gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'main' of github.com:infiniflow/ragflow into feature/1111

Browse source
This commit is contained in:
chanx 2025-11-12 14:12:15 +08:00
commit c824c2a1aa
26 changed files with 3496 additions and 3466 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
README.md
View file

@ -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:v0.21.1">
<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:v0.22.0">
</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">
@ -61,8 +61,7 @@
- 🔎 [System Architecture](#-system-architecture)
- 🎬 [Get Started](#-get-started)
- 🔧 [Configurations](#-configurations)
- 🔧 [Build a docker image without embedding models](#-build-a-docker-image-without-embedding-models)
- 🔧 [Build a docker image including embedding models](#-build-a-docker-image-including-embedding-models)
- 🔧 [Build a Docker image](#-build-a-docker-image)
- 🔨 [Launch service from source for development](#-launch-service-from-source-for-development)
- 📚 [Documentation](#-documentation)
- 📜 [Roadmap](#-roadmap)
@ -189,28 +188,29 @@ 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 `v0.21.1-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.21.1-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server.
> The command below downloads the `v0.22.0` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.22.0`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server.
```bash
$ cd ragflow/docker
# Optional: use a stable tag (see releases: https://github.com/infiniflow/ragflow/releases), e.g.: git checkout v0.21.1
# Optional: use a stable tag (see releases: https://github.com/infiniflow/ragflow/releases), e.g.: git checkout v0.22.0
# Use CPU for embedding and DeepDoc tasks:
# Use CPU for DeepDoc tasks:
$ docker compose -f docker-compose.yml up -d
# To use GPU to accelerate embedding and DeepDoc tasks:
# To use GPU to accelerate DeepDoc tasks:
# sed -i '1i DEVICE=gpu' .env
# docker compose -f docker-compose.yml up -d
```
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | -------------------------- |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
| nightly | &approx;2 | ❌ | _Unstable_ nightly build |
> Note: Prior to `v0.22.0`, we provided both images with embedding models and slim images without embedding models. Details as follows:
> Note: Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
> Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
4. Check the server status after having the server up and running:
@ -291,7 +291,7 @@ RAGFlow uses Elasticsearch by default for storing full text and vectors. To swit
> [!WARNING]
> Switching to Infinity on a Linux/arm64 machine is not yet officially supported.
## 🔧 Build a Docker image without embedding models
## 🔧 Build a Docker image
This image is approximately 2 GB in size and relies on external LLM and embedding services.

28
README_id.md
View file

@ -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:v0.21.1">
<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:v0.22.0">
</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">
@ -61,8 +61,7 @@
- 🔎 [Arsitektur Sistem](#-arsitektur-sistem)
- 🎬 [Mulai](#-mulai)
- 🔧 [Konfigurasi](#-konfigurasi)
- 🔧 [Membangun Image Docker tanpa Model Embedding](#-membangun-image-docker-tanpa-model-embedding)
- 🔧 [Membangun Image Docker dengan Model Embedding](#-membangun-image-docker-dengan-model-embedding)
- 🔧 [Membangun Image Docker](#-membangun-docker-image)
- 🔨 [Meluncurkan aplikasi dari Sumber untuk Pengembangan](#-meluncurkan-aplikasi-dari-sumber-untuk-pengembangan)
- 📚 [Dokumentasi](#-dokumentasi)
- 📜 [Peta Jalan](#-peta-jalan)
@ -187,28 +186,29 @@ 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 v0.21.1 dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.21.1, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server.
> Perintah di bawah ini mengunduh edisi v0.22.0 dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.22.0, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server.
```bash
$ cd ragflow/docker
# Opsional: gunakan tag stabil (lihat releases: https://github.com/infiniflow/ragflow/releases), contoh: git checkout v0.21.1
# Opsional: gunakan tag stabil (lihat releases: https://github.com/infiniflow/ragflow/releases), contoh: git checkout v0.22.0
# Use CPU for embedding and DeepDoc tasks:
# Use CPU for DeepDoc tasks:
$ docker compose -f docker-compose.yml up -d
# To use GPU to accelerate embedding and DeepDoc tasks:
# To use GPU to accelerate DeepDoc tasks:
# sed -i '1i DEVICE=gpu' .env
# docker compose -f docker-compose.yml up -d
```
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | -------------------------- |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
| nightly | &approx;2 | ❌ | _Unstable_ nightly build |
> Catatan: Sebelum `v0.22.0`, kami menyediakan image dengan model embedding dan image slim tanpa model embedding. Detailnya sebagai berikut:
> Catatan: Mulai dari `v0.22.0`, kami hanya menyediakan edisi slim dan tidak lagi menambahkan akhiran **-slim** pada tag image.
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
> Mulai dari `v0.22.0`, kami hanya menyediakan edisi slim dan tidak lagi menambahkan akhiran **-slim** pada tag image.
1. Periksa status server setelah server aktif dan berjalan:
@ -263,7 +263,7 @@ Pembaruan konfigurasi ini memerlukan reboot semua kontainer agar efektif:
> $ docker compose -f docker-compose.yml up -d
> ```
## 🔧 Membangun Docker Image tanpa Model Embedding
## 🔧 Membangun Docker Image
Image ini berukuran sekitar 2 GB dan bergantung pada aplikasi LLM eksternal dan embedding.

