version to 0.6.3 (#3519)

Co-authored-by: miendinh <miendinh@users.noreply.github.com>

.devcontainer/Dockerfile

@@ -1,8 +1,5 @@
 FROM mcr.microsoft.com/devcontainers/python:3.10
 
-COPY . .
-
-
 # [Optional] Uncomment this section to install additional OS packages.
 # RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
 #     && apt-get -y install --no-install-recommends <your-package-list-here>

.github/workflows/api-tests.yml

@@ -32,15 +32,22 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Install APT packages
+        uses: awalsh128/cache-apt-pkgs-action@v1
+        with:
+          packages: ffmpeg
+
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
           python-version: '3.10'
           cache: 'pip'
-          cache-dependency-path: ./api/requirements.txt
+          cache-dependency-path: |
+            ./api/requirements.txt
+            ./api/requirements-dev.txt
 
       - name: Install dependencies
-        run: pip install -r ./api/requirements.txt
+        run: pip install -r ./api/requirements.txt -r ./api/requirements-dev.txt
 
       - name: Run ModelRuntime
         run: pytest api/tests/integration_tests/model_runtime/anthropic api/tests/integration_tests/model_runtime/azure_openai api/tests/integration_tests/model_runtime/openai api/tests/integration_tests/model_runtime/chatglm api/tests/integration_tests/model_runtime/google api/tests/integration_tests/model_runtime/xinference api/tests/integration_tests/model_runtime/huggingface_hub/test_llm.py

.github/workflows/build-push.yml

@@ -46,7 +46,7 @@ jobs:
         with:
           images: ${{ env[matrix.image_name_env] }}
           tags: |
-            type=raw,value=latest,enable=${{ github.ref == 'refs/heads/main' && startsWith(github.ref, 'refs/tags/') }}
+            type=raw,value=latest,enable=${{ startsWith(github.ref, 'refs/tags/') }}
             type=ref,event=branch
             type=sha,enable=true,priority=100,prefix=,suffix=,format=long
             type=raw,value=${{ github.ref_name }},enable=${{ startsWith(github.ref, 'refs/tags/') }}

CONTRIBUTING.md

@@ -36,7 +36,7 @@ In terms of licensing, please take a minute to read our short [License and Contr
   | Feature Type                                                 | Priority        |
   | ------------------------------------------------------------ | --------------- |
   | High-Priority Features as being labeled by a team member     | High Priority   |
-  | Popular feature requests from our [community feedback board](https://feedback.dify.ai/) | Medium Priority |
+  | Popular feature requests from our [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Medium Priority |
   | Non-core features and minor enhancements                     | Low Priority    |
   | Valuable but not immediate                                   | Future-Feature  |
 

CONTRIBUTING_CN.md

@@ -34,7 +34,7 @@
   | Feature Type                                                 | Priority        |
   | ------------------------------------------------------------ | --------------- |
   | High-Priority Features as being labeled by a team member     | High Priority   |
-  | Popular feature requests from our [community feedback board](https://feedback.dify.ai/) | Medium Priority |
+  | Popular feature requests from our [community feedback board](https://github.com/langgenius/dify/discussions/categories/feedbacks) | Medium Priority |
   | Non-core features and minor enhancements                     | Low Priority    |
   | Valuable but not immediate                                   | Future-Feature  |
 

README.md

@@ -1,95 +1,176 @@
-[![](./images/GitHub_README_cover.png)](https://dify.ai)
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
 <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> |
-  <a href="./README_FR.md">Français</a>
+  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
+  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
+  <a href="https://docs.dify.ai">Documentation</a> ·
+  <a href="https://cal.com/guchenhe/60-min-meeting">Enterprise inquiry</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>
+        <img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
+    <a href="https://dify.ai/pricing" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
     <a href="https://discord.gg/FngNHpbcY7" target="_blank">
-        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
             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"
+        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             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>
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
+    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
+        <img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
+    <a href="https://github.com/langgenius/dify/" target="_blank">
+        <img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
+    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
+        <img alt="Discussion posts" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
 </p>
 
 <p align="center">
-   <a href="https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6" target="_blank">
-   📌 Check out Dify Premium on AWS and deploy it to your own AWS VPC with one-click.
-  </a>
+  <a href="./README.md"><img alt="Commits last month" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="Commits last month" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="Commits last month" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="Commits last month" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="Commits last month" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="Commits last month" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
 </p>
 
-**Dify** is an open-source LLM app development platform. Dify's intuitive interface combines a RAG pipeline, AI workflow orchestration, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
+#
 
-![](./images/demo.png)
+<p align="center">
+  <a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. Here's a list of the core features:
+</br> </br>
+
+**1. Workflow**: 
+  Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
+
+
+  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
 
 
 
-## Using our Cloud Services
+**2. Comprehensive model support**: 
+  Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama2, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
 
-You can try out [Dify.AI Cloud](https://dify.ai) now. It provides all the capabilities of the self-deployed version, and includes 200 free requests to OpenAI GPT-3.5.
+![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
-### Looking to purchase via AWS?
-Check out [Dify Premium on AWS](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. 
 
-## Dify vs. LangChain vs. Assistants API
+**3. Prompt IDE**: 
+  Intuitive interface for crafting prompts, comparing model performance, and adding additional features such as text-to-speech to a chat-based app. 
 
-| Feature | Dify.AI | Assistants API | LangChain |
-|---------|---------|----------------|-----------|
-| **Programming Approach** | API-oriented | API-oriented | Python Code-oriented |
-| **Ecosystem Strategy** | Open Source | Close Source | Open Source |
-| **RAG Engine** | Supported | Supported | Not Supported |
-| **Prompt IDE** | Included | Included | None |
-| **Supported LLMs** | Rich Variety | OpenAI-only | Rich Variety |
-| **Local Deployment** | Supported | Not Supported | Not Applicable |
+**4. RAG Pipeline**: 
+  Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats.
+
+**5. Agent capabilities**: 
+  You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DELL·E, Stable Diffusion and WolframAlpha.
+
+**6. LLMOps**: 
+  Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations.
+
+**7. Backend-as-a-Service**: 
+  All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.
+
+
+## Feature comparison
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Feature</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programming Approach</td>
+    <td align="center">API + App-oriented</td>
+    <td align="center">Python Code</td>
+    <td align="center">App-oriented</td>
+    <td align="center">API-oriented</td>
+  </tr>
+  <tr>
+    <td align="center">Supported LLMs</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">OpenAI-only</td>
+  </tr>
+  <tr>
+    <td align="center">RAG Engine</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Workflow</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Observability</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Enterprise Feature (SSO/Access control)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Local Deployment</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
+
+## Using Dify
+
+- **Cloud </br>**
+We host a [Dify Cloud](https://dify.ai) service for anyone to try with zero setup. It provides all the capabilities of the self-deployed version, and includes 200 free GPT-4 calls in the sandbox plan.
+
+- **Self-hosting Dify Community Edition</br>**
+Quickly get Dify running in your environment with this [starter guide](#quick-start).
+Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.
+
+- **Dify for enterprise / organizations</br>**
+We provide additional enterprise-centric features. [Schedule a meeting with us](https://cal.com/guchenhe/30min) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
+  > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
+
+
+## Staying ahead
+
+Star Dify on GitHub and be instantly notified of new releases.
+
+![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
 
 
 
-## Features
+## Quick start
+> Before installing Dify, make sure your machine meets the following minimum system requirements:
+> 
+>- CPU >= 2 Core
+>- RAM >= 4GB
 
-![](./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. AI Agent**: Based on Function Calling and ReAct, the Agent inference framework allows users to customize tools, what you see is what you get. Dify provides more than a dozen built-in tool calling capabilities, such as Google Search, DELL·E, Stable Diffusion, WolframAlpha, etc.
-
-
-**5. Continuous Operations**: Monitor and analyze application logs and performance, continuously improving Prompts, datasets, or models using production data.
-
-## Before You Start
-
-**Star us on GitHub, and be instantly notified for new releases!**
-
-![star-us](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)
-
-- [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
-
-### System Requirements
-
-Before installing Dify, make sure your machine meets the following minimum system requirements:
-
-- CPU >= 2 Core
-- RAM >= 4GB
-
-### Quick Start
+</br>
 
 The easiest way to start the Dify server is to run our [docker-compose.yml](docker/docker-compose.yaml) file. Before running the installation command, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
 
@@ -98,63 +179,65 @@ cd docker
 docker compose up -d
 ```
 
-After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization installation process.
+After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process.
 
-#### Deploy with Helm Chart
+> If you'd like to contribute to Dify or do additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
 
-[Helm Chart](https://helm.sh/) version, which allows Dify to be deployed on Kubernetes.
+## Next steps
+
+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 [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+
+If you'd like to configure a highly-available setup, there are community-contributed [Helm Charts](https://helm.sh/) which allow Dify to be deployed on Kubernetes.
 
 - [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
 - [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 
-### 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. You can see the full list of environment variables in our [docs](https://docs.dify.ai/getting-started/install-self-hosted/environments).
-
-
-## Star History
-
-[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
-
 At the same time, please consider supporting Dify by sharing it on social media and at events and conferences.
 
-### Projects made by community
 
-- [Chatbot Chrome Extension by @charli117](https://github.com/langgenius/chatbot-chrome-extension)
+> We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
 
-### Contributors
+**Contributors**
 
 <a href="https://github.com/langgenius/dify/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=langgenius/dify" />
 </a>
 
-### Translations
+## Community & contact
 
-We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
-
-## Community & Support
-
-* [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and checking out our feature roadmap.
+* [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
 * [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
-* [Email Support](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify). Best for: questions you have about using Dify.AI.
+* [Email](mailto:support@dify.ai?subject=[GitHub]Questions%20About%20Dify). Best for: questions you have about using Dify.AI.
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
 * [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
-* [Business Contact](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). Best for: business inquiries of licensing Dify.AI for commercial use.
 
-### Direct Meetings
+Or, schedule a meeting directly with a team member:
 
-**Help us make Dify better. Reach out directly to us**.
+<table>
+  <tr>
+    <th>Point of Contact</th>
+    <th>Purpose</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Business enquiries & product feedback</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contributions, issues & feature requests</td>
+  </tr>
+</table>
 
-|                       Point of Contact                       |                           Purpose                            |
-| :----------------------------------------------------------: | :----------------------------------------------------------: |
-| <a href='https://cal.com/guchenhe/15min' target='_blank'><img src='https://i.postimg.cc/fWBqSmjP/Git-Hub-README-Button-3x.png' border='0' alt='Git-Hub-README-Button-3x' height="60" width="214"/></a> | Product design feedback, user experience discussions, feature planning and roadmaps. |
-| <a href='https://cal.com/pinkbanana' target='_blank'><img src='https://i.postimg.cc/LsRTh87D/Git-Hub-README-Button-2x.png' border='0' alt='Git-Hub-README-Button-2x' height="60" width="225"/></a> |        Technical support, issues, or feature requests        |
+## Star history
 
-## Security Disclosure
+[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+
+
+## 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.
 

README_CN.md

@@ -1,78 +1,167 @@
-[![](./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> |
-  <a href="./README_FR.md">Français</a>
-</p>
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
+<div align="center">
+  <a href="https://cloud.dify.ai">Dify 云服务</a> ·
+  <a href="https://docs.dify.ai/getting-started/install-self-hosted">自托管</a> ·
+  <a href="https://docs.dify.ai">文档</a> ·
+  <a href="https://cal.com/guchenhe/dify-demo">预约演示</a>
+</div>
 
 <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>
+        <img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
+    <a href="https://dify.ai/pricing" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
     <a href="https://discord.gg/FngNHpbcY7" target="_blank">
-        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
             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"
+        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             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>
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
+    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
+        <img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
+    <a href="https://github.com/langgenius/dify/" target="_blank">
+        <img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
+    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
+        <img alt="Discussion posts" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
 </p>
 
-<p align="center">
-   <a href="https://mp.weixin.qq.com/s/TnyfIuH-tPi9o1KNjwVArw" target="_blank">
-   Dify 发布 AI Agent 能力：基于不同的大型语言模型构建 GPTs 和 Assistants
-  </a>
-</p>
-
-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。
-
-![](./images/demo.png)
-
-## 使用云端服务
-
-使用 [Dify.AI Cloud](https://dify.ai) 提供开源版本的所有功能,并包含 200 次 GPT 试用额度。
-
-## 为什么选择 Dify
-
-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 |
+<div align="center">
+  <a href="./README.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/英文-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/西班牙语-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/法语-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="上个月的提交次数" src="https://img.shields.io/badge/克林贡语-d9d9d9"></a>
+</div>
 
 
-## 特点
+#
 
-![](./images/models.png)
+<div align="center">
+  <a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | 趋势转变" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</div>
 
-**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)。
+Dify 是一个开源的LLM应用开发平台。其直观的界面结合了AI工作流程、RAG管道、代理功能、模型管理、可观察性功能等，让您可以快速从原型到生产。以下是其核心功能列表：
+</br> </br>
 
-**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。
+**1. 工作流**: 
+  在视觉画布上构建和测试功能强大的AI工作流程，利用以下所有功能以及更多功能。
 
-**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. AI Agent**：基于 Function Calling 和 ReAct 的 Agent 推理框架，允许用户自定义工具，所见即所得。Dify 提供了十多种内置工具调用能力，如谷歌搜索、DELL·E、Stable Diffusion、WolframAlpha 等。
+  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
 
-**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。
 
-## 在开始之前
 
-**关注我们，您将立即收到 GitHub 上所有新发布版本的通知！**
+**2. 全面的模型支持**: 
+  与数百种专有/开源LLMs以及数十种推理提供商和自托管解决方案无缝集成，涵盖GPT、Mistral、Llama2以及任何与OpenAI API兼容的模型。完整的支持模型提供商列表可在[此处](https://docs.dify.ai/getting-started/readme/model-providers)找到。
 
-![star-us](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)
+![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
-- [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)
+
+**3. Prompt IDE**: 
+  用于制作提示、比较模型性能以及向基于聊天的应用程序添加其他功能（如文本转语音）的直观界面。
+
+**4. RAG Pipeline**: 
+  广泛的RAG功能，涵盖从文档摄入到检索的所有内容，支持从PDF、PPT和其他常见文档格式中提取文本的开箱即用的支持。
+
+**5. Agent 智能体**: 
+  您可以基于LLM函数调用或ReAct定义代理，并为代理添加预构建或自定义工具。Dify为AI代理提供了50多种内置工具，如谷歌搜索、DELL·E、稳定扩散和WolframAlpha等。
+
+**6. LLMOps**: 
+  随时间监视和分析应用程序日志和性能。您可以根据生产数据和注释持续改进提示、数据集和模型。
+
+**7. 后端即服务**: 
+  所有Dify的功能都带有相应的API，因此您可以轻松地将Dify集成到自己的业务逻辑中。
+
+
+## 功能比较
+<table style="width: 100%;">
+  <tr>
+    <th align="center">功能</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI助理API</th>
+  </tr>
+  <tr>
+    <td align="center">编程方法</td>
+    <td align="center">API + 应用程序导向</td>
+    <td align="center">Python代码</td>
+    <td align="center">应用程序导向</td>
+    <td align="center">API导向</td>
+  </tr>
+  <tr>
+    <td align="center">支持的LLMs</td>
+    <td align="center">丰富多样</td>
+    <td align="center">丰富多样</td>
+    <td align="center">丰富多样</td>
+    <td align="center">仅限OpenAI</td>
+  </tr>
+  <tr>
+    <td align="center">RAG引擎</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">代理</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">工作流程</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">可观察性</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">企业功能（SSO/访问控制）</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">本地部署</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
+
+## 使用 Dify
+
+- **云 </br>**
+我们提供[ Dify 云服务](https://dify.ai)，任何人都可以零设置尝试。它提供了自部署版本的所有功能，并在沙盒计划中包含 200 次免费的 GPT-4 调用。
+
+- **自托管 Dify 社区版</br>**
+使用这个[入门指南](#quick-start)快速在您的环境中运行 Dify。
+使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。
+
+- **面向企业/组织的 Dify</br>**
+我们提供额外的面向企业的功能。[与我们安排会议](https://cal.com/guchenhe/30min)或[给我们发送电子邮件](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)讨论企业需求。 </br>
+  > 对于使用 AWS 的初创公司和中小型企业，请查看 [AWS Marketplace 上的 Dify 高级版](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)，并使用一键部署到您自己的 AWS VPC。它是一个价格实惠的 AMI 产品，提供了使用自定义徽标和品牌创建应用程序的选项。
+
+## 保持领先
+
+在 GitHub 上给 Dify Star，并立即收到新版本的通知。
+
+![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
 
 ## 安装社区版
 
@@ -110,6 +199,19 @@ docker compose up -d
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
 
 
+## Contributing
+
+对于那些想要贡献代码的人，请参阅我们的[贡献指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
+同时，请考虑通过社交媒体、活动和会议来支持Dify的分享。
+
+> 我们正在寻找贡献者来帮助将Dify翻译成除了中文和英文之外的其他语言。如果您有兴趣帮助，请参阅我们的[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)获取更多信息，并在我们的[Discord社区服务器](https://discord.gg/8Tpq4AcN9c)的`global-users`频道中留言。
+
+**Contributors**
+
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
 ## 社区与支持
 
 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。

README_ES.md

@@ -1,119 +1,245 @@
-[![](./images/describe.png)](https://dify.ai)
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
 <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> |
-  <a href="./README_FR.md">Français</a>
+  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
+  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-alojamiento</a> ·
+  <a href="https://docs.dify.ai">Documentación</a> ·
+  <a href="https://cal.com/guchenhe/dify-demo">Programar demostración</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>
+        <img alt="Insignia Estática" src="https://img.shields.io/badge/Producto-F04438"></a>
+    <a href="https://dify.ai/pricing" target="_blank">
+        <img alt="Insignia Estática" src="https://img.shields.io/badge/gratis-precios?logo=gratis&color=%20%23155EEF&label=precios&labelColor=%20%23528bff"></a>
     <a href="https://discord.gg/FngNHpbcY7" target="_blank">
-        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
-            alt="chat on Discord"></a>
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
+            alt="chat en 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>
+        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
+            alt="seguir en 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>
+        <img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
+    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
+        <img alt="Actividad de Commits el último mes" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
+    <a href="https://github.com/langgenius/dify/" target="_blank">
+        <img alt="Issues cerrados" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20cerrados&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
+    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
+        <img alt="Publicaciones de discusión" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
 </p>
 
 <p align="center">
-   <a href="https://dify.ai/blog/dify-ai-unveils-ai-agent-creating-gpts-and-assistants-with-various-llms" target="_blank">
-   Dify.AI Unveils AI Agent: Creating GPTs and Assistants with Various LLMs
-  </a>
+  <a href="./README.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Inglés-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="Actividad de Commits el último mes" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
 </p>
 
-**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.**
+#
 
-![](./images/demo.png)
+<p align="center">
+  <a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+Dify es una plataforma de desarrollo de aplicaciones de LLM de código abierto. Su interfaz intuitiva combina flujo de trabajo de IA, pipeline RAG, capacidades de agente, gestión de modelos, características de observabilidad y más, lo que le permite pasar rápidamente de un prototipo a producción. Aquí hay una lista de las características principales:
+</br> </br>
 
-## Utilizar Servicios en la Nube
+**1. Flujo de trabajo**: 
+  Construye y prueba potentes flujos de trabajo de IA en un lienzo visual, aprovechando todas las siguientes características y más.
 
-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.
 
-## Por qué Dify
+  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
 
-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.
 
-| 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
+**2. Soporte de modelos completo**: 
+  Integración perfecta con cientos de LLMs propietarios / de código abierto de docenas de proveedores de inferencia y soluciones auto-alojadas, que cubren GPT, Mistral, Llama2 y cualquier modelo compatible con la API de OpenAI. Se puede encontrar una lista completa de proveedores de modelos admitidos [aquí](https://docs.dify.ai/getting-started/readme/model-providers).
 
-![](./images/models.png)
+![proveedores-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
-**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. IDE de prompt**: 
+  Interfaz intuitiva para crear prompts, comparar el rendimiento del modelo y agregar características adicionales como texto a voz a una aplicación basada en chat. 
 
-**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. Pipeline RAG**: 
+  Amplias capacidades de RAG que cubren todo, desde la ingestión de documentos hasta la recuperación, con soporte listo para usar para la extracción de texto de PDF, PPT y otros formatos de documento comunes.
 
-**4. Agente de IA**: Basado en la llamada de funciones y ReAct, el marco de inferencia del Agente permite a los usuarios personalizar las herramientas, lo que ves es lo que obtienes. Dify proporciona más de una docena de capacidades de llamada de herramientas incorporadas, como Búsqueda de Google, DELL·E, Difusión Estable, WolframAlpha, etc.
+**5. Capacidades de agente**: 
+  Puedes definir agent
 
-**5. Operaciones Continuas**: Monitorear y analizar registros de aplicaciones y rendimiento, mejorando continuamente Prompts, conjuntos de datos o modelos usando datos de producción.
+es basados en LLM Function Calling o ReAct, y agregar herramientas preconstruidas o personalizadas para el agente. Dify proporciona más de 50 herramientas integradas para agentes de IA, como Búsqueda de Google, DELL·E, Difusión Estable y WolframAlpha.
 
-## Antes de Empezar
+**6. LLMOps**: 
+  Supervisa y analiza registros de aplicaciones y rendimiento a lo largo del tiempo. Podrías mejorar continuamente prompts, conjuntos de datos y modelos basados en datos de producción y anotaciones.
 
-**¡Danos una estrella, y recibirás notificaciones instantáneas de todos los nuevos lanzamientos en GitHub!**
+**7. Backend como servicio**: 
+  Todas las ofertas de Dify vienen con APIs correspondientes, por lo que podrías integrar Dify sin esfuerzo en tu propia lógica empresarial.
 
-![star-us](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)
 
-- [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)
+## Comparación de características
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Característica</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">API de Asistentes de OpenAI</th>
+  </tr>
+  <tr>
+    <td align="center">Enfoque de programación</td>
+    <td align="center">API + orientado a la aplicación</td>
+    <td align="center">Código Python</td>
+    <td align="center">Orientado a la aplicación</td>
+    <td align="center">Orientado a la API</td>
+  </tr>
+  <tr>
+    <td align="center">LLMs admitidos</td>
+    <td align="center">Gran variedad</td>
+    <td align="center">Gran variedad</td>
+    <td align="center">Gran variedad</td>
+    <td align="center">Solo OpenAI</td>
+  </tr>
+  <tr>
+    <td align="center">Motor RAG</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agente</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Flujo de trabajo</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Observabilidad</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Característica empresarial (SSO/Control de acceso)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Implementación local</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
 
-## Instalar la Edición Comunitaria
+## Usando Dify
 
-### Requisitos del Sistema
+- **Nube </br>**
+Hospedamos un servicio [Dify Cloud](https://dify.ai) para que cualquiera lo pruebe sin configuración. Proporciona todas las capacidades de la versión autoimplementada e incluye 200 llamadas gratuitas a GPT-4 en el plan sandbox.
 
-Antes de instalar Dify, asegúrate de que tu máquina cumpla con los siguientes requisitos mínimos del sistema:
+- **Auto-alojamiento de Dify Community Edition</br>**
+Pon rápidamente Dify en funcionamiento en tu entorno con esta [guía de inicio rápido](#quick-start).
+Usa nuestra [documentación](https://docs.dify.ai) para más referencias e instrucciones más detalladas.
 
-- CPU >= 2 núcleos
-- RAM >= 4GB
+- **Dify para Empresas / Organizaciones</br>**
+Proporcionamos características adicionales centradas en la empresa. [Programa una reunión con nosotros](https://cal.com/guchenhe/30min) o [envíanos un correo electrónico](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir las necesidades empresariales. </br>
+  > Para startups y pequeñas empresas que utilizan AWS, echa un vistazo a [Dify Premium en AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e impleméntalo en tu propio VPC de AWS con un clic. Es una AMI asequible que ofrece la opción de crear aplicaciones con logotipo y marca personalizados.
 
-### 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:
+## Manteniéndote al tanto
+
+Dale estrella a Dify en GitHub y serás notificado instantáneamente de las nuevas versiones.
+
+![danos estrella](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
+
+
+
+## Inicio Rápido
+> Antes de instalar Dify, asegúrate de que tu máquina cumpla con los siguientes requisitos mínimos del sistema:
+> 
+>- CPU >= 2 núcleos
+>- RAM >= 4GB
+
+</br>
+
+La forma más fácil de iniciar el servidor de Dify es ejecutar nuestro archivo [docker-compose.yml](docker/docker-compose.yaml). Antes de ejecutar el comando de instalación, asegúrate de que [Docker](https://docs.docker.com/get-docker/) y [Docker Compose](https://docs.docker.com/compose/install/) estén instalados en tu máquina:
 
