
+bp = Blueprint('files', __name__)
+api = ExternalApi(bp)
+
+
+from . import image_preview

api/controllers/files/image_preview.py

@@ -0,0 +1,40 @@
+from flask import request, Response
+from flask_restful import Resource
+
+import services
+from controllers.files import api
+from libs.exception import BaseHTTPException
+from services.file_service import FileService
+
+
+class ImagePreviewApi(Resource):
+    def get(self, file_id):
+        file_id = str(file_id)
+
+        timestamp = request.args.get('timestamp')
+        nonce = request.args.get('nonce')
+        sign = request.args.get('sign')
+
+        if not timestamp or not nonce or not sign:
+            return {'content': 'Invalid request.'}, 400
+
+        try:
+            generator, mimetype = FileService.get_image_preview(
+                file_id,
+                timestamp,
+                nonce,
+                sign
+            )
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        return Response(generator, mimetype=mimetype)
+
+
+api.add_resource(ImagePreviewApi, '/files/<uuid:file_id>/image-preview')
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = 'unsupported_file_type'
+    description = "File type not allowed."
+    code = 415

api/controllers/service_api/__init__.py

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

api/controllers/service_api/app/app.py

@@ -1,5 +1,6 @@
 # -*- coding:utf-8 -*-
 from flask_restful import fields, marshal_with
+from flask import current_app
 
 from controllers.service_api import api
 from controllers.service_api.wraps import AppApiResource
@@ -20,13 +21,21 @@ class AppParameterApi(AppApiResource):
         'options': fields.List(fields.String)
     }
 
+    system_parameters_fields = {
+        'image_file_size_limit': fields.String
+    }
+
     parameters_fields = {
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
         'speech_to_text': fields.Raw,
+        'retriever_resource': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
+        'sensitive_word_avoidance': fields.Raw,
+        'file_upload': fields.Raw,
+        'system_parameters': fields.Nested(system_parameters_fields)
     }
 
     @marshal_with(parameters_fields)
@@ -39,8 +48,14 @@ class AppParameterApi(AppApiResource):
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
             'speech_to_text': app_model_config.speech_to_text_dict,
+            'retriever_resource': app_model_config.retriever_resource_dict,
             'more_like_this': app_model_config.more_like_this_dict,
-            'user_input_form': app_model_config.user_input_form_list
+            'user_input_form': app_model_config.user_input_form_list,
+            'sensitive_word_avoidance': app_model_config.sensitive_word_avoidance_dict,
+            'file_upload': app_model_config.file_upload_dict,
+            'system_parameters': {
+                'image_file_size_limit': current_app.config.get('UPLOAD_IMAGE_FILE_SIZE_LIMIT')
+            }
         }
 
 

api/controllers/service_api/app/completion.py

@@ -27,9 +27,12 @@ class CompletionApi(AppApiResource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
-        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('query', type=str, location='json', default='')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
         parser.add_argument('user', type=str, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
+
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
@@ -37,13 +40,15 @@ class CompletionApi(AppApiResource):
         if end_user is None and args['user'] is not None:
             end_user = create_or_update_end_user_for_user_id(app_model, args['user'])
 
+        args['auto_generate_name'] = False
+
         try:
             response = CompletionService.completion(
                 app_model=app_model,
                 user=end_user,
                 args=args,
                 from_source='api',
-                streaming=streaming
+                streaming=streaming,
             )
 
             return compact_response(response)
@@ -88,9 +93,13 @@ class ChatApi(AppApiResource):
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
         parser.add_argument('query', type=str, required=True, location='json')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
         parser.add_argument('user', type=str, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='dev', location='json')
+        parser.add_argument('auto_generate_name', type=bool, required=False, default='True', location='json')
+
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
@@ -179,4 +188,3 @@ api.add_resource(CompletionApi, '/completion-messages')
 api.add_resource(CompletionStopApi, '/completion-messages/<string:task_id>/stop')
 api.add_resource(ChatApi, '/chat-messages')
 api.add_resource(ChatStopApi, '/chat-messages/<string:task_id>/stop')
-

api/controllers/service_api/app/conversation.py

@@ -8,25 +8,11 @@ from controllers.service_api import api
 from controllers.service_api.app import create_or_update_end_user_for_user_id
 from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import AppApiResource
+from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import TimestampField, uuid_value
 import services
 from services.conversation_service import ConversationService
 
-conversation_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'inputs': fields.Raw,
-    'status': fields.String,
-    'introduction': fields.String,
-    'created_at': TimestampField
-}
-
-conversation_infinite_scroll_pagination_fields = {
-    'limit': fields.Integer,
-    'has_more': fields.Boolean,
-    'data': fields.List(fields.Nested(conversation_fields))
-}
-
 
 class ConversationApi(AppApiResource):
 
@@ -50,7 +36,7 @@ class ConversationApi(AppApiResource):
             raise NotFound("Last Conversation Not Exists.")
 
 class ConversationDetailApi(AppApiResource):
-    @marshal_with(conversation_fields)
+    @marshal_with(simple_conversation_fields)
     def delete(self, app_model, end_user, c_id):
         if app_model.mode != 'chat':
             raise NotChatAppError()
@@ -68,9 +54,10 @@ class ConversationDetailApi(AppApiResource):
             raise NotFound("Conversation Not Exists.")
         return {"result": "success"}, 204
 
+
 class ConversationRenameApi(AppApiResource):
 
-    @marshal_with(conversation_fields)
+    @marshal_with(simple_conversation_fields)
     def post(self, app_model, end_user, c_id):
         if app_model.mode != 'chat':
             raise NotChatAppError()
@@ -78,15 +65,22 @@ class ConversationRenameApi(AppApiResource):
         conversation_id = str(c_id)
 
         parser = reqparse.RequestParser()
-        parser.add_argument('name', type=str, required=True, location='json')
+        parser.add_argument('name', type=str, required=False, location='json')
         parser.add_argument('user', type=str, location='json')
+        parser.add_argument('auto_generate', type=bool, required=False, default=False, location='json')
         args = parser.parse_args()
 
         if end_user is None and args['user'] is not None:
             end_user = create_or_update_end_user_for_user_id(app_model, args['user'])
 
         try:
-            return ConversationService.rename(app_model, conversation_id, end_user, args['name'])
+            return ConversationService.rename(
+                app_model,
+                conversation_id,
+                end_user,
+                args['name'],
+                args['auto_generate']
+            )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")
 

api/controllers/service_api/app/error.py

@@ -75,3 +75,26 @@ class ProviderNotSupportSpeechToTextError(BaseHTTPException):
     description = "Provider not support speech to text."
     code = 400
 
+
+class NoFileUploadedError(BaseHTTPException):
+    error_code = 'no_file_uploaded'
+    description = "Please upload your file."
+    code = 400
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = 'too_many_files'
+    description = "Only one file is allowed."
+    code = 400
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = 'file_too_large'
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = 'unsupported_file_type'
+    description = "File type not allowed."
+    code = 415

api/controllers/service_api/app/file.py

@@ -0,0 +1,45 @@
+from flask import request
+from flask_restful import marshal_with
+
+from controllers.service_api import api
+from controllers.service_api.wraps import AppApiResource
+from controllers.service_api.app import create_or_update_end_user_for_user_id
+from controllers.service_api.app.error import NoFileUploadedError, TooManyFilesError, FileTooLargeError, \
+    UnsupportedFileTypeError
+import services
+from services.file_service import FileService
+from fields.file_fields import file_fields
+
+
+class FileApi(AppApiResource):
+
+    @marshal_with(file_fields)
+    def post(self, app_model, end_user):
+
+        file = request.files['file']
+        user_args = request.form.get('user')
+
+        if end_user is None and user_args is not None:
+            end_user = create_or_update_end_user_for_user_id(app_model, user_args)
+
+        # check file
+        if 'file' not in request.files:
+            raise NoFileUploadedError()
+
+        if not file.mimetype:
+            raise UnsupportedFileTypeError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        try:
+            upload_file = FileService.upload_file(file, end_user)
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        return upload_file, 201
+
+
+api.add_resource(FileApi, '/files/upload')

api/controllers/service_api/app/message.py

@@ -10,12 +10,32 @@ from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import AppApiResource
 from libs.helper import TimestampField, uuid_value
 from services.message_service import MessageService
-
+from extensions.ext_database import db
+from models.model import Message, EndUser
+from fields.conversation_fields import message_file_fields
 
 class MessageListApi(AppApiResource):
     feedback_fields = {
         'rating': fields.String
     }
+    retriever_resource_fields = {
+        'id': fields.String,
+        'message_id': fields.String,
+        'position': fields.Integer,
+        'dataset_id': fields.String,
+        'dataset_name': fields.String,
+        'document_id': fields.String,
+        'document_name': fields.String,
+        'data_source_type': fields.String,
+        'segment_id': fields.String,
+        'score': fields.Float,
+        'hit_count': fields.Integer,
+        'word_count': fields.Integer,
+        'segment_position': fields.Integer,
+        'index_node_hash': fields.String,
+        'content': fields.String,
+        'created_at': TimestampField
+    }
 
     message_fields = {
         'id': fields.String,
@@ -23,7 +43,9 @@ class MessageListApi(AppApiResource):
         'inputs': fields.Raw,
         'query': fields.String,
         'answer': fields.String,
+        'message_files': fields.List(fields.Nested(message_file_fields), attribute='files'),
         'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
+        'retriever_resources': fields.List(fields.Nested(retriever_resource_fields)),
         'created_at': TimestampField
     }
 