34
README_ja.md
View file

@ -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:v0.21.1">
<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:v0.22.0">
</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">
@ -166,32 +166,32 @@
> 現在、公式に提供されているすべての Docker イメージは x86 アーキテクチャ向けにビルドされており、ARM64 用の Docker イメージは提供されていません。
> ARM64 アーキテクチャのオペレーティングシステムを使用している場合は、[このドキュメント](https://ragflow.io/docs/dev/build_docker_image)を参照して Docker イメージを自分でビルドしてください。
> 以下のコマンドは、RAGFlow Docker イメージの v0.21.1 エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.21.1 とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。
> 以下のコマンドは、RAGFlow Docker イメージの v0.22.0 エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.22.0 とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。
```bash
$ cd ragflow/docker
# 任意: 安定版タグを利用 (一覧: https://github.com/infiniflow/ragflow/releases) 例: git checkout v0.21.1
# 任意: 安定版タグを利用 (一覧: https://github.com/infiniflow/ragflow/releases) 例: git checkout v0.22.0
# Use CPU for embedding and DeepDoc tasks:
# Use CPU for DeepDoc tasks:
$ docker compose -f docker-compose.yml up -d
# To use GPU to accelerate embedding and DeepDoc tasks:
# To use GPU to accelerate DeepDoc tasks:
# sed -i '1i DEVICE=gpu' .env
# docker compose -f docker-compose.yml up -d
```
> 注意：`v0.22.0` より前のバージョンでは、embedding モデルを含むイメージと、embedding モデルを含まない slim イメージの両方を提供していました。詳細は以下の通りです：
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
> `v0.22.0` 以降、当プロジェクトでは slim エディションのみを提供し、イメージタグに **-slim** サフィックスを付けなくなりました。
1. サーバーを立ち上げた後、サーバーの状態を確認する:
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | -------------------------- |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
| nightly | &approx;2 | ❌ | _Unstable_ nightly build |
> 注意：`v0.22.0` 以降、当プロジェクトでは slim エディションのみを提供し、イメージタグに **-slim** サフィックスを付けなくなりました。
1. サーバーを立ち上げた後、サーバーの状態を確認する:
```bash
$ docker logs -f docker-ragflow-cpu-1
```
@ -263,7 +263,7 @@ RAGFlow はデフォルトで Elasticsearch を使用して全文とベクトル
> Linux/arm64 マシンでの Infinity への切り替えは正式にサポートされていません。
>
## 🔧 ソースコードで Docker イメージを作成（埋め込みモデルなし）
## 🔧 ソースコードで Docker イメージを作成
この Docker イメージのサイズは約 1GB で、外部の大モデルと埋め込みサービスに依存しています。