 ```bash
 cd docker
 docker compose up -d
 ```
 
-Después de ejecutarlo, puedes acceder al panel de control de Dify en tu navegador en [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 inicialización.
 
-### Gráfico Helm
+> Si deseas contribuir a Dify o realizar desarrollo adicional, consulta nuestra [guía para implementar desde el código fuente](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
 
-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.
+## Próximos pasos
 
-### 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
 
-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).
+. Después de realizar los cambios, ejecuta `docker-compose up -d` nuevamente. Puedes ver la lista completa de variables de entorno [aquí](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+
+Si deseas configurar una instalación altamente disponible, hay [Gráficos Helm](https://helm.sh/) contribuidos por la comunidad que permiten implementar Dify en Kubernetes.
+
+- [Gráfico Helm por @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
+- [Gráfico Helm por @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+
+
+## Contribuir
+
+Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
+Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en eventos y conferencias.
+
+
+> Estamos buscando colaboradores para ayudar con la traducción de Dify a idiomas que no sean el mandarín o el inglés. Si estás interesado en ayudar, consulta el [README de i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) para obtener más información y déjanos un comentario en el canal `global-users` de nuestro [Servidor de Comunidad en Discord](https://discord.gg/8Tpq4AcN9c).
+
+**Contribuidores**
+
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
+## Comunidad y Contacto
+
+* [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas.
+* [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
+* [Correo electrónico](mailto:support@dify.ai?subject=[GitHub]Questions%20About%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 pasar el rato con la comunidad.
+* [Twitter](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
+
+O, programa una reunión directamente con un miembro del equipo:
+
+<table>
+  <tr>
+    <th>Punto de Contacto</th>
+    <th>Propósito</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Consultas comerciales y retroalimentación del producto</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contribuciones, problemas y solicitudes de características</td>
+  </tr>
+</table>
 
 ## 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)
 
-## Comunidad y Soporte
-
-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.
-
-- [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.
 
 ## Divulgación de Seguridad
 
@@ -121,4 +247,4 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
 
 ## Licencia
 
-Este repositorio está disponible bajo la [Licencia de Código Abierto Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
+Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.

README_FR.md

@@ -1,127 +1,250 @@
-[![](./images/describe.png)](https://dify.ai)
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
 <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> |
-  <a href="./README_FR.md">Français</a>
+  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
+  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-hébergement</a> ·
+  <a href="https://docs.dify.ai">Documentation</a> ·
+  <a href="https://cal.com/guchenhe/dify-demo">Planifier une démo</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>
+        <img alt="Badge statique" src="https://img.shields.io/badge/Produit-F04438"></a>
+    <a href="https://dify.ai/pricing" target="_blank">
+        <img alt="Badge statique" src="https://img.shields.io/badge/gratuit-Tarification?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
     <a href="https://discord.gg/FngNHpbcY7" target="_blank">
-        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
-            alt="chat on Discord"></a>
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
+            alt="chat sur 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>
+        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
+            alt="suivre sur 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>
+        <img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
+    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
+        <img alt="Commits le mois dernier" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
+    <a href="https://github.com/langgenius/dify/" target="_blank">
+        <img alt="Problèmes fermés" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
+    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
+        <img alt="Messages de discussion" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
 </p>
 
 <p align="center">
-   <a href="https://dify.ai/blog/dify-ai-unveils-ai-agent-creating-gpts-and-assistants-with-various-llms" target="_blank">
-   Dify.AI Unveils AI Agent: Creating GPTs and Assistants with Various LLMs
-  </a>
+  <a href="./README.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Anglais-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="Commits le mois dernier" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
 </p>
 
+#
 
-**Dify** est une plateforme de développement d'applications LLM qui a déjà vu plus de **100,000** applications construites sur Dify.AI. Elle intègre les concepts de Backend as a Service et LLMOps, couvrant la pile technologique de base requise pour construire des applications natives d'IA générative, y compris un moteur RAG intégré. Avec Dify, **vous pouvez auto-déployer des capacités similaires aux API Assistants et GPT basées sur n'importe quels LLM.**
+<p align="center">
+  <a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+Dify est une plateforme de développement d'applications LLM open source. Son interface intuitive combine un flux de travail d'IA, un pipeline RAG, des capacités d'agent, une gestion de modèles, des fonctionnalités d'observabilité, et plus encore, vous permettant de passer rapidement du prototype à la production. Voici une liste des fonctionnalités principales:
+</br> </br>
 
-![](./images/demo.png)
-
-## Utiliser les services cloud  
-
-L'utilisation de [Dify.AI Cloud](https://dify.ai) fournit toutes les capacités de la version open source, et comprend un essai gratuit de 200 crédits GPT.
-
-## Pourquoi Dify
-
-Dify présente une neutralité de modèle et est une pile technologique complète et conçue par rapport à des bibliothèques de développement codées en dur comme LangChain. Contrairement à l'API Assistants d'OpenAI, Dify permet un déploiement local complet des services.
-
-| Fonctionnalité | Dify.AI | API Assistants | LangChain |
-|---------------|----------|-----------------|------------|
-| **Approche de programmation** | Orientée API | Orientée API | Orientée code Python |  
-| **Stratégie écosystème** | Open source | Fermé et commercial | Open source |
-| **Moteur RAG** | Pris en charge | Pris en charge | Non pris en charge |
-| **IDE d'invite** | Inclus | Inclus | Aucun |
-| **LLM pris en charge** | Grande variété | Seulement GPT | Grande variété |
-| **Déploiement local** | Pris en charge | Non pris en charge | Non applicable |
-
- ## Fonctionnalités  
-
-![](./images/models.png)
-
-**1\. Support LLM**: Intégration avec la famille de modèles GPT d'OpenAI, ou les modèles de la famille open source Llama2. En fait, Dify prend en charge les modèles commerciaux grand public et les modèles open source (déployés localement ou basés sur MaaS).  
-
-**2\. IDE d'invite**: Orchestration visuelle d'applications et de services basés sur LLMs avec votre équipe.  
-
-**3\. Moteur RAG**: Comprend diverses capacités RAG basées sur l'indexation de texte intégral ou les embeddings de base de données vectorielles, permettant le chargement direct de PDF, TXT et autres formats de texte.
-
-**4\. AI Agent**: Basé sur l'appel de fonction et ReAct, le framework d'inférence de l'Agent permet aux utilisateurs de personnaliser les outils, ce que vous voyez est ce que vous obtenez. Dify propose plus d'une douzaine de capacités d'appel d'outils intégrées, telles que la recherche Google, DELL·E, Diffusion Stable, WolframAlpha, etc.
-
-**5\. Opérations continues**: Surveillez et analysez les journaux et les performances des applications, améliorez en continu les invites, les datasets ou les modèles à l'aide de données de production.  
-
-## Avant de commencer
-
-**Étoilez-nous, et vous recevrez des notifications instantanées pour toutes les nouvelles sorties sur GitHub !**
-![star-us](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)
-
-- [Site web](https://dify.ai)  
-- [Documentation](https://docs.dify.ai)  
-- [Documentation de déploiement](https://docs.dify.ai/getting-started/install-self-hosted)   
-- [FAQ](https://docs.dify.ai/getting-started/faq)  
+**1. Flux de travail**: 
+  Construisez et testez des flux de travail d'IA puissants sur un canevas visuel, en utilisant toutes les fonctionnalités suivantes et plus encore.
 
 
-## Installer la version Communauté  
+  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
 
-### Configuration système  
 
-Avant d'installer Dify, assurez-vous que votre machine répond aux exigences minimales suivantes:  
 
-- CPU >= 2 cœurs
-- RAM >= 4 Go 
+**2. Prise en charge complète des modèles**: 
+  Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama2, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers).
 
-### Démarrage rapide 
+![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
-La façon la plus simple de démarrer le serveur Dify est d'exécuter notre fichier [docker-compose.yml](docker/docker-compose.yaml). Avant d'exécuter la commande d'installation, assurez-vous que [Docker](https://docs.docker.com/get-docker/) et [Docker Compose](https://docs.docker.com/compose/install/) sont installés sur votre machine:  
+
+**3. IDE de prompt**: 
+  Interface intuitive pour créer des prompts, comparer les performances des modèles et ajouter des fonctionnalités supplémentaires telles que la synthèse vocale à une application basée sur des chats. 
+
+**4. Pipeline RAG**: 
+  Des capacités RAG étendues qui couvrent tout, de l'ingestion de documents à la récupération, avec un support prêt à l'emploi pour l'extraction de texte à partir de PDF, PPT et autres formats de document courants.
+
+**5. Capac
+
+ités d'agent**: 
+  Vous pouvez définir des agents basés sur l'appel de fonction LLM ou ReAct, et ajouter des outils pré-construits ou personnalisés pour l'agent. Dify fournit plus de 50 outils intégrés pour les agents d'IA, tels que la recherche Google, DELL·E, Stable Diffusion et WolframAlpha.
+
+**6. LLMOps**: 
+  Surveillez et analysez les journaux d'application et les performances au fil du temps. Vous pouvez continuellement améliorer les prompts, les ensembles de données et les modèles en fonction des données de production et des annotations.
+
+**7. Backend-as-a-Service**: 
+  Toutes les offres de Dify sont accompagnées d'API correspondantes, vous permettant d'intégrer facilement Dify dans votre propre logique métier.
+
+
+## Comparaison des fonctionnalités
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Fonctionnalité</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Approche de programmation</td>
+    <td align="center">API + Application</td>
+    <td align="center">Code Python</td>
+    <td align="center">Application</td>
+    <td align="center">API</td>
+  </tr>
+  <tr>
+    <td align="center">LLMs pris en charge</td>
+    <td align="center">Grande variété</td>
+    <td align="center">Grande variété</td>
+    <td align="center">Grande variété</td>
+    <td align="center">Uniquement OpenAI</td>
+  </tr>
+  <tr>
+    <td align="center">Moteur RAG</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Flux de travail</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Observabilité</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Fonctionnalité d'entreprise (SSO/Contrôle d'accès)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Déploiement local</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
+
+## Utiliser Dify
+
+- **Cloud </br>**
+Nous hébergeons un service [Dify Cloud](https://dify.ai) pour que tout le monde puisse l'essayer sans aucune configuration. Il fournit toutes les capacités de la version auto-hébergée et comprend 200 appels GPT-4 gratuits dans le plan bac à sable.
+
+- **Auto-hébergement Dify Community Edition</br>**
+Lancez rapidement Dify dans votre environnement avec ce [guide de démarrage](#quick-start).
+Utilisez notre [documentation](https://docs.dify.ai) pour plus de références et des instructions plus détaillées.
+
+- **Dify pour les entreprises / organisations</br>**
+Nous proposons des fonctionnalités supplémentaires adaptées aux entreprises. [Planifiez une réunion avec nous](https://cal.com/guchenhe/30min) ou [envoyez-nous un e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) pour discuter des besoins de l'entreprise. </br>
+  > Pour les startups et les petites entreprises utilisant AWS, consultez [Dify Premium sur AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) et déployez-le dans votre propre VPC AWS en un clic. C'est une offre AMI abordable avec la possibilité de créer des applications avec un logo et une marque personnalisés.
+
+
+## Rester en avance
+
+Mettez une étoile à Dify sur GitHub et soyez instantanément informé des nouvelles versions.
+
+![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
+
+
+
+## Démarrage rapide
+> Avant d'installer Dify, assurez-vous que votre machine répond aux exigences système minimales suivantes:
+> 
+>- CPU >= 2 cœurs
+>- RAM >= 4 Go
+
+</br>
+
+La manière la plus simple de démarrer le serveur Dify est d'exécuter notre fichier [docker-compose.yml](docker/docker-compose.yaml). Avant d'exécuter la commande d'installation, assurez-vous que [Docker](https://docs.docker.com/get-docker/) et [Docker Compose](https://docs.docker.com/compose/install/) sont installés sur votre machine:
 
 ```bash
 cd docker
 docker compose up -d
 ```
 
-Après l'exécution, vous pouvez accéder au tableau de bord Dify dans votre navigateur à l'adresse [http://localhost/install](http://localhost/install) et démarrer le processus d'installation initiale.  
+Après l'exécution, vous pouvez accéder au tableau de bord Dify dans votre navigateur à [http://localhost/install](http://localhost/install) et commencer le processus d'initialisation.
 
-### Chart Helm 
+> Si vous souhaitez contribuer à Dify ou effectuer un développement supplémentaire, consultez notre [guide de déploiement à partir du code source](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
 
-Un grand merci à @BorisPolonsky pour nous avoir fourni une version [Helm Chart](https://helm.sh/) qui permet le déploiement de Dify sur Kubernetes.
-Vous pouvez accéder à https://github.com/BorisPolonsky/dify-helm pour des informations de déploiement.  
+## Prochaines étapes
 
-### Configuration  
+Si vous devez personnaliser la configuration, veuillez
 
-Si vous avez besoin de personnaliser la configuration, veuillez vous référer aux commentaires de notre fichier [docker-compose.yml](docker/docker-compose.yaml) et définir manuellement la configuration de l'environnement. Après avoir apporté les modifications, veuillez exécuter à nouveau `docker-compose up -d`. Vous trouverez la liste complète des variables d'environnement dans notre [documentation](https://docs.dify.ai/getting-started/install-self-hosted/environments).  
+ vous référer aux commentaires dans notre fichier [docker-compose.yml](docker/docker-compose.yaml) et définir manuellement la configuration de l'environnement. Après avoir apporté les modifications, veuillez exécuter à nouveau `docker-compose up -d`. Vous pouvez voir la liste complète des variables d'environnement [ici](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
-## Historique d'étoiles  
+Si vous souhaitez configurer une installation hautement disponible, il existe des [Helm Charts](https://helm.sh/) contribués par la communauté qui permettent de déployer Dify sur Kubernetes.
 
-[![Diagramme de l'historique des étoiles](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)  
+- [Helm Chart par @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
+- [Helm Chart par @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 
 
-## Communauté & Support  
+## Contribuer
 
-Nous vous invitons à contribuer à Dify pour aider à améliorer Dify de diverses manières, en soumettant du code, des problèmes, de nouvelles idées ou en partageant les applications d'IA intéressantes et utiles que vous avez créées sur la base de Dify. En même temps, nous vous invitons également à partager Dify lors de différents événements, conférences et réseaux sociaux.  
+Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
+Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur les réseaux sociaux et lors d'événements et de conférences.
 
-- [Problèmes GitHub](https://github.com/langgenius/dify/issues). Idéal pour : les bogues et les erreurs que vous rencontrez en utilisant Dify.AI, voir le [Guide de contribution](CONTRIBUTING.md).  
-- [Support par courriel](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify). Idéal pour : les questions que vous avez au sujet de l'utilisation de Dify.AI.   
-- [Discord](https://discord.gg/FngNHpbcY7). Idéal pour : partager vos applications et discuter avec la communauté.   
-- [Twitter](https://twitter.com/dify_ai). Idéal pour : partager vos applications et discuter avec la communauté.
-- [Licence commerciale](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry). Idéal pour : les demandes commerciales de licence de Dify.AI pour un usage commercial.  
 
-## Divulgation de la sécurité  
+> Nous recherchons des contributeurs pour aider à traduire Dify dans des langues autres que le mandarin ou l'anglais. Si vous êtes intéressé à aider, veuillez consulter le [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) pour plus d'informations, et laissez-nous un commentaire dans le canal `global-users` de notre [Serveur communautaire Discord](https://discord.gg/8Tpq4AcN9c).
 
-Pour protéger votre vie privée, veuillez éviter de publier des problèmes de sécurité sur GitHub. Envoyez plutôt vos questions à security@dify.ai et nous vous fournirons une réponse plus détaillée.  
+**Contributeurs**
 
-## Licence  
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
 
-Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement Apache 2.0 avec quelques restrictions supplémentaires.
+## Communauté & Contact
+
+* [Discussion GitHub](https://github.com/langgenius/dify/discussions). Meilleur pour: partager des commentaires et poser des questions.
+* [Problèmes GitHub](https://github.com/langgenius/dify/issues). Meilleur pour: les bogues que vous rencontrez en utilisant Dify.AI et les propositions de fonctionnalités. Consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
+* [E-mail](mailto:support@dify.ai?subject=[GitHub]Questions%20About%20Dify). Meilleur pour: les questions que vous avez sur l'utilisation de Dify.AI.
+* [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté.
+* [Twitter](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
+
+Ou, planifiez directement une réunion avec un membre de l'équipe:
+
+<table>
+  <tr>
+    <th>Point de contact</th>
+    <th>Objectif</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Demandes commerciales & retours produit</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contributions, problèmes & demandes de fonctionnalités</td>
+  </tr>
+</table>
+
+## Historique des étoiles
+
+[![Graphique de l'historique des étoiles](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+
+
+## Divulgation de sécurité
+
+Pour protéger votre vie privée, veuillez éviter de publier des problèmes de sécurité sur GitHub. Au lieu de cela, envoyez vos questions à security@dify.ai et nous vous fournirons une réponse plus détaillée.
+
+## Licence
+
+Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.

README_JA.md

@@ -1,130 +1,249 @@
-[![](./images/describe.png)](https://dify.ai)
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
 <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> |
-  <a href="./README_FR.md">Français</a>
+  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
+  <a href="https://docs.dify.ai/getting-started/install-self-hosted">自己ホスティング</a> ·
+  <a href="https://docs.dify.ai">ドキュメント</a> ·
+  <a href="https://cal.com/guchenhe/dify-demo">デモのスケジュール</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>
+        <img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
+    <a href="https://dify.ai/pricing" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
     <a href="https://discord.gg/FngNHpbcY7" target="_blank">
-        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
-            alt="chat on Discord"></a>
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
+            alt="Discordでチャット"></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>
+        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
+            alt="Twitterでフォロー"></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>
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
+    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
+        <img alt="先月のコミット" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
+    <a href="https://github.com/langgenius/dify/" target="_blank">
+        <img alt="クローズされた問題" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
+    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
+        <img alt="ディスカッション投稿" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
 </p>
 
 <p align="center">
-   <a href="https://dify.ai/blog/dify-ai-unveils-ai-agent-creating-gpts-and-assistants-with-various-llms" target="_blank">
-   Dify.AI Unveils AI Agent: Creating GPTs and Assistants with Various LLMs
-  </a>
+  <a href="./README.md"><img alt="先月のコミット" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="先月のコミット" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="先月のコミット" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="先月のコミット" src="https://img.shields.io/badge/Klingon-d9d9d9"></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。"
+<p align="center">
+  <a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
 
-Please note that translating complex technical terms can sometimes result in slight variations in meaning due to differences in language nuances.
+DifyはオープンソースのLLMアプリケーション開発プラットフォームです。直感的なインターフェースには、AIワークフロー、RAGパイプライン、エージェント機能、モデル管理、観測機能などが組み合わさっており、プロトタイプから本番までの移行を迅速に行うことができます。以下は、主要機能のリストです：
+</br> </br>
 
-![](./images/demo.png)
-
-## クラウドサービスの利用
-
-[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。
-
-## 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 |
-
- ## 機能
-
-![](./images/models.png)
-
-**1\. LLMサポート**: OpenAIのGPTファミリーモデルやLlama2ファミリーのオープンソースモデルとの統合。 実際、Difyは主要な商用モデルとオープンソースモデル(ローカルでデプロイまたはMaaSベース)をサポートしています。
-
-**2\. プロンプトIDE**: チームとのLLMベースのアプリケーションとサービスの視覚的なオーケストレーション。
-
-**3\. RAGエンジン**: フルテキストインデックスまたはベクトルデータベース埋め込みに基づくさまざまなRAG機能を含み、PDF、TXT、その他のテキストフォーマットの直接アップロードを可能にします。
-
-**4. AIエージェント**: 関数呼び出しとReActに基づくAgent推論フレームワークにより、ユーザーはツールをカスタマイズすることができます。Difyは、Google検索、DELL·E、Stable Diffusion、WolframAlphaなど、十数種類の組み込みツール呼び出し機能を提供しています。
-
-**5\. 継続的運用**: アプリケーションログとパフォーマンスを監視および分析し、運用データを使用してプロンプト、データセット、またはモデルを継続的に改善します。
-
-## 開始する前に
-
-**私たちをスターして、GitHub上でのすべての新しいリリースに対する即時通知を受け取ります！**
-
-![私たちをスターして](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)
-
-- [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) 
+**1. ワークフロー**: 
+  ビジュアルキャンバス上で強力なAIワークフローを構築してテストし、以下の機能を活用してプロトタイプを超えることができます。
 
 
-## コミュニティエディションのインストール
+  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
 
-### システム要件
 
-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 >= 2コア
-- RAM >= 4GB
+**2. 網羅的なモデルサポート**: 
+  数百のプロプライエタリ/オープンソースのLLMと、数十の推論プロバイダーおよびセルフホスティングソリューションとのシームレスな統合を提供します。GPT、Mistral、Llama2、およびOpenAI API互換のモデルをカバーします。サポートされているモデルプロバイダーの完全なリストは[こちら](https://docs
 
-### クイックスタート
+.dify.ai/getting-started/readme/model-providers)をご覧ください。
 
-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：
+![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
+
+
+**3. プロンプトIDE**: 
+  チャットベースのアプリにテキスト読み上げなどの追加機能を追加するプロンプトを作成し、モデルのパフォーマンスを比較する直感的なインターフェース。
+
+**4. RAGパイプライン**: 
+  文書の取り込みから取得までをカバーする幅広いRAG機能で、PDF、PPTなどの一般的なドキュメント形式からのテキスト抽出に対するアウトオブボックスのサポートを提供します。
+
+**5. エージェント機能**: 
+  LLM関数呼び出しまたはReActに基づいてエージェントを定義し、エージェント向けの事前構築済みまたはカスタムのツールを追加できます。Difyには、Google検索、DELL·E、Stable Diffusion、WolframAlphaなどのAIエージェント用の50以上の組み込みツールが用意されています。
+
+**6. LLMOps**: 
+  アプリケーションログとパフォーマンスを時間の経過とともにモニタリングおよび分析します。本番データと注釈に基づいて、プロンプト、データセット、およびモデルを継続的に改善できます。
+
+**7. Backend-as-a-Service**: 
+  Difyのすべての提供には、それに対応するAPIが付属しており、独自のビジネスロジックにDifyをシームレスに統合できます。
+
+
+## 機能比較
+<table style="width: 100%;">
+  <tr>
+    <th align="center">機能</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">プログラミングアプローチ</td>
+    <td align="center">API + アプリ指向</td>
+    <td align="center">Pythonコード</td>
+    <td align="center">アプリ指向</td>
+    <td align="center">API指向</td>
+  </tr>
+  <tr>
+    <td align="center">サポートされているLLM</td>
+    <td align="center">豊富なバリエーション</td>
+    <td align="center">豊富なバリエーション</td>
+    <td align="center">豊富なバリエーション</td>
+    <td align="center">OpenAIのみ</td>
+  </tr>
+  <tr>
+    <td align="center">RAGエンジン</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">エージェント</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">ワークフロー</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">観測性</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">エンタープライズ機能（SSO/アクセス制御）</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">ローカル展開</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
+
+## Difyの使用方法
+
+- **クラウド </br>**
+[こちら](https://dify.ai)のDify Cloudサービスを利用して、セットアップが不要で誰でも試すことができます。サンドボックスプランでは、200回の無料のGPT-4呼び出しが含まれています。
+
+- **Dify Community Editionのセルフホスティング</br>**
+この[スターターガイド](#quick-start)を使用して、環境でDifyをすばやく実行できます。
+さらなる参照や詳細な手順については、[ドキュメント](https://docs.dify.ai)をご覧ください。
+
+- **エンタープライズ/組織向けのDify</br>**
+追加のエンタープライズ向け機能を提供しています。[こちらからミーティ
+
+ングを予約](https://cal.com/guchenhe/30min)したり、[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)してエンタープライズのニーズについて相談してください。 </br>
+  > AWSを使用しているスタートアップや中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで独自のAWS VPCにデプロイできます。カスタムロゴとブランディングでアプリを作成するオプションを備えた手頃な価格のAMIオファリングです。
+
+
+## 先を見る
+
+GitHubでDifyにスターを付け、新しいリリースをすぐに通知されます。
+
+![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
+
+
+
+## クイックスタート
+> Difyをインストールする前に、マシンが以下の最小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 >= 2コア
+>- RAM >= 4GB
+
+</br>
+
+Difyサーバーを起動する最も簡単な方法は、当社の[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プロセスを開始できます。
+実行後、ブラウザで[http://localhost/install](http://localhost/install)にアクセスし、初期化プロセスを開始できます。
 
-### Helm Chart
+> Difyに貢献したり、追加の開発を行う場合は、[ソースコードからのデプロイガイド](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)を参照してください。
 
-@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。
+## 次のステップ
 
-### 設定
+環境設定をカスタマイズする場合は、[docker-compose.yml](docker/docker-compose.yaml)ファイル内のコメントを参照して、環境設定を手動で設定してください。変更を加えた後は、再び `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[こちら](https://docs.dify.ai/getting-started/install-self-hosted/environments)をご覧ください。
 
-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。
+高可用性のセットアップを構成する場合は、コミュニティによって提供されている[Helm Charts](https://helm.sh/)があり、これによりKubernetes上にDifyを展開できます。
+
+- [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
+- [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 
 
-## スターヒストリー
+## 貢献
 
-[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)を参照してください。
+同時に、DifyをSNSやイベント、カンファレンスで共有してサポートしていただけると幸いです。
 
-## コミュニティとサポート
 
-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。
+> Difyを英語または中国語以外の言語に翻訳してくれる貢献者を募集しています。興味がある場合は、詳細については[i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md)を参照してください。また、[Discordコミュニティサーバー](https://discord.gg/8Tpq4AcN9c)の`global-users`チャンネルにコメントを残してください。
 
-- [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。
+**貢献者**
 
-## セキュリティ
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
+## コミュニティ & お問い合わせ
+
+* [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
+* [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIの使用中に遭遇したバグや機能提案。
+* [Email](mailto:support@dify.ai?subject=[GitHub]Questions%20About%20Dify). 主に: Dify.AIの使用に関する質問。
+* [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
+* [Twitter](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
+
+または、直接チームメンバーとミーティングをスケジュールします：
+
+<table>
+  <tr>
+    <th>連絡先</th>
+    <th>目的</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com
+
+/guchenhe/30min'>ミーティング</a></td>
+    <td>無料の30分間のミーティングをスケジュールしてください。</td>
+  </tr>
+  <tr>
+    <td><a href='mailto:support@dify.ai?subject=[GitHub]Technical%20Support'>技術サポート</a></td>
+    <td>技術的な問題やサポートに関する質問</td>
+  </tr>
+  <tr>
+    <td><a href='mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry'>営業担当</a></td>
+    <td>法人ライセンスに関するお問い合わせ</td>
+  </tr>
+</table>
 
-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。
 
 ## ライセンス
 
- このリポジトリは、基本的にApache 2.0にいくつかの追加制限を加えた[Difyオープンソースライセンス](LICENSE)の下で利用できます。
+プロジェクトはMITライセンスの下で利用可能です。[LICENSE](LICENSE)をご参照ください。

README_KL.md

@@ -1,119 +1,250 @@
-[![](./images/describe.png)](https://dify.ai)
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
 <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> |
-  <a href="./README_FR.md">Français</a>
+  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
+  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
+  <a href="https://docs.dify.ai">Documentation</a> ·
+  <a href="https://cal.com/guchenhe/dify-demo">Schedule demo</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>
+        <img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
+    <a href="https://dify.ai/pricing" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
     <a href="https://discord.gg/FngNHpbcY7" target="_blank">
-        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord"
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
             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"
+        <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             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>
+        <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
+    <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
+        <img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
+    <a href="https://github.com/langgenius/dify/" target="_blank">
+        <img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
+    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
+        <img alt="Discussion posts" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></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.**
+<p align="center">
+  <a href="./README.md"><img alt="Commits last month" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="Commits last month" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="Commits last month" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="Commits last month" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="Commits last month" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="Commits last month" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+</p>
 
-![](./images/demo.png)
+#
 
-## ngIl QaQ
+<p align="center">
+  <a href="https://trendshift.io/repositories/2152" target="_blank"><img src="https://trendshift.io/api/badge/repositories/2152" alt="langgenius%2Fdify | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. Here's a list of the core features:
+</br> </br>
 
-[Dify.AI ngIl](https://dify.ai) pIm neHlaH 'ej ghaH. cha'logh wa' DIvI' 200 GPT trial credits.
+**1. Workflow**: 
+  Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
 
-## Dify WovmoH
 
-Dify Daq rIn neutrality 'ej Hoch, LangChain tInHar HubwI'. maH Daqbe'law' Qawqar, OpenAI's Assistant API Daq local neH deployment.
+  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
 
-| 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)
+**2. Comprehensive model support**: 
+  Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama2, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
 
-**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).
+![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
-**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.
+**3. Prompt IDE**: 
+  Intuitive interface for crafting prompts, comparing model performance, and adding additional features such as text-to-speech to a chat-based app. 
 
-**4. AI Agent**: Function Calling 'ej ReAct Daq Hurmey, Agent inference framework Hoch users customize tools, vaj 'oH QaQ. Dify Hoch loS ghaH 'ej wa'vatlh built-in tool calling capabilities, Google Search, DELL·E, Stable Diffusion, WolframAlpha, 'ej.
+**4. RAG Pipeline**: 
+  Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats.
 
-**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.
+**5. Agent capabilities**: 
+  You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DELL·E, Stable Diffusion and WolframAlpha.
 
-## Do'wI' qabmey lo'taH
+**6. LLMOps**: 
+  Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations.
 
-**maHvaD jatlhchugh, GitHub Daq Hoch chu' ghompu'vam tIqel yInob!**
+**7. Backend-as-a-Service**: 
+  All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.
 
-![star-us](https://github.com/langgenius/dify/assets/100913391/95f37259-7370-4456-a9f0-0bc01ef8642f)
 
-- [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) 
+## Feature Comparison
+<table style="width: 100%;">
+  <tr
 
-## Community Edition tu' yo'
+>
+    <th align="center">Feature</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programming Approach</td>
+    <td align="center">API + App-oriented</td>
+    <td align="center">Python Code</td>
+    <td align="center">App-oriented</td>
+    <td align="center">API-oriented</td>
+  </tr>
+  <tr>
+    <td align="center">Supported LLMs</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">OpenAI-only</td>
+  </tr>
+  <tr>
+    <td align="center">RAG Engine</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Workflow</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Observability</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Enterprise Feature (SSO/Access control)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Local Deployment</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
 
-### System Qab
+## Using Dify
 
-Dify yo' yo' qaqmeH SuS chenmoH 'oH qech!
+- **Cloud </br>**
+We host a [Dify Cloud](https://dify.ai) service for anyone to try with zero setup. It provides all the capabilities of the self-deployed version, and includes 200 free GPT-4 calls in the sandbox plan.
 
-- CPU >= 2 Cores
-- RAM >= 4GB
+- **Self-hosting Dify Community Edition</br>**
+Quickly get Dify running in your environment with this [starter guide](#quick-start).
+Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.
 
-### Quick Start
+- **Dify for Enterprise / Organizations</br>**
+We provide additional enterprise-centric features. [Schedule a meeting with us](https://cal.com/guchenhe/30min) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
+  > For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
 
-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:
+
+## Staying ahead
+
+Star Dify on GitHub and be instantly notified of new releases.
+
+![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
+
+
+
+## Quick Start
+> Before installing Dify, make sure your machine meets the following minimum system requirements:
+> 
+>- CPU >= 2 Core
+>- RAM >= 4GB
+
+</br>
+
+The easiest way to start the Dify server is to run our [docker-compose.yml](docker/docker-compose.yaml) file. Before running the installation command, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
 
 ```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.
+After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process.
 
-### Helm Chart
+> If you'd like to contribute to Dify or do additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
 
-@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.
+## Next steps
 
-### veS config
+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 [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
-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).
+If you'd like to configure a highly-available setup, there are community-contributed [Helm Charts](https://helm.sh/) which allow Dify to be deployed on Kubernetes.
 