@@ -77,5 +99,38 @@ class MessageFeedbackApi(AppApiResource):
         return {'result': 'success'}
 
 
+class MessageSuggestedApi(AppApiResource):
+    def get(self, app_model, end_user, message_id):
+        message_id = str(message_id)
+        if app_model.mode != 'chat':
+            raise NotChatAppError()
+        try:
+            message = db.session.query(Message).filter(
+                Message.id == message_id,
+                Message.app_id == app_model.id,
+            ).first()
+
+            if end_user is None and message.from_end_user_id is not None:
+                user = db.session.query(EndUser) \
+                    .filter(
+                        EndUser.tenant_id == app_model.tenant_id,
+                        EndUser.id == message.from_end_user_id,
+                        EndUser.type == 'service_api'
+                    ).first()
+            else:
+                user = end_user
+            questions = MessageService.get_suggested_questions_after_answer(
+                app_model=app_model,
+                user=user,
+                message_id=message_id,
+                check_enabled=False
+            )
+        except services.errors.message.MessageNotExistsError:
+            raise NotFound("Message Not Exists.")
+
+        return {'result': 'success', 'data': questions}
+
+
 api.add_resource(MessageListApi, '/messages')
 api.add_resource(MessageFeedbackApi, '/messages/<uuid:message_id>/feedbacks')
+api.add_resource(MessageSuggestedApi, '/messages/<uuid:message_id>/suggested')

api/controllers/service_api/dataset/dataset.py

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

api/controllers/service_api/dataset/document.py

@@ -1,114 +1,292 @@
-import datetime
-import uuid
+import json
 
-from flask import current_app
-from flask_restful import reqparse
+from flask import request
+from flask_restful import reqparse, marshal
+from flask_login import current_user
+from sqlalchemy import desc
 from werkzeug.exceptions import NotFound
 
 import services.dataset_service
 from controllers.service_api import api
 from controllers.service_api.app.error import ProviderNotInitializeError
 from controllers.service_api.dataset.error import ArchivedDocumentImmutableError, DocumentIndexingError, \
-    DatasetNotInitedError
+    NoFileUploadedError, TooManyFilesError
 from controllers.service_api.wraps import DatasetApiResource
+from libs.login import current_user
 from core.model_providers.error import ProviderTokenNotInitError
 from extensions.ext_database import db
-from extensions.ext_storage import storage
-from models.model import UploadFile
+from fields.document_fields import document_fields, document_status_fields
+from models.dataset import Dataset, Document, DocumentSegment
 from services.dataset_service import DocumentService
+from services.file_service import FileService
 
 
-class DocumentListApi(DatasetApiResource):
+class DocumentAddByTextApi(DatasetApiResource):
     """Resource for documents."""
 
-    def post(self, dataset):
-        """Create document."""
+    def post(self, tenant_id, dataset_id):
+        """Create document by text."""
         parser = reqparse.RequestParser()
         parser.add_argument('name', type=str, required=True, nullable=False, location='json')
         parser.add_argument('text', type=str, required=True, nullable=False, location='json')
-        parser.add_argument('doc_type', type=str, location='json')
-        parser.add_argument('doc_metadata', type=dict, location='json')
+        parser.add_argument('process_rule', type=dict, required=False, nullable=True, location='json')
+        parser.add_argument('original_document_id', type=str, required=False, location='json')
+        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
+        parser.add_argument('indexing_technique', type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False,
+                            location='json')
+        parser.add_argument('retrieval_model', type=dict, required=False, nullable=False,
+                            location='json')
         args = parser.parse_args()
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
 
-        if not dataset.indexing_technique:
-            raise DatasetNotInitedError("Dataset indexing technique must be set.")
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
 
-        doc_type = args.get('doc_type')
-        doc_metadata = args.get('doc_metadata')
+        if not dataset.indexing_technique and not args['indexing_technique']:
+            raise ValueError('indexing_technique is required.')
 
-        if doc_type and doc_type not in DocumentService.DOCUMENT_METADATA_SCHEMA:
-            raise ValueError('Invalid doc_type.')
-
-        # user uuid as file name
-        file_uuid = str(uuid.uuid4())
-        file_key = 'upload_files/' + dataset.tenant_id + '/' + file_uuid + '.txt'
-
-        # save file to storage
-        storage.save(file_key, args.get('text'))
-
-        # save file to db
-        config = current_app.config
-        upload_file = UploadFile(
-            tenant_id=dataset.tenant_id,
-            storage_type=config['STORAGE_TYPE'],
-            key=file_key,
-            name=args.get('name') + '.txt',
-            size=len(args.get('text')),
-            extension='txt',
-            mime_type='text/plain',
-            created_by=dataset.created_by,
-            created_at=datetime.datetime.utcnow(),
-            used=True,
-            used_by=dataset.created_by,
-            used_at=datetime.datetime.utcnow()
-        )
-
-        db.session.add(upload_file)
-        db.session.commit()
-
-        document_data = {
-            'data_source': {
-                'type': 'upload_file',
-                'info': [
-                    {
-                        'upload_file_id': upload_file.id
-                    }
-                ]
+        upload_file = FileService.upload_text(args.get('text'), args.get('name'))
+        data_source = {
+            'type': 'upload_file',
+            'info_list': {
+                'data_source_type': 'upload_file',
+                'file_info_list': {
+                    'file_ids': [upload_file.id]
+                }
             }
         }
+        args['data_source'] = data_source
+        # validate args
+        DocumentService.document_create_args_validate(args)
 