27
README_ko.md
View file

@ -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:v0.21.1">
<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:v0.22.0">
</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">
@ -168,28 +168,29 @@
> 모든 Docker 이미지는 x86 플랫폼을 위해 빌드되었습니다. 우리는 현재 ARM64 플랫폼을 위한 Docker 이미지를 제공하지 않습니다.
> ARM64 플랫폼을 사용 중이라면, [시스템과 호환되는 Docker 이미지를 빌드하려면 이 가이드를 사용해 주세요](https://ragflow.io/docs/dev/build_docker_image).
> 아래 명령어는 RAGFlow Docker 이미지의 v0.21.1 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.21.1과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오.
> 아래 명령어는 RAGFlow Docker 이미지의 v0.22.0 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.22.0과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오.
```bash
$ cd ragflow/docker
# Optional: use a stable tag (see releases: https://github.com/infiniflow/ragflow/releases), e.g.: git checkout v0.21.1
# Optional: use a stable tag (see releases: https://github.com/infiniflow/ragflow/releases), e.g.: git checkout v0.22.0
# Use CPU for embedding and DeepDoc tasks:
# Use CPU for DeepDoc tasks:
$ docker compose -f docker-compose.yml up -d
# To use GPU to accelerate embedding and DeepDoc tasks:
# To use GPU to accelerate DeepDoc tasks:
# sed -i '1i DEVICE=gpu' .env
# docker compose -f docker-compose.yml up -d
```
```
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
| nightly | &approx;2 | ❌ | _Unstable_ nightly build |
> 참고: `v0.22.0` 이전 버전에서는 embedding 모델이 포함된 이미지와 embedding 모델이 포함되지 않은 slim 이미지를 모두 제공했습니다. 자세한 내용은 다음과 같습니다:
> 참고: `v0.22.0`부터는 slim 에디션만 배포하며 이미지 태그에 **-slim** 접미사를 더 이상 붙이지 않습니다.
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
> `v0.22.0`부터는 slim 에디션만 배포하며 이미지 태그에 **-slim** 접미사를 더 이상 붙이지 않습니다.
1. 서버가 시작된 후 서버 상태를 확인하세요:
@ -256,7 +257,7 @@ RAGFlow 는 기본적으로 Elasticsearch 를 사용하여 전체 텍스트 및
> [!WARNING]
> Linux/arm64 시스템에서 Infinity로 전환하는 것은 공식적으로 지원되지 않습니다.
## 🔧 소스 코드로 Docker 이미지를 컴파일합니다(임베딩 모델 포함하지 않음)
## 🔧 소스 코드로 Docker 이미지를 컴파일합니다
이 Docker 이미지의 크기는 약 1GB이며, 외부 대형 모델과 임베딩 서비스에 의존합니다.

27
README_pt_br.md
View file

@ -22,7 +22,7 @@
<img alt="Badge Estático" 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:v0.21.1">
<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:v0.22.0">
</a>
<a href="https://github.com/infiniflow/ragflow/releases/latest">
<img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Última%20Relese" alt="Última Versão">
@ -186,28 +186,29 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
> Todas as imagens Docker são construídas para plataformas x86. Atualmente, não oferecemos imagens Docker para ARM64.
> Se você estiver usando uma plataforma ARM64, por favor, utilize [este guia](https://ragflow.io/docs/dev/build_docker_image) para construir uma imagem Docker compatível com o seu sistema.
> O comando abaixo baixa a edição`v0.21.1` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.21.1`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor.
> O comando abaixo baixa a edição`v0.22.0` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.22.0`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor.
```bash
$ cd ragflow/docker
# Opcional: use uma tag estável (veja releases: https://github.com/infiniflow/ragflow/releases), ex.: git checkout v0.21.1
# Opcional: use uma tag estável (veja releases: https://github.com/infiniflow/ragflow/releases), ex.: git checkout v0.22.0
# Use CPU for embedding and DeepDoc tasks:
# Use CPU for DeepDoc tasks:
$ docker compose -f docker-compose.yml up -d
# To use GPU to accelerate embedding and DeepDoc tasks:
# To use GPU to accelerate DeepDoc tasks:
# sed -i '1i DEVICE=gpu' .env
# docker compose -f docker-compose.yml up -d
```
| Tag da imagem RAGFlow | Tamanho da imagem (GB) | Possui modelos de incorporação? | Estável? |
| --------------------- | ---------------------- | --------------------------------- | ------------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Lançamento estável |
| v0.21.1-slim | &approx;2 | ❌ | Lançamento estável |
| nightly | &approx;2 | ❌ | Construção noturna instável |
> Nota: Antes da `v0.22.0`, fornecíamos imagens com modelos de embedding e imagens slim sem modelos de embedding. Detalhes a seguir:
> Observação: A partir da`v0.22.0`, distribuímos apenas a edição slim e não adicionamos mais o sufixo **-slim** às tags das imagens.
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
> A partir da `v0.22.0`, distribuímos apenas a edição slim e não adicionamos mais o sufixo **-slim** às tags das imagens.
4. Verifique o status do servidor após tê-lo iniciado:
@ -277,9 +278,9 @@ O RAGFlow usa o Elasticsearch por padrão para armazenar texto completo e vetore
```
> [!ATENÇÃO]
> A mudança para o Infinity em uma máquina Linux/arm64 ainda não é oficialmente suportada.
> A mudança para o Infinity em uma máquina Linux/arm64 ainda não é oficialmente suportada.
## 🔧 Criar uma imagem Docker sem modelos de incorporação
## 🔧 Criar uma imagem Docker
Esta imagem tem cerca de 2 GB de tamanho e depende de serviços externos de LLM e incorporação.