-## tIng qem
+- [Helm Chart by @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
+- [Helm Chart by @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
 
-[![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
+## Contributing
 
-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'.
+For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
+At the same time, please consider supporting Dify by sharing it on social media and at events and conferences.
 
-- [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
+> We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
 
-taghlI' vIngeH'a'? pong security 'oH posting GitHub. yItlhutlh, toH security@dify.ai 'ej vIngeH'a'.
+**Contributors**
+
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
+## Community & Contact
+
+* [Github Discussion](https://github.com/langgenius/dify/discussions
+
+). Best for: sharing feedback and asking questions.
+* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
+* [Email](mailto:support@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.
+
+Or, schedule a meeting directly with a team member:
+
+<table>
+  <tr>
+    <th>Point of Contact</th>
+    <th>Purpose</th>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Business enquiries & product feedback</td>
+  </tr>
+  <tr>
+    <td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
+    <td>Contributions, issues & feature requests</td>
+  </tr>
+</table>
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+
+
+## 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.
 
 ## License
 
-ghItlh puqloD chenmoH [Dify vItlhutlh Hur](LICENSE), ghaH nIvbogh Apache 2.0.
-
+This repository is available under the [Dify Open Source License](LICENSE), which is essentially Apache 2.0 with a few additional restrictions.

api/.env.example

@@ -57,7 +57,7 @@ AZURE_BLOB_ACCOUNT_URL=https://<your_account_name>.blob.core.windows.net
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
-# Vector database configuration, support: weaviate, qdrant, milvus
+# Vector database configuration, support: weaviate, qdrant, milvus, relyt
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -78,6 +78,13 @@ MILVUS_USER=root
 MILVUS_PASSWORD=Milvus
 MILVUS_SECURE=false
 
+# Relyt configuration
+RELYT_HOST=127.0.0.1
+RELYT_PORT=5432
+RELYT_USER=postgres
+RELYT_PASSWORD=postgres
+RELYT_DATABASE=postgres
+
 # Upload configuration
 UPLOAD_FILE_SIZE_LIMIT=15
 UPLOAD_FILE_BATCH_LIMIT=5
@@ -149,3 +156,7 @@ TEMPLATE_TRANSFORM_MAX_LENGTH=80000
 CODE_MAX_STRING_ARRAY_LENGTH=30
 CODE_MAX_OBJECT_ARRAY_LENGTH=30
 CODE_MAX_NUMBER_ARRAY_LENGTH=1000
+
+# API Tool configuration
+API_TOOL_DEFAULT_CONNECT_TIMEOUT=10
+API_TOOL_DEFAULT_READ_TIMEOUT=60

api/Dockerfile

@@ -11,7 +11,8 @@ RUN apt-get update \
 
 COPY requirements.txt /requirements.txt
 
-RUN pip install --prefix=/pkg -r requirements.txt
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install --prefix=/pkg -r requirements.txt
 
 # production stage
 FROM base AS production

api/README.md

@@ -17,16 +17,16 @@
    ```bash
    sed -i "/^SECRET_KEY=/c\SECRET_KEY=$(openssl rand -base64 42)" .env
    ```
-3.5 If you use Anaconda, create a new environment and activate it
+4. If you use Anaconda, create a new environment and activate it
    ```bash
    conda create --name dify python=3.10
    conda activate dify
    ```
-4. Install dependencies
+5. Install dependencies
    ```bash
    pip install -r requirements.txt
    ```
-5. Run migrate
+6. Run migrate
 
    Before the first launch, migrate the database to the latest version.
 
@@ -47,9 +47,11 @@
    pip install -r requirements.txt --upgrade --force-reinstall
    ```
 
-6. Start backend:
+7. Start backend:
    ```bash
    flask run --host 0.0.0.0 --port=5001 --debug
    ```
-7. Setup your application by visiting http://localhost:5001/console/api/setup or other apis...
-8. If you need to debug local async processing, you can run `celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail`, celery can do dataset importing and other async tasks.
+8. Setup your application by visiting http://localhost:5001/console/api/setup or other apis...
+9. If you need to debug local async processing, please start the worker service by running 
+`celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail`.
+The started celery app handles the async tasks, e.g. dataset importing and documents indexing.

api/app.py

@@ -1,16 +1,13 @@
 import os
 
-from werkzeug.exceptions import Unauthorized
-
 if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
     from gevent import monkey
+
     monkey.patch_all()
     # if os.environ.get("VECTOR_STORE") == 'milvus':
     import grpc.experimental.gevent
-    grpc.experimental.gevent.init_gevent()
 
-    import langchain
-    langchain.verbose = True
+    grpc.experimental.gevent.init_gevent()
 
 import json
 import logging
@@ -21,6 +18,7 @@ import warnings
 from flask import Flask, Response, request
 from flask_cors import CORS
 
+from werkzeug.exceptions import Unauthorized
 from commands import register_commands
 from config import CloudEditionConfig, Config
 from extensions import (
@@ -44,6 +42,7 @@ from services.account_service import AccountService
 # DO NOT REMOVE BELOW
 from events import event_handlers
 from models import account, dataset, model, source, task, tool, tools, web
+
 # DO NOT REMOVE ABOVE
 
 
@@ -51,7 +50,7 @@ warnings.simplefilter("ignore", ResourceWarning)
 
 # fix windows platform
 if os.name == "nt":
-    os.system('tzutil /s "UTC"')    
+    os.system('tzutil /s "UTC"')
 else:
     os.environ['TZ'] = 'UTC'
     time.tzset()
@@ -60,6 +59,7 @@ else:
 class DifyApp(Flask):
     pass
 
+
 # -------------
 # Configuration
 # -------------
@@ -67,6 +67,7 @@ class DifyApp(Flask):
 
 config_type = os.getenv('EDITION', default='SELF_HOSTED')  # ce edition first
 
+
 # ----------------------------
 # Application Factory Function
 # ----------------------------
@@ -192,7 +193,6 @@ def register_blueprints(app):
 app = create_app()
 celery = app.extensions["celery"]
 
-
 if app.config['TESTING']:
     print("App is running in TESTING mode")
 

api/commands.py

@@ -297,6 +297,14 @@ def migrate_knowledge_vector_database():
                         "vector_store": {"class_prefix": collection_name}
                     }
                     dataset.index_struct = json.dumps(index_struct_dict)
+                elif vector_type == "relyt":
+                    dataset_id = dataset.id
+                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
+                    index_struct_dict = {
+                        "type": 'relyt',
+                        "vector_store": {"class_prefix": collection_name}
+                    }
+                    dataset.index_struct = json.dumps(index_struct_dict)
                 else:
                     raise ValueError(f"Vector store {config.get('VECTOR_STORE')} is not supported.")
 

api/config.py

@@ -42,7 +42,7 @@ DEFAULTS = {
     'HOSTED_OPENAI_TRIAL_ENABLED': 'False',
     'HOSTED_OPENAI_TRIAL_MODELS': 'gpt-3.5-turbo,gpt-3.5-turbo-1106,gpt-3.5-turbo-instruct,gpt-3.5-turbo-16k,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-0613,gpt-3.5-turbo-0125,text-davinci-003',
     'HOSTED_OPENAI_PAID_ENABLED': 'False',
-    'HOSTED_OPENAI_PAID_MODELS': 'gpt-4,gpt-4-turbo-preview,gpt-4-1106-preview,gpt-4-0125-preview,gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-1106,gpt-3.5-turbo-0613,gpt-3.5-turbo-0125,gpt-3.5-turbo-instruct,text-davinci-003',
+    'HOSTED_OPENAI_PAID_MODELS': 'gpt-4,gpt-4-turbo-preview,gpt-4-turbo-2024-04-09,gpt-4-1106-preview,gpt-4-0125-preview,gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-1106,gpt-3.5-turbo-0613,gpt-3.5-turbo-0125,gpt-3.5-turbo-instruct,text-davinci-003',
     'HOSTED_AZURE_OPENAI_ENABLED': 'False',
     'HOSTED_AZURE_OPENAI_QUOTA_LIMIT': 200,
     'HOSTED_ANTHROPIC_QUOTA_LIMIT': 600000,
@@ -64,9 +64,10 @@ DEFAULTS = {
     'ETL_TYPE': 'dify',
     'KEYWORD_STORE': 'jieba',
     'BATCH_UPLOAD_LIMIT': 20,
-    'CODE_EXECUTION_ENDPOINT': '',
-    'CODE_EXECUTION_API_KEY': '',
+    'CODE_EXECUTION_ENDPOINT': 'http://sandbox:8194',
+    'CODE_EXECUTION_API_KEY': 'dify-sandbox',
     'TOOL_ICON_CACHE_MAX_AGE': 3600,
+    'MILVUS_DATABASE': 'default',
     'KEYWORD_DATA_SOURCE_TYPE': 'database',
 }
 
@@ -98,7 +99,7 @@ class Config:
         # ------------------------
         # General Configurations.
         # ------------------------
-        self.CURRENT_VERSION = "0.6.0-fix1"
+        self.CURRENT_VERSION = "0.6.3"
         self.COMMIT_SHA = get_env('COMMIT_SHA')
         self.EDITION = "SELF_HOSTED"
         self.DEPLOY_ENV = get_env('DEPLOY_ENV')
@@ -197,7 +198,7 @@ class Config:
 
         # ------------------------
         # Vector Store Configurations.
-        # Currently, only support: qdrant, milvus, zilliz, weaviate
+        # Currently, only support: qdrant, milvus, zilliz, weaviate, relyt
         # ------------------------
         self.VECTOR_STORE = get_env('VECTOR_STORE')
         self.KEYWORD_STORE = get_env('KEYWORD_STORE')
@@ -212,6 +213,7 @@ class Config:
         self.MILVUS_USER = get_env('MILVUS_USER')
         self.MILVUS_PASSWORD = get_env('MILVUS_PASSWORD')
         self.MILVUS_SECURE = get_env('MILVUS_SECURE')
+        self.MILVUS_DATABASE = get_env('MILVUS_DATABASE')
 
         # weaviate settings
         self.WEAVIATE_ENDPOINT = get_env('WEAVIATE_ENDPOINT')
@@ -219,6 +221,13 @@ class Config:
         self.WEAVIATE_GRPC_ENABLED = get_bool_env('WEAVIATE_GRPC_ENABLED')
         self.WEAVIATE_BATCH_SIZE = int(get_env('WEAVIATE_BATCH_SIZE'))
 
+        # relyt settings
+        self.RELYT_HOST = get_env('RELYT_HOST')
+        self.RELYT_PORT = get_env('RELYT_PORT')
+        self.RELYT_USER = get_env('RELYT_USER')
+        self.RELYT_PASSWORD = get_env('RELYT_PASSWORD')
+        self.RELYT_DATABASE = get_env('RELYT_DATABASE')
+
         # ------------------------
         # Mail Configurations.
         # ------------------------

api/controllers/console/app/conversation.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timezone
 
 import pytz
 from flask_login import current_user
@@ -262,7 +262,7 @@ def _get_conversation(app_model, conversation_id):
         raise NotFound("Conversation Not Exists.")
 
     if not conversation.read_at:
-        conversation.read_at = datetime.utcnow()
+        conversation.read_at = datetime.now(timezone.utc).replace(tzinfo=None)
         conversation.read_account_id = current_user.id
         db.session.commit()
 

api/controllers/console/auth/activate.py

@@ -1,6 +1,6 @@
 import base64
+import datetime
 import secrets
-from datetime import datetime
 
 from flask_restful import Resource, reqparse
 
@@ -66,7 +66,7 @@ class ActivateApi(Resource):
         account.timezone = args['timezone']
         account.interface_theme = 'light'
         account.status = AccountStatus.ACTIVE.value
-        account.initialized_at = datetime.utcnow()
+        account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
         return {'result': 'success'}

api/controllers/console/auth/oauth.py

@@ -1,5 +1,5 @@
 import logging
-from datetime import datetime
+from datetime import datetime, timezone
 from typing import Optional
 
 import requests
@@ -73,7 +73,7 @@ class OAuthCallback(Resource):
 
         if account.status == AccountStatus.PENDING.value:
             account.status = AccountStatus.ACTIVE.value
-            account.initialized_at = datetime.utcnow()
+            account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
         TenantService.create_owner_tenant_if_not_exist(account)

api/controllers/console/datasets/data_source.py

@@ -80,7 +80,7 @@ class DataSourceApi(Resource):
         if action == 'enable':
             if data_source_binding.disabled:
                 data_source_binding.disabled = False
-                data_source_binding.updated_at = datetime.datetime.utcnow()
+                data_source_binding.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
                 db.session.add(data_source_binding)
                 db.session.commit()
             else:
@@ -89,7 +89,7 @@ class DataSourceApi(Resource):
         if action == 'disable':
             if not data_source_binding.disabled:
                 data_source_binding.disabled = True
-                data_source_binding.updated_at = datetime.datetime.utcnow()
+                data_source_binding.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
                 db.session.add(data_source_binding)
                 db.session.commit()
             else:

api/controllers/console/datasets/datasets_document.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timezone
 
 from flask import request
 from flask_login import current_user
@@ -637,7 +637,7 @@ class DocumentProcessingApi(DocumentResource):
                 raise InvalidActionError('Document not in indexing state.')
 
             document.paused_by = current_user.id
-            document.paused_at = datetime.utcnow()
+            document.paused_at = datetime.now(timezone.utc).replace(tzinfo=None)
             document.is_paused = True
             db.session.commit()
 
@@ -717,7 +717,7 @@ class DocumentMetadataApi(DocumentResource):
                     document.doc_metadata[key] = value
 
         document.doc_type = doc_type
-        document.updated_at = datetime.utcnow()
+        document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
         return {'result': 'success', 'message': 'Document metadata updated.'}, 200
@@ -755,7 +755,7 @@ class DocumentStatusApi(DocumentResource):
             document.enabled = True
             document.disabled_at = None
             document.disabled_by = None
-            document.updated_at = datetime.utcnow()
+            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -772,9 +772,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError('Document already disabled.')
 
             document.enabled = False
-            document.disabled_at = datetime.utcnow()
+            document.disabled_at = datetime.now(timezone.utc).replace(tzinfo=None)
             document.disabled_by = current_user.id
-            document.updated_at = datetime.utcnow()
+            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times
@@ -789,9 +789,9 @@ class DocumentStatusApi(DocumentResource):
                 raise InvalidActionError('Document already archived.')
 
             document.archived = True
-            document.archived_at = datetime.utcnow()
+            document.archived_at = datetime.now(timezone.utc).replace(tzinfo=None)
             document.archived_by = current_user.id
-            document.updated_at = datetime.utcnow()
+            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
             if document.enabled:
@@ -808,7 +808,7 @@ class DocumentStatusApi(DocumentResource):
             document.archived = False
             document.archived_at = None
             document.archived_by = None
-            document.updated_at = datetime.utcnow()
+            document.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
             # Set cache to prevent indexing the same document multiple times

api/controllers/console/datasets/datasets_segments.py

@@ -1,5 +1,5 @@
 import uuid
-from datetime import datetime
+from datetime import datetime, timezone
 
 import pandas as pd
 from flask import request
@@ -192,7 +192,7 @@ class DatasetDocumentSegmentApi(Resource):
                 raise InvalidActionError("Segment is already disabled.")
 
             segment.enabled = False
-            segment.disabled_at = datetime.utcnow()
+            segment.disabled_at = datetime.now(timezone.utc).replace(tzinfo=None)
             segment.disabled_by = current_user.id
             db.session.commit()
 

api/controllers/console/explore/completion.py

@@ -1,5 +1,5 @@
 import logging
-from datetime import datetime
+from datetime import datetime, timezone
 
 from flask_login import current_user
 from flask_restful import reqparse
@@ -47,7 +47,7 @@ class CompletionApi(InstalledAppResource):
         streaming = args['response_mode'] == 'streaming'
         args['auto_generate_name'] = False
 
-        installed_app.last_used_at = datetime.utcnow()
+        installed_app.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
         try:
@@ -110,7 +110,7 @@ class ChatApi(InstalledAppResource):
 
         args['auto_generate_name'] = False
 
-        installed_app.last_used_at = datetime.utcnow()
+        installed_app.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
         try:

api/controllers/console/explore/conversation.py

@@ -6,6 +6,7 @@ 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 core.app.entities.app_invoke_entities import InvokeFrom
 from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import uuid_value
 from models.model import AppMode
@@ -39,8 +40,8 @@ class ConversationListApi(InstalledAppResource):
                 user=current_user,
                 last_id=args['last_id'],
                 limit=args['limit'],
+                invoke_from=InvokeFrom.EXPLORE,
                 pinned=pinned,
-                exclude_debug_conversation=True
             )
         except LastConversationNotExistsError:
             raise NotFound("Last Conversation Not Exists.")

api/controllers/console/explore/installed_app.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+from datetime import datetime, timezone
 
 from flask_login import current_user
 from flask_restful import Resource, inputs, marshal_with, reqparse
@@ -81,7 +81,7 @@ class InstalledAppsListApi(Resource):
                 tenant_id=current_tenant_id,
                 app_owner_tenant_id=app.tenant_id,
                 is_pinned=False,
-                last_used_at=datetime.utcnow()
+                last_used_at=datetime.now(timezone.utc).replace(tzinfo=None)
             )
             db.session.add(new_installed_app)
             db.session.commit()

api/controllers/console/workspace/account.py

@@ -1,4 +1,4 @@
-from datetime import datetime
+import datetime
 
 import pytz
 from flask import current_app, request
@@ -59,7 +59,7 @@ class AccountInitApi(Resource):
                 raise InvalidInvitationCodeError()
 
             invitation_code.status = 'used'
-            invitation_code.used_at = datetime.utcnow()
+            invitation_code.used_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             invitation_code.used_by_tenant_id = account.current_tenant_id
             invitation_code.used_by_account_id = account.id
 
@@ -67,7 +67,7 @@ class AccountInitApi(Resource):
         account.timezone = args['timezone']
         account.interface_theme = 'light'
         account.status = 'active'
-        account.initialized_at = datetime.utcnow()
+        account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
         db.session.commit()
 
         return {'result': 'success'}

api/controllers/service_api/app/app.py

@@ -1,14 +1,11 @@
-import json
 
 from flask import current_app
-from flask_restful import fields, marshal_with, Resource
+from flask_restful import Resource, fields, marshal_with
 
 from controllers.service_api import api
 from controllers.service_api.app.error import AppUnavailableError
 from controllers.service_api.wraps import validate_app_token
-from extensions.ext_database import db
-from models.model import App, AppModelConfig, AppMode
-from models.tools import ApiToolProvider
+from models.model import App, AppMode
 from services.app_service import AppService
 
 
@@ -92,6 +89,16 @@ class AppMetaApi(Resource):
         """Get app meta"""
         return AppService().get_app_meta(app_model)
 
+class AppInfoApi(Resource):
+    @validate_app_token
+    def get(self, app_model: App):
+        """Get app infomation"""
+        return {
+            'name':app_model.name,
+            'description':app_model.description
+        } 
+
 
 api.add_resource(AppParameterApi, '/parameters')
 api.add_resource(AppMetaApi, '/meta')
+api.add_resource(AppInfoApi, '/info')

api/controllers/service_api/app/conversation.py

@@ -6,6 +6,7 @@ import services
 from controllers.service_api import api
 from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
+from core.app.entities.app_invoke_entities import InvokeFrom
 from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import uuid_value
 from models.model import App, AppMode, EndUser
@@ -27,7 +28,13 @@ class ConversationApi(Resource):
         args = parser.parse_args()
 
         try:
-            return ConversationService.pagination_by_last_id(app_model, end_user, args['last_id'], args['limit'])
+            return ConversationService.pagination_by_last_id(
+                app_model=app_model,
+                user=end_user,
+                last_id=args['last_id'],
+                limit=args['limit'],
+                invoke_from=InvokeFrom.SERVICE_API
+            )
         except services.errors.conversation.LastConversationNotExistsError:
             raise NotFound("Last Conversation Not Exists.")
 

api/controllers/service_api/wraps.py

@@ -1,5 +1,5 @@
 from collections.abc import Callable
-from datetime import datetime
+from datetime import datetime, timezone
 from enum import Enum
 from functools import wraps
 from typing import Optional
@@ -183,7 +183,7 @@ def validate_and_get_api_token(scope=None):
     if not api_token:
         raise Unauthorized("Access token is invalid")
 
-    api_token.last_used_at = datetime.utcnow()
+    api_token.last_used_at = datetime.now(timezone.utc).replace(tzinfo=None)
     db.session.commit()
 
     return api_token

api/controllers/web/conversation.py

@@ -5,6 +5,7 @@ from werkzeug.exceptions import NotFound
 from controllers.web import api
 from controllers.web.error import NotChatAppError
 from controllers.web.wraps import WebApiResource
+from core.app.entities.app_invoke_entities import InvokeFrom
 from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import uuid_value
 from models.model import AppMode
@@ -37,7 +38,8 @@ class ConversationListApi(WebApiResource):
                 user=end_user,
                 last_id=args['last_id'],
                 limit=args['limit'],
-                pinned=pinned
+                invoke_from=InvokeFrom.WEB_APP,
+                pinned=pinned,
             )
         except LastConversationNotExistsError:
             raise NotFound("Last Conversation Not Exists.")

api/core/agent/base_agent_runner.py

@@ -1,10 +1,11 @@
 import json
 import logging
 import uuid
-from datetime import datetime
+from datetime import datetime, timezone
 from typing import Optional, Union, cast
 
 from core.agent.entities import AgentEntity, AgentToolEntity
+from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfig
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.apps.base_app_runner import AppRunner
@@ -14,6 +15,7 @@ from core.app.entities.app_invoke_entities import (
 )
 from core.callback_handler.agent_tool_callback_handler import DifyAgentCallbackHandler
 from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
+from core.file.message_file_parser import MessageFileParser
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.llm_entities import LLMUsage
@@ -22,6 +24,7 @@ from core.model_runtime.entities.message_entities import (
     PromptMessage,
     PromptMessageTool,
     SystemPromptMessage,
+    TextPromptMessageContent,
     ToolPromptMessage,
     UserPromptMessage,
 )
@@ -37,7 +40,7 @@ from core.tools.tool.dataset_retriever_tool import DatasetRetrieverTool
 from core.tools.tool.tool import Tool
 from core.tools.tool_manager import ToolManager
 from extensions.ext_database import db
-from models.model import Message, MessageAgentThought
+from models.model import Conversation, Message, MessageAgentThought
 from models.tools import ToolConversationVariables
 
 logger = logging.getLogger(__name__)
@@ -45,6 +48,7 @@ logger = logging.getLogger(__name__)
 class BaseAgentRunner(AppRunner):
     def __init__(self, tenant_id: str,
                  application_generate_entity: AgentChatAppGenerateEntity,
+                 conversation: Conversation,
                  app_config: AgentChatAppConfig,
                  model_config: ModelConfigWithCredentialsEntity,
                  config: AgentEntity,
@@ -72,6 +76,7 @@ class BaseAgentRunner(AppRunner):
         """
         self.tenant_id = tenant_id
         self.application_generate_entity = application_generate_entity
+        self.conversation = conversation
         self.app_config = app_config
         self.model_config = model_config
         self.config = config
@@ -118,6 +123,12 @@ class BaseAgentRunner(AppRunner):
         else:
             self.stream_tool_call = False
 
+        # check if model supports vision
+        if model_schema and ModelFeature.VISION in (model_schema.features or []):
+            self.files = application_generate_entity.files
+        else:
+            self.files = []
+
     def _repack_app_generate_entity(self, app_generate_entity: AgentChatAppGenerateEntity) \
             -> AgentChatAppGenerateEntity:
         """
@@ -227,6 +238,34 @@ class BaseAgentRunner(AppRunner):
 
         return prompt_tool
     
+    def _init_prompt_tools(self) -> tuple[dict[str, Tool], list[PromptMessageTool]]:
+        """
+        Init tools
+        """
+        tool_instances = {}
+        prompt_messages_tools = []
+
+        for tool in self.app_config.agent.tools if self.app_config.agent else []:
+            try:
+                prompt_tool, tool_entity = self._convert_tool_to_prompt_message_tool(tool)
+            except Exception:
+                # api tool may be deleted
+                continue
+            # save tool entity
+            tool_instances[tool.tool_name] = tool_entity
+            # save prompt tool
+            prompt_messages_tools.append(prompt_tool)
+
+        # convert dataset tools into ModelRuntime Tool format
+        for dataset_tool in self.dataset_tools:
+            prompt_tool = self._convert_dataset_retriever_tool_to_prompt_message_tool(dataset_tool)
+            # save prompt tool
+            prompt_messages_tools.append(prompt_tool)
+            # save tool entity
+            tool_instances[dataset_tool.identity.name] = dataset_tool
+
+        return tool_instances, prompt_messages_tools
+
     def update_prompt_message_tool(self, tool: Tool, prompt_tool: PromptMessageTool) -> PromptMessageTool:
         """
         update prompt message tool
@@ -314,7 +353,7 @@ class BaseAgentRunner(AppRunner):
                            tool_name: str,
                            tool_input: Union[str, dict],
                            thought: str, 
-                           observation: Union[str, str], 
+                           observation: Union[str, dict], 
                            tool_invoke_meta: Union[str, dict],
                            answer: str,
                            messages_ids: list[str],
@@ -401,7 +440,7 @@ class BaseAgentRunner(AppRunner):
             ToolConversationVariables.conversation_id == self.message.conversation_id,
         ).first()
 
-        db_variables.updated_at = datetime.utcnow()
+        db_variables.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
         db_variables.variables_str = json.dumps(jsonable_encoder(tool_variables.pool))
         db.session.commit()
         db.session.close()
@@ -412,15 +451,19 @@ class BaseAgentRunner(AppRunner):
         """
         result = []
         # check if there is a system message in the beginning of the conversation
-        if prompt_messages and isinstance(prompt_messages[0], SystemPromptMessage):
-            result.append(prompt_messages[0])
+        for prompt_message in prompt_messages:
+            if isinstance(prompt_message, SystemPromptMessage):
+                result.append(prompt_message)
 
         messages: list[Message] = db.session.query(Message).filter(
             Message.conversation_id == self.message.conversation_id,
         ).order_by(Message.created_at.asc()).all()
 
         for message in messages:
-            result.append(UserPromptMessage(content=message.query))
+            if message.id == self.message.id:
+                continue
+            
+            result.append(self.organize_agent_user_prompt(message))
             agent_thoughts: list[MessageAgentThought] = message.agent_thoughts
             if agent_thoughts:
                 for agent_thought in agent_thoughts:
@@ -471,3 +514,32 @@ class BaseAgentRunner(AppRunner):
         db.session.close()
 
         return result
+
+    def organize_agent_user_prompt(self, message: Message) -> UserPromptMessage:
+        message_file_parser = MessageFileParser(
+            tenant_id=self.tenant_id,
+            app_id=self.app_config.app_id,
+        )
+
+        files = message.message_files
+        if files:
+            file_extra_config = FileUploadConfigManager.convert(message.app_model_config.to_dict())
+
+            if file_extra_config:
+                file_objs = message_file_parser.transform_message_files(
+                    files,
+                    file_extra_config
+                )
+            else:
+                file_objs = []
+
+            if not file_objs:
+                return UserPromptMessage(content=message.query)
+            else:
+                prompt_message_contents = [TextPromptMessageContent(data=message.query)]
+                for file_obj in file_objs:
+                    prompt_message_contents.append(file_obj.prompt_message_content)
+
+                return UserPromptMessage(content=prompt_message_contents)
+        else:
+            return UserPromptMessage(content=message.query)

api/core/agent/cot_agent_runner.py

@@ -1,33 +1,36 @@
 import json
-import re
+from abc import ABC, abstractmethod
 from collections.abc import Generator
-from typing import Literal, Union
+from typing import Union
 
 from core.agent.base_agent_runner import BaseAgentRunner
-from core.agent.entities import AgentPromptEntity, AgentScratchpadUnit
+from core.agent.entities import AgentScratchpadUnit
+from core.agent.output_parser.cot_output_parser import CotAgentOutputParser
 from core.app.apps.base_app_queue_manager import PublishFrom
 from core.app.entities.queue_entities import QueueAgentThoughtEvent, QueueMessageEndEvent, QueueMessageFileEvent
 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     PromptMessage,
-    PromptMessageTool,
-    SystemPromptMessage,
     ToolPromptMessage,
     UserPromptMessage,
 )
-from core.model_runtime.utils.encoders import jsonable_encoder
 from core.tools.entities.tool_entities import ToolInvokeMeta
+from core.tools.tool.tool import Tool
 from core.tools.tool_engine import ToolEngine
-from models.model import Conversation, Message
+from models.model import Message
 
