Merge branch 'main' into main
This commit is contained in:
Billy Bao
GitHub
commit
d45569e354
63 changed files with 3600 additions and 3618 deletions
32
README.md
32
README.md
|
|
@ -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)
|
||||
|
|
@ -86,6 +85,7 @@ Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
|
|||
|
||||
## 🔥 Latest Updates
|
||||
|
||||
- 2025-11-12 Supports data synchronization from Confluence, AWS S3, Discord, Google Drive.
|
||||
- 2025-10-23 Supports MinerU & Docling as document parsing methods.
|
||||
- 2025-10-15 Supports orchestrable ingestion pipeline.
|
||||
- 2025-08-08 Supports OpenAI's latest GPT-5 series models.
|
||||
|
|
@ -93,7 +93,6 @@ Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
|
|||
- 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.
|
||||
- 2025-02-28 Combined with Internet search (Tavily), supports reasoning like Deep Research for any LLMs.
|
||||
- 2024-12-18 Upgrades Document Layout Analysis model in DeepDoc.
|
||||
- 2024-08-22 Support text to SQL statements through RAG.
|
||||
|
||||
|
|
@ -189,29 +188,30 @@ 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
|
||||
# This steps ensures the **entrypoint.sh** file in the code matches the Docker image version.
|
||||
|
||||
# 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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈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:
|
||||
|
||||
|
|
@ -292,7 +292,7 @@ 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.
|
||||
|
||||
|
|
|
|||
30
README_id.md
30
README_id.md
|
|
@ -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)
|
||||
|
|
@ -86,6 +85,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
|
|||
|
||||
## 🔥 Pembaruan Terbaru
|
||||
|
||||
- 2025-11-12 Mendukung sinkronisasi data dari Confluence, AWS S3, Discord, Google Drive.
|
||||
- 2025-10-23 Mendukung MinerU & Docling sebagai metode penguraian dokumen.
|
||||
- 2025-10-15 Dukungan untuk jalur data yang terorkestrasi.
|
||||
- 2025-08-08 Mendukung model seri GPT-5 terbaru dari OpenAI.
|
||||
|
|
@ -93,7 +93,6 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
|
|||
- 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.
|
||||
- 2025-02-28 dikombinasikan dengan pencarian Internet (TAVILY), mendukung penelitian mendalam untuk LLM apa pun.
|
||||
- 2024-12-18 Meningkatkan model Analisis Tata Letak Dokumen di DeepDoc.
|
||||
- 2024-08-22 Dukungan untuk teks ke pernyataan SQL melalui RAG.
|
||||
|
||||
|
|
@ -187,29 +186,30 @@ 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
|
||||
# This steps ensures the **entrypoint.sh** file in the code matches the Docker image version.
|
||||
|
||||
# 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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈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:
|
||||
|
||||
|
|
@ -264,7 +264,7 @@ 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.
|
||||
|
||||
|
|
|
|||
37
README_ja.md
37
README_ja.md
|
|
@ -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">
|
||||
|
|
@ -66,6 +66,7 @@
|
|||
|
||||
## 🔥 最新情報
|
||||
|
||||
- 2025-11-12 Confluence、AWS S3、Discord、Google Drive からのデータ同期をサポートします。
|
||||
- 2025-10-23 ドキュメント解析方法として MinerU と Docling をサポートします。
|
||||
- 2025-10-15 オーケストレーションされたデータパイプラインのサポート。
|
||||
- 2025-08-08 OpenAI の最新 GPT-5 シリーズモデルをサポートします。
|
||||
|
|
@ -73,7 +74,6 @@
|
|||
- 2025-05-23 エージェントに Python/JS コードエグゼキュータコンポーネントを追加しました。
|
||||
- 2025-05-05 言語間クエリをサポートしました。
|
||||
- 2025-03-19 PDFまたはDOCXファイル内の画像を理解するために、多モーダルモデルを使用することをサポートします。
|
||||
- 2025-02-28 インターネット検索 (TAVILY) と組み合わせて、あらゆる LLM の詳細な調査をサポートします。
|
||||
- 2024-12-18 DeepDoc のドキュメント レイアウト分析モデルをアップグレードします。
|
||||
- 2024-08-22 RAG を介して SQL ステートメントへのテキストをサポートします。
|
||||
|
||||
|
|
@ -166,34 +166,33 @@
|
|||
> 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
|
||||
# この手順は、コード内の entrypoint.sh ファイルが Docker イメージのバージョンと一致していることを確認します。
|
||||
|
||||
|
||||
# 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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈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
|
||||
```
|
||||
|
|
@ -265,7 +264,7 @@ 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。
|
||||
|
||||
|
|
|
|||
29
README_ko.md
29
README_ko.md
|
|
@ -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">
|
||||
|
|
@ -67,6 +67,7 @@
|
|||
|
||||
## 🔥 업데이트
|
||||
|
||||
- 2025-11-12 Confluence, AWS S3, Discord, Google Drive에서 데이터 동기화를 지원합니다.
|
||||
- 2025-10-23 문서 파싱 방법으로 MinerU 및 Docling을 지원합니다.
|
||||
- 2025-10-15 조정된 데이터 파이프라인 지원.
|
||||
- 2025-08-08 OpenAI의 최신 GPT-5 시리즈 모델을 지원합니다.
|
||||
|
|
@ -74,7 +75,6 @@
|
|||
- 2025-05-23 Agent에 Python/JS 코드 실행기 구성 요소를 추가합니다.
|
||||
- 2025-05-05 언어 간 쿼리를 지원합니다.
|
||||
- 2025-03-19 PDF 또는 DOCX 파일 내의 이미지를 이해하기 위해 다중 모드 모델을 사용하는 것을 지원합니다.
|
||||
- 2025-02-28 인터넷 검색(TAVILY)과 결합되어 모든 LLM에 대한 심층 연구를 지원합니다.
|
||||
- 2024-12-18 DeepDoc의 문서 레이아웃 분석 모델 업그레이드.
|
||||
- 2024-08-22 RAG를 통해 SQL 문에 텍스트를 지원합니다.
|
||||
|
||||
|
|
@ -168,29 +168,30 @@
|
|||
> 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
|
||||
# 이 단계는 코드의 entrypoint.sh 파일이 Docker 이미지 버전과 일치하도록 보장합니다.
|
||||
|
||||
# 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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈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:
|
||||
|
||||
|
|
@ -257,7 +258,7 @@ 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.
|
||||
|
||||
|
|
|
|||
|
|
@ -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">
|
||||
|
|
@ -86,6 +86,7 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
|
|||
|
||||
## 🔥 Últimas Atualizações
|
||||
|
||||
- 12-11-2025 Suporta a sincronização de dados do Confluence, AWS S3, Discord e Google Drive.
|
||||
- 23-10-2025 Suporta MinerU e Docling como métodos de análise de documentos.
|
||||
- 15-10-2025 Suporte para pipelines de dados orquestrados.
|
||||
- 08-08-2025 Suporta a mais recente série GPT-5 da OpenAI.
|
||||
|
|
@ -93,7 +94,6 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
|
|||
- 23-05-2025 Adicione o componente executor de código Python/JS ao Agente.
|
||||
- 05-05-2025 Suporte a consultas entre idiomas.
|
||||
- 19-03-2025 Suporta o uso de um modelo multi-modal para entender imagens dentro de arquivos PDF ou DOCX.
|
||||
- 28-02-2025 combinado com a pesquisa na Internet (T AVI LY), suporta pesquisas profundas para qualquer LLM.
|
||||
- 18-12-2024 Atualiza o modelo de Análise de Layout de Documentos no DeepDoc.
|
||||
- 22-08-2024 Suporta conversão de texto para comandos SQL via RAG.
|
||||
|
||||
|
|
@ -186,29 +186,30 @@ 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
|
||||
# Esta etapa garante que o arquivo entrypoint.sh no código corresponda à versão da imagem do Docker.
|
||||
|
||||
# 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 | ≈9 | ✔️ | Lançamento estável |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Lançamento estável |
|
||||
| nightly | ≈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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈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:
|
||||
|
||||
|
|
@ -278,9 +279,9 @@ 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.
|
||||
|
||||
|
|
|
|||
|
|
@ -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">
|
||||
|
|
@ -85,6 +85,7 @@
|
|||
|
||||
## 🔥 近期更新
|
||||
|
||||
- 2025-11-12 支援從 Confluence、AWS S3、Discord、Google Drive 進行資料同步。
|
||||
- 2025-10-23 支援 MinerU 和 Docling 作為文件解析方法。
|
||||
- 2025-10-15 支援可編排的資料管道。
|
||||
- 2025-08-08 支援 OpenAI 最新的 GPT-5 系列模型。
|
||||
|
|
@ -92,7 +93,6 @@
|
|||
- 2025-05-23 為 Agent 新增 Python/JS 程式碼執行器元件。
|
||||
- 2025-05-05 支援跨語言查詢。
|
||||
- 2025-03-19 PDF和DOCX中的圖支持用多模態大模型去解析得到描述.
|
||||
- 2025-02-28 結合網路搜尋（Tavily），對於任意大模型實現類似 Deep Research 的推理功能.
|
||||
- 2024-12-18 升級了 DeepDoc 的文檔佈局分析模型。
|
||||
- 2024-08-22 支援用 RAG 技術實現從自然語言到 SQL 語句的轉換。
|
||||
|
||||
|
|
@ -185,29 +185,30 @@
|
|||
> 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
|
||||
# 此步驟確保程式碼中的 entrypoint.sh 檔案與 Docker 映像版本一致。
|
||||
|
||||
# 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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈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。
|
||||
|
|
@ -289,7 +290,7 @@ 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。
|
||||
|
||||
|
|
|
|||
19
README_zh.md
19
README_zh.md
|
|
@ -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">
|
||||
|
|
@ -85,6 +85,7 @@
|
|||
|
||||
## 🔥 近期更新
|
||||
|
||||
- 2025-11-12 支持从 Confluence、AWS S3、Discord、Google Drive 进行数据同步。
|
||||
- 2025-10-23 支持 MinerU 和 Docling 作为文档解析方法。
|
||||
- 2025-10-15 支持可编排的数据管道。
|
||||
- 2025-08-08 支持 OpenAI 最新的 GPT-5 系列模型。
|
||||
|
|
@ -92,7 +93,6 @@
|
|||
- 2025-05-23 Agent 新增 Python/JS 代码执行器组件。
|
||||
- 2025-05-05 支持跨语言查询。
|
||||
- 2025-03-19 PDF 和 DOCX 中的图支持用多模态大模型去解析得到描述.
|
||||
- 2025-02-28 结合互联网搜索（Tavily），对于任意大模型实现类似 Deep Research 的推理功能.
|
||||
- 2024-12-18 升级了 DeepDoc 的文档布局分析模型。
|
||||
- 2024-08-22 支持用 RAG 技术实现从自然语言到 SQL 语句的转换。
|
||||
|
||||
|
|
@ -186,29 +186,30 @@
|
|||
> 请注意，目前官方提供的所有 Docker 镜像均基于 x86 架构构建，并不提供基于 ARM64 的 Docker 镜像。
|
||||
> 如果你的操作系统是 ARM64 架构，请参考[这篇文档](https://ragflow.io/docs/dev/build_docker_image)自行构建 Docker 镜像。
|
||||
|
||||
> 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.21.1`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.21.1` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。
|
||||
> 运行以下命令会自动下载 RAGFlow Docker 镜像 `v0.22.0`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.22.0` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
|
||||
# 可选：使用稳定版本标签（查看发布：https://github.com/infiniflow/ragflow/releases），例如, `git checkout v0.21.1`
|
||||
# 可选：使用稳定版本标签（查看发布：https://github.com/infiniflow/ragflow/releases），例如：git checkout v0.22.0
|
||||
# 这一步确保代码中的 entrypoint.sh 文件与 Docker 镜像的版本保持一致。
|
||||
|
||||
# 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：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 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
|
||||
> 注意：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。
|
||||
> 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]
|
||||
> 如果你遇到 Docker 镜像拉不下来的问题，可以在 **docker/.env** 文件内根据变量 `RAGFLOW_IMAGE` 的注释提示选择华为云或者阿里云的相应镜像。
|
||||
|
|
@ -288,7 +289,7 @@ RAGFlow 默认使用 Elasticsearch 存储文本和向量数据. 如果要切换
|
|||
> [!WARNING]
|
||||
> Infinity 目前官方并未正式支持在 Linux/arm64 架构下的机器上运行.
|
||||
|
||||
## 🔧 源码编译 Docker 镜像（不含 embedding 模型）
|
||||
## 🔧 源码编译 Docker 镜像
|
||||
|
||||
本 Docker 镜像大小约 2 GB 左右并且依赖外部的大模型和 embedding 服务。
|
||||
|
||||
|
|
|
|||
|
|
@ -349,7 +349,7 @@ class Canvas(Graph):
|
|||
i += 1
|
||||
else:
|
||||
for _, ele in cpn.get_input_elements().items():
|
||||
if isinstance(ele, dict) and ele.get("_cpn_id") and ele.get("_cpn_id") not in self.path[:i]:
|
||||
if isinstance(ele, dict) and ele.get("_cpn_id") and ele.get("_cpn_id") not in self.path[:i] and self.path[0].lower().find("userfillup") < 0:
|
||||
self.path.pop(i)
|
||||
t -= 1
|
||||
break
|
||||
|
|
|
|||
|
|
@ -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.",
|
||||
|
|
|
|||
|
|
@ -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"
|
||||
|
|
|
|||
|
|
@ -89,19 +89,12 @@ def init_superuser():
|
|||
|
||||
|
||||
def init_llm_factory():
|
||||
try:
|
||||
LLMService.filter_delete([(LLM.fid == "MiniMax" or LLM.fid == "Minimax")])
|
||||
LLMService.filter_delete([(LLM.fid == "cohere")])
|
||||
LLMFactoriesService.filter_delete([LLMFactories.name == "cohere"])
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
LLMFactoriesService.filter_delete([1 == 1])
|
||||
factory_llm_infos = settings.FACTORY_LLM_INFOS
|
||||
for factory_llm_info in factory_llm_infos:
|
||||
info = deepcopy(factory_llm_info)
|
||||
llm_infos = info.pop("llm")
|
||||
try:
|
||||
LLMFactoriesService.filter_delete([LLMFactories.name == factory_llm_info["name"]])
|
||||
LLMFactoriesService.save(**info)
|
||||
except Exception:
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -236,13 +236,13 @@ class Connector2KbService(CommonService):
|
|||
conn_id = conn["id"]
|
||||
connector_ids.append(conn_id)
|
||||
if conn_id in old_conn_ids:
|
||||
cls.update_by_id(conn_id, {"auto_parse": conn.get("auto_parse", "1")})
|
||||
cls.filter_update([cls.model.connector_id==conn_id, cls.model.kb_id==kb_id], {"auto_parse": conn.get("auto_parse", "1")})
|
||||
continue
|
||||
cls.save(**{
|
||||
"id": get_uuid(),
|
||||
"connector_id": conn_id,
|
||||
"kb_id": kb_id,
|
||||
"auto_parse": conn.get("auto_parse", "1")
|
||||
"auto_parse": conn.get("auto_parse", "1")
|
||||
})
|
||||
SyncLogsService.schedule(conn_id, kb_id, reindex=True)
|
||||
|
||||
|
|
|
|||
|
|
@ -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]
|
||||
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -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]
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
[general]
|
||||
version = "0.6.4"
|
||||
version = "0.6.5"
|
||||
time_zone = "utc-8"
|
||||
|
||||
[network]
|
||||
|
|
|
|||
|
|
@ -97,14 +97,7 @@ RAGFlow utilizes MinIO as its object storage solution, leveraging its scalabilit
|
|||
- `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:v0.21.1` (the RAGFlow Docker image without embedding models).
|
||||
|
||||
:::tip NOTE
|
||||
If you cannot download the RAGFlow Docker image, try the following mirrors.
|
||||
|
|
|
|||
|
|
@ -42,11 +42,7 @@ cd ragflow/
|
|||
```
|
||||
|
||||
2. Install Python dependencies:
|
||||
- slim:
|
||||
```bash
|
||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
||||
```
|
||||
- full:
|
||||
|
||||
```bash
|
||||
uv sync --python 3.10 # install RAGFlow dependent python modules
|
||||
```
|
||||
|
|
|
|||
|
|
@ -60,7 +60,7 @@ Where:
|
|||
|
||||
### Transports
|
||||
|
||||
The RAGFlow MCP server supports two transports: the legacy SSE transport (served at `/sse`), introduced on November 5, 2024 and deprecated on March 26, 2025, and the streamable-HTTP transport (served at `/mcp`). The legacy SSE transport and the streamable HTTP transport with JSON responses are enabled by default. To disable either transport, use the flags `--no-transport-sse-enabled` or `--no-transport-streamable-http-enabled`. To disable JSON responses for the streamable HTTP transport, use the `--no-json-response` flag.
|
||||
The RAGFlow MCP server supports two transports: the legacy SSE transport (served at `/sse`), introduced on November 5, 2024, and deprecated on March 26, 2025, and the streamable-HTTP transport (served at `/mcp`). The legacy SSE transport and the streamable HTTP transport with JSON responses are enabled by default. To disable either transport, use the flags `--no-transport-sse-enabled` or `--no-transport-streamable-http-enabled`. To disable JSON responses for the streamable HTTP transport, use the `--no-json-response` flag.
|
||||
|
||||
### Launch from Docker
|
||||
|
||||
|
|
|
|||
31
docs/faq.mdx
31
docs/faq.mdx
|
|
@ -26,27 +26,9 @@ The "garbage in garbage out" status quo remains unchanged despite the fact that
|
|||
|
||||
---
|
||||
|
||||
### Differences between RAGFlow full edition and RAGFlow slim edition?
|
||||
|
||||
Each RAGFlow release is available in two editions:
|
||||
|
||||
- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1-slim`
|
||||
- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1`
|
||||
|
||||
Note: Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
|
||||
|
||||
---
|
||||
|
||||
### Which embedding models can be deployed locally?
|
||||
|
||||
RAGFlow offers two Docker image editions, `v0.21.1-slim` and `v0.21.1`:
|
||||
|
||||
- `infiniflow/ragflow:v0.21.1-slim` (default): The RAGFlow Docker image without embedding models.
|
||||
- `infiniflow/ragflow:v0.21.1`: The RAGFlow Docker image with the following built-in embedding models:
|
||||
- `BAAI/bge-large-zh-v1.5`
|
||||
- `maidalun1020/bce-embedding-base_v1`
|
||||
|
||||
Note: Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
|
||||
Starting from `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -65,7 +47,7 @@ If you build RAGFlow from source, the version number is also in the system log:
|
|||
/ _, _// ___ |/ /_/ // __/ / // /_/ /| |/ |/ /
|
||||
/_/ |_|/_/ |_|\____//_/ /_/ \____/ |__/|__/
|
||||
|
||||
2025-02-18 10:10:43,835 INFO 1445658 RAGFlow version: v0.15.0-50-g6daae7f2 full
|
||||
2025-02-18 10:10:43,835 INFO 1445658 RAGFlow version: v0.15.0-50-g6daae7f2
|
||||
```
|
||||
|
||||
Where:
|
||||
|
|
@ -73,9 +55,6 @@ Where:
|
|||
- `v0.15.0`: The officially published release.
|
||||
- `50`: The number of git commits since the official release.
|
||||
- `g6daae7f2`: `g` is the prefix, and `6daae7f2` is the first seven characters of the current commit ID.
|
||||
- `full`/`slim`: The RAGFlow edition.
|
||||
- `full`: The full RAGFlow edition.
|
||||
- `slim`: The RAGFlow edition without embedding models and Python packages.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -172,7 +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'
|
||||
|
|
@ -214,7 +193,7 @@ This error suggests that you do not have Internet access or are unable to connec
|
|||
|
||||
---
|
||||
|
||||
### `WARNING: can't find /raglof/rag/res/borker.tm`
|
||||
### `WARNING: can't find /ragflow/rag/res/borker.tm`
|
||||
|
||||
Ignore this warning and continue. All system warnings can be ignored.
|
||||
|
||||
|
|
@ -434,7 +413,7 @@ See [here](./guides/models/deploy_local_llm.mdx) for more information.
|
|||
|
||||
For a locally deployed RAGFlow: the total file size limit per upload is 1GB, with a batch upload limit of 32 files. There is no cap on the total number of files per account. To update this 1GB file size limit:
|
||||
|
||||
- In **docker/.env**, upcomment `# MAX_CONTENT_LENGTH=1073741824`, adjust the value as needed, and note that `1073741824` represents 1GB in bytes.
|
||||
- In **docker/.env**, uncomment `# MAX_CONTENT_LENGTH=1073741824`, adjust the value as needed, and note that `1073741824` represents 1GB in bytes.
|
||||
- If you update the value of `MAX_CONTENT_LENGTH` in **docker/.env**, ensure that you update `client_max_body_size` in **nginx/nginx.conf** accordingly.
|
||||
|
||||
:::tip NOTE
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ The service status page displays of all services within the RAGFlow system.
|
|||
- **Search**: Use the search bar to quickly find services by **Name** or **Service Type**.
|
||||
- **Actions** (hover over a row to see action buttons):
|
||||
- **Extra Info**: Display additional configuration information of a service in a dialog.
|
||||
- **Service Details**: Display detailed status information of a service in a dialog. According to services's type, a service's status information could be displayed as a plain text, a key-value data list, a data table or a bar chart.
|
||||
- **Service Details**: Display detailed status information of a service in a dialog. According to service's type, a service's status information could be displayed as a plain text, a key-value data list, a data table or a bar chart.
|
||||
|
||||
|
||||
### User management
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ The **+ Add tools** and **+ Add agent** sections are used *only* when you need t
|
|||
|
||||
### 6. Choose the next component
|
||||
|
||||
When necessary, click the **+** button on the **Agent** component to choose the next component in the worflow from the dropdown list.
|
||||
When necessary, click the **+** button on the **Agent** component to choose the next component in the workflow from the dropdown list.
|
||||
|
||||
## Connect to an MCP server as a client
|
||||
|
||||
|
|
@ -97,7 +97,7 @@ Update your MCP server's name, URL (including the API key), server type, and oth
|
|||
|
||||
To ensure reliable tool calls, you may specify within the system prompt which tasks should trigger each tool call.
|
||||
|
||||
### 6. View the availabe tools of your MCP server
|
||||
### 6. View the available tools of your MCP server
|
||||
|
||||
On the canvas, click the newly-populated Tavily server to view and select its available tools:
|
||||
|
||||
|
|
@ -113,7 +113,7 @@ Click the dropdown menu of **Model** to show the model configuration window.
|
|||
- **Model**: The chat model to use.
|
||||
- Ensure you set the chat model correctly on the **Model providers** page.
|
||||
- You can use different models for different components to increase flexibility or improve overall performance.
|
||||
- **Creavity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
- **Creativity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
This parameter has three options:
|
||||
- **Improvise**: Produces more creative responses.
|
||||
- **Precise**: (Default) Produces more conservative responses.
|
||||
|
|
@ -137,7 +137,7 @@ Click the dropdown menu of **Model** to show the model configuration window.
|
|||
|
||||
:::tip NOTE
|
||||
- It is not necessary to stick with the same model for all components. If a specific model is not performing well for a particular task, consider using a different one.
|
||||
- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Creavity**.
|
||||
- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Creativity**.
|
||||
:::
|
||||
|
||||
### System prompt
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ Click the dropdown menu of **Model** to show the model configuration window.
|
|||
- **Model**: The chat model to use.
|
||||
- Ensure you set the chat model correctly on the **Model providers** page.
|
||||
- You can use different models for different components to increase flexibility or improve overall performance.
|
||||
- **Creavity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
- **Creativity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
This parameter has three options:
|
||||
- **Improvise**: Produces more creative responses.
|
||||
- **Precise**: (Default) Produces more conservative responses.
|
||||
|
|
@ -66,7 +66,7 @@ Click the dropdown menu of **Model** to show the model configuration window.
|
|||
|
||||
:::tip NOTE
|
||||
- It is not necessary to stick with the same model for all components. If a specific model is not performing well for a particular task, consider using a different one.
|
||||
- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Creavity**.
|
||||
- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Creativity**.
|
||||
:::
|
||||
|
||||
### Message window size
|
||||
|
|
|
|||
|
|
@ -163,7 +163,7 @@ pandas
|
|||
requests
|
||||
openpyxl # here it is
|
||||
|
||||
(ragflow) ➜ ragflow/sandbox main ✗ make # rebuild the docker image, this command will rebuild the iamge and start the service immediately. To build image only, using `make build` instead.
|
||||
(ragflow) ➜ ragflow/sandbox main ✗ make # rebuild the docker image, this command will rebuild the image and start the service immediately. To build image only, using `make build` instead.
|
||||
|
||||
(ragflow) ➜ ragflow/sandbox main ✗ docker exec -it sandbox_python_0 /bin/bash # entering container to check if the package is installed
|
||||
|
||||
|
|
@ -189,7 +189,7 @@ To import your JavaScript packages, navigate to `sandbox_base_image/nodejs` and
|
|||
|
||||
(ragflow) ➜ ragflow/sandbox/sandbox_base_image/nodejs main ✓ cd ../.. # go back to sandbox root directory
|
||||
|
||||
(ragflow) ➜ ragflow/sandbox main ✗ make # rebuild the docker image, this command will rebuild the iamge and start the service immediately. To build image only, using `make build` instead.
|
||||
(ragflow) ➜ ragflow/sandbox main ✗ make # rebuild the docker image, this command will rebuild the image and start the service immediately. To build image only, using `make build` instead.
|
||||
|
||||
(ragflow) ➜ ragflow/sandbox main ✗ docker exec -it sandbox_nodejs_0 /bin/bash # entering container to check if the package is installed
|
||||
|
||||
|
|
|
|||
|
|
@ -40,12 +40,12 @@ For dynamic SQL queries, you can include variables in your SQL queries, such as
|
|||
|
||||
### Database type
|
||||
|
||||
The supported database type. Currently the following database types are available:
|
||||
The supported database type. Currently, the following database types are available:
|
||||
|
||||
- MySQL
|
||||
- PostreSQL
|
||||
- PostgreSQL
|
||||
- MariaDB
|
||||
- Microsoft SQL Server (Myssql)
|
||||
- Microsoft SQL Server (Mssql)
|
||||
|
||||
### Database
|
||||
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ A component that sets the parsing rules for your dataset.
|
|||
|
||||
---
|
||||
|
||||
A **Parser** component is auto-populated on the ingestion pipeline canvas and required in all ingestion pipeline workflows. Just like the **Extract** stage in the traditional ETL process, a **Parser** component in an ingestion pipeline defines how various file types are parsed into structured data. Click the component to display its configuration panel. In this configuration panel, you set the parsing rules for various file types.
|
||||
A **Parser** component is autopopulated on the ingestion pipeline canvas and required in all ingestion pipeline workflows. Just like the **Extract** stage in the traditional ETL process, a **Parser** component in an ingestion pipeline defines how various file types are parsed into structured data. Click the component to display its configuration panel. In this configuration panel, you set the parsing rules for various file types.
|
||||
|
||||
## Configurations
|
||||
|
||||
|
|
@ -39,7 +39,7 @@ The output of a PDF parser is `json`. In the PDF parser, you select the parsing
|
|||
- [Docling](https://github.com/docling-project/docling): (Experimental) An open-source document processing tool for gen AI.
|
||||
- A third-party visual model from a specific model provider.
|
||||
|
||||
:::danger IMPORTANG
|
||||
:::danger IMPORTANT
|
||||
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports MinerU (>= 2.6.3) as an optional PDF parser with multiple backends. RAGFlow acts only as a client for MinerU, calling it to parse documents, reading the output files, and ingesting the parsed content. To use this feature, follow these steps:
|
||||
|
||||
1. Prepare MinerU:
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
||||
|
|
@ -61,7 +61,7 @@ Click the **Run** button on the top of canvas to test the retrieval results.
|
|||
|
||||
### 7. Choose the next component
|
||||
|
||||
When necessary, click the **+** button on the **Retrieval** component to choose the next component in the worflow from the dropdown list.
|
||||
When necessary, click the **+** button on the **Retrieval** component to choose the next component in the workflow from the dropdown list.
|
||||
|
||||
|
||||
## Configurations
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ Click the dropdown menu of **Model** to show the model configuration window.
|
|||
- **Model**: The chat model to use.
|
||||
- Ensure you set the chat model correctly on the **Model providers** page.
|
||||
- You can use different models for different components to increase flexibility or improve overall performance.
|
||||
- **Creavity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
- **Creativity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
This parameter has three options:
|
||||
- **Improvise**: Produces more creative responses.
|
||||
- **Precise**: (Default) Produces more conservative responses.
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ An Agent’s response time generally depends on many factors, e.g., the LLM’s
|
|||
|
||||
- For simple tasks, such as retrieval, rewriting, formatting, or structured data extraction, use concise prompts, remove planning or reasoning instructions, enforce output length limits, and select smaller or Turbo-class models. This significantly reduces latency and cost with minimal impact on quality.
|
||||
|
||||
- For complex tasks, like multi-step reasoning, cross-document synthesis, or tool-based workflows, maintain or enhance prompts that include planning, reflection, and verification steps.
|
||||
- For complex tasks, like multistep reasoning, cross-document synthesis, or tool-based workflows, maintain or enhance prompts that include planning, reflection, and verification steps.
|
||||
|
||||
- In multi-Agent orchestration systems, delegate simple subtasks to sub-Agents using smaller, faster models, and reserve more powerful models for the lead Agent to handle complexity and uncertainty.
|
||||
|
||||
|
|
|
|||
|
|
@ -55,7 +55,7 @@ You start an AI conversation by creating an assistant.
|
|||
4. Update Model-specific Settings:
|
||||
|
||||
- In **Model**: you select the chat model. Though you have selected the default chat model in **System Model Settings**, RAGFlow allows you to choose an alternative chat model for your dialogue.
|
||||
- **Creavity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
- **Creativity**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**.
|
||||
This parameter has three options:
|
||||
- **Improvise**: Produces more creative responses.
|
||||
- **Precise**: (Default) Produces more conservative responses.
|
||||
|
|
|
|||
|
|
@ -58,7 +58,7 @@ The Auto-keyword or Auto-question values relate closely to the chunking size in
|
|||
|---------------------------------------------------------------------|---------------------------------|----------------------------|----------------------------|
|
||||
| Internal process guidance for employee handbook | Small, under 10 pages | 0 | 0 |
|
||||
| Customer service FAQs | Medium, 10–100 pages | 3–7 | 1–3 |
|
||||
| Technical whitepapers: Development standards, protocol details | Large, over 100 pages | 2–4 | 1–2 |
|
||||
| Technical white papers: Development standards, protocol details | Large, over 100 pages | 2–4 | 1–2 |
|
||||
| Contracts / Regulations / Legal clause retrieval | Large, over 50 pages | 2–5 | 0–1 |
|
||||
| Multi-repository layered new documents + old archive | Many | Adjust as appropriate |Adjust as appropriate |
|
||||
| Social media comment pool: multilingual & mixed spelling | Very large volume of short text | 8–12 | 0 |
|
||||
|
|
|
|||
|
|
@ -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.
|
||||
|
|
|
|||
|
|
@ -91,7 +91,7 @@ Nope. The knowledge graph does *not* update *until* you regenerate a knowledge g
|
|||
|
||||
### How to remove a generated knowledge graph?
|
||||
|
||||
On the **Configuration** page of your dataset, find the **Knoweledge graph** field and click the recycle bin button to the right of the field.
|
||||
On the **Configuration** page of your dataset, find the **Knowledge graph** field and click the recycle bin button to the right of the field.
|
||||
|
||||
### Where is the created knowledge graph stored?
|
||||
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ Convert complex Excel spreadsheets into HTML tables.
|
|||
When using the **General** chunking method, you can enable the **Excel to HTML** toggle to convert spreadsheet files into HTML tables. If it is disabled, spreadsheet tables will be represented as key-value pairs. For complex tables that cannot be simply represented this way, you must enable this feature.
|
||||
|
||||
:::caution WARNING
|
||||
The feature is disabled by default. If your dataset contains spreadsheets with complex tables and you do not enable this feature, RAGFlow will not throw an error but your tables are likely to be garbled.
|
||||
The feature is disabled by default. If your dataset contains spreadsheets with complex tables, and you do not enable this feature, RAGFlow will not throw an error but your tables are likely to be garbled.
|
||||
:::
|
||||
|
||||
## Scenarios
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ RAPTOR (Recursive Abstractive Processing for Tree Organized Retrieval) is an enh
|
|||
|
||||
|
||||
|
||||
Our tests with this new approach demonstrate state-of-the-art (SOTA) results on question-answering tasks requiring complex, multi-step reasoning. By combining RAPTOR retrieval with our built-in chunking methods and/or other retrieval-augmented generation (RAG) approaches, you can further improve your question-answering accuracy.
|
||||
Our tests with this new approach demonstrate state-of-the-art (SOTA) results on question-answering tasks requiring complex, multistep reasoning. By combining RAPTOR retrieval with our built-in chunking methods and/or other retrieval-augmented generation (RAG) approaches, you can further improve your question-answering accuracy.
|
||||
|
||||
:::danger WARNING
|
||||
Enabling RAPTOR requires significant memory, computational resources, and tokens.
|
||||
|
|
@ -29,7 +29,7 @@ The recursive clustering and summarization capture a broad understanding (by the
|
|||
|
||||
## Scenarios
|
||||
|
||||
For multi-hop question-answering tasks involving complex, multi-step reasoning, a semantic gap often exists between the question and its answer. As a result, searching with the question often fails to retrieve the relevant chunks that contribute to the correct answer. RAPTOR addresses this challenge by providing the chat model with richer and more context-aware and relevant chunks to summarize, enabling a holistic understanding without losing granular details.
|
||||
For multi-hop question-answering tasks involving complex, multistep reasoning, a semantic gap often exists between the question and its answer. As a result, searching with the question often fails to retrieve the relevant chunks that contribute to the correct answer. RAPTOR addresses this challenge by providing the chat model with richer and more context-aware and relevant chunks to summarize, enabling a holistic understanding without losing granular details.
|
||||
|
||||
:::tip NOTE
|
||||
Knowledge graphs can also be used for multi-hop question-answering tasks. See [Construct knowledge graph](./construct_knowledge_graph.md) for details. You may use either approach or both, but ensure you understand the memory, computational, and token costs involved.
|
||||
|
|
|
|||
|
|
@ -23,7 +23,7 @@ RAGFlow isn't one-size-fits-all. It is built for flexibility and supports deeper
|
|||
- **Laws**
|
||||
- **Presentation**
|
||||
- **One**
|
||||
- To use a third-party visual model for parsing PDFs, ensure you have set a default img2txt model under **Set default models** on the **Model providers** page.
|
||||
- To use a third-party visual model for parsing PDFs, ensure you have set a default VLM under **Set default models** on the **Model providers** page.
|
||||
|
||||
## Quickstart
|
||||
|
||||
|
|
@ -39,7 +39,7 @@ RAGFlow isn't one-size-fits-all. It is built for flexibility and supports deeper
|
|||
- [Docling](https://github.com/docling-project/docling): (Experimental) An open-source document processing tool for gen AI.
|
||||
- A third-party visual model from a specific model provider.
|
||||
|
||||
:::danger IMPORTANG
|
||||
:::danger IMPORTANT
|
||||
MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports MinerU (>= 2.6.3) as an optional PDF parser with multiple backends. RAGFlow acts only as a client for MinerU, calling it to parse documents, reading the output files, and ingesting the parsed content. To use this feature, follow these steps:
|
||||
|
||||
1. Prepare MinerU:
|
||||
|
|
@ -90,7 +90,7 @@ MinerU PDF document parsing is available starting from v0.22.0. RAGFlow supports
|
|||
```
|
||||
|
||||
3. Restart the ragflow-server.
|
||||
4. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and slect **MinerU** in **PDF parser**.
|
||||
4. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and select **MinerU** in **PDF parser**.
|
||||
5. If you use a custom ingestion pipeline instead, you must also complete the first three steps before selecting **MinerU** in the **Parsing method** section of the **Parser** component.
|
||||
:::
|
||||
|
||||
|
|
@ -102,7 +102,7 @@ Third-party visual models are marked **Experimental**, because we have not fully
|
|||
|
||||
### When should I select DeepDoc or a third-party visual model as the PDF parser?
|
||||
|
||||
Use a visual model to extract data if your PDFs contain formatted or image-based text rather than plain text. DeepDoc is the default visual model but can be time-consuming. You can also choose a lightweight or high-performance img2txt model depending on your needs and hardware capabilities.
|
||||
Use a visual model to extract data if your PDFs contain formatted or image-based text rather than plain text. DeepDoc is the default visual model but can be time-consuming. You can also choose a lightweight or high-performance VLM depending on your needs and hardware capabilities.
|
||||
|
||||
### Can I select a visual model to parse my DOCX files?
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
---
|
||||
sidebar_position: -7
|
||||
slug: /set_metada
|
||||
slug: /set_metadata
|
||||
---
|
||||
|
||||
# Set metadata
|
||||
|
|
|
|||
|
|
@ -73,7 +73,7 @@ Creating a tag set is *not* for once and for all. Oftentimes, you may find it ne
|
|||
### Update tag set in tag frequency table
|
||||
|
||||
1. Navigate to the **Configuration** page in your tag set.
|
||||
2. Click the **Table** tab under **Tag view** to view the tag frequncy table, where you can update tag names or delete tags.
|
||||
2. Click the **Table** tab under **Tag view** to view the tag frequency table, where you can update tag names or delete tags.
|
||||
|
||||
:::danger IMPORTANT
|
||||
When a tag set is updated, you must re-parse the documents in your dataset so that their tags can be updated accordingly.
|
||||
|
|
|
|||
|
|
@ -89,7 +89,7 @@ Once the restore process is complete, you can start the RAGFlow services on your
|
|||
docker-compose -f docker/docker-compose.yml up -d
|
||||
```
|
||||
|
||||
**Note:** If you already have build an service by docker-compose before, you may need to backup your data for target machine like this guide above and run like:
|
||||
**Note:** If you already have built a service by docker-compose before, you may need to backup your data for target machine like this guide above and run like:
|
||||
|
||||
```bash
|
||||
# Please backup by `sh docker/migration.sh backup backup_dir_name` before you do the following line.
|
||||
|
|
|
|||
|
|
@ -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.
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ slug: /join_or_leave_team
|
|||
|
||||
# Join or leave a team
|
||||
|
||||
Accept an invite to join a team, decline an invite, or leave a team.
|
||||
Accept an invitation to join a team, decline an invitation, or leave a team.
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
|
|
@ -189,12 +189,8 @@ 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:
|
||||
|
||||
:::tip NOTE
|
||||
The command below downloads the `v0.21.1-slim` edition of the RAGFlow Docker image. Refer to 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. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1` for the full edition `v0.21.1`.
|
||||
:::
|
||||
|
||||
```bash
|
||||
# Use CPU for embedding and DeepDoc tasks:
|
||||
# Use CPU for DeepDoc tasks:
|
||||
$ docker compose -f docker-compose.yml up -d
|
||||
```
|
||||
|
||||
|
|
@ -202,27 +198,17 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
|
|||
<APITable>
|
||||
```
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models and Python packages? | Stable? |
|
||||
| ------------------- | --------------- | ----------------------------------------- | ------------------------ |
|
||||
| v0.21.1 | ≈9 | ✔️ | Stable release |
|
||||
| v0.21.1-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
| RAGFlow image tag | Image size (GB) | Stable? |
|
||||
| ------------------- | --------------- | ------------------------ |
|
||||
| v0.21.1 | ≈2 | Stable release |
|
||||
| nightly | ≈2 | _Unstable_ nightly build |
|
||||
|
||||
```mdx-code-block
|
||||
</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. For example, a slim edition image will expand to around 7 GB once unpacked.
|
||||
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.
|
||||
:::
|
||||
|
||||
4. Check the server status after having the server up and running:
|
||||
|
|
|
|||
|
|
@ -7,21 +7,42 @@ slug: /release_notes
|
|||
|
||||
Key features, improvements and bug fixes in the latest releases.
|
||||
|
||||
:::info
|
||||
Each RAGFlow release is available in two editions:
|
||||
- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1-slim`
|
||||
- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1`
|
||||
:::
|
||||
## v0.22.0
|
||||
|
||||
Released on November 12, 2025.
|
||||
|
||||
### Breaking Changes
|
||||
|
||||
:::danger IMPORTANT
|
||||
The embedding models included in a full edition 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 may be compromised if you use them to embed documents in other languages.
|
||||
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.
|
||||
|
|
|
|||
|
|
@ -96,7 +96,7 @@ ragflow:
|
|||
infinity:
|
||||
image:
|
||||
repository: infiniflow/infinity
|
||||
tag: v0.6.4
|
||||
tag: v0.6.5
|
||||
pullPolicy: IfNotPresent
|
||||
pullSecrets: []
|
||||
storage:
|
||||
|
|
|
|||
|
|
@ -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",
|
||||
|
|
|
|||
|
|
@ -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"]
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -149,13 +149,13 @@ export const SelectWithSearch = forwardRef<
|
|||
<span className="leading-none truncate">{selectLabel}</span>
|
||||
</span>
|
||||
) : (
|
||||
<span className="text-muted-foreground">{placeholder}</span>
|
||||
<span className="text-text-disabled">{placeholder}</span>
|
||||
)}
|
||||
<div className="flex items-center justify-between">
|
||||
{value && allowClear && (
|
||||
<>
|
||||
<XIcon
|
||||
className="h-4 mx-2 cursor-pointer text-muted-foreground"
|
||||
className="h-4 mx-2 cursor-pointer text-text-disabled"
|
||||
onClick={handleClear}
|
||||
/>
|
||||
<Separator
|
||||
|
|
|
|||
|
|
@ -127,7 +127,7 @@ const RaptorFormFields = ({
|
|||
</FormLabel>
|
||||
<div className="w-3/4">
|
||||
<FormControl>
|
||||
<Radio.Group {...field}>
|
||||
<Radio.Group {...field} disabled={!!data?.finish_at}>
|
||||
<div className={'flex gap-4 w-full text-text-secondary '}>
|
||||
<Radio value="dataset">{t('scopeDataset')}</Radio>
|
||||
<Radio value="file">{t('scopeSingleFile')}</Radio>
|
||||
|
|
|
|||
|
|
@ -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();
|
||||
}
|
||||
|
|
|
|||
|
|
@ -694,6 +694,7 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
|
|||
tocEnhanceTip: ` During the parsing of the document, table of contents information was generated (see the 'Enable Table of Contents Extraction' option in the General method). This allows the large model to return table of contents items relevant to the user's query, thereby using these items to retrieve related chunks and apply weighting to these chunks during the sorting process. This approach is derived from mimicking the behavioral logic of how humans search for knowledge in books.`,
|
||||
},
|
||||
setting: {
|
||||
selectModelPlaceholder: 'Select model',
|
||||
configureModelTitle: 'Configure model',
|
||||
confluenceIsCloudTip:
|
||||
'Check if this is a Confluence Cloud instance, uncheck for Confluence Server/Data Center',
|
||||
|
|
@ -729,7 +730,7 @@ Example: general/v2/`,
|
|||
google_driveSharedFoldersTip:
|
||||
'Comma-separated Google Drive folder links to crawl.',
|
||||
availableSourcesDescription: 'Select a data source to add',
|
||||
availableSources: 'Available Sources',
|
||||
availableSources: 'Available sources',
|
||||
datasourceDescription: 'Manage your data source and connections',
|
||||
save: 'Save',
|
||||
search: 'Search',
|
||||
|
|
@ -748,7 +749,7 @@ Example: general/v2/`,
|
|||
'Please enter your current password to change your password.',
|
||||
model: 'Model providers',
|
||||
systemModelDescription: 'Please complete these settings before beginning',
|
||||
dataSources: 'Data Sources',
|
||||
dataSources: 'Data sources',
|
||||
team: 'Team',
|
||||
system: 'System',
|
||||
logout: 'Log out',
|
||||
|
|
@ -787,8 +788,8 @@ Example: general/v2/`,
|
|||
'Please enter the API key (for locally deployed model,ignore this).',
|
||||
apiKeyTip:
|
||||
'The API key can be obtained by registering the corresponding LLM supplier.',
|
||||
showMoreModels: 'View Models',
|
||||
hideModels: 'Hide Models',
|
||||
showMoreModels: 'View models',
|
||||
hideModels: 'Hide models',
|
||||
baseUrl: 'Base-Url',
|
||||
baseUrlTip:
|
||||
'If your API key is from OpenAI, just ignore it. Any other intermediate providers will give this base url with the API key.',
|
||||
|
|
@ -813,7 +814,7 @@ Example: general/v2/`,
|
|||
ttsModel: 'TTS',
|
||||
ttsModelTip:
|
||||
'The default text-to-speech model. If you cannot find a model from the dropdown, check https://ragflow.io/docs/dev/supported_models to see if your model provider supports this model.',
|
||||
workspace: 'Workspace',
|
||||
workspace: 'workspace',
|
||||
upgrade: 'Upgrade',
|
||||
addLlmTitle: 'Add LLM',
|
||||
editLlmTitle: 'Edit {{name}} Model',
|
||||
|
|
@ -921,11 +922,11 @@ Example: general/v2/`,
|
|||
add: 'Add',
|
||||
updateDate: 'Date',
|
||||
role: 'State',
|
||||
invite: 'Invite Member',
|
||||
invite: 'Invite member',
|
||||
agree: 'Accept',
|
||||
refuse: 'Decline',
|
||||
teamMembers: 'Team Members',
|
||||
joinedTeams: 'Joined Teams',
|
||||
teamMembers: 'Team members',
|
||||
joinedTeams: 'Joined teams',
|
||||
sureDelete: 'Are you sure to remove this member?',
|
||||
quit: 'Quit',
|
||||
sureQuit: 'Are you sure you want to quit the team you joined?',
|
||||
|
|
@ -1825,7 +1826,7 @@ Important structured information may include: names, dates, locations, events, k
|
|||
addMCP: 'Add MCP',
|
||||
editMCP: 'Edit MCP',
|
||||
toolsAvailable: 'tools available',
|
||||
mcpServers: 'MCP Servers',
|
||||
mcpServers: 'MCP servers',
|
||||
customizeTheListOfMcpServers: 'Customize the list of MCP servers',
|
||||
cachedTools: 'cached tools',
|
||||
bulkManage: 'Bulk manage',
|
||||
|
|
|
|||
|
|
@ -684,6 +684,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
|
|||
tocEnhanceTip: `解析文档时生成了目录信息（见General方法的‘启用目录抽取’），让大模型返回和用户问题相关的目录项，从而利用目录项拿到相关chunk，对这些chunk在排序中进行加权。这种方法来源于模仿人类查询书本中知识的行为逻辑`,
|
||||
},
|
||||
setting: {
|
||||
selectModelPlaceholder: '请选择模型',
|
||||
configureModelTitle: '配置模型',
|
||||
confluenceIsCloudTip:
|
||||
'检查这是否是 Confluence Cloud 实例，如果是 Confluence 服务/数据中心，则取消选中。',
|
||||
|
|
|
|||
|
|
@ -126,7 +126,7 @@ function AdminLogin() {
|
|||
color="rgb(128, 255, 248)"
|
||||
/>
|
||||
|
||||
<BgSvg />
|
||||
<BgSvg isPaused={true} />
|
||||
|
||||
<div className="absolute top-3 left-0 w-full">
|
||||
<div className="absolute mt-12 ml-12 flex items-center">
|
||||
|
|
|
|||
|
|
@ -5,7 +5,9 @@ const aspectRatio = {
|
|||
bottom: 704,
|
||||
};
|
||||
|
||||
export const BgSvg = () => {
|
||||
export const BgSvg = ({ isPaused = false }: { isPaused?: boolean }) => {
|
||||
const animationClass = isPaused ? 'paused' : '';
|
||||
|
||||
const def = (
|
||||
path: string,
|
||||
id: number | string = '',
|
||||
|
|
@ -124,7 +126,7 @@ export const BgSvg = () => {
|
|||
<div className="absolute inset-0 overflow-hidden pointer-events-none ">
|
||||
<div className="absolute top-0 left-0 right-0 w-full">
|
||||
<div
|
||||
className={`w-full ml-10`}
|
||||
className={`w-full ml-10 ${animationClass}`}
|
||||
style={{ height: aspectRatio['top'] + 'px' }}
|
||||
>
|
||||
{def(
|
||||
|
|
@ -134,7 +136,7 @@ export const BgSvg = () => {
|
|||
)}
|
||||
</div>
|
||||
<div
|
||||
className={`w-full -mt-48`}
|
||||
className={`w-full -mt-48 ${animationClass}`}
|
||||
style={{ height: aspectRatio['middle'] + 'px' }}
|
||||
>
|
||||
{def(
|
||||
|
|
@ -144,7 +146,7 @@ export const BgSvg = () => {
|
|||
)}
|
||||
</div>
|
||||
<div
|
||||
className={`w-full -mt-72`}
|
||||
className={`w-full -mt-72 ${animationClass}`}
|
||||
style={{ height: aspectRatio['bottom'] + 'px' }}
|
||||
>
|
||||
{def(
|
||||
|
|
|
|||
|
|
@ -1,6 +1,3 @@
|
|||
.animate-glow {
|
||||
animation: glow 16s infinite linear;
|
||||
}
|
||||
.mask-path {
|
||||
stroke-width: 8;
|
||||
::after {
|
||||
|
|
@ -34,11 +31,20 @@
|
|||
stroke-dashoffset: -600;
|
||||
} /* 15+300-30=285 */
|
||||
}
|
||||
|
||||
.animate-glow {
|
||||
animation: glow 16s infinite linear;
|
||||
}
|
||||
.animate-highlight {
|
||||
animation: highlight-flow 16s linear infinite;
|
||||
}
|
||||
|
||||
.paused {
|
||||
.animate-glow,
|
||||
.animate-highlight {
|
||||
animation-play-state: paused;
|
||||
}
|
||||
}
|
||||
|
||||
//////////////////////////////////////////////////////////////////////////
|
||||
.perspective-1000 {
|
||||
perspective: 1000px;
|
||||
|
|
@ -47,11 +53,13 @@
|
|||
min-height: 680px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
will-change: transform;
|
||||
}
|
||||
.transform-style-3d {
|
||||
transform-style: preserve-3d;
|
||||
-webkit-transform-style: preserve-3d;
|
||||
transition-duration: 0.4s;
|
||||
will-change: transform;
|
||||
}
|
||||
.backface-hidden {
|
||||
backface-visibility: hidden;
|
||||
|
|
|
|||
|
|
@ -42,7 +42,9 @@ const Login = () => {
|
|||
useLoginWithChannel();
|
||||
const { t } = useTranslation('translation', { keyPrefix: 'login' });
|
||||
const [isLoginPage, setIsLoginPage] = useState(true);
|
||||
const [showPassword, setShowPassword] = useState(false);
|
||||
|
||||
const [isUserInteracting, setIsUserInteracting] = useState(true);
|
||||
|
||||
const loading =
|
||||
signLoading ||
|
||||
registerLoading ||
|
||||
|
|
@ -152,9 +154,8 @@ const Login = () => {
|
|||
color={'rgb(128, 255, 248)'}
|
||||
/>
|
||||
<div className=" h-[inherit] relative overflow-auto">
|
||||
<BgSvg />
|
||||
<BgSvg isPaused={isUserInteracting} />
|
||||
|
||||
{/* <SpotlightTopRight opcity={0.7} coverage={10} /> */}
|
||||
<div className="absolute top-3 flex flex-col items-center mb-12 w-full text-text-primary">
|
||||
<div className="flex items-center mb-4 w-full pl-10 pt-10 ">
|
||||
<div className="w-12 h-12 p-2 rounded-lg flex items-center justify-center mr-3">
|
||||
|
|
@ -237,7 +238,7 @@ const Login = () => {
|
|||
<FormControl>
|
||||
<div className="relative">
|
||||
<Input
|
||||
type={showPassword ? 'text' : 'password'}
|
||||
type={'password'}
|
||||
placeholder={t('passwordPlaceholder')}
|
||||
autoComplete={
|
||||
title === 'login'
|
||||
|
|
|
|||
|
|
@ -189,7 +189,7 @@ export const DataSourceFormFields = {
|
|||
name: 'config.credentials.google_tokens',
|
||||
type: FormFieldType.Textarea,
|
||||
required: true,
|
||||
render: (fieldProps) => (
|
||||
render: (fieldProps: any) => (
|
||||
<GoogleDriveTokenField
|
||||
value={fieldProps.value}
|
||||
onChange={fieldProps.onChange}
|
||||
|
|
|
|||
|
|
@ -161,7 +161,7 @@ const SystemSetting = ({ onOk, loading }: IProps) => {
|
|||
value={value}
|
||||
options={options}
|
||||
onChange={(value) => handleFieldChange(id, value)}
|
||||
placeholder={tcommon('selectPlaceholder')}
|
||||
placeholder={t('selectModelPlaceholder')}
|
||||
/>
|
||||
</div>
|
||||
);
|
||||
|
|
|
|||
|
|
@ -123,16 +123,14 @@ export const AvailableModels: FC<{
|
|||
<div
|
||||
key={model.name}
|
||||
className=" border border-border-button rounded-lg p-3 hover:bg-bg-input transition-colors group"
|
||||
onClick={() => handleAddModel(model.name)}
|
||||
>
|
||||
<div className="flex items-center space-x-3 mb-3">
|
||||
<LlmIcon name={model.name} imgClass="h-8 w-8 text-text-primary" />
|
||||
<div className="flex-1">
|
||||
<h3 className="font-medium truncate">{model.name}</h3>
|
||||
</div>
|
||||
<Button
|
||||
className=" px-2 items-center gap-0 text-xs h-6 rounded-md transition-colors hidden group-hover:flex"
|
||||
onClick={() => handleAddModel(model.name)}
|
||||
>
|
||||
<Button className=" px-2 items-center gap-0 text-xs h-6 rounded-md transition-colors hidden group-hover:flex">
|
||||
<Plus size={12} />
|
||||
{t('addTheModel')}
|
||||
</Button>
|
||||
|
|
|
|||
|
|
@ -17,9 +17,11 @@ import { useEffect } from 'react';
|
|||
import { useHandleMenuClick } from './hooks';
|
||||
|
||||
const menuItems = [
|
||||
{ icon: User, label: t('setting.profile'), key: Routes.Profile },
|
||||
{ icon: Users, label: t('setting.team'), key: Routes.Team },
|
||||
{ icon: Server, label: t('setting.dataSources'), key: Routes.DataSource },
|
||||
{ icon: Box, label: t('setting.model'), key: Routes.Model },
|
||||
{ icon: Banknote, label: 'MCP', key: Routes.Mcp },
|
||||
{ icon: Users, label: t('setting.team'), key: Routes.Team },
|
||||
{ icon: User, label: t('setting.profile'), key: Routes.Profile },
|
||||
{ icon: Unplug, label: t('setting.api'), key: Routes.Api },
|
||||
// {
|
||||
// icon: MessageSquareQuote,
|
||||
|
|
@ -27,10 +29,8 @@ const menuItems = [
|
|||
// key: Routes.Profile,
|
||||
// },
|
||||
// { icon: TextSearch, label: 'Retrieval Templates', key: Routes.Profile },
|
||||
{ icon: Server, label: t('setting.dataSources'), key: Routes.DataSource },
|
||||
// { icon: Cog, label: t('setting.system'), key: Routes.System },
|
||||
// { icon: Banknote, label: 'Plan', key: Routes.Plan },
|
||||
{ icon: Banknote, label: 'MCP', key: Routes.Mcp },
|
||||
];
|
||||
|
||||
export function SideBar() {
|
||||
|
|
|
|||
|
|
@ -367,7 +367,7 @@ const routes = [
|
|||
component: '@/pages/user-setting',
|
||||
layout: false,
|
||||
routes: [
|
||||
{ path: '/user-setting', redirect: '/user-setting/profile' },
|
||||
{ path: '/user-setting', redirect: `/user-setting${Routes.DataSource}` },
|
||||
{
|
||||
path: '/user-setting/profile',
|
||||
// component: '@/pages/user-setting/setting-profile',
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue