Merge branch 'main' into support_baidu_vdb

Author: zhangping24

.github/ISSUE_TEMPLATE/agent_scenario_request.yml

@@ -0,0 +1,46 @@
+name: "❤️‍🔥ᴬᴳᴱᴺᵀ Agent scenario request"
+description: Propose a agent scenario request for RAGFlow.
+title: "[Agent Scenario Request]: "
+labels: ["❤️‍🔥ᴬᴳᴱᴺᵀ agent scenario"]
+body:
+  - type: checkboxes
+    attributes:
+      label: Self Checks
+      description: "Please check the following in order to be responded in time :)"
+      options:
+        - label: I have searched for existing issues [search for existing issues](https://github.com/infiniflow/ragflow/issues), including closed ones.
+          required: true
+        - label: I confirm that I am using English to submit this report ([Language Policy](https://github.com/infiniflow/ragflow/issues/5910)).
+          required: true
+        - label: Non-english title submitions will be closed directly ( 非英文标题的提交将会被直接关闭 ) ([Language Policy](https://github.com/infiniflow/ragflow/issues/5910)).
+          required: true
+        - label: "Please do not modify this template :) and fill in all the required fields."
+          required: true
+  - type: textarea
+    attributes:
+      label: Is your feature request related to a scenario?
+      description: |
+        A clear and concise description of what the scenario is. Ex. I'm always frustrated when [...]
+      render: Markdown
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: Describe the feature you'd like
+      description: A clear and concise description of what you want to happen.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Documentation, adoption, use case
+      description: If you can, explain some scenarios how users might use this, situations it would be helpful in. Any API designs, mockups, or diagrams are also helpful.
+      render: Markdown
+    validations:
+      required: false
+  - type: textarea
+    attributes:
+      label: Additional information
+      description: |
+        Add any other context or screenshots about the feature request here.
+    validations:
+      required: false

.github/workflows/tests.yml

@@ -67,6 +67,7 @@ jobs:
 
       - name: Start ragflow:nightly-slim
         run: |
+          sudo docker compose -f docker/docker-compose.yml down --volumes --remove-orphans
           echo -e "\nRAGFLOW_IMAGE=infiniflow/ragflow:nightly-slim" >> docker/.env
           sudo docker compose -f docker/docker-compose.yml up -d
 
@@ -88,7 +89,12 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && uv pip install . && source .venv/bin/activate && cd test/test_sdk_api && pytest -s --tb=short get_email.py t_dataset.py t_chat.py t_session.py t_document.py t_chunk.py
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
 
       - name: Run frontend api tests against Elasticsearch
         run: |
@@ -98,7 +104,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
+          cd sdk/python && UV_LINK_MODE=copy uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
           
       - name: Run http api tests against Elasticsearch
         run: |
@@ -113,7 +119,7 @@ jobs:
           else
             export HTTP_API_TEST_LEVEL=p2
           fi
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_http_api && pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL}
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
 
       - name: Stop ragflow:nightly
         if: always()  # always run this step even if previous steps failed
@@ -132,7 +138,12 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && uv pip install . && source .venv/bin/activate && cd test/test_sdk_api && pytest -s --tb=short get_email.py t_dataset.py t_chat.py t_session.py t_document.py t_chunk.py
+          if [[ $GITHUB_EVENT_NAME == 'schedule' ]]; then
+            export HTTP_API_TEST_LEVEL=p3
+          else
+            export HTTP_API_TEST_LEVEL=p2
+          fi
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && uv pip install sdk/python && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_sdk_api
 
       - name: Run frontend api tests against Infinity
         run: |
@@ -142,7 +153,7 @@ jobs:
             echo "Waiting for service to be available..."
             sleep 5
           done
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
+          cd sdk/python && UV_LINK_MODE=copy uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
 
       - name: Run http api tests against Infinity
         run: |
@@ -157,7 +168,7 @@ jobs:
           else
             export HTTP_API_TEST_LEVEL=p2
           fi
-          cd sdk/python && uv sync --python 3.10 --group test --frozen && source .venv/bin/activate && cd test/test_http_api && DOC_ENGINE=infinity pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL}
+          UV_LINK_MODE=copy uv sync --python 3.10 --only-group test --no-default-groups --frozen && DOC_ENGINE=infinity uv run --only-group test --no-default-groups pytest -s --tb=short --level=${HTTP_API_TEST_LEVEL} test/testcases/test_http_api
 
       - name: Stop ragflow:nightly
         if: always()  # always run this step even if previous steps failed

.gitignore

@@ -193,3 +193,5 @@ dist
 # SvelteKit build / generate output
 .svelte-kit
 
+# Default backup dir
+backup

.trivyignore

@@ -0,0 +1,15 @@
+**/*.md
+**/*.min.js
+**/*.min.css
+**/*.svg
+**/*.png
+**/*.jpg
+**/*.jpeg
+**/*.gif
+**/*.woff
+**/*.woff2
+**/*.map
+**/*.webp
+**/*.ico
+**/*.ttf
+**/*.eot

README.md

@@ -6,8 +6,8 @@
 
 <p align="center">
   <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-DBEDFA"></a>
-  <a href="./README_tzh.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-DFE0E5"></a>
   <a href="./README_zh.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_tzh.md"><img alt="繁體版中文自述文件" src="https://img.shields.io/badge/繁體中文-DFE0E5"></a>
   <a href="./README_ja.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-DFE0E5"></a>
   <a href="./README_ko.md"><img alt="한국어" src="https://img.shields.io/badge/한국어-DFE0E5"></a>
   <a href="./README_id.md"><img alt="Bahasa Indonesia" src="https://img.shields.io/badge/Bahasa Indonesia-DFE0E5"></a>
@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.19.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -71,22 +71,22 @@
 
 ## 💡 What is RAGFlow?
 
-[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document
-understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models)
-to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted
-data.
+[RAGFlow](https://ragflow.io/) is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs. It offers a streamlined RAG workflow adaptable to enterprises of any scale. Powered by a converged context engine and pre-built agent templates, RAGFlow enables developers to transform complex data into high-fidelity, production-ready AI systems with exceptional efficiency and precision.
 
 ## 🎮 Demo
 
 Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/7248/2f6baa3e-1092-4f11-866d-36f6a9d075e5" width="1200"/>
-<img src="https://github.com/user-attachments/assets/504bbbf1-c9f7-4d83-8cc5-e9cb63c26db6" width="1200"/>
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/chunking.gif" width="1200"/>
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/agentic-dark.gif" width="1200"/>
 </div>
 
 ## 🔥 Latest Updates
 
+- 2025-08-08 Supports OpenAI's latest GPT-5 series models.
+- 2025-08-04 Supports new models, including Kimi K2 and Grok 4.
+- 2025-08-01 Supports agentic workflow and MCP.
 - 2025-05-23 Adds a Python/JavaScript code executor component to Agent.
 - 2025-05-05 Supports cross-language query.
 - 2025-03-19 Supports using a multi-modal model to make sense of images within PDF or DOCX files.
@@ -187,7 +187,7 @@ releases! 🌟
 > All Docker images are built for x86 platforms. We don't currently offer Docker images for ARM64.
 > If you are on an ARM64 platform, follow [this guide](https://ragflow.io/docs/dev/build_docker_image) to build a Docker image compatible with your system.
 
-   > The command below downloads the `v0.19.0-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.19.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.19.0` for the full edition `v0.19.0`.
+   > The command below downloads the `v0.20.4-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.4-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4` for the full edition `v0.20.4`.
 
    ```bash
    $ cd ragflow/docker
@@ -200,8 +200,8 @@ releases! 🌟
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    |-------------------|-----------------|-----------------------|--------------------------|
-   | v0.19.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.19.0-slim      | &approx;2       | ❌                   | Stable release            |
+   | v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.4-slim      | &approx;2       | ❌                   | Stable release            |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                   | _Unstable_ nightly build  |
 
@@ -304,7 +304,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
 
 ## 🔨 Launch service from source for development
 
-1. Install uv, or skip this step if it is already installed:
+1. Install `uv` and `pre-commit`, or skip this step if they are already installed:
 
    ```bash
    pipx install uv pre-commit
@@ -345,8 +345,10 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    sudo apt-get install libjemalloc-dev
    # centos
    sudo yum install jemalloc
+   # mac
+   sudo brew install jemalloc
    ```
-   
+
 6. Launch backend service:
 
    ```bash

README_id.md

@@ -6,8 +6,8 @@
 
 <p align="center">
   <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-DFE0E5"></a>
-  <a href="./README_tzh.md"><img alt="繁體中文文件" src="https://img.shields.io/badge/繁體中文-DFE0E5"></a>
   <a href="./README_zh.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-DFE0E5"></a>
+  <a href="./README_tzh.md"><img alt="繁體中文版自述文件" src="https://img.shields.io/badge/繁體中文-DFE0E5"></a>
   <a href="./README_ja.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-DFE0E5"></a>
   <a href="./README_ko.md"><img alt="한국어" src="https://img.shields.io/badge/한국어-DFE0E5"></a>
   <a href="./README_id.md"><img alt="Bahasa Indonesia" src="https://img.shields.io/badge/Bahasa Indonesia-DBEDFA"></a>
@@ -22,7 +22,7 @@
         <img alt="Lencana Daring" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.19.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Rilis%20Terbaru" alt="Rilis Terbaru">
@@ -67,19 +67,22 @@
 