         try:
             documents, batch = DocumentService.save_document_with_dataset_id(
                 dataset=dataset,
-                document_data=document_data,
-                account=dataset.created_by_account,
-                dataset_process_rule=dataset.latest_process_rule,
+                document_data=args,
+                account=current_user,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
                 created_from='api'
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
         document = documents[0]
-        if doc_type and doc_metadata:
-            metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[doc_type]
 
-            document.doc_metadata = {}
-
-            for key, value_type in metadata_schema.items():
-                value = doc_metadata.get(key)
-                if value is not None and isinstance(value, value_type):
-                    document.doc_metadata[key] = value
-
-            document.doc_type = doc_type
-            document.updated_at = datetime.datetime.utcnow()
-            db.session.commit()
-
-        return {'id': document.id}
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
 
 
-class DocumentApi(DatasetApiResource):
-    def delete(self, dataset, document_id):
+class DocumentUpdateByTextApi(DatasetApiResource):
+    """Resource for update documents."""
+
+    def post(self, tenant_id, dataset_id, document_id):
+        """Update document by text."""
+        parser = reqparse.RequestParser()
+        parser.add_argument('name', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('text', type=str, required=False, nullable=True, location='json')
+        parser.add_argument('process_rule', type=dict, required=False, nullable=True, location='json')
+        parser.add_argument('doc_form', type=str, default='text_model', required=False, nullable=False, location='json')
+        parser.add_argument('doc_language', type=str, default='English', required=False, nullable=False,
+                            location='json')
+        parser.add_argument('retrieval_model', type=dict, required=False, nullable=False,
+                            location='json')
+        args = parser.parse_args()
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
+
+        if args['text']:
+            upload_file = FileService.upload_text(args.get('text'), args.get('name'))
+            data_source = {
+                'type': 'upload_file',
+                'info_list': {
+                    'data_source_type': 'upload_file',
+                    'file_info_list': {
+                        'file_ids': [upload_file.id]
+                    }
+                }
+            }
+            args['data_source'] = data_source
+        # validate args
+        args['original_document_id'] = str(document_id)
+        DocumentService.document_create_args_validate(args)
+
+        try:
+            documents, batch = DocumentService.save_document_with_dataset_id(
+                dataset=dataset,
+                document_data=args,
+                account=current_user,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
+                created_from='api'
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        document = documents[0]
+
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
+
+
+class DocumentAddByFileApi(DatasetApiResource):
+    """Resource for documents."""
+    def post(self, tenant_id, dataset_id):
+        """Create document by upload file."""
+        args = {}
+        if 'data' in request.form:
+            args = json.loads(request.form['data'])
+        if 'doc_form' not in args:
+            args['doc_form'] = 'text_model'
+        if 'doc_language' not in args:
+            args['doc_language'] = 'English'
+        # get dataset info
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
+        if not dataset.indexing_technique and not args['indexing_technique']:
+            raise ValueError('indexing_technique is required.')
+
+        # save file info
+        file = request.files['file']
+        # check file
+        if 'file' not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        upload_file = FileService.upload_file(file, current_user)
+        data_source = {
+            'type': 'upload_file',
+            'info_list': {
+                'file_info_list': {
+                    'file_ids': [upload_file.id]
+                }
+            }
+        }
+        args['data_source'] = data_source
+        # validate args
+        DocumentService.document_create_args_validate(args)
+
+        try:
+            documents, batch = DocumentService.save_document_with_dataset_id(
+                dataset=dataset,
+                document_data=args,
+                account=dataset.created_by_account,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
+                created_from='api'
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        document = documents[0]
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
+
+
+class DocumentUpdateByFileApi(DatasetApiResource):
+    """Resource for update documents."""
+
+    def post(self, tenant_id, dataset_id, document_id):
+        """Update document by upload file."""
+        args = {}
+        if 'data' in request.form:
+            args = json.loads(request.form['data'])
+        if 'doc_form' not in args:
+            args['doc_form'] = 'text_model'
+        if 'doc_language' not in args:
+            args['doc_language'] = 'English'
+
+        # get dataset info
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
+        if 'file' in request.files:
+            # save file info
+            file = request.files['file']
+
+
+            if len(request.files) > 1:
+                raise TooManyFilesError()
+
+            upload_file = FileService.upload_file(file, current_user)
+            data_source = {
+                'type': 'upload_file',
+                'info_list': {
+                    'file_info_list': {
+                        'file_ids': [upload_file.id]
+                    }
+                }
+            }
+            args['data_source'] = data_source
+        # validate args
+        args['original_document_id'] = str(document_id)
+        DocumentService.document_create_args_validate(args)
+
+        try:
+            documents, batch = DocumentService.save_document_with_dataset_id(
+                dataset=dataset,
+                document_data=args,
+                account=dataset.created_by_account,
+                dataset_process_rule=dataset.latest_process_rule if 'process_rule' not in args else None,
+                created_from='api'
+            )
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        document = documents[0]
+        documents_and_batch_fields = {
+            'document': marshal(document, document_fields),
+            'batch': batch
+        }
+        return documents_and_batch_fields, 200
+
+
+class DocumentDeleteApi(DatasetApiResource):
+    def delete(self, tenant_id, dataset_id, document_id):
         """Delete document."""
         document_id = str(document_id)
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+
+        # get dataset info
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+
+        if not dataset:
+            raise ValueError('Dataset is not exist.')
 