25
README_tzh.md
View file

@ -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:v0.21.1">
<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:v0.22.0">
</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">
@ -185,28 +185,29 @@
> 所有 Docker 映像檔都是為 x86 平台建置的。目前，我們不提供 ARM64 平台的 Docker 映像檔。
> 如果您使用的是 ARM64 平台，請使用 [這份指南](https://ragflow.io/docs/dev/build_docker_image) 來建置適合您系統的 Docker 映像檔。
> 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.21.1`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.21.1` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。
> 執行以下指令會自動下載 RAGFlow Docker 映像 `v0.22.0`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.22.0` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。
```bash
$ cd ragflow/docker
# 可選：使用穩定版標籤（查看發佈：https://github.com/infiniflow/ragflow/releases），例：git checkout v0.21.1
# 可選：使用穩定版標籤（查看發佈：https://github.com/infiniflow/ragflow/releases），例：git checkout v0.22.0
# Use CPU for embedding and DeepDoc tasks:
# Use CPU for DeepDoc tasks:
$ docker compose -f docker-compose.yml up -d
# To use GPU to accelerate embedding and DeepDoc tasks:
# To use GPU to accelerate DeepDoc tasks:
# sed -i '1i DEVICE=gpu' .env
# docker compose -f docker-compose.yml up -d
```
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | -------------------------- |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
| nightly | &approx;2 | ❌ | _Unstable_ nightly build |
> 注意：在 `v0.22.0` 之前的版本，我們會同時提供包含 embedding 模型的映像和不含 embedding 模型的 slim 映像。具體如下：
> 注意：自 `v0.22.0` 起，我們僅發佈 slim 版本，並且不再在映像標籤後附加 **-slim** 後綴。
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
> 從 `v0.22.0` 開始，我們只發佈 slim 版本，並且不再在映像標籤後附加 **-slim** 後綴。
> [!TIP]
> 如果你遇到 Docker 映像檔拉不下來的問題，可以在 **docker/.env** 檔案內根據變數 `RAGFLOW_IMAGE` 的註解提示選擇華為雲或阿里雲的對應映像。
@ -288,7 +289,7 @@ RAGFlow 預設使用 Elasticsearch 儲存文字和向量資料. 如果要切換
> [!WARNING]
> Infinity 目前官方並未正式支援在 Linux/arm64 架構下的機器上運行.
## 🔧 原始碼編譯 Docker 映像（不含 embedding 模型）
## 🔧 原始碼編譯 Docker 映像
本 Docker 映像大小約 2 GB 左右並且依賴外部的大模型和 embedding 服務。