 
-class CotAgentRunner(BaseAgentRunner):
+class CotAgentRunner(BaseAgentRunner, ABC):
     _is_first_iteration = True
     _ignore_observation_providers = ['wenxin']
+    _historic_prompt_messages: list[PromptMessage] = None
+    _agent_scratchpad: list[AgentScratchpadUnit] = None
+    _instruction: str = None
+    _query: str = None
+    _prompt_messages_tools: list[PromptMessage] = None
 
-    def run(self, conversation: Conversation,
-        message: Message,
+    def run(self, message: Message,
         query: str,
         inputs: dict[str, str],
     ) -> Union[Generator, LLMResult]:
@@ -36,9 +39,7 @@ class CotAgentRunner(BaseAgentRunner):
         """
         app_generate_entity = self.application_generate_entity
         self._repack_app_generate_entity(app_generate_entity)
-
-        agent_scratchpad: list[AgentScratchpadUnit] = []
-        self._init_agent_scratchpad(agent_scratchpad, self.history_prompt_messages)
+        self._init_react_state(query)
 
         # check model mode
         if 'Observation' not in app_generate_entity.model_config.stop:
@@ -47,38 +48,19 @@ class CotAgentRunner(BaseAgentRunner):
 
         app_config = self.app_config
 
-        # override inputs
+        # init instruction
         inputs = inputs or {}
         instruction = app_config.prompt_template.simple_prompt_template
-        instruction = self._fill_in_inputs_from_external_data_tools(instruction, inputs)
+        self._instruction = self._fill_in_inputs_from_external_data_tools(instruction, inputs)
 
         iteration_step = 1
         max_iteration_steps = min(app_config.agent.max_iteration, 5) + 1
 
-        prompt_messages = self.history_prompt_messages
-
         # convert tools into ModelRuntime Tool format
-        prompt_messages_tools: list[PromptMessageTool] = []
-        tool_instances = {}
-        for tool in app_config.agent.tools if app_config.agent else []:
-            try:
-                prompt_tool, tool_entity = self._convert_tool_to_prompt_message_tool(tool)
-            except Exception:
-                # api tool may be deleted
-                continue
-            # save tool entity
-            tool_instances[tool.tool_name] = tool_entity
-            # save prompt tool
-            prompt_messages_tools.append(prompt_tool)
-
-        # convert dataset tools into ModelRuntime Tool format
-        for dataset_tool in self.dataset_tools:
-            prompt_tool = self._convert_dataset_retriever_tool_to_prompt_message_tool(dataset_tool)
-            # save prompt tool
-            prompt_messages_tools.append(prompt_tool)
-            # save tool entity
-            tool_instances[dataset_tool.identity.name] = dataset_tool
+        tool_instances, self._prompt_messages_tools = self._init_prompt_tools()
 
+        prompt_messages = self._organize_prompt_messages()
+        
         function_call_state = True
         llm_usage = {
             'usage': None
@@ -103,7 +85,7 @@ class CotAgentRunner(BaseAgentRunner):
 
             if iteration_step == max_iteration_steps:
                 # the last iteration, remove all tools
-                prompt_messages_tools = []
+                self._prompt_messages_tools = []
 
             message_file_ids = []
 
@@ -120,18 +102,8 @@ class CotAgentRunner(BaseAgentRunner):
                     agent_thought_id=agent_thought.id
                 ), PublishFrom.APPLICATION_MANAGER)
 
-            # update prompt messages
-            prompt_messages = self._organize_cot_prompt_messages(
-                mode=app_generate_entity.model_config.mode,
-                prompt_messages=prompt_messages,
-                tools=prompt_messages_tools,
-                agent_scratchpad=agent_scratchpad,
-                agent_prompt_message=app_config.agent.prompt,
-                instruction=instruction,
-                input=query
-            )
-
             # recalc llm max tokens
+            prompt_messages = self._organize_prompt_messages()
             self.recalc_llm_max_tokens(self.model_config, prompt_messages)
             # invoke model
             chunks: Generator[LLMResultChunk, None, None] = model_instance.invoke_llm(
@@ -149,7 +121,7 @@ class CotAgentRunner(BaseAgentRunner):
                 raise ValueError("failed to invoke llm")
             
             usage_dict = {}
-            react_chunks = self._handle_stream_react(chunks, usage_dict)
+            react_chunks = CotAgentOutputParser.handle_react_stream_output(chunks)
             scratchpad = AgentScratchpadUnit(
                 agent_response='',
                 thought='',
@@ -165,30 +137,12 @@ class CotAgentRunner(BaseAgentRunner):
                 ), PublishFrom.APPLICATION_MANAGER)
 
             for chunk in react_chunks:
-                if isinstance(chunk, dict):
-                    scratchpad.agent_response += json.dumps(chunk)
-                    try:
-                        if scratchpad.action:
-                            raise Exception("")
-                        scratchpad.action_str = json.dumps(chunk)
-                        scratchpad.action = AgentScratchpadUnit.Action(
-                            action_name=chunk['action'],
-                            action_input=chunk['action_input']
-                        )
-                    except:
-                        scratchpad.thought += json.dumps(chunk)
-                        yield LLMResultChunk(
-                            model=self.model_config.model,
-                            prompt_messages=prompt_messages,
-                            system_fingerprint='',
-                            delta=LLMResultChunkDelta(
-                                index=0,
-                                message=AssistantPromptMessage(
-                                    content=json.dumps(chunk, ensure_ascii=False) # if ensure_ascii=True, the text in webui maybe garbled text
-                                ),
-                                usage=None
-                            )
-                        )
+                if isinstance(chunk, AgentScratchpadUnit.Action):
+                    action = chunk
+                    # detect action
+                    scratchpad.agent_response += json.dumps(chunk.dict())
+                    scratchpad.action_str = json.dumps(chunk.dict())
+                    scratchpad.action = action
                 else:
                     scratchpad.agent_response += chunk
                     scratchpad.thought += chunk
@@ -206,27 +160,29 @@ class CotAgentRunner(BaseAgentRunner):
                     )
 
             scratchpad.thought = scratchpad.thought.strip() or 'I am thinking about how to help you'
-            agent_scratchpad.append(scratchpad)
-                        
+            self._agent_scratchpad.append(scratchpad)
+            
             # get llm usage
             if 'usage' in usage_dict:
                 increase_usage(llm_usage, usage_dict['usage'])
             else:
                 usage_dict['usage'] = LLMUsage.empty_usage()
             
-            self.save_agent_thought(agent_thought=agent_thought,
-                                    tool_name=scratchpad.action.action_name if scratchpad.action else '',
-                                    tool_input={
-                                        scratchpad.action.action_name: scratchpad.action.action_input
-                                    } if scratchpad.action else '',
-                                    tool_invoke_meta={},
-                                    thought=scratchpad.thought,
-                                    observation='',
-                                    answer=scratchpad.agent_response,
-                                    messages_ids=[],
-                                    llm_usage=usage_dict['usage'])
+            self.save_agent_thought(
+                agent_thought=agent_thought,
+                tool_name=scratchpad.action.action_name if scratchpad.action else '',
+                tool_input={
+                    scratchpad.action.action_name: scratchpad.action.action_input
+                } if scratchpad.action else {},
+                tool_invoke_meta={},
+                thought=scratchpad.thought,
+                observation='',
+                answer=scratchpad.agent_response,
+                messages_ids=[],
+                llm_usage=usage_dict['usage']
+            )
             
-            if scratchpad.action and scratchpad.action.action_name.lower() != "final answer":
+            if not scratchpad.is_final():
                 self.queue_manager.publish(QueueAgentThoughtEvent(
                     agent_thought_id=agent_thought.id
                 ), PublishFrom.APPLICATION_MANAGER)
@@ -238,106 +194,43 @@ class CotAgentRunner(BaseAgentRunner):
                 if scratchpad.action.action_name.lower() == "final answer":
                     # action is final answer, return final answer directly
                     try:
-                        final_answer = scratchpad.action.action_input if \
-                            isinstance(scratchpad.action.action_input, str) else \
-                                json.dumps(scratchpad.action.action_input)
+                        if isinstance(scratchpad.action.action_input, dict):
+                            final_answer = json.dumps(scratchpad.action.action_input)
+                        elif isinstance(scratchpad.action.action_input, str):
+                            final_answer = scratchpad.action.action_input
+                        else:
+                            final_answer = f'{scratchpad.action.action_input}'
                     except json.JSONDecodeError:
                         final_answer = f'{scratchpad.action.action_input}'
                 else:
                     function_call_state = True
-
                     # action is tool call, invoke tool
-                    tool_call_name = scratchpad.action.action_name
-                    tool_call_args = scratchpad.action.action_input
-                    tool_instance = tool_instances.get(tool_call_name)
-                    if not tool_instance:
-                        answer = f"there is not a tool named {tool_call_name}"
-                        self.save_agent_thought(
-                            agent_thought=agent_thought, 
-                            tool_name='',
-                            tool_input='',
-                            tool_invoke_meta=ToolInvokeMeta.error_instance(
-                                f"there is not a tool named {tool_call_name}"
-                            ).to_dict(),
-                            thought=None, 
-                            observation={
-                                tool_call_name: answer
-                            }, 
-                            answer=answer,
-                            messages_ids=[]
-                        )
-                        self.queue_manager.publish(QueueAgentThoughtEvent(
-                            agent_thought_id=agent_thought.id
-                        ), PublishFrom.APPLICATION_MANAGER)
-                    else:
-                        if isinstance(tool_call_args, str):
-                            try:
-                                tool_call_args = json.loads(tool_call_args)
-                            except json.JSONDecodeError:
-                                pass
+                    tool_invoke_response, tool_invoke_meta = self._handle_invoke_action(
+                        action=scratchpad.action, 
+                        tool_instances=tool_instances,
+                        message_file_ids=message_file_ids
+                    )
+                    scratchpad.observation = tool_invoke_response
+                    scratchpad.agent_response = tool_invoke_response
 
-                        # invoke tool
-                        tool_invoke_response, message_files, tool_invoke_meta = ToolEngine.agent_invoke(
-                            tool=tool_instance,
-                            tool_parameters=tool_call_args,
-                            user_id=self.user_id,
-                            tenant_id=self.tenant_id,
-                            message=self.message,
-                            invoke_from=self.application_generate_entity.invoke_from,
-                            agent_tool_callback=self.agent_callback
-                        )
-                        # publish files
-                        for message_file, save_as in message_files:
-                            if save_as:
-                                self.variables_pool.set_file(tool_name=tool_call_name, value=message_file.id, name=save_as)
+                    self.save_agent_thought(
+                        agent_thought=agent_thought,
+                        tool_name=scratchpad.action.action_name,
+                        tool_input={scratchpad.action.action_name: scratchpad.action.action_input},
+                        thought=scratchpad.thought,
+                        observation={scratchpad.action.action_name: tool_invoke_response},
+                        tool_invoke_meta=tool_invoke_meta.to_dict(),
+                        answer=scratchpad.agent_response,
+                        messages_ids=message_file_ids,
+                        llm_usage=usage_dict['usage']
+                    )
 
-                            # publish message file
-                            self.queue_manager.publish(QueueMessageFileEvent(
-                                message_file_id=message_file.id
-                            ), PublishFrom.APPLICATION_MANAGER)
-                            # add message file ids
-                            message_file_ids.append(message_file.id)
-
-                        # publish files
-                        for message_file, save_as in message_files:
-                            if save_as:
-                                self.variables_pool.set_file(tool_name=tool_call_name,
-                                                                value=message_file.id,
-                                                                name=save_as)
-                            self.queue_manager.publish(QueueMessageFileEvent(
-                                message_file_id=message_file.id
-                            ), PublishFrom.APPLICATION_MANAGER)
-
-                        message_file_ids = [message_file.id for message_file, _ in message_files]
-
-                        observation = tool_invoke_response
-
-                        # save scratchpad
-                        scratchpad.observation = observation
-
-                        # save agent thought
-                        self.save_agent_thought(
-                            agent_thought=agent_thought, 
-                            tool_name=tool_call_name,
-                            tool_input={
-                                tool_call_name: tool_call_args
-                            },
-                            tool_invoke_meta={
-                                tool_call_name: tool_invoke_meta.to_dict()
-                            },
-                            thought=None,
-                            observation={
-                                tool_call_name: observation
-                            }, 
-                            answer=scratchpad.agent_response,
-                            messages_ids=message_file_ids,
-                        )
-                        self.queue_manager.publish(QueueAgentThoughtEvent(
-                            agent_thought_id=agent_thought.id
-                        ), PublishFrom.APPLICATION_MANAGER)
+                    self.queue_manager.publish(QueueAgentThoughtEvent(
+                        agent_thought_id=agent_thought.id
+                    ), PublishFrom.APPLICATION_MANAGER)
 
                 # update prompt tool message
-                for prompt_tool in prompt_messages_tools:
+                for prompt_tool in self._prompt_messages_tools:
                     self.update_prompt_message_tool(tool_instances[prompt_tool.name], prompt_tool)
 
             iteration_step += 1
@@ -379,96 +272,63 @@ class CotAgentRunner(BaseAgentRunner):
             system_fingerprint=''
         )), PublishFrom.APPLICATION_MANAGER)
 
-    def _handle_stream_react(self, llm_response: Generator[LLMResultChunk, None, None], usage: dict) \
-        -> Generator[Union[str, dict], None, None]:
-        def parse_json(json_str):
+    def _handle_invoke_action(self, action: AgentScratchpadUnit.Action, 
+                              tool_instances: dict[str, Tool],
+                              message_file_ids: list[str]) -> tuple[str, ToolInvokeMeta]:
+        """
+        handle invoke action
+        :param action: action
+        :param tool_instances: tool instances
+        :return: observation, meta
+        """
+        # action is tool call, invoke tool
+        tool_call_name = action.action_name
+        tool_call_args = action.action_input
+        tool_instance = tool_instances.get(tool_call_name)
+
+        if not tool_instance:
+            answer = f"there is not a tool named {tool_call_name}"
+            return answer, ToolInvokeMeta.error_instance(answer)
+        
+        if isinstance(tool_call_args, str):
             try:
-                return json.loads(json_str.strip())
-            except:
-                return json_str
-            
-        def extra_json_from_code_block(code_block) -> Generator[Union[dict, str], None, None]:
-            code_blocks = re.findall(r'```(.*?)```', code_block, re.DOTALL)
-            if not code_blocks:
-                return
-            for block in code_blocks:
-                json_text = re.sub(r'^[a-zA-Z]+\n', '', block.strip(), flags=re.MULTILINE)
-                yield parse_json(json_text)
-            
-        code_block_cache = ''
-        code_block_delimiter_count = 0
-        in_code_block = False
-        json_cache = ''
-        json_quote_count = 0
-        in_json = False
-        got_json = False
-    
-        for response in llm_response:
-            response = response.delta.message.content
-            if not isinstance(response, str):
-                continue
+                tool_call_args = json.loads(tool_call_args)
+            except json.JSONDecodeError:
+                pass
 
-            # stream
-            index = 0
-            while index < len(response):
-                steps = 1
-                delta = response[index:index+steps]
-                if delta == '`':
-                    code_block_cache += delta
-                    code_block_delimiter_count += 1
-                else:
-                    if not in_code_block:
-                        if code_block_delimiter_count > 0:
-                            yield code_block_cache
-                        code_block_cache = ''
-                    else:
-                        code_block_cache += delta
-                    code_block_delimiter_count = 0
+        # invoke tool
+        tool_invoke_response, message_files, tool_invoke_meta = ToolEngine.agent_invoke(
+            tool=tool_instance,
+            tool_parameters=tool_call_args,
+            user_id=self.user_id,
+            tenant_id=self.tenant_id,
+            message=self.message,
+            invoke_from=self.application_generate_entity.invoke_from,
+            agent_tool_callback=self.agent_callback
+        )
 
-                if code_block_delimiter_count == 3:
-                    if in_code_block:
-                        yield from extra_json_from_code_block(code_block_cache)
-                        code_block_cache = ''
-                        
-                    in_code_block = not in_code_block
-                    code_block_delimiter_count = 0
+        # publish files
+        for message_file, save_as in message_files:
+            if save_as:
+                self.variables_pool.set_file(tool_name=tool_call_name, value=message_file.id, name=save_as)
 
-                if not in_code_block:
-                    # handle single json
-                    if delta == '{':
-                        json_quote_count += 1
-                        in_json = True
-                        json_cache += delta
-                    elif delta == '}':
-                        json_cache += delta
-                        if json_quote_count > 0:
-                            json_quote_count -= 1
-                            if json_quote_count == 0:
-                                in_json = False
-                                got_json = True
-                                index += steps
-                                continue
-                    else:
-                        if in_json:
-                            json_cache += delta
+            # publish message file
+            self.queue_manager.publish(QueueMessageFileEvent(
+                message_file_id=message_file.id
+            ), PublishFrom.APPLICATION_MANAGER)
+            # add message file ids
+            message_file_ids.append(message_file.id)
 
-                    if got_json:
-                        got_json = False
-                        yield parse_json(json_cache)
-                        json_cache = ''
-                        json_quote_count = 0
-                        in_json = False
-                    
-                if not in_code_block and not in_json:
-                    yield delta.replace('`', '')
+        return tool_invoke_response, tool_invoke_meta
 
-                index += steps
-
-        if code_block_cache:
-            yield code_block_cache
-
-        if json_cache:
-            yield parse_json(json_cache)
+    def _convert_dict_to_action(self, action: dict) -> AgentScratchpadUnit.Action:
+        """
+        convert dict to action
+        """
+        return AgentScratchpadUnit.Action(
+            action_name=action['action'],
+            action_input=action['action_input']
+        )
 
     def _fill_in_inputs_from_external_data_tools(self, instruction: str, inputs: dict) -> str:
         """
@@ -482,15 +342,46 @@ class CotAgentRunner(BaseAgentRunner):
 
         return instruction
     
-    def _init_agent_scratchpad(self, 
-                               agent_scratchpad: list[AgentScratchpadUnit],
-                               messages: list[PromptMessage]
-                               ) -> list[AgentScratchpadUnit]:
+    def _init_react_state(self, query) -> None:
         """
         init agent scratchpad
         """
+        self._query = query
+        self._agent_scratchpad = []
+        self._historic_prompt_messages = self._organize_historic_prompt_messages()
+    
+    @abstractmethod
+    def _organize_prompt_messages(self) -> list[PromptMessage]:
+        """
+            organize prompt messages
+        """
+
+    def _format_assistant_message(self, agent_scratchpad: list[AgentScratchpadUnit]) -> str:
+        """
+            format assistant message
+        """
+        message = ''
+        for scratchpad in agent_scratchpad:
+            if scratchpad.is_final():
+                message += f"Final Answer: {scratchpad.agent_response}"
+            else:
+                message += f"Thought: {scratchpad.thought}\n\n"
+                if scratchpad.action_str:
+                    message += f"Action: {scratchpad.action_str}\n\n"
+                if scratchpad.observation:
+                    message += f"Observation: {scratchpad.observation}\n\n"
+
+        return message
+
+    def _organize_historic_prompt_messages(self) -> list[PromptMessage]:
+        """
+            organize historic prompt messages
+        """
+        result: list[PromptMessage] = []
+        scratchpad: list[AgentScratchpadUnit] = []
         current_scratchpad: AgentScratchpadUnit = None
-        for message in messages:
+
+        for message in self.history_prompt_messages:
             if isinstance(message, AssistantPromptMessage):
                 current_scratchpad = AgentScratchpadUnit(
                     agent_response=message.content,
@@ -505,186 +396,29 @@ class CotAgentRunner(BaseAgentRunner):
                             action_name=message.tool_calls[0].function.name,
                             action_input=json.loads(message.tool_calls[0].function.arguments)
                         )
+                        current_scratchpad.action_str = json.dumps(
+                            current_scratchpad.action.to_dict()
+                        )
                     except:
                         pass
-                    
-                agent_scratchpad.append(current_scratchpad)
+                
+                scratchpad.append(current_scratchpad)
             elif isinstance(message, ToolPromptMessage):
                 if current_scratchpad:
                     current_scratchpad.observation = message.content
+            elif isinstance(message, UserPromptMessage):
+                result.append(message)
+
+                if scratchpad:
+                    result.append(AssistantPromptMessage(
+                        content=self._format_assistant_message(scratchpad)
+                    ))
+
+                scratchpad = []
+
+        if scratchpad:
+            result.append(AssistantPromptMessage(
+                content=self._format_assistant_message(scratchpad)
+            ))
         
-        return agent_scratchpad
-
-    def _check_cot_prompt_messages(self, mode: Literal["completion", "chat"], 
-                                      agent_prompt_message: AgentPromptEntity,
-    ):
-        """
-            check chain of thought prompt messages, a standard prompt message is like:
-                Respond to the human as helpfully and accurately as possible. 
-
-                {{instruction}}
-
-                You have access to the following tools:
-
-                {{tools}}
-
-                Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).
-                Valid action values: "Final Answer" or {{tool_names}}
-
-                Provide only ONE action per $JSON_BLOB, as shown:
-
-                ```
-                {
-                "action": $TOOL_NAME,
-                "action_input": $ACTION_INPUT
-                }
-                ```
-        """
-
-        # parse agent prompt message
-        first_prompt = agent_prompt_message.first_prompt
-        next_iteration = agent_prompt_message.next_iteration
-
-        if not isinstance(first_prompt, str) or not isinstance(next_iteration, str):
-            raise ValueError("first_prompt or next_iteration is required in CoT agent mode")
-        
-        # check instruction, tools, and tool_names slots
-        if not first_prompt.find("{{instruction}}") >= 0:
-            raise ValueError("{{instruction}} is required in first_prompt")
-        if not first_prompt.find("{{tools}}") >= 0:
-            raise ValueError("{{tools}} is required in first_prompt")
-        if not first_prompt.find("{{tool_names}}") >= 0:
-            raise ValueError("{{tool_names}} is required in first_prompt")
-        
-        if mode == "completion":
-            if not first_prompt.find("{{query}}") >= 0:
-                raise ValueError("{{query}} is required in first_prompt")
-            if not first_prompt.find("{{agent_scratchpad}}") >= 0:
-                raise ValueError("{{agent_scratchpad}} is required in first_prompt")
-        
-        if mode == "completion":
-            if not next_iteration.find("{{observation}}") >= 0:
-                raise ValueError("{{observation}} is required in next_iteration")
-            
-    def _convert_scratchpad_list_to_str(self, agent_scratchpad: list[AgentScratchpadUnit]) -> str:
-        """
-            convert agent scratchpad list to str
-        """
-        next_iteration = self.app_config.agent.prompt.next_iteration
-
-        result = ''
-        for scratchpad in agent_scratchpad:
-            result += (scratchpad.thought or '') + (scratchpad.action_str or '') + \
-                next_iteration.replace("{{observation}}", scratchpad.observation or 'It seems that no response is available')
-
-        return result
-    
-    def _organize_cot_prompt_messages(self, mode: Literal["completion", "chat"],
-                                      prompt_messages: list[PromptMessage],
-                                      tools: list[PromptMessageTool], 
-                                      agent_scratchpad: list[AgentScratchpadUnit],
-                                      agent_prompt_message: AgentPromptEntity,
-                                      instruction: str,
-                                      input: str,
-        ) -> list[PromptMessage]:
-        """
-            organize chain of thought prompt messages, a standard prompt message is like:
-                Respond to the human as helpfully and accurately as possible. 
-
-                {{instruction}}
-
-                You have access to the following tools:
-
-                {{tools}}
-
-                Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).
-                Valid action values: "Final Answer" or {{tool_names}}
-
-                Provide only ONE action per $JSON_BLOB, as shown:
-
-                ```
-                {{{{
-                "action": $TOOL_NAME,
-                "action_input": $ACTION_INPUT
-                }}}}
-                ```
-        """
-
-        self._check_cot_prompt_messages(mode, agent_prompt_message)
-
-        # parse agent prompt message
-        first_prompt = agent_prompt_message.first_prompt
-
-        # parse tools
-        tools_str = self._jsonify_tool_prompt_messages(tools)
-
-        # parse tools name
-        tool_names = '"' + '","'.join([tool.name for tool in tools]) + '"'
-
-        # get system message
-        system_message = first_prompt.replace("{{instruction}}", instruction) \
-                                     .replace("{{tools}}", tools_str) \
-                                     .replace("{{tool_names}}", tool_names)
-
-        # organize prompt messages
-        if mode == "chat":
-            # override system message
-            overridden = False
-            prompt_messages = prompt_messages.copy()
-            for prompt_message in prompt_messages:
-                if isinstance(prompt_message, SystemPromptMessage):
-                    prompt_message.content = system_message
-                    overridden = True
-                    break
-            
-            # convert tool prompt messages to user prompt messages
-            for idx, prompt_message in enumerate(prompt_messages):
-                if isinstance(prompt_message, ToolPromptMessage):
-                    prompt_messages[idx] = UserPromptMessage(
-                        content=prompt_message.content
-                    )
-
-            if not overridden:
-                prompt_messages.insert(0, SystemPromptMessage(
-                    content=system_message,
-                ))
-
-            # add assistant message
-            if len(agent_scratchpad) > 0 and not self._is_first_iteration:
-                prompt_messages.append(AssistantPromptMessage(
-                    content=(agent_scratchpad[-1].thought or '') + (agent_scratchpad[-1].action_str or ''),
-                ))
-            
-            # add user message
-            if len(agent_scratchpad) > 0 and not self._is_first_iteration:
-                prompt_messages.append(UserPromptMessage(
-                    content=(agent_scratchpad[-1].observation or 'It seems that no response is available'),
-                ))
-
-            self._is_first_iteration = False
-
-            return prompt_messages
-        elif mode == "completion":
-            # parse agent scratchpad
-            agent_scratchpad_str = self._convert_scratchpad_list_to_str(agent_scratchpad)
-            self._is_first_iteration = False
-            # parse prompt messages
-            return [UserPromptMessage(
-                content=first_prompt.replace("{{instruction}}", instruction)
-                                    .replace("{{tools}}", tools_str)
-                                    .replace("{{tool_names}}", tool_names)
-                                    .replace("{{query}}", input)
-                                    .replace("{{agent_scratchpad}}", agent_scratchpad_str),
-            )]
-        else:
-            raise ValueError(f"mode {mode} is not supported")
-            
-    def _jsonify_tool_prompt_messages(self, tools: list[PromptMessageTool]) -> str:
-        """
-            jsonify tool prompt messages
-        """
-        tools = jsonable_encoder(tools)
-        try:
-            return json.dumps(tools, ensure_ascii=False)
-        except json.JSONDecodeError:
-            return json.dumps(tools)
+        return result

api/core/agent/cot_chat_agent_runner.py

@@ -0,0 +1,71 @@
+import json
+
+from core.agent.cot_agent_runner import CotAgentRunner
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    PromptMessage,
+    SystemPromptMessage,
+    UserPromptMessage,
+)
+from core.model_runtime.utils.encoders import jsonable_encoder
+
+
+class CotChatAgentRunner(CotAgentRunner):
+    def _organize_system_prompt(self) -> SystemPromptMessage:
+        """
+        Organize system prompt
+        """
+        prompt_entity = self.app_config.agent.prompt
+        first_prompt = prompt_entity.first_prompt
+
+        system_prompt = first_prompt \
+            .replace("{{instruction}}", self._instruction) \
+            .replace("{{tools}}", json.dumps(jsonable_encoder(self._prompt_messages_tools))) \
+            .replace("{{tool_names}}", ', '.join([tool.name for tool in self._prompt_messages_tools]))
+
+        return SystemPromptMessage(content=system_prompt)
+
+    def _organize_prompt_messages(self) -> list[PromptMessage]:
+        """
+        Organize 
+        """
+        # organize system prompt
+        system_message = self._organize_system_prompt()
+
+        # organize historic prompt messages
+        historic_messages = self._historic_prompt_messages
+
+        # organize current assistant messages
+        agent_scratchpad = self._agent_scratchpad
+        if not agent_scratchpad:
+            assistant_messages = []
+        else:
+            assistant_message = AssistantPromptMessage(content='')
+            for unit in agent_scratchpad:
+                if unit.is_final():
+                    assistant_message.content += f"Final Answer: {unit.agent_response}"
+                else:
+                    assistant_message.content += f"Thought: {unit.thought}\n\n"
+                    if unit.action_str:
+                        assistant_message.content += f"Action: {unit.action_str}\n\n"
+                    if unit.observation:
+                        assistant_message.content += f"Observation: {unit.observation}\n\n"
+
+            assistant_messages = [assistant_message]
+
+        # query messages
+        query_messages = UserPromptMessage(content=self._query)
+
+        if assistant_messages:
+            messages = [
+                system_message,
+                *historic_messages,
+                query_messages,
+                *assistant_messages,
+                UserPromptMessage(content='continue')
+            ]
+        else:
+            messages = [system_message, *historic_messages, query_messages]
+
+        # join all messages
+        return messages

api/core/agent/cot_completion_agent_runner.py

@@ -0,0 +1,69 @@
+import json
+
+from core.agent.cot_agent_runner import CotAgentRunner
+from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage, UserPromptMessage
+from core.model_runtime.utils.encoders import jsonable_encoder
+
+
+class CotCompletionAgentRunner(CotAgentRunner):
+    def _organize_instruction_prompt(self) -> str:
+        """
+        Organize instruction prompt
+        """
+        prompt_entity = self.app_config.agent.prompt
+        first_prompt = prompt_entity.first_prompt
+
+        system_prompt = first_prompt.replace("{{instruction}}", self._instruction) \
+            .replace("{{tools}}", json.dumps(jsonable_encoder(self._prompt_messages_tools))) \
+            .replace("{{tool_names}}", ', '.join([tool.name for tool in self._prompt_messages_tools]))
+        
+        return system_prompt
+
+    def _organize_historic_prompt(self) -> str:
+        """
+        Organize historic prompt
+        """
+        historic_prompt_messages = self._historic_prompt_messages
+        historic_prompt = ""
+
+        for message in historic_prompt_messages:
+            if isinstance(message, UserPromptMessage):
+                historic_prompt += f"Question: {message.content}\n\n"
+            elif isinstance(message, AssistantPromptMessage):
+                historic_prompt += message.content + "\n\n"
+
+        return historic_prompt
+
+    def _organize_prompt_messages(self) -> list[PromptMessage]:
+        """
+        Organize prompt messages
+        """
+        # organize system prompt
+        system_prompt = self._organize_instruction_prompt()
+
+        # organize historic prompt messages
+        historic_prompt = self._organize_historic_prompt()
+
+        # organize current assistant messages
+        agent_scratchpad = self._agent_scratchpad
+        assistant_prompt = ''
+        for unit in agent_scratchpad:
+            if unit.is_final():
+                assistant_prompt += f"Final Answer: {unit.agent_response}"
+            else:
+                assistant_prompt += f"Thought: {unit.thought}\n\n"
+                if unit.action_str:
+                    assistant_prompt += f"Action: {unit.action_str}\n\n"
+                if unit.observation:
+                    assistant_prompt += f"Observation: {unit.observation}\n\n"
+
+        # query messages
+        query_prompt = f"Question: {self._query}"
+
+        # join all messages
+        prompt = system_prompt \
+            .replace("{{historic_messages}}", historic_prompt) \
+            .replace("{{agent_scratchpad}}", assistant_prompt) \
+            .replace("{{query}}", query_prompt)
+
+        return [UserPromptMessage(content=prompt)]

api/core/agent/entities.py

@@ -34,12 +34,29 @@ class AgentScratchpadUnit(BaseModel):
         action_name: str
         action_input: Union[dict, str]
 
+        def to_dict(self) -> dict:
+            """
+            Convert to dictionary.
+            """
+            return {
+                'action': self.action_name,
+                'action_input': self.action_input,
+            }
+
     agent_response: Optional[str] = None
     thought: Optional[str] = None
     action_str: Optional[str] = None
     observation: Optional[str] = None
     action: Optional[Action] = None
 
+    def is_final(self) -> bool:
+        """
+        Check if the scratchpad unit is final.
+        """
+        return self.action is None or (
+            'final' in self.action.action_name.lower() and 
+            'answer' in self.action.action_name.lower()
+        )
 
 class AgentEntity(BaseModel):
     """

api/core/agent/fc_agent_runner.py

@@ -1,6 +1,7 @@
 import json
 import logging
 from collections.abc import Generator
+from copy import deepcopy
 from typing import Any, Union
 
 from core.agent.base_agent_runner import BaseAgentRunner
@@ -10,21 +11,21 @@ from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk,
 from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     PromptMessage,
-    PromptMessageTool,
+    PromptMessageContentType,
     SystemPromptMessage,
+    TextPromptMessageContent,
     ToolPromptMessage,
     UserPromptMessage,
 )
 from core.tools.entities.tool_entities import ToolInvokeMeta
 from core.tools.tool_engine import ToolEngine
-from models.model import Conversation, Message, MessageAgentThought
+from models.model import Message
 
 logger = logging.getLogger(__name__)
 
 class FunctionCallAgentRunner(BaseAgentRunner):
-    def run(self, conversation: Conversation,
-                message: Message,
-                query: str,
+    def run(self, 
+            message: Message, query: str, **kwargs: Any
     ) -> Generator[LLMResultChunk, None, None]:
         """
         Run FunctionCall agent application
@@ -35,40 +36,17 @@ class FunctionCallAgentRunner(BaseAgentRunner):
 
         prompt_template = app_config.prompt_template.simple_prompt_template or ''
         prompt_messages = self.history_prompt_messages
-        prompt_messages = self.organize_prompt_messages(
-            prompt_template=prompt_template,
-            query=query,
-            prompt_messages=prompt_messages
-        )
+        prompt_messages = self._init_system_message(prompt_template, prompt_messages)
+        prompt_messages = self._organize_user_query(query, prompt_messages)
 
         # convert tools into ModelRuntime Tool format
-        prompt_messages_tools: list[PromptMessageTool] = []
-        tool_instances = {}
-        for tool in app_config.agent.tools if app_config.agent else []:
-            try:
-                prompt_tool, tool_entity = self._convert_tool_to_prompt_message_tool(tool)
-            except Exception:
-                # api tool may be deleted
-                continue
-            # save tool entity
-            tool_instances[tool.tool_name] = tool_entity
-            # save prompt tool
-            prompt_messages_tools.append(prompt_tool)
-
-        # convert dataset tools into ModelRuntime Tool format
-        for dataset_tool in self.dataset_tools:
-            prompt_tool = self._convert_dataset_retriever_tool_to_prompt_message_tool(dataset_tool)
-            # save prompt tool
-            prompt_messages_tools.append(prompt_tool)
-            # save tool entity
-            tool_instances[dataset_tool.identity.name] = dataset_tool
+        tool_instances, prompt_messages_tools = self._init_prompt_tools()
 
         iteration_step = 1
         max_iteration_steps = min(app_config.agent.max_iteration, 5) + 1
 
         # continue to run until there is not any tool call
         function_call_state = True
-        agent_thoughts: list[MessageAgentThought] = []
         llm_usage = {
             'usage': None
         }
@@ -207,19 +185,25 @@ class FunctionCallAgentRunner(BaseAgentRunner):
                     )
                 )
 
+            assistant_message = AssistantPromptMessage(
+                content='',
+                tool_calls=[]
+            )
             if tool_calls:
-                prompt_messages.append(AssistantPromptMessage(
-                    content='',
-                    name='',
-                    tool_calls=[AssistantPromptMessage.ToolCall(
+                assistant_message.tool_calls=[
+                    AssistantPromptMessage.ToolCall(
                         id=tool_call[0],
                         type='function',
                         function=AssistantPromptMessage.ToolCall.ToolCallFunction(
                             name=tool_call[1],
                             arguments=json.dumps(tool_call[2], ensure_ascii=False)
                         )
-                    ) for tool_call in tool_calls]
-                ))
+                    ) for tool_call in tool_calls
+                ]
+            else:
+                assistant_message.content = response
+            
+            prompt_messages.append(assistant_message)
 
             # save thought
             self.save_agent_thought(
@@ -239,12 +223,6 @@ class FunctionCallAgentRunner(BaseAgentRunner):
             
             final_answer += response + '\n'
 
-            # update prompt messages
-            if response.strip():
-                prompt_messages.append(AssistantPromptMessage(
-                    content=response,
-                ))
-            
             # call tools
             tool_responses = []
             for tool_call_id, tool_call_name, tool_call_args in tool_calls:
@@ -287,9 +265,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
                     }
                 
                 tool_responses.append(tool_response)
-                prompt_messages = self.organize_prompt_messages(
-                    prompt_template=prompt_template,
-                    query=None,
+                prompt_messages = self._organize_assistant_message(
                     tool_call_id=tool_call_id,
                     tool_call_name=tool_call_name,
                     tool_response=tool_response['tool_response'],
@@ -324,6 +300,8 @@ class FunctionCallAgentRunner(BaseAgentRunner):
 
             iteration_step += 1
 
+            prompt_messages = self._clear_user_prompt_image_messages(prompt_messages)
+
         self.update_db_variables(self.variables_pool, self.db_variables_pool)
         # publish end event
         self.queue_manager.publish(QueueMessageEndEvent(llm_result=LLMResult(
@@ -386,29 +364,68 @@ class FunctionCallAgentRunner(BaseAgentRunner):
 
         return tool_calls
 
-    def organize_prompt_messages(self, prompt_template: str,
-                                 query: str = None, 
-                                 tool_call_id: str = None, tool_call_name: str = None, tool_response: str = None,
-                                 prompt_messages: list[PromptMessage] = None
-                                 ) -> list[PromptMessage]:
+    def _init_system_message(self, prompt_template: str, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
         """
-        Organize prompt messages
+        Initialize system message
         """
-        
-        if not prompt_messages:
-            prompt_messages = [
+        if not prompt_messages and prompt_template:
+            return [
                 SystemPromptMessage(content=prompt_template),
-                UserPromptMessage(content=query),
             ]
+        
+        if prompt_messages and not isinstance(prompt_messages[0], SystemPromptMessage) and prompt_template:
+            prompt_messages.insert(0, SystemPromptMessage(content=prompt_template))
+
+        return prompt_messages
+
+    def _organize_user_query(self, query,  prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+        """
+        Organize user query
+        """
+        if self.files:
+            prompt_message_contents = [TextPromptMessageContent(data=query)]
+            for file_obj in self.files:
+                prompt_message_contents.append(file_obj.prompt_message_content)
+
+            prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
         else:
-            if tool_response:
-                prompt_messages = prompt_messages.copy()
-                prompt_messages.append(
-                    ToolPromptMessage(
-                        content=tool_response,
-                        tool_call_id=tool_call_id,
-                        name=tool_call_name,
-                    )
+            prompt_messages.append(UserPromptMessage(content=query))
+
+        return prompt_messages
+    
+    def _organize_assistant_message(self, tool_call_id: str = None, tool_call_name: str = None, tool_response: str = None, 
+                                    prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
+        """
+        Organize assistant message
+        """
+        prompt_messages = deepcopy(prompt_messages)
+
+        if tool_response is not None:
+            prompt_messages.append(
+                ToolPromptMessage(
+                    content=tool_response,
+                    tool_call_id=tool_call_id,
+                    name=tool_call_name,
                 )
+            )
+
+        return prompt_messages
+    
+    def _clear_user_prompt_image_messages(self, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
+        """
+        As for now, gpt supports both fc and vision at the first iteration.
+        We need to remove the image messages from the prompt messages at the first iteration.
+        """
+        prompt_messages = deepcopy(prompt_messages)
+
+        for prompt_message in prompt_messages:
+            if isinstance(prompt_message, UserPromptMessage):
+                if isinstance(prompt_message.content, list):
+                    prompt_message.content = '\n'.join([
+                        content.data if content.type == PromptMessageContentType.TEXT else 
+                        '[image]' if content.type == PromptMessageContentType.IMAGE else
+                        '[file]' 
+                        for content in prompt_message.content 
+                    ])
 
         return prompt_messages

api/core/agent/output_parser/cot_output_parser.py

@@ -0,0 +1,183 @@
+import json
+import re
+from collections.abc import Generator
+from typing import Union
+
+from core.agent.entities import AgentScratchpadUnit
+from core.model_runtime.entities.llm_entities import LLMResultChunk
+
+
+class CotAgentOutputParser:
+    @classmethod
+    def handle_react_stream_output(cls, llm_response: Generator[LLMResultChunk, None, None]) -> \
+        Generator[Union[str, AgentScratchpadUnit.Action], None, None]:
+        def parse_action(json_str):
+            try:
+                action = json.loads(json_str)
+                action_name = None
+                action_input = None
+
+                for key, value in action.items():
+                    if 'input' in key.lower():
+                        action_input = value
+                    else:
+                        action_name = value
+
+                if action_name is not None and action_input is not None:
+                    return AgentScratchpadUnit.Action(
+                        action_name=action_name,
+                        action_input=action_input,
+                    )
+                else:
+                    return json_str or ''
+            except:
+                return json_str or ''
+            
+        def extra_json_from_code_block(code_block) -> Generator[Union[dict, str], None, None]:
+            code_blocks = re.findall(r'```(.*?)```', code_block, re.DOTALL)
+            if not code_blocks:
+                return
+            for block in code_blocks:
+                json_text = re.sub(r'^[a-zA-Z]+\n', '', block.strip(), flags=re.MULTILINE)
+                yield parse_action(json_text)
+            
+        code_block_cache = ''
+        code_block_delimiter_count = 0
+        in_code_block = False
+        json_cache = ''
+        json_quote_count = 0
+        in_json = False
+        got_json = False
+
+        action_cache = ''
+        action_str = 'action:'
+        action_idx = 0
+
+        thought_cache = ''
+        thought_str = 'thought:'
+        thought_idx = 0
+
+        for response in llm_response:
+            response = response.delta.message.content
+            if not isinstance(response, str):
+                continue
+
+            # stream
+            index = 0
+            while index < len(response):
+                steps = 1
+                delta = response[index:index+steps]
+                last_character = response[index-1] if index > 0 else ''
+
+                if delta == '`':
+                    code_block_cache += delta
+                    code_block_delimiter_count += 1
+                else:
+                    if not in_code_block:
+                        if code_block_delimiter_count > 0:
+                            yield code_block_cache
+                        code_block_cache = ''
+                    else:
+                        code_block_cache += delta
+                    code_block_delimiter_count = 0
+
+                if not in_code_block and not in_json:
+                    if delta.lower() == action_str[action_idx] and action_idx == 0:
+                        if last_character not in ['\n', ' ', '']:
+                            index += steps
+                            yield delta
+                            continue
+
+                        action_cache += delta
+                        action_idx += 1
+                        if action_idx == len(action_str):
+                            action_cache = ''
+                            action_idx = 0
+                        index += steps
+                        continue
+                    elif delta.lower() == action_str[action_idx] and action_idx > 0:
+                        action_cache += delta
+                        action_idx += 1
+                        if action_idx == len(action_str):
+                            action_cache = ''
+                            action_idx = 0
+                        index += steps
+                        continue
+                    else:
+                        if action_cache:
+                            yield action_cache
+                            action_cache = ''
+                            action_idx = 0
+                    
+                    if delta.lower() == thought_str[thought_idx] and thought_idx == 0:
+                        if last_character not in ['\n', ' ', '']:
+                            index += steps
+                            yield delta
+                            continue
+
+                        thought_cache += delta
+                        thought_idx += 1
+                        if thought_idx == len(thought_str):
+                            thought_cache = ''
+                            thought_idx = 0
+                        index += steps
+                        continue
+                    elif delta.lower() == thought_str[thought_idx] and thought_idx > 0:
+                        thought_cache += delta
+                        thought_idx += 1
+                        if thought_idx == len(thought_str):
+                            thought_cache = ''
+                            thought_idx = 0
+                        index += steps
+                        continue
+                    else:
+                        if thought_cache:
+                            yield thought_cache
+                            thought_cache = ''
+                            thought_idx = 0
+
+                if code_block_delimiter_count == 3:
+                    if in_code_block:
+                        yield from extra_json_from_code_block(code_block_cache)
+                        code_block_cache = ''
+                        
+                    in_code_block = not in_code_block
+                    code_block_delimiter_count = 0
+
+                if not in_code_block:
+                    # handle single json
+                    if delta == '{':
+                        json_quote_count += 1
+                        in_json = True
+                        json_cache += delta
+                    elif delta == '}':
+                        json_cache += delta
+                        if json_quote_count > 0:
+                            json_quote_count -= 1
+                            if json_quote_count == 0:
+                                in_json = False
+                                got_json = True
+                                index += steps
+                                continue
+                    else:
+                        if in_json:
+                            json_cache += delta
+
+                    if got_json:
+                        got_json = False
+                        yield parse_action(json_cache)
+                        json_cache = ''
+                        json_quote_count = 0
+                        in_json = False
+                    
+                if not in_code_block and not in_json:
+                    yield delta.replace('`', '')
+
+                index += steps
+
+        if code_block_cache:
+            yield code_block_cache
+
+        if json_cache:
+            yield parse_action(json_cache)
+

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

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -189,6 +190,8 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
+                if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
+                    logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except Exception as e:
                 logger.exception("Unknown Error when generating")

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

@@ -98,6 +98,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
         )
 
         self._stream_generate_routes = self._get_stream_generate_routes()
+        self._conversation_name_generate_thread = None
 
     def process(self) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
         """
@@ -108,6 +109,12 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
         db.session.refresh(self._user)
         db.session.close()
 
+        # start generate conversation name thread
+        self._conversation_name_generate_thread = self._generate_conversation_name(
+            self._conversation,
+            self._application_generate_entity.query
+        )
+
         generator = self._process_stream_response()
         if self._stream:
             return self._to_stream_response(generator)
@@ -278,6 +285,9 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
             else:
                 continue
 
+        if self._conversation_name_generate_thread:
+            self._conversation_name_generate_thread.join()
+
     def _save_message(self) -> None:
         """
         Save message.

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

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -198,6 +199,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
+                if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
+                    logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except Exception as e:
                 logger.exception("Unknown Error when generating")

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

@@ -1,7 +1,8 @@
 import logging
 from typing import cast
 
-from core.agent.cot_agent_runner import CotAgentRunner
+from core.agent.cot_chat_agent_runner import CotChatAgentRunner
+from core.agent.cot_completion_agent_runner import CotCompletionAgentRunner
 from core.agent.entities import AgentEntity
 from core.agent.fc_agent_runner import FunctionCallAgentRunner
 from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfig
@@ -11,8 +12,8 @@ from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, Mo
 from core.app.entities.queue_entities import QueueAnnotationReplyEvent
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
-from core.model_runtime.entities.llm_entities import LLMUsage
-from core.model_runtime.entities.model_entities import ModelFeature
+from core.model_runtime.entities.llm_entities import LLMMode, LLMUsage
+from core.model_runtime.entities.model_entities import ModelFeature, ModelPropertyKey
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.moderation.base import ModerationException
 from core.tools.entities.tool_entities import ToolRuntimeVariablePool
@@ -207,48 +208,40 @@ class AgentChatAppRunner(AppRunner):
 
         # start agent runner
         if agent_entity.strategy == AgentEntity.Strategy.CHAIN_OF_THOUGHT:
-            assistant_cot_runner = CotAgentRunner(
-                tenant_id=app_config.tenant_id,
-                application_generate_entity=application_generate_entity,
-                app_config=app_config,
-                model_config=application_generate_entity.model_config,
-                config=agent_entity,
-                queue_manager=queue_manager,
-                message=message,
-                user_id=application_generate_entity.user_id,
-                memory=memory,
-                prompt_messages=prompt_message,
-                variables_pool=tool_variables,
-                db_variables=tool_conversation_variables,
-                model_instance=model_instance
-            )
-            invoke_result = assistant_cot_runner.run(
-                conversation=conversation,
-                message=message,
-                query=query,
-                inputs=inputs,
-            )
+            # check LLM mode
+            if model_schema.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
+                runner_cls = CotChatAgentRunner
+            elif model_schema.model_properties.get(ModelPropertyKey.MODE) == LLMMode.COMPLETION.value:
+                runner_cls = CotCompletionAgentRunner
+            else:
+                raise ValueError(f"Invalid LLM mode: {model_schema.model_properties.get(ModelPropertyKey.MODE)}")
         elif agent_entity.strategy == AgentEntity.Strategy.FUNCTION_CALLING:
-            assistant_fc_runner = FunctionCallAgentRunner(
-                tenant_id=app_config.tenant_id,
-                application_generate_entity=application_generate_entity,
-                app_config=app_config,
-                model_config=application_generate_entity.model_config,
-                config=agent_entity,
-                queue_manager=queue_manager,
-                message=message,
-                user_id=application_generate_entity.user_id,
-                memory=memory,
-                prompt_messages=prompt_message,
-                variables_pool=tool_variables,
-                db_variables=tool_conversation_variables,
-                model_instance=model_instance
-            )
-            invoke_result = assistant_fc_runner.run(
-                conversation=conversation,
-                message=message,
-                query=query,
-            )
+            runner_cls = FunctionCallAgentRunner
+        else:
+            raise ValueError(f"Invalid agent strategy: {agent_entity.strategy}")
+        
+        runner = runner_cls(
+            tenant_id=app_config.tenant_id,
+            application_generate_entity=application_generate_entity,
+            conversation=conversation,
+            app_config=app_config,
+            model_config=application_generate_entity.model_config,
+            config=agent_entity,
+            queue_manager=queue_manager,
+            message=message,
+            user_id=application_generate_entity.user_id,
+            memory=memory,
+            prompt_messages=prompt_message,
+            variables_pool=tool_variables,
+            db_variables=tool_conversation_variables,
+            model_instance=model_instance
+        )
+
+        invoke_result = runner.run(
+            message=message,
+            query=query,
+            inputs=inputs,
+        )
 
         # handle invoke result
         self._handle_invoke_result(

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

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -195,6 +196,8 @@ class ChatAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
+                if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
+                    logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except Exception as e:
                 logger.exception("Unknown Error when generating")

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

@@ -156,6 +156,8 @@ class ChatAppRunner(AppRunner):
 
             dataset_retrieval = DatasetRetrieval()
             context = dataset_retrieval.retrieve(
+                app_id=app_record.id,
+                user_id=application_generate_entity.user_id,
                 tenant_id=app_record.tenant_id,
                 model_config=application_generate_entity.model_config,
                 config=app_config.dataset,

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

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -184,6 +185,8 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
+                if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
+                    logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except Exception as e:
                 logger.exception("Unknown Error when generating")

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

@@ -116,6 +116,8 @@ class CompletionAppRunner(AppRunner):
 
             dataset_retrieval = DatasetRetrieval()
             context = dataset_retrieval.retrieve(
+                app_id=app_record.id,
+                user_id=application_generate_entity.user_id,
                 tenant_id=app_record.tenant_id,
                 model_config=application_generate_entity.model_config,
                 config=dataset_config,

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

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -137,6 +138,8 @@ class WorkflowAppGenerator(BaseAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
+                if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
+                    logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except Exception as e:
                 logger.exception("Unknown Error when generating")

api/core/app/task_pipeline/easy_ui_based_generate_task_pipeline.py

@@ -97,6 +97,8 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
             )
         )
 
+        self._conversation_name_generate_thread = None
+
     def process(self) -> Union[
         ChatbotAppBlockingResponse,
         CompletionAppBlockingResponse,
@@ -110,6 +112,13 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
         db.session.refresh(self._message)
         db.session.close()
 
+        if self._application_generate_entity.app_config.app_mode != AppMode.COMPLETION:
+            # start generate conversation name thread
+            self._conversation_name_generate_thread = self._generate_conversation_name(
+                self._conversation,
+                self._application_generate_entity.query
+            )
+
         generator = self._process_stream_response()
         if self._stream:
             return self._to_stream_response(generator)
@@ -256,6 +265,9 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
             else:
                 continue
 
+        if self._conversation_name_generate_thread:
+            self._conversation_name_generate_thread.join()
+
     def _save_message(self) -> None:
         """
         Save message.

api/core/app/task_pipeline/message_cycle_manage.py

@@ -1,5 +1,8 @@
+from threading import Thread
 from typing import Optional, Union
 
+from flask import Flask, current_app
+
 from core.app.entities.app_invoke_entities import (
     AdvancedChatAppGenerateEntity,
     AgentChatAppGenerateEntity,
@@ -19,9 +22,10 @@ from core.app.entities.task_entities import (
     MessageReplaceStreamResponse,
     MessageStreamResponse,
 )
+from core.llm_generator.llm_generator import LLMGenerator
 from core.tools.tool_file_manager import ToolFileManager
 from extensions.ext_database import db
-from models.model import MessageAnnotation, MessageFile
+from models.model import AppMode, Conversation, MessageAnnotation, MessageFile
 from services.annotation_service import AppAnnotationService
 
 
@@ -34,6 +38,59 @@ class MessageCycleManage:
     ]
     _task_state: Union[EasyUITaskState, AdvancedChatTaskState]
 
+    def _generate_conversation_name(self, conversation: Conversation, query: str) -> Optional[Thread]:
+        """
+        Generate conversation name.
+        :param conversation: conversation
+        :param query: query
+        :return: thread
+        """
+        is_first_message = self._application_generate_entity.conversation_id is None
+        extras = self._application_generate_entity.extras
+        auto_generate_conversation_name = extras.get('auto_generate_conversation_name', True)
+
+        if auto_generate_conversation_name and is_first_message:
+            # start generate thread
+            thread = Thread(target=self._generate_conversation_name_worker, kwargs={
+                'flask_app': current_app._get_current_object(),
+                'conversation_id': conversation.id,
+                'query': query
+            })
+
+            thread.start()
+
+            return thread
+
+        return None
+
+    def _generate_conversation_name_worker(self,
+                                           flask_app: Flask,
+                                           conversation_id: str,
+                                           query: str):
+        with flask_app.app_context():
+            # get conversation and message
+            conversation = (
+                db.session.query(Conversation)
+                .filter(Conversation.id == conversation_id)
+                .first()
+            )
+
+            if conversation.mode != AppMode.COMPLETION.value:
+                app_model = conversation.app
+                if not app_model:
+                    return
+
+                # generate conversation name
+                try:
+                    name = LLMGenerator.generate_conversation_name(app_model.tenant_id, query)
+                    conversation.name = name
+                except:
+                    pass
+
+                db.session.merge(conversation)
+                db.session.commit()
+                db.session.close()
+
     def _handle_annotation_reply(self, event: QueueAnnotationReplyEvent) -> Optional[MessageAnnotation]:
         """
         Handle annotation reply.

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -1,6 +1,6 @@
 import json
 import time
-from datetime import datetime
+from datetime import datetime, timezone
 from typing import Any, Optional, Union, cast
 
 from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom, WorkflowAppGenerateEntity
@@ -120,7 +120,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.utcnow()
+        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
 
         db.session.commit()
         db.session.refresh(workflow_run)
@@ -149,7 +149,7 @@ class WorkflowCycleManage:
         workflow_run.elapsed_time = time.perf_counter() - start_at
         workflow_run.total_tokens = total_tokens
         workflow_run.total_steps = total_steps
-        workflow_run.finished_at = datetime.utcnow()
+        workflow_run.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
 
         db.session.commit()
         db.session.refresh(workflow_run)
@@ -223,7 +223,7 @@ class WorkflowCycleManage:
         workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
         workflow_node_execution.execution_metadata = json.dumps(jsonable_encoder(execution_metadata)) \
             if execution_metadata else None
-        workflow_node_execution.finished_at = datetime.utcnow()
+        workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
 
         db.session.commit()
         db.session.refresh(workflow_node_execution)
@@ -251,7 +251,7 @@ class WorkflowCycleManage:
         workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
         workflow_node_execution.error = error
         workflow_node_execution.elapsed_time = time.perf_counter() - start_at
-        workflow_node_execution.finished_at = datetime.utcnow()
+        workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
         workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
         workflow_node_execution.process_data = json.dumps(process_data) if process_data else None
         workflow_node_execution.outputs = json.dumps(outputs) if outputs else None

api/core/callback_handler/agent_tool_callback_handler.py

@@ -1,12 +1,32 @@
 import os
-from typing import Any, Optional, Union
+from typing import Any, Optional, TextIO, Union
 
-from langchain.callbacks.base import BaseCallbackHandler
-from langchain.input import print_text
 from pydantic import BaseModel
 
+_TEXT_COLOR_MAPPING = {
+    "blue": "36;1",
+    "yellow": "33;1",
+    "pink": "38;5;200",
+    "green": "32;1",
+    "red": "31;1",
+}
 
-class DifyAgentCallbackHandler(BaseCallbackHandler, BaseModel):
+def get_colored_text(text: str, color: str) -> str:
+    """Get colored text."""
+    color_str = _TEXT_COLOR_MAPPING[color]
+    return f"\u001b[{color_str}m\033[1;3m{text}\u001b[0m"
+
+
+def print_text(
+    text: str, color: Optional[str] = None, end: str = "", file: Optional[TextIO] = None
+) -> None:
+    """Print text with highlighting and no end characters."""
+    text_to_print = get_colored_text(text, color) if color else text
+    print(text_to_print, end=end, file=file)
+    if file:
+        file.flush()  # ensure all printed content are written to file
+
+class DifyAgentCallbackHandler(BaseModel):
     """Callback Handler that prints to std out."""
     color: Optional[str] = ''
     current_loop = 1

api/core/embedding/cached_embedding.py

@@ -41,7 +41,8 @@ class CacheEmbedding(Embeddings):
             embedding_queue_embeddings = []
             try:
                 model_type_instance = cast(TextEmbeddingModel, self._model_instance.model_type_instance)
-                model_schema = model_type_instance.get_model_schema(self._model_instance.model, self._model_instance.credentials)
+                model_schema = model_type_instance.get_model_schema(self._model_instance.model,
+                                                                    self._model_instance.credentials)
                 max_chunks = model_schema.model_properties[ModelPropertyKey.MAX_CHUNKS] \
                     if model_schema and ModelPropertyKey.MAX_CHUNKS in model_schema.model_properties else 1
                 for i in range(0, len(embedding_queue_texts), max_chunks):
@@ -61,17 +62,20 @@ class CacheEmbedding(Embeddings):
                         except Exception as e:
                             logging.exception('Failed transform embedding: ', e)
                 cache_embeddings = []
-                for i, embedding in zip(embedding_queue_indices, embedding_queue_embeddings):
-                    text_embeddings[i] = embedding
-                    hash = helper.generate_text_hash(texts[i])
-                    if hash not in cache_embeddings:
-                        embedding_cache = Embedding(model_name=self._model_instance.model,
-                                              hash=hash,
-                                              provider_name=self._model_instance.provider)
-                        embedding_cache.set_embedding(embedding)
-                        db.session.add(embedding_cache)
-                        cache_embeddings.append(hash)
-                db.session.commit()
+                try:
+                    for i, embedding in zip(embedding_queue_indices, embedding_queue_embeddings):
+                        text_embeddings[i] = embedding
+                        hash = helper.generate_text_hash(texts[i])
+                        if hash not in cache_embeddings:
+                            embedding_cache = Embedding(model_name=self._model_instance.model,
+                                                        hash=hash,
+                                                        provider_name=self._model_instance.provider)
+                            embedding_cache.set_embedding(embedding)
+                            db.session.add(embedding_cache)
+                            cache_embeddings.append(hash)
+                    db.session.commit()
+                except IntegrityError:
+                    db.session.rollback()
             except Exception as ex:
                 db.session.rollback()
                 logger.error('Failed to embed documents: ', ex)

api/core/entities/message_entities.py

@@ -1,19 +1,8 @@
 import enum
-from typing import Any, cast
+from typing import Any
 
-from langchain.schema import AIMessage, BaseMessage, FunctionMessage, HumanMessage, SystemMessage
 from pydantic import BaseModel
 
-from core.model_runtime.entities.message_entities import (
-    AssistantPromptMessage,
-    ImagePromptMessageContent,
-    PromptMessage,
-    SystemPromptMessage,
-    TextPromptMessageContent,
-    ToolPromptMessage,
-    UserPromptMessage,
-)
-
 
 class PromptMessageFileType(enum.Enum):
     IMAGE = 'image'
@@ -38,98 +27,3 @@ class ImagePromptMessageFile(PromptMessageFile):
 
     type: PromptMessageFileType = PromptMessageFileType.IMAGE
     detail: DETAIL = DETAIL.LOW
-
-
-class LCHumanMessageWithFiles(HumanMessage):
-    # content: Union[str, list[Union[str, Dict]]]
-    content: str
-    files: list[PromptMessageFile]
-
-
-def lc_messages_to_prompt_messages(messages: list[BaseMessage]) -> list[PromptMessage]:
-    prompt_messages = []
-    for message in messages:
-        if isinstance(message, HumanMessage):
-            if isinstance(message, LCHumanMessageWithFiles):
-                file_prompt_message_contents = []
-                for file in message.files:
-                    if file.type == PromptMessageFileType.IMAGE:
-                        file = cast(ImagePromptMessageFile, file)
-                        file_prompt_message_contents.append(ImagePromptMessageContent(
-                            data=file.data,
-                            detail=ImagePromptMessageContent.DETAIL.HIGH
-                            if file.detail.value == "high" else ImagePromptMessageContent.DETAIL.LOW
-                        ))
-
-                prompt_message_contents = [TextPromptMessageContent(data=message.content)]
-                prompt_message_contents.extend(file_prompt_message_contents)
-
-                prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
-            else:
-                prompt_messages.append(UserPromptMessage(content=message.content))
-        elif isinstance(message, AIMessage):
-            message_kwargs = {
-                'content': message.content
-            }
-
-            if 'function_call' in message.additional_kwargs:
-                message_kwargs['tool_calls'] = [
-                    AssistantPromptMessage.ToolCall(
-                        id=message.additional_kwargs['function_call']['id'],
-                        type='function',
-                        function=AssistantPromptMessage.ToolCall.ToolCallFunction(
-                            name=message.additional_kwargs['function_call']['name'],
-                            arguments=message.additional_kwargs['function_call']['arguments']
-                        )
-                    )
-                ]
-
-            prompt_messages.append(AssistantPromptMessage(**message_kwargs))
-        elif isinstance(message, SystemMessage):
-            prompt_messages.append(SystemPromptMessage(content=message.content))
-        elif isinstance(message, FunctionMessage):
-            prompt_messages.append(ToolPromptMessage(content=message.content, tool_call_id=message.name))
-
-    return prompt_messages
-
-
-def prompt_messages_to_lc_messages(prompt_messages: list[PromptMessage]) -> list[BaseMessage]:
-    messages = []
-    for prompt_message in prompt_messages:
-        if isinstance(prompt_message, UserPromptMessage):
-            if isinstance(prompt_message.content, str):
-                messages.append(HumanMessage(content=prompt_message.content))
-            else:
-                message_contents = []
-                for content in prompt_message.content:
-                    if isinstance(content, TextPromptMessageContent):
-                        message_contents.append(content.data)
-                    elif isinstance(content, ImagePromptMessageContent):
-                        message_contents.append({
-                            'type': 'image',
-                            'data': content.data,
-                            'detail': content.detail.value
-                        })
-
-                messages.append(HumanMessage(content=message_contents))
-        elif isinstance(prompt_message, AssistantPromptMessage):
-            message_kwargs = {
-                'content': prompt_message.content
-            }
-
-            if prompt_message.tool_calls:
-                message_kwargs['additional_kwargs'] = {
-                    'function_call': {
-                        'id': prompt_message.tool_calls[0].id,
-                        'name': prompt_message.tool_calls[0].function.name,
-                        'arguments': prompt_message.tool_calls[0].function.arguments
-                    }
-                }
-
-            messages.append(AIMessage(**message_kwargs))
-        elif isinstance(prompt_message, SystemPromptMessage):
-            messages.append(SystemMessage(content=prompt_message.content))
-        elif isinstance(prompt_message, ToolPromptMessage):
-            messages.append(FunctionMessage(name=prompt_message.tool_call_id, content=prompt_message.content))
-
-    return messages

api/core/entities/provider_configuration.py

@@ -203,7 +203,7 @@ class ProviderConfiguration(BaseModel):
         if provider_record:
             provider_record.encrypted_config = json.dumps(credentials)
             provider_record.is_valid = True
-            provider_record.updated_at = datetime.datetime.utcnow()
+            provider_record.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             db.session.commit()
         else:
             provider_record = Provider(
@@ -351,7 +351,7 @@ class ProviderConfiguration(BaseModel):
         if provider_model_record:
             provider_model_record.encrypted_config = json.dumps(credentials)
             provider_model_record.is_valid = True
-            provider_model_record.updated_at = datetime.datetime.utcnow()
+            provider_model_record.updated_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             db.session.commit()
         else:
             provider_model_record = ProviderModel(

api/core/helper/code_executor/code_executor.py

@@ -1,17 +1,17 @@
-from os import environ
 from typing import Literal, Optional
 
 from httpx import post
 from pydantic import BaseModel
 from yarl import URL
 
+from config import get_env
 from core.helper.code_executor.javascript_transformer import NodeJsTemplateTransformer
 from core.helper.code_executor.jina2_transformer import Jinja2TemplateTransformer
 from core.helper.code_executor.python_transformer import PythonTemplateTransformer
 
 # Code Executor
-CODE_EXECUTION_ENDPOINT = environ.get('CODE_EXECUTION_ENDPOINT', '')
-CODE_EXECUTION_API_KEY = environ.get('CODE_EXECUTION_API_KEY', '')
+CODE_EXECUTION_ENDPOINT = get_env('CODE_EXECUTION_ENDPOINT')
+CODE_EXECUTION_API_KEY = get_env('CODE_EXECUTION_API_KEY')
 
 CODE_EXECUTION_TIMEOUT= (10, 60)
 
@@ -27,6 +27,7 @@ class CodeExecutionResponse(BaseModel):
     message: str
     data: Data
 
+
 class CodeExecutor:
     @classmethod
     def execute_code(cls, language: Literal['python3', 'javascript', 'jinja2'], code: str, inputs: dict) -> dict:

api/core/helper/code_executor/javascript_transformer.py

@@ -29,16 +29,16 @@ class NodeJsTemplateTransformer(TemplateTransformer):
         :param inputs: inputs
         :return:
         """
-        
+
         # transform inputs to json string
-        inputs_str = json.dumps(inputs, indent=4)
+        inputs_str = json.dumps(inputs, indent=4, ensure_ascii=False)
 
         # replace code and inputs
         runner = NODEJS_RUNNER.replace('{{code}}', code)
         runner = runner.replace('{{inputs}}', inputs_str)
 
         return runner, NODEJS_PRELOAD
-    
+
     @classmethod
     def transform_response(cls, response: str) -> dict:
         """

api/core/helper/code_executor/jina2_transformer.py

@@ -62,10 +62,10 @@ class Jinja2TemplateTransformer(TemplateTransformer):
 
         # transform jinja2 template to python code
         runner = PYTHON_RUNNER.replace('{{code}}', code)
-        runner = runner.replace('{{inputs}}', json.dumps(inputs, indent=4))
+        runner = runner.replace('{{inputs}}', json.dumps(inputs, indent=4, ensure_ascii=False))
 
         return runner, JINJA2_PRELOAD
-    
+
     @classmethod
     def transform_response(cls, response: str) -> dict:
         """
@@ -81,4 +81,4 @@ class Jinja2TemplateTransformer(TemplateTransformer):
 
         return {
             'result': result
-        }
+        }

api/core/helper/code_executor/python_transformer.py

@@ -34,7 +34,7 @@ class PythonTemplateTransformer(TemplateTransformer):
         """
         
         # transform inputs to json string
-        inputs_str = json.dumps(inputs, indent=4)
+        inputs_str = json.dumps(inputs, indent=4, ensure_ascii=False)
 
         # replace code and inputs
         runner = PYTHON_RUNNER.replace('{{code}}', code)

api/core/indexing_runner.py

@@ -19,6 +19,7 @@ from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.model_entities import ModelType, PriceType
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
+from core.rag.datasource.keyword.keyword_factory import Keyword
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from core.rag.index_processor.index_processor_base import BaseIndexProcessor
 from core.rag.index_processor.index_processor_factory import IndexProcessorFactory
@@ -80,7 +81,7 @@ class IndexingRunner:
             except ProviderTokenNotInitError as e:
                 dataset_document.indexing_status = 'error'
                 dataset_document.error = str(e.description)
-                dataset_document.stopped_at = datetime.datetime.utcnow()
+                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
                 db.session.commit()
             except ObjectDeletedError:
                 logging.warning('Document deleted, document id: {}'.format(dataset_document.id))
@@ -88,7 +89,7 @@ class IndexingRunner:
                 logging.exception("consume document failed")
                 dataset_document.indexing_status = 'error'
                 dataset_document.error = str(e)
-                dataset_document.stopped_at = datetime.datetime.utcnow()
+                dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
                 db.session.commit()
 
     def run_in_splitting_status(self, dataset_document: DatasetDocument):
@@ -139,13 +140,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = 'error'
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.utcnow()
+            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = 'error'
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.utcnow()
+            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
     def run_in_indexing_status(self, dataset_document: DatasetDocument):
@@ -201,13 +202,13 @@ class IndexingRunner:
         except ProviderTokenNotInitError as e:
             dataset_document.indexing_status = 'error'
             dataset_document.error = str(e.description)
-            dataset_document.stopped_at = datetime.datetime.utcnow()
+            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             db.session.commit()
         except Exception as e:
             logging.exception("consume document failed")
             dataset_document.indexing_status = 'error'
             dataset_document.error = str(e)
-            dataset_document.stopped_at = datetime.datetime.utcnow()
+            dataset_document.stopped_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             db.session.commit()
 
     def indexing_estimate(self, tenant_id: str, extract_settings: list[ExtractSetting], tmp_processing_rule: dict,
@@ -381,7 +382,7 @@ class IndexingRunner:
             after_indexing_status="splitting",
             extra_update_params={
                 DatasetDocument.word_count: sum([len(text_doc.page_content) for text_doc in text_docs]),
-                DatasetDocument.parsing_completed_at: datetime.datetime.utcnow()
+                DatasetDocument.parsing_completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             }
         )
 
@@ -466,7 +467,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.utcnow()
+        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -481,7 +482,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.utcnow()
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             }
         )
 
@@ -657,18 +658,25 @@ class IndexingRunner:
         if embedding_model_instance:
             embedding_model_type_instance = embedding_model_instance.model_type_instance
             embedding_model_type_instance = cast(TextEmbeddingModel, embedding_model_type_instance)
-        with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
-            futures = []
-            for i in range(0, len(documents), chunk_size):
-                chunk_documents = documents[i:i + chunk_size]
-                futures.append(executor.submit(self._process_chunk, current_app._get_current_object(), index_processor,
-                                               chunk_documents, dataset,
-                                               dataset_document, embedding_model_instance,
-                                               embedding_model_type_instance))
+        # create keyword index
+        create_keyword_thread = threading.Thread(target=self._process_keyword_index,
+                                                 args=(current_app._get_current_object(),
+                                                       dataset.id, dataset_document.id, documents))
+        create_keyword_thread.start()
+        if dataset.indexing_technique == 'high_quality':
+            with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
+                futures = []
+                for i in range(0, len(documents), chunk_size):
+                    chunk_documents = documents[i:i + chunk_size]
+                    futures.append(executor.submit(self._process_chunk, current_app._get_current_object(), index_processor,
+                                                   chunk_documents, dataset,
+                                                   dataset_document, embedding_model_instance,
+                                                   embedding_model_type_instance))
 
-            for future in futures:
-                tokens += future.result()
+                for future in futures:
+                    tokens += future.result()
 
+        create_keyword_thread.join()
         indexing_end_at = time.perf_counter()
 
         # update document status to completed
@@ -677,11 +685,32 @@ class IndexingRunner:
             after_indexing_status="completed",
             extra_update_params={
                 DatasetDocument.tokens: tokens,
-                DatasetDocument.completed_at: datetime.datetime.utcnow(),
+                DatasetDocument.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
                 DatasetDocument.indexing_latency: indexing_end_at - indexing_start_at,
             }
         )
 
+    def _process_keyword_index(self, flask_app, dataset_id, document_id, documents):
+        with flask_app.app_context():
+            dataset = Dataset.query.filter_by(id=dataset_id).first()
+            if not dataset:
+                raise ValueError("no dataset found")
+            keyword = Keyword(dataset)
+            keyword.create(documents)
+            if dataset.indexing_technique != 'high_quality':
+                document_ids = [document.metadata['doc_id'] for document in documents]
+                db.session.query(DocumentSegment).filter(
+                    DocumentSegment.document_id == document_id,
+                    DocumentSegment.index_node_id.in_(document_ids),
+                    DocumentSegment.status == "indexing"
+                ).update({
+                    DocumentSegment.status: "completed",
+                    DocumentSegment.enabled: True,
+                    DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                })
+
+                db.session.commit()
+
     def _process_chunk(self, flask_app, index_processor, chunk_documents, dataset, dataset_document,
                        embedding_model_instance, embedding_model_type_instance):
         with flask_app.app_context():
@@ -700,7 +729,7 @@ class IndexingRunner:
                 )
 
             # load index
-            index_processor.load(dataset, chunk_documents)
+            index_processor.load(dataset, chunk_documents, with_keywords=False)
 
             document_ids = [document.metadata['doc_id'] for document in chunk_documents]
             db.session.query(DocumentSegment).filter(
@@ -710,7 +739,7 @@ class IndexingRunner:
             ).update({
                 DocumentSegment.status: "completed",
                 DocumentSegment.enabled: True,
-                DocumentSegment.completed_at: datetime.datetime.utcnow()
+                DocumentSegment.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             })
 
             db.session.commit()
@@ -809,7 +838,7 @@ class IndexingRunner:
         doc_store.add_documents(documents)
 
         # update document status to indexing
-        cur_time = datetime.datetime.utcnow()
+        cur_time = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
         self._update_document_index_status(
             document_id=dataset_document.id,
             after_indexing_status="indexing",
@@ -824,7 +853,7 @@ class IndexingRunner:
             dataset_document_id=dataset_document.id,
             update_params={
                 DocumentSegment.status: "indexing",
-                DocumentSegment.indexing_at: datetime.datetime.utcnow()
+                DocumentSegment.indexing_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
             }
         )
         pass

api/core/llm_generator/llm_generator.py

@@ -1,8 +1,7 @@
 import json
 import logging
 
-from langchain.schema import OutputParserException
-
+from core.llm_generator.output_parser.errors import OutputParserException
 from core.llm_generator.output_parser.rule_config_generator import RuleConfigGeneratorOutputParser
 from core.llm_generator.output_parser.suggested_questions_after_answer import SuggestedQuestionsAfterAnswerOutputParser
 from core.llm_generator.prompts import CONVERSATION_TITLE_PROMPT, GENERATOR_QA_PROMPT

api/core/llm_generator/output_parser/errors.py

@@ -0,0 +1,2 @@
+class OutputParserException(Exception):
+    pass

api/core/llm_generator/output_parser/rule_config_generator.py

@@ -1,12 +1,11 @@
 from typing import Any
 
-from langchain.schema import BaseOutputParser, OutputParserException
-
+from core.llm_generator.output_parser.errors import OutputParserException
 from core.llm_generator.prompts import RULE_CONFIG_GENERATE_TEMPLATE
 from libs.json_in_md_parser import parse_and_check_json_markdown
 
 
-class RuleConfigGeneratorOutputParser(BaseOutputParser):
+class RuleConfigGeneratorOutputParser:
 
     def get_format_instructions(self) -> str:
         return RULE_CONFIG_GENERATE_TEMPLATE

api/core/llm_generator/output_parser/suggested_questions_after_answer.py

@@ -2,12 +2,10 @@ import json
 import re
 from typing import Any
 
-from langchain.schema import BaseOutputParser
-
 from core.llm_generator.prompts import SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT
 
 
-class SuggestedQuestionsAfterAnswerOutputParser(BaseOutputParser):
+class SuggestedQuestionsAfterAnswerOutputParser:
 
     def get_format_instructions(self) -> str:
         return SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT

api/core/memory/token_buffer_memory.py

@@ -3,6 +3,7 @@ from core.file.message_file_parser import MessageFileParser
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
+    ImagePromptMessageContent,
     PromptMessage,
     PromptMessageRole,
     TextPromptMessageContent,
@@ -124,7 +125,17 @@ class TokenBufferMemory:
             else:
                 continue
 
-            message = f"{role}: {m.content}"
-            string_messages.append(message)
+            if isinstance(m.content, list):
+                inner_msg = ""
+                for content in m.content:
+                    if isinstance(content, TextPromptMessageContent):
+                        inner_msg += f"{content.data}\n"
+                    elif isinstance(content, ImagePromptMessageContent):
+                        inner_msg += "[image]\n"
+
+                string_messages.append(f"{role}: {inner_msg.strip()}")
+            else:
+                message = f"{role}: {m.content}"
+                string_messages.append(message)
 
         return "\n".join(string_messages)

api/core/model_runtime/model_providers/azure_openai/azure_openai.yaml

@@ -99,6 +99,12 @@ model_credential_schema:
           show_on:
             - variable: __model_type
               value: llm
+        - label:
+            en_US: gpt-4-turbo-2024-04-09
+          value: gpt-4-turbo-2024-04-09
+          show_on:
+            - variable: __model_type
+              value: llm
         - label:
             en_US: gpt-4-0125-preview
           value: gpt-4-0125-preview

api/core/model_runtime/model_providers/azure_openai/llm/llm.py

@@ -343,8 +343,12 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
 
             delta = chunk.choices[0]
 
-            if delta.finish_reason is None and (delta.delta.content is None or delta.delta.content == '') and \
-                delta.delta.function_call is None:
+            # Handling exceptions when content filters' streaming mode is set to asynchronous modified filter
+            if delta.delta is None or (
+                delta.finish_reason is None
+                and (delta.delta.content is None or delta.delta.content == '')
+                and delta.delta.function_call is None
+            ):
                 continue
             
             # assistant_message_tool_calls = delta.delta.tool_calls

api/core/model_runtime/model_providers/bedrock/bedrock.yaml

@@ -15,6 +15,7 @@ help:
     en_US: https://console.aws.amazon.com/
 supported_model_types:
   - llm
+  - text-embedding
 configurate_methods:
   - predefined-model
 provider_credential_schema:
@@ -74,7 +75,7 @@ provider_credential_schema:
       label:
         en_US: Available Model Name
         zh_Hans: 可用模型名称
-      type: secret-input
+      type: text-input
       placeholder:
         en_US: A model you have access to (e.g. amazon.titan-text-lite-v1) for validation.
         zh_Hans: 为了进行验证，请输入一个您可用的模型名称 (例如：amazon.titan-text-lite-v1)

api/core/model_runtime/model_providers/bedrock/llm/amazon.titan-text-express-v1.yaml

@@ -2,8 +2,6 @@ model: amazon.titan-text-express-v1
 label:
   en_US: Titan Text G1 - Express
 model_type: llm
-features:
-  - agent-thought
 model_properties:
   mode: chat
   context_size: 8192

api/core/model_runtime/model_providers/bedrock/llm/amazon.titan-text-lite-v1.yaml

@@ -2,8 +2,6 @@ model: amazon.titan-text-lite-v1
 label:
   en_US: Titan Text G1 - Lite
 model_type: llm
-features:
-  - agent-thought
 model_properties:
   mode: chat
   context_size: 4096

api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-v1.yaml

@@ -50,3 +50,4 @@ pricing:
   output: '0.024'
   unit: '0.001'
   currency: USD
+deprecated: true

api/core/model_runtime/model_providers/bedrock/llm/cohere.command-light-text-v14.yaml

@@ -22,7 +22,7 @@ parameter_rules:
     min: 0
     max: 500
     default: 0
-  - name: max_tokens_to_sample
+  - name: max_tokens
     use_template: max_tokens
     required: true
     default: 4096

api/core/model_runtime/model_providers/bedrock/llm/cohere.command-text-v14.yaml

@@ -8,9 +8,9 @@ model_properties:
 parameter_rules:
   - name: temperature
     use_template: temperature
-  - name: top_p
+  - name: p
     use_template: top_p
-  - name: top_k
+  - name: k
     label:
       zh_Hans: 取样数量
       en_US: Top k
@@ -19,7 +19,7 @@ parameter_rules:
       zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
       en_US: Only sample from the top K options for each subsequent token.
     required: false
-  - name: max_tokens_to_sample
+  - name: max_tokens
     use_template: max_tokens
     required: true
     default: 4096

api/core/model_runtime/model_providers/bedrock/llm/llm.py

@@ -402,25 +402,25 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
         :param credentials: model credentials
         :return:
         """
-
-        if "anthropic.claude-3" in model:
-            try:
-                self._invoke_claude(model=model,
-                                        credentials=credentials,
-                                        prompt_messages=[{"role": "user", "content": "ping"}],
-                                        model_parameters={},
-                                        stop=None,
-                                        stream=False)
-
-            except Exception as ex:
-                raise CredentialsValidateFailedError(str(ex))
-
+        required_params = {}
+        if "anthropic" in model:
+            required_params = {
+                "max_tokens": 32,
+            }
+        elif "ai21" in model:
+            # ValidationException: Malformed input request: #/temperature: expected type: Number, found: Null#/maxTokens: expected type: Integer, found: Null#/topP: expected type: Number, found: Null, please reformat your input and try again.
+            required_params = {
+                "temperature": 0.7,
+                "topP": 0.9,
+                "maxTokens": 32,
+            }
+            
         try:
             ping_message = UserPromptMessage(content="ping")
-            self._generate(model=model,
+            self._invoke(model=model,
                            credentials=credentials,
                            prompt_messages=[ping_message],
-                           model_parameters={},
+                           model_parameters=required_params,
                            stream=False)
         
         except ClientError as ex:
@@ -503,7 +503,7 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
 
         if model_prefix == "amazon":
             payload["textGenerationConfig"] = { **model_parameters }
-            payload["textGenerationConfig"]["stopSequences"] = ["User:"] + (stop if stop else [])
+            payload["textGenerationConfig"]["stopSequences"] = ["User:"]
             
             payload["inputText"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
         
@@ -513,10 +513,6 @@ class BedrockLargeLanguageModel(LargeLanguageModel):
             payload["maxTokens"] = model_parameters.get("maxTokens")
             payload["prompt"] = self._convert_messages_to_prompt(prompt_messages, model_prefix)
 
-            # jurassic models only support a single stop sequence
-            if stop:
-                payload["stopSequences"] = stop[0]
-
             if model_parameters.get("presencePenalty"):
                 payload["presencePenalty"] = {model_parameters.get("presencePenalty")}
             if model_parameters.get("frequencyPenalty"):

api/core/model_runtime/model_providers/bedrock/text_embedding/_position.yaml

@@ -0,0 +1,3 @@
+- amazon.titan-embed-text-v1
+- cohere.embed-english-v3
+- cohere.embed-multilingual-v3

api/core/model_runtime/model_providers/bedrock/text_embedding/amazon.titan-embed-text-v1.yaml

@@ -0,0 +1,8 @@
+model: amazon.titan-embed-text-v1
+model_type: text-embedding
+model_properties:
+  context_size: 8192
+pricing:
+  input: '0.0001'
+  unit: '0.001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/text_embedding/cohere.embed-english-v3.yaml

@@ -0,0 +1,8 @@
+model: cohere.embed-english-v3
+model_type: text-embedding
+model_properties:
+  context_size: 512
+pricing:
+  input: '0.1'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/text_embedding/cohere.embed-multilingual-v3.yaml

@@ -0,0 +1,8 @@
+model: cohere.embed-multilingual-v3
+model_type: text-embedding
+model_properties:
+  context_size: 512
+pricing:
+  input: '0.1'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/bedrock/text_embedding/text_embedding.py

@@ -0,0 +1,234 @@
+import json
+import logging
+import time
+from typing import Optional
+
+import boto3
+from botocore.config import Config
+from botocore.exceptions import (
+    ClientError,
+    EndpointConnectionError,
+    NoRegionError,
+    ServiceNotInRegionError,
+    UnknownServiceError,
+)
+
+from core.model_runtime.entities.model_entities import PriceType
+from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
+from core.model_runtime.errors.invoke import (
+    InvokeAuthorizationError,
+    InvokeBadRequestError,
+    InvokeConnectionError,
+    InvokeError,
+    InvokeRateLimitError,
+    InvokeServerUnavailableError,
+)
+from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
+
+logger = logging.getLogger(__name__)
+
+class BedrockTextEmbeddingModel(TextEmbeddingModel):
+
+
+    def _invoke(self, model: str, credentials: dict,
+                texts: list[str], user: Optional[str] = None) \
+            -> TextEmbeddingResult:
+        """
+        Invoke text embedding model
+
+        :param model: model name
+        :param credentials: model credentials
+        :param texts: texts to embed
+        :param user: unique user id
+        :return: embeddings result
+        """
+        client_config = Config(
+            region_name=credentials["aws_region"]
+        )
+
+        bedrock_runtime = boto3.client(
+            service_name='bedrock-runtime',
+            config=client_config,
+            aws_access_key_id=credentials["aws_access_key_id"],
+            aws_secret_access_key=credentials["aws_secret_access_key"]
+        )
+
+        embeddings = []
+        token_usage = 0
+        
+        model_prefix = model.split('.')[0]
+         
+        if model_prefix == "amazon" :
+           for text in texts:
+              body = {
+                 "inputText": text,
+              }
+              response_body = self._invoke_bedrock_embedding(model, bedrock_runtime, body)
+              embeddings.extend([response_body.get('embedding')])
+              token_usage += response_body.get('inputTextTokenCount')
+           logger.warning(f'Total Tokens: {token_usage}')
+           result = TextEmbeddingResult(
+                model=model,
+                embeddings=embeddings,
+                usage=self._calc_response_usage(
+                    model=model,
+                    credentials=credentials,
+                    tokens=token_usage
+                )
+           )
+           return result
+           
+        if model_prefix == "cohere" :
+           input_type = 'search_document' if len(texts) > 1 else 'search_query'
+           for text in texts:
+              body = {
+                 "texts": [text],
+                 "input_type": input_type,
+              }
+              response_body = self._invoke_bedrock_embedding(model, bedrock_runtime, body)
+              embeddings.extend(response_body.get('embeddings'))
+              token_usage += len(text)
+           result = TextEmbeddingResult(
+                model=model,
+                embeddings=embeddings,
+                usage=self._calc_response_usage(
+                    model=model,
+                    credentials=credentials,
+                    tokens=token_usage
+                )
+           )
+           return result
+        
+        #others
+        raise ValueError(f"Got unknown model prefix {model_prefix} when handling block response")
+
+
+    def get_num_tokens(self, model: str, credentials: dict, texts: list[str]) -> int:
+        """
+        Get number of tokens for given prompt messages
+
+        :param model: model name
+        :param credentials: model credentials
+        :param texts: texts to embed
+        :return:
+        """
+        num_tokens = 0
+        for text in texts:
+            num_tokens += self._get_num_tokens_by_gpt2(text)
+        return num_tokens
+
+    def validate_credentials(self, model: str, credentials: dict) -> None:
+        """
+        Validate model credentials
+
+        :param model: model name
+        :param credentials: model credentials
+        :return:
+        """
+    
+    @property
+    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
+        """
+        Map model invoke error to unified error
+        The key is the ermd = genai.GenerativeModel(model)ror type thrown to the caller
+        The value is the md = genai.GenerativeModel(model)error type thrown by the model,
+        which needs to be converted into a unified error type for the caller.
+
+        :return: Invoke emd = genai.GenerativeModel(model)rror mapping
+        """
+        return {
+            InvokeConnectionError: [],
+            InvokeServerUnavailableError: [],
+            InvokeRateLimitError: [],
+            InvokeAuthorizationError: [],
+            InvokeBadRequestError: []
+        }
+    
+    def _create_payload(self, model_prefix: str, texts: list[str], model_parameters: dict, stop: Optional[list[str]] = None, stream: bool = True):
+        """
+        Create payload for bedrock api call depending on model provider
+        """
+        payload = dict()
+
+        if model_prefix == "amazon":
+            payload['inputText'] = texts
+
+    
+    def _calc_response_usage(self, model: str, credentials: dict, tokens: int) -> EmbeddingUsage:
+        """
+        Calculate response usage
+
+        :param model: model name
+        :param credentials: model credentials
+        :param tokens: input tokens
+        :return: usage
+        """
+        # get input price info
+        input_price_info = self.get_price(
+            model=model,
+            credentials=credentials,
+            price_type=PriceType.INPUT,
+            tokens=tokens
+        )
+
+        # transform usage
+        usage = EmbeddingUsage(
+            tokens=tokens,
+            total_tokens=tokens,
+            unit_price=input_price_info.unit_price,
+            price_unit=input_price_info.unit,
+            total_price=input_price_info.total_amount,
+            currency=input_price_info.currency,
+            latency=time.perf_counter() - self.started_at
+        )
+
+        return usage
+    
+    def _map_client_to_invoke_error(self, error_code: str, error_msg: str) -> type[InvokeError]:
+        """
+        Map client error to invoke error
+
+        :param error_code: error code
+        :param error_msg: error message
+        :return: invoke error
+        """
+
+        if error_code == "AccessDeniedException":
+            return InvokeAuthorizationError(error_msg)
+        elif error_code in ["ResourceNotFoundException", "ValidationException"]:
+            return InvokeBadRequestError(error_msg)
+        elif error_code in ["ThrottlingException", "ServiceQuotaExceededException"]:
+            return InvokeRateLimitError(error_msg)
+        elif error_code in ["ModelTimeoutException", "ModelErrorException", "InternalServerException", "ModelNotReadyException"]:
+            return InvokeServerUnavailableError(error_msg)
+        elif error_code == "ModelStreamErrorException":
+            return InvokeConnectionError(error_msg)
+
+        return InvokeError(error_msg)
+    
+
+    def _invoke_bedrock_embedding(self, model: str, bedrock_runtime, body: dict, ):
+        accept = 'application/json' 
+        content_type = 'application/json'
+        try:
+            response = bedrock_runtime.invoke_model(
+                body=json.dumps(body), 
+                modelId=model, 
+                accept=accept, 
+                contentType=content_type
+            )
+            response_body = json.loads(response.get('body').read().decode('utf-8'))
+            return response_body
+        except ClientError as ex:
+            error_code = ex.response['Error']['Code']
+            full_error_msg = f"{error_code}: {ex.response['Error']['Message']}"
+            raise self._map_client_to_invoke_error(error_code, full_error_msg)
+        
+        except (EndpointConnectionError, NoRegionError, ServiceNotInRegionError) as ex:
+            raise InvokeConnectionError(str(ex))
+
+        except UnknownServiceError as ex:
+            raise InvokeServerUnavailableError(str(ex))
+
+        except Exception as ex:
+            raise InvokeError(str(ex))

api/core/model_runtime/model_providers/cohere/llm/_position.yaml

@@ -1,3 +1,5 @@
+- command-r
+- command-r-plus
 - command-chat
 - command-light-chat
 - command-nightly-chat

api/core/model_runtime/model_providers/cohere/llm/command-chat.yaml

@@ -31,7 +31,7 @@ parameter_rules:
     max: 500
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
   - name: preamble_override
     label:

api/core/model_runtime/model_providers/cohere/llm/command-light-chat.yaml

@@ -31,7 +31,7 @@ parameter_rules:
     max: 500
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
   - name: preamble_override
     label:

api/core/model_runtime/model_providers/cohere/llm/command-light-nightly-chat.yaml

@@ -31,7 +31,7 @@ parameter_rules:
     max: 500
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
   - name: preamble_override
     label:

api/core/model_runtime/model_providers/cohere/llm/command-light-nightly.yaml

@@ -35,7 +35,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
 pricing:
   input: '0.3'

api/core/model_runtime/model_providers/cohere/llm/command-light.yaml

@@ -35,7 +35,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
 pricing:
   input: '0.3'

api/core/model_runtime/model_providers/cohere/llm/command-nightly-chat.yaml

@@ -31,7 +31,7 @@ parameter_rules:
     max: 500
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
   - name: preamble_override
     label:

api/core/model_runtime/model_providers/cohere/llm/command-nightly.yaml

@@ -35,7 +35,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
 pricing:
   input: '1.0'

api/core/model_runtime/model_providers/cohere/llm/command-r-plus.yaml

@@ -0,0 +1,45 @@
+model: command-r-plus
+label:
+  en_US: command-r-plus
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    max: 5.0
+  - name: p
+    use_template: top_p
+    default: 0.75
+    min: 0.01
+    max: 0.99
+  - name: k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 0
+    min: 0
+    max: 500
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    max: 4096
+pricing:
+  input: '3'
+  output: '15'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/cohere/llm/command-r.yaml

@@ -0,0 +1,45 @@
+model: command-r
+label:
+  en_US: command-r
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    max: 5.0
+  - name: p
+    use_template: top_p
+    default: 0.75
+    min: 0.01
+    max: 0.99
+  - name: k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 0
+    min: 0
+    max: 500
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    max: 4096
+pricing:
+  input: '0.5'
+  output: '1.5'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/cohere/llm/command.yaml

@@ -35,7 +35,7 @@ parameter_rules:
     use_template: frequency_penalty
   - name: max_tokens
     use_template: max_tokens
-    default: 256
+    default: 1024
     max: 4096
 pricing:
   input: '1.0'

api/core/model_runtime/model_providers/cohere/llm/llm.py

@@ -1,20 +1,38 @@
+import json
 import logging
-from collections.abc import Generator
+from collections.abc import Generator, Iterator
 from typing import Optional, Union, cast
 
 import cohere
-from cohere.responses import Chat, Generations
-from cohere.responses.chat import StreamEnd, StreamingChat, StreamTextGeneration
-from cohere.responses.generation import StreamingGenerations, StreamingText
+from cohere import (
+    ChatMessage,
+    ChatStreamRequestToolResultsItem,
+    GenerateStreamedResponse,
+    GenerateStreamedResponse_StreamEnd,
+    GenerateStreamedResponse_StreamError,
+    GenerateStreamedResponse_TextGeneration,
+    Generation,
+    NonStreamedChatResponse,
+    StreamedChatResponse,
+    StreamedChatResponse_StreamEnd,
+    StreamedChatResponse_TextGeneration,
+    StreamedChatResponse_ToolCallsGeneration,
+    Tool,
+    ToolCall,
+    ToolParameterDefinitionsValue,
+)
+from cohere.core import RequestOptions
 
 from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     PromptMessage,
     PromptMessageContentType,
+    PromptMessageRole,
     PromptMessageTool,
     SystemPromptMessage,
     TextPromptMessageContent,
+    ToolPromptMessage,
     UserPromptMessage,
 )
 from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, I18nObject, ModelType
@@ -64,6 +82,7 @@ class CohereLargeLanguageModel(LargeLanguageModel):
                 credentials=credentials,
                 prompt_messages=prompt_messages,
                 model_parameters=model_parameters,
+                tools=tools,
                 stop=stop,
                 stream=stream,
                 user=user
@@ -159,19 +178,26 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         if stop:
             model_parameters['end_sequences'] = stop
 
-        response = client.generate(
-            prompt=prompt_messages[0].content,
-            model=model,
-            stream=stream,
-            **model_parameters,
-        )
-
         if stream:
+            response = client.generate_stream(
+                prompt=prompt_messages[0].content,
+                model=model,
+                **model_parameters,
+                request_options=RequestOptions(max_retries=0)
+            )
+
             return self._handle_generate_stream_response(model, credentials, response, prompt_messages)
+        else:
+            response = client.generate(
+                prompt=prompt_messages[0].content,
+                model=model,
+                **model_parameters,
+                request_options=RequestOptions(max_retries=0)
+            )
 
-        return self._handle_generate_response(model, credentials, response, prompt_messages)
+            return self._handle_generate_response(model, credentials, response, prompt_messages)
 
-    def _handle_generate_response(self, model: str, credentials: dict, response: Generations,
+    def _handle_generate_response(self, model: str, credentials: dict, response: Generation,
                                   prompt_messages: list[PromptMessage]) \
             -> LLMResult:
         """
@@ -191,8 +217,8 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         )
 
         # calculate num tokens
-        prompt_tokens = response.meta['billed_units']['input_tokens']
-        completion_tokens = response.meta['billed_units']['output_tokens']
+        prompt_tokens = int(response.meta.billed_units.input_tokens)
+        completion_tokens = int(response.meta.billed_units.output_tokens)
 
         # transform usage
         usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
@@ -207,7 +233,7 @@ class CohereLargeLanguageModel(LargeLanguageModel):
 
         return response
 
-    def _handle_generate_stream_response(self, model: str, credentials: dict, response: StreamingGenerations,
+    def _handle_generate_stream_response(self, model: str, credentials: dict, response: Iterator[GenerateStreamedResponse],
                                          prompt_messages: list[PromptMessage]) -> Generator:
         """
         Handle llm stream response
@@ -220,8 +246,8 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         index = 1
         full_assistant_content = ''
         for chunk in response:
-            if isinstance(chunk, StreamingText):
-                chunk = cast(StreamingText, chunk)
+            if isinstance(chunk, GenerateStreamedResponse_TextGeneration):
+                chunk = cast(GenerateStreamedResponse_TextGeneration, chunk)
                 text = chunk.text
 
                 if text is None:
@@ -244,10 +270,16 @@ class CohereLargeLanguageModel(LargeLanguageModel):
                 )
 
                 index += 1
-            elif chunk is None:
+            elif isinstance(chunk, GenerateStreamedResponse_StreamEnd):
+                chunk = cast(GenerateStreamedResponse_StreamEnd, chunk)
+
                 # calculate num tokens
-                prompt_tokens = response.meta['billed_units']['input_tokens']
-                completion_tokens = response.meta['billed_units']['output_tokens']
+                prompt_tokens = self._num_tokens_from_messages(model, credentials, prompt_messages)
+                completion_tokens = self._num_tokens_from_messages(
+                    model,
+                    credentials,
+                    [AssistantPromptMessage(content=full_assistant_content)]
+                )
 
                 # transform usage
                 usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
@@ -258,14 +290,18 @@ class CohereLargeLanguageModel(LargeLanguageModel):
                     delta=LLMResultChunkDelta(
                         index=index,
                         message=AssistantPromptMessage(content=''),
-                        finish_reason=response.finish_reason,
+                        finish_reason=chunk.finish_reason,
                         usage=usage
                     )
                 )
                 break
+            elif isinstance(chunk, GenerateStreamedResponse_StreamError):
+                chunk = cast(GenerateStreamedResponse_StreamError, chunk)
+                raise InvokeBadRequestError(chunk.err)
 
     def _chat_generate(self, model: str, credentials: dict,
-                       prompt_messages: list[PromptMessage], model_parameters: dict, stop: Optional[list[str]] = None,
+                       prompt_messages: list[PromptMessage], model_parameters: dict,
+                       tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None,
                        stream: bool = True, user: Optional[str] = None) -> Union[LLMResult, Generator]:
         """
         Invoke llm chat model
@@ -274,6 +310,7 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         :param credentials: credentials
         :param prompt_messages: prompt messages
         :param model_parameters: model parameters
+        :param tools: tools for tool calling
         :param stop: stop words
         :param stream: is stream response
         :param user: unique user id
@@ -282,32 +319,49 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         # initialize client
         client = cohere.Client(credentials.get('api_key'))
 
-        if user:
-            model_parameters['user_name'] = user
+        if stop:
+            model_parameters['stop_sequences'] = stop
 
-        message, chat_histories = self._convert_prompt_messages_to_message_and_chat_histories(prompt_messages)
+        if tools:
+            if len(tools) == 1:
+                raise ValueError("Cohere tool call requires at least two tools to be specified.")
+
+            model_parameters['tools'] = self._convert_tools(tools)
+
+        message, chat_histories, tool_results \
+            = self._convert_prompt_messages_to_message_and_chat_histories(prompt_messages)
+
+        if tool_results:
+            model_parameters['tool_results'] = tool_results
 
         # chat model
         real_model = model
         if self.get_model_schema(model, credentials).fetch_from == FetchFrom.PREDEFINED_MODEL:
             real_model = model.removesuffix('-chat')
 
-        response = client.chat(
-            message=message,
-            chat_history=chat_histories,
-            model=real_model,
-            stream=stream,
-            return_preamble=True,
-            **model_parameters,
-        )
-
         if stream:
-            return self._handle_chat_generate_stream_response(model, credentials, response, prompt_messages, stop)
+            response = client.chat_stream(
+                message=message,
+                chat_history=chat_histories,
+                model=real_model,
+                **model_parameters,
+                request_options=RequestOptions(max_retries=0)
+            )
 
-        return self._handle_chat_generate_response(model, credentials, response, prompt_messages, stop)
+            return self._handle_chat_generate_stream_response(model, credentials, response, prompt_messages)
+        else:
+            response = client.chat(
+                message=message,
+                chat_history=chat_histories,
+                model=real_model,
+                **model_parameters,
+                request_options=RequestOptions(max_retries=0)
+            )
 
-    def _handle_chat_generate_response(self, model: str, credentials: dict, response: Chat,
-                                       prompt_messages: list[PromptMessage], stop: Optional[list[str]] = None) \
+            return self._handle_chat_generate_response(model, credentials, response, prompt_messages)
+
+    def _handle_chat_generate_response(self, model: str, credentials: dict, response: NonStreamedChatResponse,
+                                       prompt_messages: list[PromptMessage]) \
             -> LLMResult:
         """
         Handle llm chat response
@@ -316,14 +370,27 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         :param credentials: credentials
         :param response: response
         :param prompt_messages: prompt messages
-        :param stop: stop words
         :return: llm response
         """
         assistant_text = response.text
 
+        tool_calls = []
+        if response.tool_calls:
+            for cohere_tool_call in response.tool_calls:
+                tool_call = AssistantPromptMessage.ToolCall(
+                    id=cohere_tool_call.name,
+                    type='function',
+                    function=AssistantPromptMessage.ToolCall.ToolCallFunction(
+                        name=cohere_tool_call.name,
+                        arguments=json.dumps(cohere_tool_call.parameters)
+                    )
+                )
+                tool_calls.append(tool_call)
+
         # transform assistant message to prompt message
         assistant_prompt_message = AssistantPromptMessage(
-            content=assistant_text
+            content=assistant_text,
+            tool_calls=tool_calls
         )
 
         # calculate num tokens
@@ -333,44 +400,38 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         # transform usage
         usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
 
-        if stop:
-            # enforce stop tokens
-            assistant_text = self.enforce_stop_tokens(assistant_text, stop)
-            assistant_prompt_message = AssistantPromptMessage(
-                content=assistant_text
-            )
-
         # transform response
         response = LLMResult(
             model=model,
             prompt_messages=prompt_messages,
             message=assistant_prompt_message,
-            usage=usage,
-            system_fingerprint=response.preamble
+            usage=usage
         )
 
         return response
 
-    def _handle_chat_generate_stream_response(self, model: str, credentials: dict, response: StreamingChat,
-                                              prompt_messages: list[PromptMessage],
-                                              stop: Optional[list[str]] = None) -> Generator:
+    def _handle_chat_generate_stream_response(self, model: str, credentials: dict,
+                                              response: Iterator[StreamedChatResponse],
+                                              prompt_messages: list[PromptMessage]) -> Generator:
         """
         Handle llm chat stream response
 
         :param model: model name
         :param response: response
         :param prompt_messages: prompt messages
-        :param stop: stop words
         :return: llm response chunk generator
         """
 
-        def final_response(full_text: str, index: int, finish_reason: Optional[str] = None,
-                           preamble: Optional[str] = None) -> LLMResultChunk:
+        def final_response(full_text: str,
+                           tool_calls: list[AssistantPromptMessage.ToolCall],
+                           index: int,
+                           finish_reason: Optional[str] = None) -> LLMResultChunk:
             # calculate num tokens
             prompt_tokens = self._num_tokens_from_messages(model, credentials, prompt_messages)
 
             full_assistant_prompt_message = AssistantPromptMessage(
-                content=full_text
+                content=full_text,
+                tool_calls=tool_calls
             )
             completion_tokens = self._num_tokens_from_messages(model, credentials, [full_assistant_prompt_message])
 
@@ -380,10 +441,9 @@ class CohereLargeLanguageModel(LargeLanguageModel):
             return LLMResultChunk(
                 model=model,
                 prompt_messages=prompt_messages,
-                system_fingerprint=preamble,
                 delta=LLMResultChunkDelta(
                     index=index,
-                    message=AssistantPromptMessage(content=''),
+                    message=AssistantPromptMessage(content='', tool_calls=tool_calls),
                     finish_reason=finish_reason,
                     usage=usage
                 )
@@ -391,9 +451,10 @@ class CohereLargeLanguageModel(LargeLanguageModel):
 
         index = 1
         full_assistant_content = ''
+        tool_calls = []
         for chunk in response:
-            if isinstance(chunk, StreamTextGeneration):
-                chunk = cast(StreamTextGeneration, chunk)
+            if isinstance(chunk, StreamedChatResponse_TextGeneration):
+                chunk = cast(StreamedChatResponse_TextGeneration, chunk)
                 text = chunk.text
 
                 if text is None:
@@ -404,12 +465,6 @@ class CohereLargeLanguageModel(LargeLanguageModel):
                     content=text
                 )
 
-                # stop
-                # notice: This logic can only cover few stop scenarios
-                if stop and text in stop:
-                    yield final_response(full_assistant_content, index, 'stop')
-                    break
-
                 full_assistant_content += text
 
                 yield LLMResultChunk(
@@ -422,39 +477,96 @@ class CohereLargeLanguageModel(LargeLanguageModel):
                 )
 
                 index += 1
-            elif isinstance(chunk, StreamEnd):
-                chunk = cast(StreamEnd, chunk)
-                yield final_response(full_assistant_content, index, chunk.finish_reason, response.preamble)
+            elif isinstance(chunk, StreamedChatResponse_ToolCallsGeneration):
+                chunk = cast(StreamedChatResponse_ToolCallsGeneration, chunk)
+                if chunk.tool_calls:
+                    for cohere_tool_call in chunk.tool_calls:
+                        tool_call = AssistantPromptMessage.ToolCall(
+                            id=cohere_tool_call.name,
+                            type='function',
+                            function=AssistantPromptMessage.ToolCall.ToolCallFunction(
+                                name=cohere_tool_call.name,
+                                arguments=json.dumps(cohere_tool_call.parameters)
+                            )
+                        )
+                        tool_calls.append(tool_call)
+            elif isinstance(chunk, StreamedChatResponse_StreamEnd):
+                chunk = cast(StreamedChatResponse_StreamEnd, chunk)
+                yield final_response(full_assistant_content, tool_calls, index, chunk.finish_reason)
                 index += 1
 
     def _convert_prompt_messages_to_message_and_chat_histories(self, prompt_messages: list[PromptMessage]) \
-            -> tuple[str, list[dict]]:
+            -> tuple[str, list[ChatMessage], list[ChatStreamRequestToolResultsItem]]:
         """
         Convert prompt messages to message and chat histories
         :param prompt_messages: prompt messages
         :return:
         """
         chat_histories = []
+        latest_tool_call_n_outputs = []
         for prompt_message in prompt_messages:
-            chat_histories.append(self._convert_prompt_message_to_dict(prompt_message))
+            if prompt_message.role == PromptMessageRole.ASSISTANT:
+                prompt_message = cast(AssistantPromptMessage, prompt_message)
+                if prompt_message.tool_calls:
+                    for tool_call in prompt_message.tool_calls:
+                        latest_tool_call_n_outputs.append(ChatStreamRequestToolResultsItem(
+                            call=ToolCall(
+                                name=tool_call.function.name,
+                                parameters=json.loads(tool_call.function.arguments)
+                            ),
+                            outputs=[]
+                        ))
+                else:
+                    cohere_prompt_message = self._convert_prompt_message_to_dict(prompt_message)
+                    if cohere_prompt_message:
+                        chat_histories.append(cohere_prompt_message)
+            elif prompt_message.role == PromptMessageRole.TOOL:
+                prompt_message = cast(ToolPromptMessage, prompt_message)
+                if latest_tool_call_n_outputs:
+                    i = 0
+                    for tool_call_n_outputs in latest_tool_call_n_outputs:
+                        if tool_call_n_outputs.call.name == prompt_message.tool_call_id:
+                            latest_tool_call_n_outputs[i] = ChatStreamRequestToolResultsItem(
+                                call=ToolCall(
+                                    name=tool_call_n_outputs.call.name,
+                                    parameters=tool_call_n_outputs.call.parameters
+                                ),
+                                outputs=[{
+                                    "result": prompt_message.content
+                                }]
+                            )
+                            break
+                        i += 1
+            else:
+                cohere_prompt_message = self._convert_prompt_message_to_dict(prompt_message)
+                if cohere_prompt_message:
+                    chat_histories.append(cohere_prompt_message)
+
+        if latest_tool_call_n_outputs:
+            new_latest_tool_call_n_outputs = []
+            for tool_call_n_outputs in latest_tool_call_n_outputs:
+                if tool_call_n_outputs.outputs:
+                    new_latest_tool_call_n_outputs.append(tool_call_n_outputs)
+
+            latest_tool_call_n_outputs = new_latest_tool_call_n_outputs
 
         # get latest message from chat histories and pop it
         if len(chat_histories) > 0:
             latest_message = chat_histories.pop()
-            message = latest_message['message']
+            message = latest_message.message
         else:
             raise ValueError('Prompt messages is empty')
 
-        return message, chat_histories
+        return message, chat_histories, latest_tool_call_n_outputs
 
-    def _convert_prompt_message_to_dict(self, message: PromptMessage) -> dict:
+    def _convert_prompt_message_to_dict(self, message: PromptMessage) -> Optional[ChatMessage]:
         """
         Convert PromptMessage to dict for Cohere model
         """
         if isinstance(message, UserPromptMessage):
             message = cast(UserPromptMessage, message)
             if isinstance(message.content, str):
-                message_dict = {"role": "USER", "message": message.content}
+                chat_message = ChatMessage(role="USER", message=message.content)
             else:
                 sub_message_text = ''
                 for message_content in message.content:
@@ -462,20 +574,57 @@ class CohereLargeLanguageModel(LargeLanguageModel):
                         message_content = cast(TextPromptMessageContent, message_content)
                         sub_message_text += message_content.data
 
-                message_dict = {"role": "USER", "message": sub_message_text}
+                chat_message = ChatMessage(role="USER", message=sub_message_text)
         elif isinstance(message, AssistantPromptMessage):
             message = cast(AssistantPromptMessage, message)
-            message_dict = {"role": "CHATBOT", "message": message.content}
+            if not message.content:
+                return None
+            chat_message = ChatMessage(role="CHATBOT", message=message.content)
         elif isinstance(message, SystemPromptMessage):
             message = cast(SystemPromptMessage, message)
-            message_dict = {"role": "USER", "message": message.content}
+            chat_message = ChatMessage(role="USER", message=message.content)
+        elif isinstance(message, ToolPromptMessage):
+            return None
         else:
             raise ValueError(f"Got unknown type {message}")
 
-        if message.name:
-            message_dict["user_name"] = message.name
+        return chat_message
 
-        return message_dict
+    def _convert_tools(self, tools: list[PromptMessageTool]) -> list[Tool]:
+        """
+        Convert tools to Cohere model
+        """
+        cohere_tools = []
+        for tool in tools:
+            properties = tool.parameters['properties']
+            required_properties = tool.parameters['required']
+
+            parameter_definitions = {}
+            for p_key, p_val in properties.items():
+                required = False
+                if p_key in required_properties:
+                    required = True
+
+                desc = p_val['description']
+                if 'enum' in p_val:
+                    desc += (f"; Only accepts one of the following predefined options: "
+                             f"[{', '.join(p_val['enum'])}]")
+
+                parameter_definitions[p_key] = ToolParameterDefinitionsValue(
+                    description=desc,
+                    type=p_val['type'],
+                    required=required
+                )
+
+            cohere_tool = Tool(
+                name=tool.name,
+                description=tool.description,
+                parameter_definitions=parameter_definitions
+            )
+
+            cohere_tools.append(cohere_tool)
+
+        return cohere_tools
 
     def _num_tokens_from_string(self, model: str, credentials: dict, text: str) -> int:
         """
@@ -494,12 +643,16 @@ class CohereLargeLanguageModel(LargeLanguageModel):
             model=model
         )
 
-        return response.length
+        return len(response.tokens)
 
     def _num_tokens_from_messages(self, model: str, credentials: dict, messages: list[PromptMessage]) -> int:
         """Calculate num tokens Cohere model."""
-        messages = [self._convert_prompt_message_to_dict(m) for m in messages]
-        message_strs = [f"{message['role']}: {message['message']}" for message in messages]
+        calc_messages = []
+        for message in messages:
+            cohere_message = self._convert_prompt_message_to_dict(message)
+            if cohere_message:
+                calc_messages.append(cohere_message)
+        message_strs = [f"{message.role}: {message.message}" for message in calc_messages]
         message_str = "\n".join(message_strs)
 
         real_model = model
@@ -565,13 +718,21 @@ class CohereLargeLanguageModel(LargeLanguageModel):
         """
         return {
             InvokeConnectionError: [
-                cohere.CohereConnectionError
+                cohere.errors.service_unavailable_error.ServiceUnavailableError
+            ],
+            InvokeServerUnavailableError: [
+                cohere.errors.internal_server_error.InternalServerError
+            ],
+            InvokeRateLimitError: [
+                cohere.errors.too_many_requests_error.TooManyRequestsError
+            ],
+            InvokeAuthorizationError: [
+                cohere.errors.unauthorized_error.UnauthorizedError,
+                cohere.errors.forbidden_error.ForbiddenError
             ],
-            InvokeServerUnavailableError: [],
-            InvokeRateLimitError: [],
-            InvokeAuthorizationError: [],
             InvokeBadRequestError: [
-                cohere.CohereAPIError,
-                cohere.CohereError,
+                cohere.core.api_error.ApiError,
+                cohere.errors.bad_request_error.BadRequestError,
+                cohere.errors.not_found_error.NotFoundError,
             ]
         }

api/core/model_runtime/model_providers/cohere/rerank/_position.yaml

@@ -0,0 +1,4 @@
+- rerank-english-v2.0
+- rerank-english-v3.0
+- rerank-multilingual-v2.0
+- rerank-multilingual-v3.0

api/core/model_runtime/model_providers/cohere/rerank/rerank-english-v3.0.yaml

@@ -0,0 +1,4 @@
+model: rerank-english-v3.0
+model_type: rerank
+model_properties:
+  context_size: 5120

api/core/model_runtime/model_providers/cohere/rerank/rerank-multilingual-v3.0.yaml

@@ -0,0 +1,4 @@
+model: rerank-multilingual-v3.0
+model_type: rerank
+model_properties:
+  context_size: 5120

api/core/model_runtime/model_providers/cohere/rerank/rerank.py

@@ -1,6 +1,7 @@
 from typing import Optional
 
 import cohere
+from cohere.core import RequestOptions
 
 from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
 from core.model_runtime.errors.invoke import (
@@ -44,19 +45,21 @@ class CohereRerankModel(RerankModel):
 
         # initialize client
         client = cohere.Client(credentials.get('api_key'))
-        results = client.rerank(
+        response = client.rerank(
             query=query,
             documents=docs,
             model=model,
-            top_n=top_n
+            top_n=top_n,
+            return_documents=True,
+            request_options=RequestOptions(max_retries=0)
         )
 
         rerank_documents = []
-        for idx, result in enumerate(results):
+        for idx, result in enumerate(response.results):
             # format document
             rerank_document = RerankDocument(
                 index=result.index,
-                text=result.document['text'],
+                text=result.document.text,
                 score=result.relevance_score,
             )
 
@@ -108,13 +111,21 @@ class CohereRerankModel(RerankModel):
         """
         return {
             InvokeConnectionError: [
-                cohere.CohereConnectionError,
+                cohere.errors.service_unavailable_error.ServiceUnavailableError
+            ],
+            InvokeServerUnavailableError: [
+                cohere.errors.internal_server_error.InternalServerError
+            ],
+            InvokeRateLimitError: [
+                cohere.errors.too_many_requests_error.TooManyRequestsError
+            ],
+            InvokeAuthorizationError: [
+                cohere.errors.unauthorized_error.UnauthorizedError,
+                cohere.errors.forbidden_error.ForbiddenError
             ],
-            InvokeServerUnavailableError: [],
-            InvokeRateLimitError: [],
-            InvokeAuthorizationError: [],
             InvokeBadRequestError: [
-                cohere.CohereAPIError,
-                cohere.CohereError,
+                cohere.core.api_error.ApiError,
+                cohere.errors.bad_request_error.BadRequestError,
+                cohere.errors.not_found_error.NotFoundError,
             ]
         }

api/core/model_runtime/model_providers/cohere/text_embedding/text_embedding.py

@@ -3,7 +3,7 @@ from typing import Optional
 
 import cohere
 import numpy as np
-from cohere.responses import Tokens
+from cohere.core import RequestOptions
 
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
@@ -52,8 +52,8 @@ class CohereTextEmbeddingModel(TextEmbeddingModel):
                 text=text
             )
 
-            for j in range(0, tokenize_response.length, context_size):
-                tokens += [tokenize_response.token_strings[j: j + context_size]]
+            for j in range(0, len(tokenize_response), context_size):
+                tokens += [tokenize_response[j: j + context_size]]
                 indices += [i]
 
         batched_embeddings = []
@@ -127,9 +127,9 @@ class CohereTextEmbeddingModel(TextEmbeddingModel):
         except Exception as e:
             raise self._transform_invoke_error(e)
 
-        return response.length
+        return len(response)
 
-    def _tokenize(self, model: str, credentials: dict, text: str) -> Tokens:
+    def _tokenize(self, model: str, credentials: dict, text: str) -> list[str]:
         """
         Tokenize text
         :param model: model name
@@ -138,17 +138,19 @@ class CohereTextEmbeddingModel(TextEmbeddingModel):
         :return:
         """
         if not text:
-            return Tokens([], [], {})
+            return []
 
         # initialize client
         client = cohere.Client(credentials.get('api_key'))
 
         response = client.tokenize(
             text=text,
-            model=model
+            model=model,
+            offline=False,
+            request_options=RequestOptions(max_retries=0)
         )
 
-        return response
+        return response.token_strings
 
     def validate_credentials(self, model: str, credentials: dict) -> None:
         """
@@ -184,10 +186,11 @@ class CohereTextEmbeddingModel(TextEmbeddingModel):
         response = client.embed(
             texts=texts,
             model=model,
-            input_type='search_document' if len(texts) > 1 else 'search_query'
+            input_type='search_document' if len(texts) > 1 else 'search_query',
+            request_options=RequestOptions(max_retries=1)
         )
 
-        return response.embeddings, response.meta['billed_units']['input_tokens']
+        return response.embeddings, int(response.meta.billed_units.input_tokens)
 
     def _calc_response_usage(self, model: str, credentials: dict, tokens: int) -> EmbeddingUsage:
         """
@@ -231,13 +234,21 @@ class CohereTextEmbeddingModel(TextEmbeddingModel):
         """
         return {
             InvokeConnectionError: [
-                cohere.CohereConnectionError
+                cohere.errors.service_unavailable_error.ServiceUnavailableError
+            ],
+            InvokeServerUnavailableError: [
+                cohere.errors.internal_server_error.InternalServerError
+            ],
+            InvokeRateLimitError: [
+                cohere.errors.too_many_requests_error.TooManyRequestsError
+            ],
+            InvokeAuthorizationError: [
+                cohere.errors.unauthorized_error.UnauthorizedError,
+                cohere.errors.forbidden_error.ForbiddenError
             ],
-            InvokeServerUnavailableError: [],
-            InvokeRateLimitError: [],
-            InvokeAuthorizationError: [],
             InvokeBadRequestError: [
-                cohere.CohereAPIError,
-                cohere.CohereError,
+                cohere.core.api_error.ApiError,
+                cohere.errors.bad_request_error.BadRequestError,
+                cohere.errors.not_found_error.NotFoundError,
             ]
         }

api/core/model_runtime/model_providers/google/llm/gemini-1.5-pro-latest.yaml

@@ -0,0 +1,39 @@
+model: gemini-1.5-pro-latest
+label:
+  en_US: Gemini 1.5 Pro
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 1048576
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens_to_sample
+    use_template: max_tokens
+    required: true
+    default: 8192
+    min: 1
+    max: 8192
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/google/llm/gemini-pro.yaml

@@ -4,6 +4,8 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - tool-call
+  - stream-tool-call
 model_properties:
   mode: chat
   context_size: 30720

api/core/model_runtime/model_providers/google/llm/llm.py

@@ -1,7 +1,9 @@
+import json
 import logging
 from collections.abc import Generator
 from typing import Optional, Union
 
+import google.ai.generativelanguage as glm
 import google.api_core.exceptions as exceptions
 import google.generativeai as genai
 import google.generativeai.client as client
@@ -13,9 +15,9 @@ from core.model_runtime.entities.message_entities import (
     AssistantPromptMessage,
     PromptMessage,
     PromptMessageContentType,
-    PromptMessageRole,
     PromptMessageTool,
     SystemPromptMessage,
+    ToolPromptMessage,
     UserPromptMessage,
 )
 from core.model_runtime.errors.invoke import (
@@ -62,7 +64,7 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
         :return: full response or stream response chunk generator result
         """
         # invoke model
-        return self._generate(model, credentials, prompt_messages, model_parameters, stop, stream, user)
+        return self._generate(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
     
     def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
                        tools: Optional[list[PromptMessageTool]] = None) -> int:
@@ -94,6 +96,32 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
         )
 
         return text.rstrip()
+    
+    def _convert_tools_to_glm_tool(self, tools: list[PromptMessageTool]) -> glm.Tool:
+        """
+        Convert tool messages to glm tools
+
+        :param tools: tool messages
+        :return: glm tools
+        """
+        return glm.Tool(
+            function_declarations=[
+                glm.FunctionDeclaration(
+                    name=tool.name,
+                    parameters=glm.Schema(
+                        type=glm.Type.OBJECT,
+                        properties={
+                            key: {
+                                'type_': value.get('type', 'string').upper(),
+                                'description': value.get('description', ''),
+                                'enum': value.get('enum', [])
+                            } for key, value in tool.parameters.get('properties', {}).items()
+                        },
+                        required=tool.parameters.get('required', [])
+                    ),
+                ) for tool in tools
+            ]
+        )
 
     def validate_credentials(self, model: str, credentials: dict) -> None:
         """
@@ -105,7 +133,7 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
         """
         
         try:
-            ping_message = PromptMessage(content="ping", role="system")
+            ping_message = SystemPromptMessage(content="ping")
             self._generate(model, credentials, [ping_message], {"max_tokens_to_sample": 5})
             
         except Exception as ex:
@@ -114,8 +142,9 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
 
     def _generate(self, model: str, credentials: dict,
                   prompt_messages: list[PromptMessage], model_parameters: dict,
-                  stop: Optional[list[str]] = None, stream: bool = True,
-                  user: Optional[str] = None) -> Union[LLMResult, Generator]:
+                  tools: Optional[list[PromptMessageTool]] = None, stop: Optional[list[str]] = None, 
+                  stream: bool = True, user: Optional[str] = None
+        ) -> Union[LLMResult, Generator]:
         """
         Invoke large language model
 
@@ -153,7 +182,6 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
                 else:
                     history.append(content)
 
-
         # Create a new ClientManager with tenant's API key
         new_client_manager = client._ClientManager()
         new_client_manager.configure(api_key=credentials["google_api_key"])
@@ -167,14 +195,15 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
             HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_NONE,
             HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
         }
-        
+
         response = google_model.generate_content(
             contents=history,
             generation_config=genai.types.GenerationConfig(
                 **config_kwargs
             ),
             stream=stream,
-            safety_settings=safety_settings
+            safety_settings=safety_settings,
+            tools=self._convert_tools_to_glm_tool(tools) if tools else None,
         )
 
         if stream:
@@ -228,43 +257,61 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
         """
         index = -1
         for chunk in response:
-            content = chunk.text
-            index += 1
-           
-            assistant_prompt_message = AssistantPromptMessage(
-                content=content if content else '',
-            )
-  
-            if not response._done:
-                
-                # transform assistant message to prompt message
-                yield LLMResultChunk(
-                    model=model,
-                    prompt_messages=prompt_messages,
-                    delta=LLMResultChunkDelta(
-                        index=index,
-                        message=assistant_prompt_message
-                    )
+            for part in chunk.parts:
+                assistant_prompt_message = AssistantPromptMessage(
+                    content=''
                 )
-            else:
-                
-                # calculate num tokens
-                prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
-                completion_tokens = self.get_num_tokens(model, credentials, [assistant_prompt_message])
 
-                # transform usage
-                usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
-                
-                yield LLMResultChunk(
-                    model=model,
-                    prompt_messages=prompt_messages,
-                    delta=LLMResultChunkDelta(
-                        index=index,
-                        message=assistant_prompt_message,
-                        finish_reason=chunk.candidates[0].finish_reason,
-                        usage=usage
+                if part.text:
+                    assistant_prompt_message.content += part.text
+
+                if part.function_call:
+                    assistant_prompt_message.tool_calls = [
+                        AssistantPromptMessage.ToolCall(
+                            id=part.function_call.name,
+                            type='function',
+                            function=AssistantPromptMessage.ToolCall.ToolCallFunction(
+                                name=part.function_call.name,
+                                arguments=json.dumps({
+                                    key: value 
+                                    for key, value in part.function_call.args.items()
+                                })
+                            )
+                        )
+                    ]
+
+                index += 1
+    
+                if not response._done:
+                    
+                    # transform assistant message to prompt message
+                    yield LLMResultChunk(
+                        model=model,
+                        prompt_messages=prompt_messages,
+                        delta=LLMResultChunkDelta(
+                            index=index,
+                            message=assistant_prompt_message
+                        )
+                    )
+                else:
+                    
+                    # calculate num tokens
+                    prompt_tokens = self.get_num_tokens(model, credentials, prompt_messages)
+                    completion_tokens = self.get_num_tokens(model, credentials, [assistant_prompt_message])
+
+                    # transform usage
+                    usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
+                    
+                    yield LLMResultChunk(
+                        model=model,
+                        prompt_messages=prompt_messages,
+                        delta=LLMResultChunkDelta(
+                            index=index,
+                            message=assistant_prompt_message,
+                            finish_reason=chunk.candidates[0].finish_reason,
+                            usage=usage
+                        )
                     )
-                )
 
     def _convert_one_message_to_text(self, message: PromptMessage) -> str:
         """
@@ -288,6 +335,8 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
             message_text = f"{ai_prompt} {content}"
         elif isinstance(message, SystemPromptMessage):
             message_text = f"{human_prompt} {content}"
+        elif isinstance(message, ToolPromptMessage):
+            message_text = f"{human_prompt} {content}"
         else:
             raise ValueError(f"Got unknown type {message}")
 
@@ -300,26 +349,53 @@ class GoogleLargeLanguageModel(LargeLanguageModel):
         :param message: one PromptMessage
         :return: glm Content representation of message
         """
-
-        parts = []
-        if (isinstance(message.content, str)):
-            parts.append(to_part(message.content))
+        if isinstance(message, UserPromptMessage):
+            glm_content = {
+                "role": "user",
+                "parts": []
+            }
+            if (isinstance(message.content, str)):
+                glm_content['parts'].append(to_part(message.content))
+            else:
+                for c in message.content:
+                    if c.type == PromptMessageContentType.TEXT:
+                        glm_content['parts'].append(to_part(c.data))
+                    else:
+                        metadata, data = c.data.split(',', 1)
+                        mime_type = metadata.split(';', 1)[0].split(':')[1]
+                        blob = {"inline_data":{"mime_type":mime_type,"data":data}}
+                        glm_content['parts'].append(blob)
+            return glm_content
+        elif isinstance(message, AssistantPromptMessage):
+            glm_content = {
+                "role": "model",
+                "parts": []
+            }
+            if message.content:
+                glm_content['parts'].append(to_part(message.content))
+            if message.tool_calls:
+                glm_content["parts"].append(to_part(glm.FunctionCall(
+                    name=message.tool_calls[0].function.name,
+                    args=json.loads(message.tool_calls[0].function.arguments),
+                )))
+            return glm_content
+        elif isinstance(message, SystemPromptMessage):
+            return {
+                "role": "user",
+                "parts": [to_part(message.content)]
+            }
+        elif isinstance(message, ToolPromptMessage):
+            return {
+                "role": "function",
+                "parts": [glm.Part(function_response=glm.FunctionResponse(
+                    name=message.name,
+                    response={
+                        "response": message.content
+                    }
+                ))]
+            }
         else:
-            for c in message.content:
-                if c.type == PromptMessageContentType.TEXT:
-                    parts.append(to_part(c.data))
-                else:
-                    metadata, data = c.data.split(',', 1)
-                    mime_type = metadata.split(';', 1)[0].split(':')[1]
-                    blob = {"inline_data":{"mime_type":mime_type,"data":data}}
-                    parts.append(blob)
-
-        glm_content = {
-            "role": "user" if message.role in (PromptMessageRole.USER, PromptMessageRole.SYSTEM) else "model",
-            "parts": parts
-        }
-        
-        return glm_content
+            raise ValueError(f"Got unknown type {message}")
     
     @property
     def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:

api/core/model_runtime/model_providers/moonshot/llm/llm.py

@@ -1,8 +1,31 @@
+import json
 from collections.abc import Generator
-from typing import Optional, Union
+from typing import Optional, Union, cast
 
-from core.model_runtime.entities.llm_entities import LLMResult
-from core.model_runtime.entities.message_entities import PromptMessage, PromptMessageTool
+import requests
+
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta
+from core.model_runtime.entities.message_entities import (
+    AssistantPromptMessage,
+    ImagePromptMessageContent,
+    PromptMessage,
+    PromptMessageContent,
+    PromptMessageContentType,
+    PromptMessageTool,
+    SystemPromptMessage,
+    ToolPromptMessage,
+    UserPromptMessage,
+)
+from core.model_runtime.entities.model_entities import (
+    AIModelEntity,
+    FetchFrom,
+    ModelFeature,
+    ModelPropertyKey,
+    ModelType,
+    ParameterRule,
+    ParameterType,
+)
 from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
 
 
@@ -13,6 +36,7 @@ class MoonshotLargeLanguageModel(OAIAPICompatLargeLanguageModel):
                 stream: bool = True, user: Optional[str] = None) \
             -> Union[LLMResult, Generator]:
         self._add_custom_parameters(credentials)
+        self._add_function_call(model, credentials)
         user = user[:32] if user else None
         return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
 
@@ -20,7 +44,286 @@ class MoonshotLargeLanguageModel(OAIAPICompatLargeLanguageModel):
         self._add_custom_parameters(credentials)
         super().validate_credentials(model, credentials)
 
-    @staticmethod
-    def _add_custom_parameters(credentials: dict) -> None:
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity | None:
+        return AIModelEntity(
+            model=model,
+            label=I18nObject(en_US=model, zh_Hans=model),
+            model_type=ModelType.LLM,
+            features=[ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL, ModelFeature.STREAM_TOOL_CALL] 
+                if credentials.get('function_calling_type') == 'tool_call' 
+                else [],
+            fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
+            model_properties={
+                ModelPropertyKey.CONTEXT_SIZE: int(credentials.get('context_size', 4096)),
+                ModelPropertyKey.MODE: LLMMode.CHAT.value,
+            },
+            parameter_rules=[
+                ParameterRule(
+                    name='temperature',
+                    use_template='temperature',
+                    label=I18nObject(en_US='Temperature', zh_Hans='温度'),
+                    type=ParameterType.FLOAT,
+                ),
+                ParameterRule(
+                    name='max_tokens',
+                    use_template='max_tokens',
+                    default=512,
+                    min=1,
+                    max=int(credentials.get('max_tokens', 4096)),
+                    label=I18nObject(en_US='Max Tokens', zh_Hans='最大标记'),
+                    type=ParameterType.INT,
+                ),
+                ParameterRule(
+                    name='top_p',
+                    use_template='top_p',
+                    label=I18nObject(en_US='Top P', zh_Hans='Top P'),
+                    type=ParameterType.FLOAT,
+                ),
+            ]
+        )
+
+    def _add_custom_parameters(self, credentials: dict) -> None:
         credentials['mode'] = 'chat'
         credentials['endpoint_url'] = 'https://api.moonshot.cn/v1'
+
+    def _add_function_call(self, model: str, credentials: dict) -> None:
+        model_schema = self.get_model_schema(model, credentials)
+        if model_schema and set([
+            ModelFeature.TOOL_CALL, ModelFeature.MULTI_TOOL_CALL
+        ]).intersection(model_schema.features or []):
+            credentials['function_calling_type'] = 'tool_call'
+
+    def _convert_prompt_message_to_dict(self, message: PromptMessage) -> dict:
+        """
+        Convert PromptMessage to dict for OpenAI API format
+        """
+        if isinstance(message, UserPromptMessage):
+            message = cast(UserPromptMessage, message)
+            if isinstance(message.content, str):
+                message_dict = {"role": "user", "content": message.content}
+            else:
+                sub_messages = []
+                for message_content in message.content:
+                    if message_content.type == PromptMessageContentType.TEXT:
+                        message_content = cast(PromptMessageContent, message_content)
+                        sub_message_dict = {
+                            "type": "text",
+                            "text": message_content.data
+                        }
+                        sub_messages.append(sub_message_dict)
+                    elif message_content.type == PromptMessageContentType.IMAGE:
+                        message_content = cast(ImagePromptMessageContent, message_content)
+                        sub_message_dict = {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": message_content.data,
+                                "detail": message_content.detail.value
+                            }
+                        }
+                        sub_messages.append(sub_message_dict)
+                message_dict = {"role": "user", "content": sub_messages}
+        elif isinstance(message, AssistantPromptMessage):
+            message = cast(AssistantPromptMessage, message)
+            message_dict = {"role": "assistant", "content": message.content}
+            if message.tool_calls:
+                message_dict["tool_calls"] = []
+                for function_call in message.tool_calls:
+                    message_dict["tool_calls"].append({
+                        "id": function_call.id,
+                        "type": function_call.type,
+                        "function": {
+                            "name": function_call.function.name,
+                            "arguments": function_call.function.arguments
+                        }
+                    })
+        elif isinstance(message, ToolPromptMessage):
+            message = cast(ToolPromptMessage, message)
+            message_dict = {"role": "tool", "content": message.content, "tool_call_id": message.tool_call_id}
+        elif isinstance(message, SystemPromptMessage):
+            message = cast(SystemPromptMessage, message)
+            message_dict = {"role": "system", "content": message.content}
+        else:
+            raise ValueError(f"Got unknown type {message}")
+
+        if message.name:
+            message_dict["name"] = message.name
+
+        return message_dict
+
+    def _extract_response_tool_calls(self, response_tool_calls: list[dict]) -> list[AssistantPromptMessage.ToolCall]:
+        """
+        Extract tool calls from response
+
+        :param response_tool_calls: response tool calls
+        :return: list of tool calls
+        """
+        tool_calls = []
+        if response_tool_calls:
+            for response_tool_call in response_tool_calls:
+                function = AssistantPromptMessage.ToolCall.ToolCallFunction(
+                    name=response_tool_call["function"]["name"] if response_tool_call.get("function", {}).get("name") else "",
+                    arguments=response_tool_call["function"]["arguments"] if response_tool_call.get("function", {}).get("arguments") else ""
+                )
+
+                tool_call = AssistantPromptMessage.ToolCall(
+                    id=response_tool_call["id"] if response_tool_call.get("id") else "",
+                    type=response_tool_call["type"] if response_tool_call.get("type") else "",
+                    function=function
+                )
+                tool_calls.append(tool_call)
+
+        return tool_calls
+
+    def _handle_generate_stream_response(self, model: str, credentials: dict, response: requests.Response,
+                                         prompt_messages: list[PromptMessage]) -> Generator:
+        """
+        Handle llm stream response
+
+        :param model: model name
+        :param credentials: model credentials
+        :param response: streamed response
+        :param prompt_messages: prompt messages
+        :return: llm response chunk generator
+        """
+        full_assistant_content = ''
+        chunk_index = 0
+
+        def create_final_llm_result_chunk(index: int, message: AssistantPromptMessage, finish_reason: str) \
+                -> LLMResultChunk:
+            # calculate num tokens
+            prompt_tokens = self._num_tokens_from_string(model, prompt_messages[0].content)
+            completion_tokens = self._num_tokens_from_string(model, full_assistant_content)
+
+            # transform usage
+            usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
+
+            return LLMResultChunk(
+                model=model,
+                prompt_messages=prompt_messages,
+                delta=LLMResultChunkDelta(
+                    index=index,
+                    message=message,
+                    finish_reason=finish_reason,
+                    usage=usage
+                )
+            )
+
+        tools_calls: list[AssistantPromptMessage.ToolCall] = []
+        finish_reason = "Unknown"
+
+        def increase_tool_call(new_tool_calls: list[AssistantPromptMessage.ToolCall]):
+            def get_tool_call(tool_name: str):
+                if not tool_name:
+                    return tools_calls[-1]
+
+                tool_call = next((tool_call for tool_call in tools_calls if tool_call.function.name == tool_name), None)
+                if tool_call is None:
+                    tool_call = AssistantPromptMessage.ToolCall(
+                        id='',
+                        type='',
+                        function=AssistantPromptMessage.ToolCall.ToolCallFunction(name=tool_name, arguments="")
+                    )
+                    tools_calls.append(tool_call)
+
+                return tool_call
+
+            for new_tool_call in new_tool_calls:
+                # get tool call
+                tool_call = get_tool_call(new_tool_call.function.name)
+                # update tool call
+                if new_tool_call.id:
+                    tool_call.id = new_tool_call.id
+                if new_tool_call.type:
+                    tool_call.type = new_tool_call.type
+                if new_tool_call.function.name:
+                    tool_call.function.name = new_tool_call.function.name
+                if new_tool_call.function.arguments:
+                    tool_call.function.arguments += new_tool_call.function.arguments
+
+        for chunk in response.iter_lines(decode_unicode=True, delimiter="\n\n"):
+            if chunk:
+                # ignore sse comments
+                if chunk.startswith(':'):
+                    continue
+                decoded_chunk = chunk.strip().lstrip('data: ').lstrip()
+                chunk_json = None
+                try:
+                    chunk_json = json.loads(decoded_chunk)
+                # stream ended
+                except json.JSONDecodeError as e:
+                    yield create_final_llm_result_chunk(
+                        index=chunk_index + 1,
+                        message=AssistantPromptMessage(content=""),
+                        finish_reason="Non-JSON encountered."
+                    )
+                    break
+                if not chunk_json or len(chunk_json['choices']) == 0:
+                    continue
+
+                choice = chunk_json['choices'][0]
+                finish_reason = chunk_json['choices'][0].get('finish_reason')
+                chunk_index += 1
+
+                if 'delta' in choice:
+                    delta = choice['delta']
+                    delta_content = delta.get('content')
+
+                    assistant_message_tool_calls = delta.get('tool_calls', None)
+                    # assistant_message_function_call = delta.delta.function_call
+
+                    # extract tool calls from response
+                    if assistant_message_tool_calls:
+                        tool_calls = self._extract_response_tool_calls(assistant_message_tool_calls)
+                        increase_tool_call(tool_calls)
+
+                    if delta_content is None or delta_content == '':
+                        continue
+
+                    # transform assistant message to prompt message
+                    assistant_prompt_message = AssistantPromptMessage(
+                        content=delta_content,
+                        tool_calls=tool_calls if assistant_message_tool_calls else []
+                    )
+
+                    full_assistant_content += delta_content
+                elif 'text' in choice:
+                    choice_text = choice.get('text', '')
+                    if choice_text == '':
+                        continue
+
+                    # transform assistant message to prompt message
+                    assistant_prompt_message = AssistantPromptMessage(content=choice_text)
+                    full_assistant_content += choice_text
+                else:
+                    continue
+
+                # check payload indicator for completion
+                yield LLMResultChunk(
+                    model=model,
+                    prompt_messages=prompt_messages,
+                    delta=LLMResultChunkDelta(
+                        index=chunk_index,
+                        message=assistant_prompt_message,
+                    )
+                )
+
+            chunk_index += 1
+        
+        if tools_calls:
+            yield LLMResultChunk(
+                model=model,
+                prompt_messages=prompt_messages,
+                delta=LLMResultChunkDelta(
+                    index=chunk_index,
+                    message=AssistantPromptMessage(
+                        tool_calls=tools_calls,
+                        content=""
+                    ),
+                )
+            )
+
+        yield create_final_llm_result_chunk(
+            index=chunk_index,
+            message=AssistantPromptMessage(content=""),
+            finish_reason=finish_reason
+        )