         document = DocumentService.get_document(dataset.id, document_id)
 
@@ -126,8 +304,85 @@ class DocumentApi(DatasetApiResource):
         except services.errors.document.DocumentIndexingError:
             raise DocumentIndexingError('Cannot delete document during indexing.')
 
-        return {'result': 'success'}, 204
+        return {'result': 'success'}, 200
 
 
-api.add_resource(DocumentListApi, '/documents')
-api.add_resource(DocumentApi, '/documents/<uuid:document_id>')
+class DocumentListApi(DatasetApiResource):
+    def get(self, tenant_id, dataset_id):
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        page = request.args.get('page', default=1, type=int)
+        limit = request.args.get('limit', default=20, type=int)
+        search = request.args.get('keyword', default=None, type=str)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+
+        query = Document.query.filter_by(
+            dataset_id=str(dataset_id), tenant_id=tenant_id)
+
+        if search:
+            search = f'%{search}%'
+            query = query.filter(Document.name.like(search))
+
+        query = query.order_by(desc(Document.created_at))
+
+        paginated_documents = query.paginate(
+            page=page, per_page=limit, max_per_page=100, error_out=False)
+        documents = paginated_documents.items
+
+        response = {
+            'data': marshal(documents, document_fields),
+            'has_more': len(documents) == limit,
+            'limit': limit,
+            'total': paginated_documents.total,
+            'page': page
+        }
+
+        return response
+
+
+class DocumentIndexingStatusApi(DatasetApiResource):
+    def get(self, tenant_id, dataset_id, batch):
+        dataset_id = str(dataset_id)
+        batch = str(batch)
+        tenant_id = str(tenant_id)
+        # get dataset
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # get documents
+        documents = DocumentService.get_batch_documents(dataset_id, batch)
+        if not documents:
+            raise NotFound('Documents not found.')
+        documents_status = []
+        for document in documents:
+            completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                              DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+            total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                          DocumentSegment.status != 're_segment').count()
+            document.completed_segments = completed_segments
+            document.total_segments = total_segments
+            if document.is_paused:
+                document.indexing_status = 'paused'
+            documents_status.append(marshal(document, document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
+api.add_resource(DocumentAddByTextApi, '/datasets/<uuid:dataset_id>/document/create_by_text')
+api.add_resource(DocumentAddByFileApi, '/datasets/<uuid:dataset_id>/document/create_by_file')
+api.add_resource(DocumentUpdateByTextApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text')
+api.add_resource(DocumentUpdateByFileApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file')
+api.add_resource(DocumentDeleteApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>')
+api.add_resource(DocumentListApi, '/datasets/<uuid:dataset_id>/documents')
+api.add_resource(DocumentIndexingStatusApi, '/datasets/<uuid:dataset_id>/documents/<string:batch>/indexing-status')

api/controllers/service_api/dataset/error.py

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

api/controllers/service_api/dataset/segment.py

@@ -0,0 +1,201 @@
+from flask_login import current_user
+from flask_restful import reqparse, marshal
+from werkzeug.exceptions import NotFound
+from controllers.service_api import api
+from controllers.service_api.app.error import ProviderNotInitializeError
+from controllers.service_api.wraps import DatasetApiResource
+from core.model_providers.error import ProviderTokenNotInitError, LLMBadRequestError
+from core.model_providers.model_factory import ModelFactory
+from extensions.ext_database import db
+from fields.segment_fields import segment_fields
+from models.dataset import Dataset, DocumentSegment
+from services.dataset_service import DatasetService, DocumentService, SegmentService
+
+
+class SegmentApi(DatasetApiResource):
+    """Resource for segments."""
+    def post(self, tenant_id, dataset_id, document_id):
+        """Create single segment."""
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        # check embedding model setting
+        if dataset.indexing_technique == 'high_quality':
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument('segments', type=list, required=False, nullable=True, location='json')
+        args = parser.parse_args()
+        for args_item in args['segments']:
+            SegmentService.segment_create_args_validate(args_item, document)
+        segments = SegmentService.multi_create_segment(args['segments'], document, dataset)
+        return {
+            'data': marshal(segments, segment_fields),
+            'doc_form': document.doc_form
+        }, 200
+
+    def get(self, tenant_id, dataset_id, document_id):
+        """Create single segment."""
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        # check embedding model setting
+        if dataset.indexing_technique == 'high_quality':
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+
+        parser = reqparse.RequestParser()
+        parser.add_argument('status', type=str,
+                            action='append', default=[], location='args')
+        parser.add_argument('keyword', type=str, default=None, location='args')
+        args = parser.parse_args()
+
+        status_list = args['status']
+        keyword = args['keyword']
+
+        query = DocumentSegment.query.filter(
+            DocumentSegment.document_id == str(document_id),
+            DocumentSegment.tenant_id == current_user.current_tenant_id
+        )
+
+        if status_list:
+            query = query.filter(DocumentSegment.status.in_(status_list))
+
+        if keyword:
+            query = query.where(DocumentSegment.content.ilike(f'%{keyword}%'))
+
+        total = query.count()
+        segments = query.order_by(DocumentSegment.position).all()
+        return {
+            'data': marshal(segments, segment_fields),
+            'doc_form': document.doc_form,
+            'total': total
+        }, 200
+
+
+class DatasetSegmentApi(DatasetApiResource):
+    def delete(self, tenant_id, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        # check segment
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id),
+            DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound('Segment not found.')
+        SegmentService.delete_segment(segment, document, dataset)
+        return {'result': 'success'}, 200
+
+    def post(self, tenant_id, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(
+            Dataset.tenant_id == tenant_id,
+            Dataset.id == dataset_id
+        ).first()
+        if not dataset:
+            raise NotFound('Dataset not found.')
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound('Document not found.')
+        if dataset.indexing_technique == 'high_quality':
+            # check embedding model setting
+            try:
+                ModelFactory.get_embedding_model(
+                    tenant_id=current_user.current_tenant_id,
+                    model_provider_name=dataset.embedding_model_provider,
+                    model_name=dataset.embedding_model
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    f"No Embedding Model available. Please configure a valid provider "
+                    f"in the Settings -> Model Provider.")
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+            # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id),
+            DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound('Segment not found.')
+
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument('segments', type=dict, required=False, nullable=True, location='json')
+        args = parser.parse_args()
+
+        SegmentService.segment_create_args_validate(args['segments'], document)
+        segment = SegmentService.update_segment(args['segments'], segment, document, dataset)
+        return {
+            'data': marshal(segment, segment_fields),
+            'doc_form': document.doc_form
+        }, 200
+
+
+api.add_resource(SegmentApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments')
+api.add_resource(DatasetSegmentApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>')

api/controllers/service_api/wraps.py

@@ -2,12 +2,14 @@
 from datetime import datetime
 from functools import wraps
 
-from flask import request
+from flask import request, current_app
+from flask_login import user_logged_in
 from flask_restful import Resource
 from werkzeug.exceptions import NotFound, Unauthorized
 
+from libs.login import _get_user
 from extensions.ext_database import db
-from models.dataset import Dataset
+from models.account import Tenant, TenantAccountJoin, Account
 from models.model import ApiToken, App
 
 
@@ -43,12 +45,24 @@ def validate_dataset_token(view=None):
         @wraps(view)
         def decorated(*args, **kwargs):
             api_token = validate_and_get_api_token('dataset')
-
-            dataset = db.session.query(Dataset).filter(Dataset.id == api_token.dataset_id).first()
-            if not dataset:
-                raise NotFound()
-
-            return view(dataset, *args, **kwargs)
+            tenant_account_join = db.session.query(Tenant, TenantAccountJoin) \
+                .filter(Tenant.id == api_token.tenant_id) \
+                .filter(TenantAccountJoin.tenant_id == Tenant.id) \
+                .filter(TenantAccountJoin.role == 'owner') \
+                .one_or_none()
+            if tenant_account_join:
+                tenant, ta = tenant_account_join
+                account = Account.query.filter_by(id=ta.account_id).first()
+                # Login admin
+                if account:
+                    account.current_tenant = tenant
+                    current_app.login_manager._update_request_context_with_user(account)
+                    user_logged_in.send(current_app._get_current_object(), user=_get_user())
+                else:
+                    raise Unauthorized("Tenant owner account is not exist.")
+            else:
+                raise Unauthorized("Tenant is not exist.")
+            return view(api_token.tenant_id, *args, **kwargs)
         return decorated
 
     if view:

api/controllers/web/__init__.py

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

api/controllers/web/app.py

@@ -1,5 +1,6 @@
 # -*- coding:utf-8 -*-
 from flask_restful import marshal_with, fields
+from flask import current_app
 
 from controllers.web import api
 from controllers.web.wraps import WebApiResource
@@ -19,13 +20,21 @@ class AppParameterApi(WebApiResource):
         'options': fields.List(fields.String)
     }
 
+    system_parameters_fields = {
+        'image_file_size_limit': fields.String
+    }
+
     parameters_fields = {
         'opening_statement': fields.String,
         'suggested_questions': fields.Raw,
         'suggested_questions_after_answer': fields.Raw,
         'speech_to_text': fields.Raw,
+        'retriever_resource': fields.Raw,
         'more_like_this': fields.Raw,
         'user_input_form': fields.Raw,
+        'sensitive_word_avoidance': fields.Raw,
+        'file_upload': fields.Raw,
+        'system_parameters': fields.Nested(system_parameters_fields)
     }
 
     @marshal_with(parameters_fields)
@@ -38,8 +47,14 @@ class AppParameterApi(WebApiResource):
             'suggested_questions': app_model_config.suggested_questions_list,
             'suggested_questions_after_answer': app_model_config.suggested_questions_after_answer_dict,
             'speech_to_text': app_model_config.speech_to_text_dict,
+            'retriever_resource': app_model_config.retriever_resource_dict,
             'more_like_this': app_model_config.more_like_this_dict,
-            'user_input_form': app_model_config.user_input_form_list
+            'user_input_form': app_model_config.user_input_form_list,
+            'sensitive_word_avoidance': app_model_config.sensitive_word_avoidance_dict,
+            'file_upload': app_model_config.file_upload_dict,
+            'system_parameters': {
+                'image_file_size_limit': current_app.config.get('UPLOAD_IMAGE_FILE_SIZE_LIMIT')
+            }
         }
 
 

api/controllers/web/completion.py

@@ -29,11 +29,15 @@ class CompletionApi(WebApiResource):
 
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
-        parser.add_argument('query', type=str, location='json')
+        parser.add_argument('query', type=str, location='json', default='')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='web_app', location='json')
+
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
+        args['auto_generate_name'] = False
 
         try:
             response = CompletionService.completion(
@@ -86,11 +90,15 @@ class ChatApi(WebApiResource):
         parser = reqparse.RequestParser()
         parser.add_argument('inputs', type=dict, required=True, location='json')
         parser.add_argument('query', type=str, required=True, location='json')
+        parser.add_argument('files', type=list, required=False, location='json')
         parser.add_argument('response_mode', type=str, choices=['blocking', 'streaming'], location='json')
         parser.add_argument('conversation_id', type=uuid_value, location='json')
+        parser.add_argument('retriever_from', type=str, required=False, default='web_app', location='json')
+
         args = parser.parse_args()
 
         streaming = args['response_mode'] == 'streaming'
+        args['auto_generate_name'] = False
 
         try:
             response = CompletionService.completion(
@@ -135,7 +143,7 @@ class ChatStopApi(WebApiResource):
         return {'result': 'success'}, 200
 
 
-def compact_response(response: Union[dict | Generator]) -> Response:
+def compact_response(response: Union[dict, Generator]) -> Response:
     if isinstance(response, dict):
         return Response(response=json.dumps(response), status=200, mimetype='application/json')
     else:

api/controllers/web/conversation.py

@@ -6,26 +6,12 @@ from werkzeug.exceptions import NotFound
 from controllers.web import api
 from controllers.web.error import NotChatAppError
 from controllers.web.wraps import WebApiResource
+from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import TimestampField, uuid_value
 from services.conversation_service import ConversationService
 from services.errors.conversation import LastConversationNotExistsError, ConversationNotExistsError
 from services.web_conversation_service import WebConversationService
 
-conversation_fields = {
-    'id': fields.String,
-    'name': fields.String,
-    'inputs': fields.Raw,
-    'status': fields.String,
-    'introduction': fields.String,
-    'created_at': TimestampField
-}
-
-conversation_infinite_scroll_pagination_fields = {
-    'limit': fields.Integer,
-    'has_more': fields.Boolean,
-    'data': fields.List(fields.Nested(conversation_fields))
-}
-
 
 class ConversationListApi(WebApiResource):
 
@@ -73,7 +59,7 @@ class ConversationApi(WebApiResource):
 
 class ConversationRenameApi(WebApiResource):
 
-    @marshal_with(conversation_fields)
+    @marshal_with(simple_conversation_fields)
     def post(self, app_model, end_user, c_id):
         if app_model.mode != 'chat':
             raise NotChatAppError()
@@ -81,11 +67,18 @@ class ConversationRenameApi(WebApiResource):
         conversation_id = str(c_id)
 
         parser = reqparse.RequestParser()
-        parser.add_argument('name', type=str, required=True, location='json')
+        parser.add_argument('name', type=str, required=False, location='json')
+        parser.add_argument('auto_generate', type=bool, required=False, default='False', location='json')
         args = parser.parse_args()
 
         try:
-            return ConversationService.rename(app_model, conversation_id, end_user, args['name'])
+            return ConversationService.rename(
+                app_model,
+                conversation_id,
+                end_user,
+                args['name'],
+                args['auto_generate']
+            )
         except ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")
 

api/controllers/web/error.py

@@ -85,4 +85,28 @@ class UnsupportedAudioTypeError(BaseHTTPException):
 class ProviderNotSupportSpeechToTextError(BaseHTTPException):
     error_code = 'provider_not_support_speech_to_text'
     description = "Provider not support speech to text."
-    code = 400
+    code = 400
+
+
+class NoFileUploadedError(BaseHTTPException):
+    error_code = 'no_file_uploaded'
+    description = "Please upload your file."
+    code = 400
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = 'too_many_files'
+    description = "Only one file is allowed."
+    code = 400
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = 'file_too_large'
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = 'unsupported_file_type'
+    description = "File type not allowed."
+    code = 415

api/controllers/web/file.py

@@ -0,0 +1,36 @@
+from flask import request
+from flask_restful import marshal_with
+
+from controllers.web import api
+from controllers.web.wraps import WebApiResource
+from controllers.web.error import NoFileUploadedError, TooManyFilesError, FileTooLargeError, \
+    UnsupportedFileTypeError
+import services
+from services.file_service import FileService
+from fields.file_fields import file_fields
+
+
+class FileApi(WebApiResource):
+
+    @marshal_with(file_fields)
+    def post(self, app_model, end_user):
+        # get file from request
+        file = request.files['file']
+
+        # check file
+        if 'file' not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+        try:
+            upload_file = FileService.upload_file(file, end_user)
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        return upload_file, 201
+
+
+api.add_resource(FileApi, '/files/upload')

api/controllers/web/message.py

@@ -22,6 +22,7 @@ from services.errors.app import MoreLikeThisDisabledError
 from services.errors.conversation import ConversationNotExistsError
 from services.errors.message import MessageNotExistsError, SuggestedQuestionsAfterAnswerDisabledError
 from services.message_service import MessageService
+from fields.conversation_fields import message_file_fields
 
 
 class MessageListApi(WebApiResource):
@@ -29,13 +30,34 @@ class MessageListApi(WebApiResource):
         'rating': fields.String
     }
 
+    retriever_resource_fields = {
+        'id': fields.String,
+        'message_id': fields.String,
+        'position': fields.Integer,
+        'dataset_id': fields.String,
+        'dataset_name': fields.String,
+        'document_id': fields.String,
+        'document_name': fields.String,
+        'data_source_type': fields.String,
+        'segment_id': fields.String,
+        'score': fields.Float,
+        'hit_count': fields.Integer,
+        'word_count': fields.Integer,
+        'segment_position': fields.Integer,
+        'index_node_hash': fields.String,
+        'content': fields.String,
+        'created_at': TimestampField
+    }
+
     message_fields = {
         'id': fields.String,
         'conversation_id': fields.String,
         'inputs': fields.Raw,
         'query': fields.String,
         'answer': fields.String,
+        'message_files': fields.List(fields.Nested(message_file_fields), attribute='files'),
         'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
+        'retriever_resources': fields.List(fields.Nested(retriever_resource_fields)),
         'created_at': TimestampField
     }
 
@@ -95,7 +117,7 @@ class MessageMoreLikeThisApi(WebApiResource):
         streaming = args['response_mode'] == 'streaming'
 
         try:
-            response = CompletionService.generate_more_like_this(app_model, end_user, message_id, streaming)
+            response = CompletionService.generate_more_like_this(app_model, end_user, message_id, streaming, 'web_app')
             return compact_response(response)
         except MessageNotExistsError:
             raise NotFound("Message Not Exists.")

api/controllers/web/saved_message.py

@@ -8,6 +8,8 @@ from controllers.web.wraps import WebApiResource
 from libs.helper import uuid_value, TimestampField
 from services.errors.message import MessageNotExistsError
 from services.saved_message_service import SavedMessageService
+from fields.conversation_fields import message_file_fields
+
 
 feedback_fields = {
     'rating': fields.String
@@ -18,6 +20,7 @@ message_fields = {
     'inputs': fields.Raw,
     'query': fields.String,
     'answer': fields.String,
+    'message_files': fields.List(fields.Nested(message_file_fields), attribute='files'),
     'feedback': fields.Nested(feedback_fields, attribute='user_feedback', allow_null=True),
     'created_at': TimestampField
 }