8
README_zh.md
View file

@ -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:v0.21.2">
<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:v0.22.0">
</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">
@ -200,14 +200,14 @@
# sed -i '1i DEVICE=gpu' .env
# docker compose -f docker-compose.yml up -d
```
> 注意：在 `v0.22.0` 之前的版本，我们会同时提供包含 embedding 模型的镜像和不含 embedding 模型的 slim 镜像。具体如下：
> 注意：在 `v0.22.0` 之前的版本，我们会同时提供包含 embedding 模型的镜像和不含 embedding 模型的 slim 镜像。具体如下：
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
| ----------------- | --------------- | --------------------- | ------------------------ |
| v0.21.1 | &approx;9 | ✔️ | Stable release |
| v0.21.1-slim | &approx;2 | ❌ | Stable release |
> 从 `v0.22.0` 开始，我们只发布 slim 版本，并且不再在镜像标签后附加 **-slim** 后缀。
> [!TIP]

4
agent/templates/user_interaction.json
View file

@ -1,8 +1,8 @@
{
"id": 27,
"title": {
"en": "Interacting with the Agent",
"zh": "用户与 Agent 交互"
"en": "Interactive Agent",
"zh": "可交互的 Agent"
},
"description": {
"en": "During the Agent’s execution, users can actively intervene and interact with the Agent to adjust or guide its output, ensuring the final result aligns with their intentions.",

3
api/db/__init__.py
View file

@ -70,4 +70,7 @@ class PipelineTaskType(StrEnum):
VALID_PIPELINE_TASK_TYPES = {PipelineTaskType.PARSE, PipelineTaskType.DOWNLOAD, PipelineTaskType.RAPTOR, PipelineTaskType.GRAPH_RAG, PipelineTaskType.MINDMAP}
PIPELINE_SPECIAL_PROGRESS_FREEZE_TASK_TYPES = {PipelineTaskType.RAPTOR.lower(), PipelineTaskType.GRAPH_RAG.lower(), PipelineTaskType.MINDMAP.lower()}
KNOWLEDGEBASE_FOLDER_NAME=".knowledgebase"

40
api/db/services/document_service.py
View file

@ -27,7 +27,7 @@ import xxhash
from peewee import fn, Case, JOIN
from api.constants import IMG_BASE64_PREFIX, FILE_NAME_LEN_LIMIT
from api.db import FileType, UserTenantRole, CanvasCategory
from api.db import PIPELINE_SPECIAL_PROGRESS_FREEZE_TASK_TYPES, FileType, UserTenantRole, CanvasCategory
from api.db.db_models import DB, Document, Knowledgebase, Task, Tenant, UserTenant, File2Document, File, UserCanvas, \
User
from api.db.db_utils import bulk_insert_into_db
@ -372,12 +372,16 @@ class DocumentService(CommonService):
def get_unfinished_docs(cls):
fields = [cls.model.id, cls.model.process_begin_at, cls.model.parser_config, cls.model.progress_msg,
cls.model.run, cls.model.parser_id]
unfinished_task_query = Task.select(Task.doc_id).where(
(Task.progress >= 0) & (Task.progress < 1)
)
docs = cls.model.select(*fields) \
.where(
cls.model.status == StatusEnum.VALID.value,
~(cls.model.type == FileType.VIRTUAL.value),
cls.model.progress < 1,
cls.model.progress > 0)
(((cls.model.progress < 1) & (cls.model.progress > 0)) |
(cls.model.id.in_(unfinished_task_query)))) # including unfinished tasks like GraphRAG, RAPTOR and Mindmap
return list(docs.dicts())
@classmethod
@ -619,13 +623,17 @@ class DocumentService(CommonService):
@classmethod
@DB.connection_context()
def begin2parse(cls, docid):
cls.update_by_id(
docid, {"progress": random.random() * 1 / 100.,
"progress_msg": "Task is queued...",
"process_begin_at": get_format_time(),
"run": TaskStatus.RUNNING.value
})
def begin2parse(cls, doc_id, keep_progress=False):
info = {
"progress_msg": "Task is queued...",
"process_begin_at": get_format_time(),
}
if not keep_progress:
info["progress"] = random.random() * 1 / 100.
info["run"] = TaskStatus.RUNNING.value
# keep the doc in DONE state when keep_progress=True for GraphRAG, RAPTOR and Mindmap tasks
cls.update_by_id(doc_id, info)
@classmethod
@DB.connection_context()
@ -684,8 +692,13 @@ class DocumentService(CommonService):
bad = 0
e, doc = DocumentService.get_by_id(d["id"])
status = doc.run # TaskStatus.RUNNING.value
doc_progress = doc.progress if doc and doc.progress else 0.0
special_task_running = False
priority = 0
for t in tsks:
task_type = (t.task_type or "").lower()
if task_type in PIPELINE_SPECIAL_PROGRESS_FREEZE_TASK_TYPES:
special_task_running = True
if 0 <= t.progress < 1:
finished = False
if t.progress == -1:
@ -702,13 +715,15 @@ class DocumentService(CommonService):
prg = 1
status = TaskStatus.DONE.value
# only for special task and parsed docs and unfinised
freeze_progress = special_task_running and doc_progress >= 1 and not finished
msg = "\n".join(sorted(msg))
info = {
"process_duration": datetime.timestamp(
datetime.now()) -
d["process_begin_at"].timestamp(),
"run": status}
if prg != 0:
if prg != 0 and not freeze_progress:
info["progress"] = prg
if msg:
info["progress_msg"] = msg
@ -858,7 +873,7 @@ def queue_raptor_o_graphrag_tasks(sample_doc_id, ty, priority, fake_doc_id="", d
task["doc_id"] = fake_doc_id
task["doc_ids"] = doc_ids
DocumentService.begin2parse(sample_doc_id["id"])
DocumentService.begin2parse(sample_doc_id["id"], keep_progress=True)
assert REDIS_CONN.queue_product(settings.get_svr_queue_name(priority), message=task), "Can't access Redis. Please check the Redis' status."
return task["id"]
@ -1012,4 +1027,3 @@ def doc_upload_and_parse(conversation_id, file_objs, user_id):
doc_id, kb.id, token_counts[doc_id], chunk_counts[doc_id], 0)
return [d["id"] for d, _ in files]

8
docker/.env
View file

@ -106,13 +106,7 @@ ADMIN_SVR_HTTP_PORT=9381
SVR_MCP_PORT=9382
# The RAGFlow Docker image to download. v0.22+ doesn't include embedding models.
# Defaults to the v0.21.1-slim edition, which is the RAGFlow Docker image without embedding models.
RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1-slim
# RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1
# The Docker image of the v0.21.1 edition includes built-in embedding models:
# - BAAI/bge-large-zh-v1.5
# - maidalun1020/bce-embedding-base_v1
#
RAGFLOW_IMAGE=infiniflow/ragflow:v0.22.0
# If you cannot download the RAGFlow Docker image:
# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:v0.21.1

8
docker/README.md
View file

@ -77,13 +77,7 @@ The [.env](./.env) file contains important environment variables for Docker.
- `SVR_HTTP_PORT`
The port used to expose RAGFlow's HTTP API service to the host machine, allowing **external** access to the service running inside the Docker container. Defaults to `9380`.
- `RAGFLOW-IMAGE`
The Docker image edition. Available editions:
- `infiniflow/ragflow:v0.21.1-slim` (default): The RAGFlow Docker image without embedding models.
- `infiniflow/ragflow:v0.21.1`: The RAGFlow Docker image with embedding models including:
- Built-in embedding models:
- `BAAI/bge-large-zh-v1.5`
- `maidalun1020/bce-embedding-base_v1`
The Docker image edition. Defaults to `infiniflow/ragflow:v0.22.0`. The RAGFlow Docker image does not include embedding models.
> [!TIP]

2
docker/docker-compose-base.yml
View file

@ -72,7 +72,7 @@ services:
infinity:
profiles:
- infinity
image: infiniflow/infinity:v0.6.4
image: infiniflow/infinity:v0.6.5
volumes:
- infinity_data:/var/infinity
- ./infinity_conf.toml:/infinity_conf.toml

2
docker/infinity_conf.toml
View file

@ -1,5 +1,5 @@
[general]
version = "0.6.4"
version = "0.6.5"
time_zone = "utc-8"
[network]

2
docs/faq.mdx
View file

@ -151,7 +151,7 @@ See [Build a RAGFlow Docker image](./develop/build_docker_image.mdx).
### Cannot access https://huggingface.co
A locally deployed RAGflow downloads OCR and embedding modules from [Huggingface website](https://huggingface.co) by default. If your machine is unable to access this site, the following error occurs and PDF parsing fails:
A locally deployed RAGflow downloads OCR models from [Huggingface website](https://huggingface.co) by default. If your machine is unable to access this site, the following error occurs and PDF parsing fails:
```
FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/huggingface/hub/models--InfiniFlow--deepdoc/snapshots/be0c1e50eef6047b412d1800aa89aba4d275f997/ocr.res'

2
docs/guides/agent/agent_component_reference/retrieval.mdx
View file

@ -38,7 +38,7 @@ By default, you can use `sys.query`, which is the user query and the default out
### 3. Select dataset(s) to query
You can specify one or multiple datasets to retrieve data from. If selecting mutiple, ensure they use the same embedding model.
You can specify one or multiple datasets to retrieve data from. If selecting multiple, ensure they use the same embedding model.
### 4. Expand **Advanced Settings** to configure the retrieval method

1
docs/guides/dataset/best_practices/accelerate_doc_indexing.mdx
View file

@ -12,7 +12,6 @@ A checklist to speed up document parsing and indexing.
Please note that some of your settings may consume a significant amount of time. If you often find that document parsing is time-consuming, here is a checklist to consider:
- Use GPU to reduce embedding time.
- On the configuration page of your dataset, switch off **Use RAPTOR to enhance retrieval**.
- Extracting knowledge graph (GraphRAG) is time-consuming.
- Disable **Auto-keyword** and **Auto-question** on the configuration page of your dataset, as both depend on the LLM.

5
docs/guides/models/deploy_local_llm.mdx
View file

@ -107,7 +107,6 @@ Max retries exceeded with url: /api/chat (Caused by NewConnectionError('<urllib3
Click on your logo **>** **Model providers** **>** **System Model Settings** to update your model:
- *You should now be able to find **llama3.2** from the dropdown list under **Chat model**, and **bge-m3** from the dropdown list under **Embedding model**.*
- _If your local model is an embedding model, you should find it under **Embedding model**._
### 6. Update Chat Configuration
@ -158,14 +157,10 @@ Click on your logo **>** **Model providers** **>** **System Model Settings** to
*You should now be able to find **mistral** from the dropdown list under **Chat model**.*
> If your local model is an embedding model, you should find your local model under **Embedding model**.
### 7. Update Chat Configuration
Update your chat model accordingly in **Chat Configuration**:
> If your local model is an embedding model, update it on the configuration page of your dataset.
## Deploy a local model using IPEX-LLM
[IPEX-LLM](https://github.com/intel-analytics/ipex-llm) is a PyTorch library for running LLMs on local Intel CPUs or GPUs (including iGPU or discrete GPUs like Arc, Flex, and Max) with low latency. It supports Ollama on Linux and Windows systems.

11
docs/quickstart.mdx
View file

@ -190,7 +190,7 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
3. Use the pre-built Docker images and start up the server:
```bash
# Use CPU for embedding and DeepDoc tasks:
# Use CPU for DeepDoc tasks:
$ docker compose -f docker-compose.yml up -d
```
@ -207,15 +207,6 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
</APITable>
```
:::danger IMPORTANT
The embedding models included in `v0.21.1` and `nightly` are:
- BAAI/bge-large-zh-v1.5
- maidalun1020/bce-embedding-base_v1
These two embedding models are optimized specifically for English and Chinese, so performance will be compromised if you use them to embed documents in other languages.
:::
:::tip NOTE
The image size shown refers to the size of the *downloaded* Docker image, which is compressed. When Docker runs the image, it unpacks it, resulting in significantly greater disk usage. A Docker image will expand to around 7 GB once unpacked.
:::

36
docs/release_notes.md
View file

@ -7,6 +7,42 @@ slug: /release_notes
Key features, improvements and bug fixes in the latest releases.
## v0.22.0
Released on November 12, 2025.
### Breaking Changes
:::danger IMPORTANT
From this release onwards, we ship only the slim edition (without embedding models) Docker image and no longer append the `-slim` suffix to the image tag.
:::
### New Features
- Dataset:
- Supports data synchronization from five online sources (AWS S3, Google Drive, Notion, Confluence, and Discord).
- RAPTOR can be built across an entire dataset or on individual documents.
- Ingestion pipeline: Supports [Docling document parsing](https://github.com/docling-project/docling) in the **Parser** component.
- Launches a new administrative Web UI dashboard for graphical user management and service status monitoring.
- Agent:
- Supports structured output.
- Supports metadata filtering in the **Retrieval** component.
- Introduces a **Variable aggregator** component with data operation and session variable definition capabilities.
### Improvements
- Agent: Supports visualizing previous components' outputs in the **Await Response** component.
- Revamps the model provider page.
- Upgrades RAGFlow's document engine Infinity to v0.6.5.
### Added Models
- Kimi-K2-Thinking
### New agent templates
- Interactive Agent, incorporates real-time user feedback to dynamically optimize Agent output.
## v0.21.1
Released on October 23, 2025.

2
helm/values.yaml
View file

@ -96,7 +96,7 @@ ragflow:
infinity:
image:
repository: infiniflow/infinity
tag: v0.6.4
tag: v0.6.5
pullPolicy: IfNotPresent
pullSecrets: []
storage:

2
pyproject.toml
View file

@ -49,7 +49,7 @@ dependencies = [
"html-text==0.6.2",
"httpx[socks]>=0.28.1,<0.29.0",
"huggingface-hub>=0.25.0,<0.26.0",
"infinity-sdk==0.6.4",
"infinity-sdk==0.6.5",
"infinity-emb>=0.0.66,<0.0.67",
"itsdangerous==2.1.2",
"json-repair==0.35.0",

3
rag/svr/task_executor.py
View file

@ -24,6 +24,7 @@ import time
import json_repair
from api.db import PIPELINE_SPECIAL_PROGRESS_FREEZE_TASK_TYPES
from api.db.services.knowledgebase_service import KnowledgebaseService
from api.db.services.pipeline_operation_log_service import PipelineOperationLogService
from common.connection_utils import timeout
@ -192,7 +193,7 @@ async def collect():
canceled = False
if msg.get("doc_id", "") in [GRAPH_RAPTOR_FAKE_DOC_ID, CANVAS_DEBUG_DOC_ID]:
task = msg
if task["task_type"] in ["graphrag", "raptor", "mindmap"]:
if task["task_type"] in PIPELINE_SPECIAL_PROGRESS_FREEZE_TASK_TYPES:
task = TaskService.get_task(msg["id"], msg["doc_ids"])
if task:
task["doc_id"] = msg["doc_id"]

4
rag/utils/infinity_conn.py
View file

@ -156,7 +156,6 @@ class InfinityConnection(DocStoreConnection):
msg = f"Infinity {infinity_uri} is unhealthy in 120s."
logger.error(msg)
raise Exception(msg)
self.column_vec_patt = re.compile(r"q_(?P<vector_size>\d+)_vec")
logger.info(f"Infinity {infinity_uri} is healthy.")
def _migrate_db(self, inf_conn):
@ -324,8 +323,7 @@ class InfinityConnection(DocStoreConnection):
output.append(score_func)
if PAGERANK_FLD not in output:
output.append(PAGERANK_FLD)
output = [f for f in output if f != "_score" and self.column_vec_patt.match(f) is None]
logger.info(f"infinity output fields: {output}")
output = [f for f in output if f != "_score"]
if limit <= 0:
# ElasticSearch default limit is 10000
limit = 10000

6644
uv.lock generated
View file

File diff suppressed because it is too large Load diff

6
web/src/components/ragflow-avatar.tsx
View file

@ -11,6 +11,8 @@ const PREDEFINED_COLORS = [
];
const getStringHash = (str: string): number => {
if (typeof str !== 'string') return 0;
const normalized = str.trim().toLowerCase();
let hash = 104729;
const seed = 0x9747b28c;
@ -41,8 +43,8 @@ export const RAGFlowAvatar = memo(
>(({ name, avatar, isPerson = false, className, ...props }, ref) => {
// Generate initial letter logic
const getInitials = (name?: string) => {
if (!name) return '';
const parts = name.trim().split(/\s+/);
if (typeof name !== 'string' || !name) return '';
const parts = name?.trim().split(/\s+/);
if (parts.length === 1) {
return parts[0][0].toUpperCase();
}