 ## 💡 Apa Itu RAGFlow?
 
-[RAGFlow](https://ragflow.io/) adalah mesin RAG (Retrieval-Augmented Generation) open-source berbasis pemahaman dokumen yang mendalam. Platform ini menyediakan alur kerja RAG yang efisien untuk bisnis dengan berbagai skala, menggabungkan LLM (Large Language Models) untuk menyediakan kemampuan tanya-jawab yang benar dan didukung oleh referensi dari data terstruktur kompleks.
+[RAGFlow](https://ragflow.io/) adalah mesin RAG (Retrieval-Augmented Generation) open-source terkemuka yang mengintegrasikan teknologi RAG mutakhir dengan kemampuan Agent untuk menciptakan lapisan kontekstual superior bagi LLM. Menyediakan alur kerja RAG yang efisien dan dapat diadaptasi untuk perusahaan segala skala. Didukung oleh mesin konteks terkonvergensi dan template Agent yang telah dipra-bangun, RAGFlow memungkinkan pengembang mengubah data kompleks menjadi sistem AI kesetiaan-tinggi dan siap-produksi dengan efisiensi dan presisi yang luar biasa.
 
 ## 🎮 Demo
 
 Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 
 <div align="center" style="margin-top:20px;margin-bottom:20px;">
-<img src="https://github.com/infiniflow/ragflow/assets/7248/2f6baa3e-1092-4f11-866d-36f6a9d075e5" width="1200"/>
-<img src="https://github.com/user-attachments/assets/504bbbf1-c9f7-4d83-8cc5-e9cb63c26db6" width="1200"/>
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/chunking.gif" width="1200"/>
+<img src="https://raw.githubusercontent.com/infiniflow/ragflow-docs/refs/heads/image/image/agentic-dark.gif" width="1200"/>
 </div>
 
 ## 🔥 Pembaruan Terbaru
 
+- 2025-08-08 Mendukung model seri GPT-5 terbaru dari OpenAI.
+- 2025-08-04 Mendukung model baru, termasuk Kimi K2 dan Grok 4.
+- 2025-08-01 Mendukung alur kerja agen dan MCP.
 - 2025-05-23 Menambahkan komponen pelaksana kode Python/JS ke Agen.
 - 2025-05-05 Mendukung kueri lintas bahasa.
 - 2025-03-19 Mendukung penggunaan model multi-modal untuk memahami gambar di dalam file PDF atau DOCX.
@@ -178,7 +181,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 > Semua gambar Docker dibangun untuk platform x86. Saat ini, kami tidak menawarkan gambar Docker untuk ARM64.
 > Jika Anda menggunakan platform ARM64, [silakan gunakan panduan ini untuk membangun gambar Docker yang kompatibel dengan sistem Anda](https://ragflow.io/docs/dev/build_docker_image).
 
-> Perintah di bawah ini mengunduh edisi v0.19.0-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.19.0-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.19.0 untuk edisi lengkap v0.19.0.
+> Perintah di bawah ini mengunduh edisi v0.20.4-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.4-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4 untuk edisi lengkap v0.20.4.
 
 ```bash
 $ cd ragflow/docker
@@ -191,8 +194,8 @@ $ docker compose -f docker-compose.yml up -d
 
 | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
 | ----------------- | --------------- | --------------------- | ------------------------ |
-| v0.19.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-| v0.19.0-slim      | &approx;2       | ❌                    | Stable release           |
+| v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| v0.20.4-slim      | &approx;2       | ❌                    | Stable release           |
 | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
 | nightly-slim      | &approx;2       | ❌                    | _Unstable_ nightly build |
 
@@ -268,7 +271,7 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
 
 ## 🔨 Menjalankan Aplikasi dari untuk Pengembangan
 
-1. Instal uv, atau lewati langkah ini jika sudah terinstal:
+1. Instal `uv` dan `pre-commit`, atau lewati langkah ini jika sudah terinstal:
 
    ```bash
    pipx install uv pre-commit
@@ -309,6 +312,8 @@ docker build --platform linux/amd64 -f Dockerfile -t infiniflow/ragflow:nightly
    sudo apt-get install libjemalloc-dev
    # centos
    sudo yum install jemalloc
+   # mac
+   sudo brew install jemalloc
    ```
 
 6. Jalankan aplikasi backend: