mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-01-04 03:25:30 +08:00
Compare commits
30 Commits
d874683ae4
...
v0.20.2
| Author | SHA1 | Date | |
|---|---|---|---|
| e6cb74b27f | |||
| 00f54c207e | |||
| d0dc56166c | |||
| e15e39f183 | |||
| 33f3e05b75 | |||
| b8bfbac2e5 | |||
| d5729e598f | |||
| f2c5ad170d | |||
| 0aa3c4cdae | |||
| f123587538 | |||
| a41a646909 | |||
| 787e0c6786 | |||
| 05ee1be1e9 | |||
| a0d630365c | |||
| b5b8032a56 | |||
| ccb9f0b0d7 | |||
| a0ab619aeb | |||
| 32349481ef | |||
| 2b9ed935f3 | |||
| 188c0f614b | |||
| dad97869b6 | |||
| 57c8a37285 | |||
| 9d0fed601d | |||
| fe32952825 | |||
| 5808aef28c | |||
| ca720bd811 | |||
| ba11312766 | |||
| c8bbf7452d | |||
| b08650bc4c | |||
| fb77f9917b |
@ -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:v0.20.1">
|
||||
<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:v0.20.2">
|
||||
</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">
|
||||
@ -190,7 +190,7 @@ releases! 🌟
|
||||
> All Docker images are built for x86 platforms. We don't currently offer Docker images for ARM64.
|
||||
> If you are on an ARM64 platform, follow [this guide](https://ragflow.io/docs/dev/build_docker_image) to build a Docker image compatible with your system.
|
||||
|
||||
> The command below downloads the `v0.20.1-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.1-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:v0.20.1` for the full edition `v0.20.1`.
|
||||
> The command below downloads the `v0.20.2-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.2-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2` for the full edition `v0.20.2`.
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
@ -203,8 +203,8 @@ releases! 🌟
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
|
||||
|-------------------|-----------------|-----------------------|--------------------------|
|
||||
| v0.20.1 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.1-slim | ≈2 | ❌ | Stable release |
|
||||
| v0.20.2 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.2-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈9 | :heavy_check_mark: | _Unstable_ nightly build |
|
||||
| nightly-slim | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
|
||||
|
||||
@ -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:v0.20.1">
|
||||
<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:v0.20.2">
|
||||
</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">
|
||||
@ -181,7 +181,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
|
||||
> Semua gambar Docker dibangun untuk platform x86. Saat ini, kami tidak menawarkan gambar Docker untuk ARM64.
|
||||
> Jika Anda menggunakan platform ARM64, [silakan gunakan panduan ini untuk membangun gambar Docker yang kompatibel dengan sistem Anda](https://ragflow.io/docs/dev/build_docker_image).
|
||||
|
||||
> Perintah di bawah ini mengunduh edisi v0.20.1-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.1-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1 untuk edisi lengkap v0.20.1.
|
||||
> Perintah di bawah ini mengunduh edisi v0.20.2-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.2-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2 untuk edisi lengkap v0.20.2.
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
@ -194,8 +194,8 @@ $ docker compose -f docker-compose.yml up -d
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
|
||||
| ----------------- | --------------- | --------------------- | ------------------------ |
|
||||
| v0.20.1 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.1-slim | ≈2 | ❌ | Stable release |
|
||||
| v0.20.2 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.2-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈9 | :heavy_check_mark: | _Unstable_ nightly build |
|
||||
| nightly-slim | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
|
||||
|
||||
@ -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:v0.20.1">
|
||||
<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:v0.20.2">
|
||||
</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">
|
||||
@ -160,7 +160,7 @@
|
||||
> 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 v0.20.1-slim 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。v0.20.1-slim 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。例えば、完全版 v0.20.1 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1 と設定します。
|
||||
> 以下のコマンドは、RAGFlow Docker イメージの v0.20.2-slim 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。v0.20.2-slim 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。例えば、完全版 v0.20.2 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2 と設定します。
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
@ -173,8 +173,8 @@
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
|
||||
| ----------------- | --------------- | --------------------- | ------------------------ |
|
||||
| v0.20.1 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.1-slim | ≈2 | ❌ | Stable release |
|
||||
| v0.20.2 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.2-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈9 | :heavy_check_mark: | _Unstable_ nightly build |
|
||||
| nightly-slim | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
|
||||
|
||||
@ -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:v0.20.1">
|
||||
<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:v0.20.2">
|
||||
</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">
|
||||
@ -160,7 +160,7 @@
|
||||
> 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 v0.20.1-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.20.1-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.20.1을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1로 설정합니다.
|
||||
> 아래 명령어는 RAGFlow Docker 이미지의 v0.20.2-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.20.2-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.20.2을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2로 설정합니다.
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
@ -173,8 +173,8 @@
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
|
||||
| ----------------- | --------------- | --------------------- | ------------------------ |
|
||||
| v0.20.1 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.1-slim | ≈2 | ❌ | Stable release |
|
||||
| v0.20.2 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.2-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈9 | :heavy_check_mark: | _Unstable_ nightly build |
|
||||
| nightly-slim | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
|
||||
|
||||
@ -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:v0.20.1">
|
||||
<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:v0.20.2">
|
||||
</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">
|
||||
@ -180,7 +180,7 @@ 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 `v0.20.1-slim` 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 `v0.20.1-slim`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor. Por exemplo: defina `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` para a edição completa `v0.20.1`.
|
||||
> O comando abaixo baixa a edição `v0.20.2-slim` 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 `v0.20.2-slim`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor. Por exemplo: defina `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2` para a edição completa `v0.20.2`.
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
@ -193,8 +193,8 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
|
||||
|
||||
| Tag da imagem RAGFlow | Tamanho da imagem (GB) | Possui modelos de incorporação? | Estável? |
|
||||
| --------------------- | ---------------------- | ------------------------------- | ------------------------ |
|
||||
| v0.20.1 | ~9 | :heavy_check_mark: | Lançamento estável |
|
||||
| v0.20.1-slim | ~2 | ❌ | Lançamento estável |
|
||||
| v0.20.2 | ~9 | :heavy_check_mark: | Lançamento estável |
|
||||
| v0.20.2-slim | ~2 | ❌ | Lançamento estável |
|
||||
| nightly | ~9 | :heavy_check_mark: | _Instável_ build noturno |
|
||||
| nightly-slim | ~2 | ❌ | _Instável_ build noturno |
|
||||
|
||||
|
||||
@ -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:v0.20.1">
|
||||
<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:v0.20.2">
|
||||
</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">
|
||||
@ -183,7 +183,7 @@
|
||||
> 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 `v0.20.1-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.20.1-slim` 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。例如，你可以透過設定 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` 來下載 RAGFlow 鏡像的 `v0.20.1` 完整發行版。
|
||||
> 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.20.2-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.20.2-slim` 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。例如，你可以透過設定 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2` 來下載 RAGFlow 鏡像的 `v0.20.2` 完整發行版。
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
@ -196,8 +196,8 @@
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
|
||||
| ----------------- | --------------- | --------------------- | ------------------------ |
|
||||
| v0.20.1 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.1-slim | ≈2 | ❌ | Stable release |
|
||||
| v0.20.2 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.2-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈9 | :heavy_check_mark: | _Unstable_ nightly build |
|
||||
| nightly-slim | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
|
||||
|
||||
@ -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:v0.20.1">
|
||||
<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:v0.20.2">
|
||||
</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">
|
||||
@ -183,7 +183,7 @@
|
||||
> 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 `v0.20.1-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.20.1-slim` 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。比如，你可以通过设置 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` 来下载 RAGFlow 镜像的 `v0.20.1` 完整发行版。
|
||||
> 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.20.2-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.20.2-slim` 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。比如，你可以通过设置 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2` 来下载 RAGFlow 镜像的 `v0.20.2` 完整发行版。
|
||||
|
||||
```bash
|
||||
$ cd ragflow/docker
|
||||
@ -196,8 +196,8 @@
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models? | Stable? |
|
||||
| ----------------- | --------------- | --------------------- | ------------------------ |
|
||||
| v0.20.1 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.1-slim | ≈2 | ❌ | Stable release |
|
||||
| v0.20.2 | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| v0.20.2-slim | ≈2 | ❌ | Stable release |
|
||||
| nightly | ≈9 | :heavy_check_mark: | _Unstable_ nightly build |
|
||||
| nightly-slim | ≈2 | ❌ | _Unstable_ nightly build |
|
||||
|
||||
|
||||
@ -484,7 +484,7 @@ class Canvas:
|
||||
threads.append(exe.submit(FileService.parse, file["name"], FileService.get_blob(file["created_by"], file["id"]), True, file["created_by"]))
|
||||
return [th.result() for th in threads]
|
||||
|
||||
def tool_use_callback(self, agent_id: str, func_name: str, params: dict, result: Any):
|
||||
def tool_use_callback(self, agent_id: str, func_name: str, params: dict, result: Any, elapsed_time=None):
|
||||
agent_ids = agent_id.split("-->")
|
||||
agent_name = self.get_component_name(agent_ids[0])
|
||||
path = agent_name if len(agent_ids) < 2 else agent_name+"-->"+"-->".join(agent_ids[1:])
|
||||
@ -493,16 +493,16 @@ class Canvas:
|
||||
if bin:
|
||||
obj = json.loads(bin.encode("utf-8"))
|
||||
if obj[-1]["component_id"] == agent_ids[0]:
|
||||
obj[-1]["trace"].append({"path": path, "tool_name": func_name, "arguments": params, "result": result})
|
||||
obj[-1]["trace"].append({"path": path, "tool_name": func_name, "arguments": params, "result": result, "elapsed_time": elapsed_time})
|
||||
else:
|
||||
obj.append({
|
||||
"component_id": agent_ids[0],
|
||||
"trace": [{"path": path, "tool_name": func_name, "arguments": params, "result": result}]
|
||||
"trace": [{"path": path, "tool_name": func_name, "arguments": params, "result": result, "elapsed_time": elapsed_time}]
|
||||
})
|
||||
else:
|
||||
obj = [{
|
||||
"component_id": agent_ids[0],
|
||||
"trace": [{"path": path, "tool_name": func_name, "arguments": params, "result": result}]
|
||||
"trace": [{"path": path, "tool_name": func_name, "arguments": params, "result": result, "elapsed_time": elapsed_time}]
|
||||
}]
|
||||
REDIS_CONN.set_obj(f"{self.task_id}-{self.message_id}-logs", obj, 60*10)
|
||||
except Exception as e:
|
||||
|
||||
@ -22,7 +22,7 @@ from functools import partial
|
||||
from typing import Any
|
||||
|
||||
import json_repair
|
||||
|
||||
from timeit import default_timer as timer
|
||||
from agent.tools.base import LLMToolPluginCallSession, ToolParamBase, ToolBase, ToolMeta
|
||||
from api.db.services.llm_service import LLMBundle
|
||||
from api.db.services.tenant_llm_service import TenantLLMService
|
||||
@ -215,8 +215,9 @@ class Agent(LLM, ToolBase):
|
||||
hist = deepcopy(history)
|
||||
last_calling = ""
|
||||
if len(hist) > 3:
|
||||
st = timer()
|
||||
user_request = full_question(messages=history, chat_mdl=self.chat_mdl)
|
||||
self.callback("Multi-turn conversation optimization", {}, user_request)
|
||||
self.callback("Multi-turn conversation optimization", {}, user_request, elapsed_time=timer()-st)
|
||||
else:
|
||||
user_request = history[-1]["content"]
|
||||
|
||||
@ -263,12 +264,13 @@ class Agent(LLM, ToolBase):
|
||||
if not need2cite or cited:
|
||||
return
|
||||
|
||||
st = timer()
|
||||
txt = ""
|
||||
for delta_ans in self._gen_citations(entire_txt):
|
||||
yield delta_ans, 0
|
||||
txt += delta_ans
|
||||
|
||||
self.callback("gen_citations", {}, txt)
|
||||
self.callback("gen_citations", {}, txt, elapsed_time=timer()-st)
|
||||
|
||||
def append_user_content(hist, content):
|
||||
if hist[-1]["role"] == "user":
|
||||
@ -276,8 +278,9 @@ class Agent(LLM, ToolBase):
|
||||
else:
|
||||
hist.append({"role": "user", "content": content})
|
||||
|
||||
st = timer()
|
||||
task_desc = analyze_task(self.chat_mdl, prompt, user_request, tool_metas)
|
||||
self.callback("analyze_task", {}, task_desc)
|
||||
self.callback("analyze_task", {}, task_desc, elapsed_time=timer()-st)
|
||||
for _ in range(self._param.max_rounds + 1):
|
||||
response, tk = next_step(self.chat_mdl, hist, tool_metas, task_desc)
|
||||
# self.callback("next_step", {}, str(response)[:256]+"...")
|
||||
@ -303,9 +306,10 @@ class Agent(LLM, ToolBase):
|
||||
|
||||
thr.append(executor.submit(use_tool, name, args))
|
||||
|
||||
st = timer()
|
||||
reflection = reflect(self.chat_mdl, hist, [th.result() for th in thr])
|
||||
append_user_content(hist, reflection)
|
||||
self.callback("reflection", {}, str(reflection))
|
||||
self.callback("reflection", {}, str(reflection), elapsed_time=timer()-st)
|
||||
|
||||
except Exception as e:
|
||||
logging.exception(msg=f"Wrong JSON argument format in LLM ReAct response: {e}")
|
||||
|
||||
@ -479,7 +479,7 @@ class ComponentBase(ABC):
|
||||
|
||||
def get_input_elements_from_text(self, txt: str) -> dict[str, dict[str, str]]:
|
||||
res = {}
|
||||
for r in re.finditer(self.variable_ref_patt, txt, flags=re.IGNORECASE):
|
||||
for r in re.finditer(self.variable_ref_patt, txt, flags=re.IGNORECASE|re.DOTALL):
|
||||
exp = r.group(1)
|
||||
cpn_id, var_nm = exp.split("@") if exp.find("@")>0 else ("", exp)
|
||||
res[exp] = {
|
||||
|
||||
@ -54,6 +54,8 @@ class Message(ComponentBase):
|
||||
if k in kwargs:
|
||||
continue
|
||||
v = v["value"]
|
||||
if not v:
|
||||
v = ""
|
||||
ans = ""
|
||||
if isinstance(v, partial):
|
||||
for t in v():
|
||||
@ -94,6 +96,8 @@ class Message(ComponentBase):
|
||||
continue
|
||||
|
||||
v = self._canvas.get_variable_value(exp)
|
||||
if not v:
|
||||
v = ""
|
||||
if isinstance(v, partial):
|
||||
cnt = ""
|
||||
for t in v():
|
||||
|
||||
@ -24,6 +24,7 @@ from api.utils import hash_str2int
|
||||
from rag.llm.chat_model import ToolCallSession
|
||||
from rag.prompts.prompts import kb_prompt
|
||||
from rag.utils.mcp_tool_call_conn import MCPToolCallSession
|
||||
from timeit import default_timer as timer
|
||||
|
||||
|
||||
class ToolParameter(TypedDict):
|
||||
@ -49,12 +50,13 @@ class LLMToolPluginCallSession(ToolCallSession):
|
||||
|
||||
def tool_call(self, name: str, arguments: dict[str, Any]) -> Any:
|
||||
assert name in self.tools_map, f"LLM tool {name} does not exist"
|
||||
st = timer()
|
||||
if isinstance(self.tools_map[name], MCPToolCallSession):
|
||||
resp = self.tools_map[name].tool_call(name, arguments, 60)
|
||||
else:
|
||||
resp = self.tools_map[name].invoke(**arguments)
|
||||
|
||||
self.callback(name, arguments, resp)
|
||||
self.callback(name, arguments, resp, elapsed_time=timer()-st)
|
||||
return resp
|
||||
|
||||
def get_tool_obj(self, name):
|
||||
|
||||
@ -67,9 +67,17 @@ class CodeExecParam(ToolParamBase):
|
||||
"description": """
|
||||
This tool has a sandbox that can execute code written in 'Python'/'Javascript'. It recieves a piece of code and return a Json string.
|
||||
Here's a code example for Python(`main` function MUST be included):
|
||||
def main(arg1: str, arg2: str) -> dict:
|
||||
def main() -> dict:
|
||||
\"\"\"
|
||||
Generate Fibonacci numbers within 100.
|
||||
\"\"\"
|
||||
def fibonacci_recursive(n):
|
||||
if n <= 1:
|
||||
return n
|
||||
else:
|
||||
return fibonacci_recursive(n-1) + fibonacci_recursive(n-2)
|
||||
return {
|
||||
"result": arg1 + arg2,
|
||||
"result": fibonacci_recursive(100),
|
||||
}
|
||||
|
||||
Here's a code example for Javascript(`main` function MUST be included and exported):
|
||||
|
||||
@ -79,6 +79,17 @@ class ExeSQL(ToolBase, ABC):
|
||||
|
||||
@timeout(os.environ.get("COMPONENT_EXEC_TIMEOUT", 60))
|
||||
def _invoke(self, **kwargs):
|
||||
|
||||
def convert_decimals(obj):
|
||||
from decimal import Decimal
|
||||
if isinstance(obj, Decimal):
|
||||
return float(obj) # 或 str(obj)
|
||||
elif isinstance(obj, dict):
|
||||
return {k: convert_decimals(v) for k, v in obj.items()}
|
||||
elif isinstance(obj, list):
|
||||
return [convert_decimals(item) for item in obj]
|
||||
return obj
|
||||
|
||||
sql = kwargs.get("sql")
|
||||
if not sql:
|
||||
raise Exception("SQL for `ExeSQL` MUST not be empty.")
|
||||
@ -122,7 +133,11 @@ class ExeSQL(ToolBase, ABC):
|
||||
single_res = pd.DataFrame([i for i in cursor.fetchmany(self._param.max_records)])
|
||||
single_res.columns = [i[0] for i in cursor.description]
|
||||
|
||||
sql_res.append(single_res.to_dict(orient='records'))
|
||||
for col in single_res.columns:
|
||||
if pd.api.types.is_datetime64_any_dtype(single_res[col]):
|
||||
single_res[col] = single_res[col].dt.strftime('%Y-%m-%d')
|
||||
|
||||
sql_res.append(convert_decimals(single_res.to_dict(orient='records')))
|
||||
formalized_content.append(single_res.to_markdown(index=False, floatfmt=".6f"))
|
||||
|
||||
self.set_output("json", sql_res)
|
||||
@ -130,4 +145,4 @@ class ExeSQL(ToolBase, ABC):
|
||||
return self.output("formalized_content")
|
||||
|
||||
def thoughts(self) -> str:
|
||||
return "Query sent—waiting for the data."
|
||||
return "Query sent—waiting for the data."
|
||||
|
||||
@ -86,10 +86,16 @@ class Retrieval(ToolBase, ABC):
|
||||
kb_ids.append(id)
|
||||
continue
|
||||
kb_nm = self._canvas.get_variable_value(id)
|
||||
e, kb = KnowledgebaseService.get_by_name(kb_nm, self._canvas._tenant_id)
|
||||
if not e:
|
||||
raise Exception(f"Dataset({kb_nm}) does not exist.")
|
||||
kb_ids.append(kb.id)
|
||||
# if kb_nm is a list
|
||||
kb_nm_list = kb_nm if isinstance(kb_nm, list) else [kb_nm]
|
||||
for nm_or_id in kb_nm_list:
|
||||
e, kb = KnowledgebaseService.get_by_name(nm_or_id,
|
||||
self._canvas._tenant_id)
|
||||
if not e:
|
||||
e, kb = KnowledgebaseService.get_by_id(nm_or_id)
|
||||
if not e:
|
||||
raise Exception(f"Dataset({nm_or_id}) does not exist.")
|
||||
kb_ids.append(kb.id)
|
||||
|
||||
filtered_kb_ids: list[str] = list(set([kb_id for kb_id in kb_ids if kb_id]))
|
||||
|
||||
|
||||
@ -74,11 +74,11 @@ def rm():
|
||||
@login_required
|
||||
def save():
|
||||
req = request.json
|
||||
req["user_id"] = current_user.id
|
||||
if not isinstance(req["dsl"], str):
|
||||
req["dsl"] = json.dumps(req["dsl"], ensure_ascii=False)
|
||||
req["dsl"] = json.loads(req["dsl"])
|
||||
if "id" not in req:
|
||||
req["user_id"] = current_user.id
|
||||
if UserCanvasService.query(user_id=current_user.id, title=req["title"].strip()):
|
||||
return get_data_error_result(message=f"{req['title'].strip()} already exists.")
|
||||
req["id"] = get_uuid()
|
||||
@ -115,6 +115,12 @@ def getsse(canvas_id):
|
||||
if not objs:
|
||||
return get_data_error_result(message='Authentication error: API key is invalid!"')
|
||||
tenant_id = objs[0].tenant_id
|
||||
if not UserCanvasService.query(user_id=tenant_id, id=canvas_id):
|
||||
return get_json_result(
|
||||
data=False,
|
||||
message='Only owner of canvas authorized for this operation.',
|
||||
code=RetCode.OPERATING_ERROR
|
||||
)
|
||||
e, c = UserCanvasService.get_by_id(canvas_id)
|
||||
if not e or c.user_id != tenant_id:
|
||||
return get_data_error_result(message="canvas not found.")
|
||||
|
||||
@ -23,15 +23,18 @@ from flask_login import current_user, login_required
|
||||
|
||||
from api import settings
|
||||
from api.db import LLMType, ParserType
|
||||
from api.db.services.dialog_service import meta_filter
|
||||
from api.db.services.document_service import DocumentService
|
||||
from api.db.services.knowledgebase_service import KnowledgebaseService
|
||||
from api.db.services.llm_service import LLMBundle
|
||||
from api.db.services.search_service import SearchService
|
||||
from api.db.services.user_service import UserTenantService
|
||||
from api.utils.api_utils import get_data_error_result, get_json_result, server_error_response, validate_request
|
||||
from rag.app.qa import beAdoc, rmPrefix
|
||||
from rag.app.tag import label_question
|
||||
from rag.nlp import rag_tokenizer, search
|
||||
from rag.prompts import cross_languages, keyword_extraction
|
||||
from rag.prompts.prompts import gen_meta_filter
|
||||
from rag.settings import PAGERANK_FLD
|
||||
from rag.utils import rmSpace
|
||||
|
||||
@ -288,13 +291,26 @@ def retrieval_test():
|
||||
if isinstance(kb_ids, str):
|
||||
kb_ids = [kb_ids]
|
||||
doc_ids = req.get("doc_ids", [])
|
||||
similarity_threshold = float(req.get("similarity_threshold", 0.0))
|
||||
vector_similarity_weight = float(req.get("vector_similarity_weight", 0.3))
|
||||
use_kg = req.get("use_kg", False)
|
||||
top = int(req.get("top_k", 1024))
|
||||
langs = req.get("cross_languages", [])
|
||||
tenant_ids = []
|
||||
|
||||
if req.get("search_id", ""):
|
||||
search_config = SearchService.get_detail(req.get("search_id", "")).get("search_config", {})
|
||||
meta_data_filter = search_config.get("meta_data_filter", {})
|
||||
metas = DocumentService.get_meta_by_kbs(kb_ids)
|
||||
if meta_data_filter.get("method") == "auto":
|
||||
chat_mdl = LLMBundle(current_user.id, LLMType.CHAT, llm_name=search_config.get("chat_id", ""))
|
||||
filters = gen_meta_filter(chat_mdl, metas, question)
|
||||
doc_ids.extend(meta_filter(metas, filters))
|
||||
if not doc_ids:
|
||||
doc_ids = None
|
||||
elif meta_data_filter.get("method") == "manual":
|
||||
doc_ids.extend(meta_filter(metas, meta_data_filter["manual"]))
|
||||
if not doc_ids:
|
||||
doc_ids = None
|
||||
|
||||
try:
|
||||
tenants = UserTenantService.query(user_id=current_user.id)
|
||||
for kb_id in kb_ids:
|
||||
@ -327,7 +343,9 @@ def retrieval_test():
|
||||
|
||||
labels = label_question(question, [kb])
|
||||
ranks = settings.retrievaler.retrieval(question, embd_mdl, tenant_ids, kb_ids, page, size,
|
||||
similarity_threshold, vector_similarity_weight, top,
|
||||
float(req.get("similarity_threshold", 0.0)),
|
||||
float(req.get("vector_similarity_weight", 0.3)),
|
||||
top,
|
||||
doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"),
|
||||
rank_feature=labels
|
||||
)
|
||||
|
||||
@ -17,23 +17,19 @@ import json
|
||||
import re
|
||||
import traceback
|
||||
from copy import deepcopy
|
||||
|
||||
import trio
|
||||
from flask import Response, request
|
||||
from flask_login import current_user, login_required
|
||||
|
||||
from api import settings
|
||||
from api.db import LLMType
|
||||
from api.db.db_models import APIToken
|
||||
from api.db.services.conversation_service import ConversationService, structure_answer
|
||||
from api.db.services.dialog_service import DialogService, ask, chat
|
||||
from api.db.services.knowledgebase_service import KnowledgebaseService
|
||||
from api.db.services.dialog_service import DialogService, ask, chat, gen_mindmap
|
||||
from api.db.services.llm_service import LLMBundle
|
||||
from api.db.services.search_service import SearchService
|
||||
from api.db.services.tenant_llm_service import TenantLLMService
|
||||
from api.db.services.user_service import TenantService, UserTenantService
|
||||
from api.utils.api_utils import get_data_error_result, get_json_result, server_error_response, validate_request
|
||||
from graphrag.general.mind_map_extractor import MindMapExtractor
|
||||
from rag.app.tag import label_question
|
||||
from rag.prompts.prompt_template import load_prompt
|
||||
from rag.prompts.prompts import chunks_format
|
||||
|
||||
|
||||
@ -343,10 +339,18 @@ def ask_about():
|
||||
req = request.json
|
||||
uid = current_user.id
|
||||
|
||||
search_id = req.get("search_id", "")
|
||||
search_app = None
|
||||
search_config = {}
|
||||
if search_id:
|
||||
search_app = SearchService.get_detail(search_id)
|
||||
if search_app:
|
||||
search_config = search_app.get("search_config", {})
|
||||
|
||||
def stream():
|
||||
nonlocal req, uid
|
||||
try:
|
||||
for ans in ask(req["question"], req["kb_ids"], uid):
|
||||
for ans in ask(req["question"], req["kb_ids"], uid, search_config=search_config):
|
||||
yield "data:" + json.dumps({"code": 0, "message": "", "data": ans}, ensure_ascii=False) + "\n\n"
|
||||
except Exception as e:
|
||||
yield "data:" + json.dumps({"code": 500, "message": str(e), "data": {"answer": "**ERROR**: " + str(e), "reference": []}}, ensure_ascii=False) + "\n\n"
|
||||
@ -365,18 +369,14 @@ def ask_about():
|
||||
@validate_request("question", "kb_ids")
|
||||
def mindmap():
|
||||
req = request.json
|
||||
kb_ids = req["kb_ids"]
|
||||
e, kb = KnowledgebaseService.get_by_id(kb_ids[0])
|
||||
if not e:
|
||||
return get_data_error_result(message="Knowledgebase not found!")
|
||||
search_id = req.get("search_id", "")
|
||||
search_app = SearchService.get_detail(search_id) if search_id else {}
|
||||
search_config = search_app.get("search_config", {}) if search_app else {}
|
||||
kb_ids = search_config.get("kb_ids", [])
|
||||
kb_ids.extend(req["kb_ids"])
|
||||
kb_ids = list(set(kb_ids))
|
||||
|
||||
embd_mdl = LLMBundle(kb.tenant_id, LLMType.EMBEDDING, llm_name=kb.embd_id)
|
||||
chat_mdl = LLMBundle(current_user.id, LLMType.CHAT)
|
||||
question = req["question"]
|
||||
ranks = settings.retrievaler.retrieval(question, embd_mdl, kb.tenant_id, kb_ids, 1, 12, 0.3, 0.3, aggs=False, rank_feature=label_question(question, [kb]))
|
||||
mindmap = MindMapExtractor(chat_mdl)
|
||||
mind_map = trio.run(mindmap, [c["content_with_weight"] for c in ranks["chunks"]])
|
||||
mind_map = mind_map.output
|
||||
mind_map = gen_mindmap(req["question"], kb_ids, search_app.get("tenant_id", current_user.id), search_config)
|
||||
if "error" in mind_map:
|
||||
return server_error_response(Exception(mind_map["error"]))
|
||||
return get_json_result(data=mind_map)
|
||||
@ -387,41 +387,20 @@ def mindmap():
|
||||
@validate_request("question")
|
||||
def related_questions():
|
||||
req = request.json
|
||||
|
||||
search_id = req.get("search_id", "")
|
||||
search_config = {}
|
||||
if search_id:
|
||||
if search_app := SearchService.get_detail(search_id):
|
||||
search_config = search_app.get("search_config", {})
|
||||
|
||||
question = req["question"]
|
||||
chat_mdl = LLMBundle(current_user.id, LLMType.CHAT)
|
||||
prompt = """
|
||||
Role: You are an AI language model assistant tasked with generating 5-10 related questions based on a user’s original query. These questions should help expand the search query scope and improve search relevance.
|
||||
|
||||
Instructions:
|
||||
Input: You are provided with a user’s question.
|
||||
Output: Generate 5-10 alternative questions that are related to the original user question. These alternatives should help retrieve a broader range of relevant documents from a vector database.
|
||||
Context: Focus on rephrasing the original question in different ways, making sure the alternative questions are diverse but still connected to the topic of the original query. Do not create overly obscure, irrelevant, or unrelated questions.
|
||||
Fallback: If you cannot generate any relevant alternatives, do not return any questions.
|
||||
Guidance:
|
||||
1. Each alternative should be unique but still relevant to the original query.
|
||||
2. Keep the phrasing clear, concise, and easy to understand.
|
||||
3. Avoid overly technical jargon or specialized terms unless directly relevant.
|
||||
4. Ensure that each question contributes towards improving search results by broadening the search angle, not narrowing it.
|
||||
chat_id = search_config.get("chat_id", "")
|
||||
chat_mdl = LLMBundle(current_user.id, LLMType.CHAT, chat_id)
|
||||
|
||||
Example:
|
||||
Original Question: What are the benefits of electric vehicles?
|
||||
|
||||
Alternative Questions:
|
||||
1. How do electric vehicles impact the environment?
|
||||
2. What are the advantages of owning an electric car?
|
||||
3. What is the cost-effectiveness of electric vehicles?
|
||||
4. How do electric vehicles compare to traditional cars in terms of fuel efficiency?
|
||||
5. What are the environmental benefits of switching to electric cars?
|
||||
6. How do electric vehicles help reduce carbon emissions?
|
||||
7. Why are electric vehicles becoming more popular?
|
||||
8. What are the long-term savings of using electric vehicles?
|
||||
9. How do electric vehicles contribute to sustainability?
|
||||
10. What are the key benefits of electric vehicles for consumers?
|
||||
|
||||
Reason:
|
||||
Rephrasing the original query into multiple alternative questions helps the user explore different aspects of their search topic, improving the quality of search results.
|
||||
These questions guide the search engine to provide a more comprehensive set of relevant documents.
|
||||
"""
|
||||
gen_conf = search_config.get("llm_setting", {"temperature": 0.9})
|
||||
prompt = load_prompt("related_question")
|
||||
ans = chat_mdl.chat(
|
||||
prompt,
|
||||
[
|
||||
@ -433,6 +412,6 @@ Related search terms:
|
||||
""",
|
||||
}
|
||||
],
|
||||
{"temperature": 0.9},
|
||||
gen_conf,
|
||||
)
|
||||
return get_json_result(data=[re.sub(r"^[0-9]\. ", "", a) for a in ans.split("\n") if re.match(r"^[0-9]\. ", a)])
|
||||
|
||||
@ -16,6 +16,7 @@
|
||||
|
||||
from flask import request
|
||||
from flask_login import login_required, current_user
|
||||
from api.db.services import duplicate_name
|
||||
from api.db.services.dialog_service import DialogService
|
||||
from api.db import StatusEnum
|
||||
from api.db.services.tenant_llm_service import TenantLLMService
|
||||
@ -41,6 +42,15 @@ def set_dialog():
|
||||
return get_data_error_result(message="Dialog name can't be empty.")
|
||||
if len(name.encode("utf-8")) > 255:
|
||||
return get_data_error_result(message=f"Dialog name length is {len(name)} which is larger than 255")
|
||||
|
||||
if is_create and DialogService.query(tenant_id=current_user.id, name=name.strip()):
|
||||
name = name.strip()
|
||||
name = duplicate_name(
|
||||
DialogService.query,
|
||||
name=name,
|
||||
tenant_id=current_user.id,
|
||||
status=StatusEnum.VALID.value)
|
||||
|
||||
description = req.get("description", "A helpful dialog")
|
||||
icon = req.get("icon", "")
|
||||
top_n = req.get("top_n", 6)
|
||||
|
||||
@ -19,6 +19,7 @@ import time
|
||||
import tiktoken
|
||||
from flask import Response, jsonify, request
|
||||
from agent.canvas import Canvas
|
||||
from api import settings
|
||||
from api.db import LLMType, StatusEnum
|
||||
from api.db.db_models import APIToken
|
||||
from api.db.services.api_service import API4ConversationService
|
||||
@ -26,12 +27,17 @@ from api.db.services.canvas_service import UserCanvasService, completionOpenAI
|
||||
from api.db.services.canvas_service import completion as agent_completion
|
||||
from api.db.services.conversation_service import ConversationService, iframe_completion
|
||||
from api.db.services.conversation_service import completion as rag_completion
|
||||
from api.db.services.dialog_service import DialogService, ask, chat
|
||||
from api.db.services.dialog_service import DialogService, ask, chat, gen_mindmap
|
||||
from api.db.services.knowledgebase_service import KnowledgebaseService
|
||||
from api.db.services.llm_service import LLMBundle
|
||||
from api.db.services.search_service import SearchService
|
||||
from api.db.services.user_service import UserTenantService
|
||||
from api.utils import get_uuid
|
||||
from api.utils.api_utils import check_duplicate_ids, get_data_openai, get_error_data_result, get_result, token_required, validate_request
|
||||
from api.utils.api_utils import check_duplicate_ids, get_data_openai, get_error_data_result, get_json_result, get_result, server_error_response, token_required, validate_request
|
||||
from rag.app.tag import label_question
|
||||
from rag.prompts import chunks_format
|
||||
from rag.prompts.prompt_template import load_prompt
|
||||
from rag.prompts.prompts import cross_languages, keyword_extraction
|
||||
|
||||
|
||||
@manager.route("/chats/<chat_id>/sessions", methods=["POST"]) # noqa: F821
|
||||
@ -808,6 +814,29 @@ def chatbot_completions(dialog_id):
|
||||
return get_result(data=answer)
|
||||
|
||||
|
||||
@manager.route("/chatbots/<dialog_id>/info", methods=["GET"]) # noqa: F821
|
||||
def chatbots_inputs(dialog_id):
|
||||
token = request.headers.get("Authorization").split()
|
||||
if len(token) != 2:
|
||||
return get_error_data_result(message='Authorization is not valid!"')
|
||||
token = token[1]
|
||||
objs = APIToken.query(beta=token)
|
||||
if not objs:
|
||||
return get_error_data_result(message='Authentication error: API key is invalid!"')
|
||||
|
||||
e, dialog = DialogService.get_by_id(dialog_id)
|
||||
if not e:
|
||||
return get_error_data_result(f"Can't find dialog by ID: {dialog_id}")
|
||||
|
||||
return get_result(
|
||||
data={
|
||||
"title": dialog.name,
|
||||
"avatar": dialog.icon,
|
||||
"prologue": dialog.prompt_config.get("prologue", ""),
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@manager.route("/agentbots/<agent_id>/completions", methods=["POST"]) # noqa: F821
|
||||
def agent_bot_completions(agent_id):
|
||||
req = request.json
|
||||
@ -855,3 +884,225 @@ def begin_inputs(agent_id):
|
||||
"prologue": canvas.get_prologue()
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@manager.route("/searchbots/ask", methods=["POST"]) # noqa: F821
|
||||
@validate_request("question", "kb_ids")
|
||||
def ask_about_embedded():
|
||||
token = request.headers.get("Authorization").split()
|
||||
if len(token) != 2:
|
||||
return get_error_data_result(message='Authorization is not valid!"')
|
||||
token = token[1]
|
||||
objs = APIToken.query(beta=token)
|
||||
if not objs:
|
||||
return get_error_data_result(message='Authentication error: API key is invalid!"')
|
||||
|
||||
req = request.json
|
||||
uid = objs[0].tenant_id
|
||||
|
||||
search_id = req.get("search_id", "")
|
||||
search_config = {}
|
||||
if search_id:
|
||||
if search_app := SearchService.get_detail(search_id):
|
||||
search_config = search_app.get("search_config", {})
|
||||
|
||||
def stream():
|
||||
nonlocal req, uid
|
||||
try:
|
||||
for ans in ask(req["question"], req["kb_ids"], uid, search_config):
|
||||
yield "data:" + json.dumps({"code": 0, "message": "", "data": ans}, ensure_ascii=False) + "\n\n"
|
||||
except Exception as e:
|
||||
yield "data:" + json.dumps({"code": 500, "message": str(e), "data": {"answer": "**ERROR**: " + str(e), "reference": []}}, ensure_ascii=False) + "\n\n"
|
||||
yield "data:" + json.dumps({"code": 0, "message": "", "data": True}, ensure_ascii=False) + "\n\n"
|
||||
|
||||
resp = Response(stream(), mimetype="text/event-stream")
|
||||
resp.headers.add_header("Cache-control", "no-cache")
|
||||
resp.headers.add_header("Connection", "keep-alive")
|
||||
resp.headers.add_header("X-Accel-Buffering", "no")
|
||||
resp.headers.add_header("Content-Type", "text/event-stream; charset=utf-8")
|
||||
return resp
|
||||
|
||||
|
||||
@manager.route("/searchbots/retrieval_test", methods=['POST']) # noqa: F821
|
||||
@validate_request("kb_id", "question")
|
||||
def retrieval_test_embedded():
|
||||
token = request.headers.get("Authorization").split()
|
||||
if len(token) != 2:
|
||||
return get_error_data_result(message='Authorization is not valid!"')
|
||||
token = token[1]
|
||||
objs = APIToken.query(beta=token)
|
||||
if not objs:
|
||||
return get_error_data_result(message='Authentication error: API key is invalid!"')
|
||||
|
||||
req = request.json
|
||||
page = int(req.get("page", 1))
|
||||
size = int(req.get("size", 30))
|
||||
question = req["question"]
|
||||
kb_ids = req["kb_id"]
|
||||
if isinstance(kb_ids, str):
|
||||
kb_ids = [kb_ids]
|
||||
doc_ids = req.get("doc_ids", [])
|
||||
similarity_threshold = float(req.get("similarity_threshold", 0.0))
|
||||
vector_similarity_weight = float(req.get("vector_similarity_weight", 0.3))
|
||||
use_kg = req.get("use_kg", False)
|
||||
top = int(req.get("top_k", 1024))
|
||||
langs = req.get("cross_languages", [])
|
||||
tenant_ids = []
|
||||
|
||||
tenant_id = objs[0].tenant_id
|
||||
if not tenant_id:
|
||||
return get_error_data_result(message="permission denined.")
|
||||
|
||||
try:
|
||||
tenants = UserTenantService.query(user_id=tenant_id)
|
||||
for kb_id in kb_ids:
|
||||
for tenant in tenants:
|
||||
if KnowledgebaseService.query(
|
||||
tenant_id=tenant.tenant_id, id=kb_id):
|
||||
tenant_ids.append(tenant.tenant_id)
|
||||
break
|
||||
else:
|
||||
return get_json_result(
|
||||
data=False, message='Only owner of knowledgebase authorized for this operation.',
|
||||
code=settings.RetCode.OPERATING_ERROR)
|
||||
|
||||
e, kb = KnowledgebaseService.get_by_id(kb_ids[0])
|
||||
if not e:
|
||||
return get_error_data_result(message="Knowledgebase not found!")
|
||||
|
||||
if langs:
|
||||
question = cross_languages(kb.tenant_id, None, question, langs)
|
||||
|
||||
embd_mdl = LLMBundle(kb.tenant_id, LLMType.EMBEDDING.value, llm_name=kb.embd_id)
|
||||
|
||||
rerank_mdl = None
|
||||
if req.get("rerank_id"):
|
||||
rerank_mdl = LLMBundle(kb.tenant_id, LLMType.RERANK.value, llm_name=req["rerank_id"])
|
||||
|
||||
if req.get("keyword", False):
|
||||
chat_mdl = LLMBundle(kb.tenant_id, LLMType.CHAT)
|
||||
question += keyword_extraction(chat_mdl, question)
|
||||
|
||||
labels = label_question(question, [kb])
|
||||
ranks = settings.retrievaler.retrieval(question, embd_mdl, tenant_ids, kb_ids, page, size,
|
||||
similarity_threshold, vector_similarity_weight, top,
|
||||
doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"),
|
||||
rank_feature=labels
|
||||
)
|
||||
if use_kg:
|
||||
ck = settings.kg_retrievaler.retrieval(question,
|
||||
tenant_ids,
|
||||
kb_ids,
|
||||
embd_mdl,
|
||||
LLMBundle(kb.tenant_id, LLMType.CHAT))
|
||||
if ck["content_with_weight"]:
|
||||
ranks["chunks"].insert(0, ck)
|
||||
|
||||
for c in ranks["chunks"]:
|
||||
c.pop("vector", None)
|
||||
ranks["labels"] = labels
|
||||
|
||||
return get_json_result(data=ranks)
|
||||
except Exception as e:
|
||||
if str(e).find("not_found") > 0:
|
||||
return get_json_result(data=False, message='No chunk found! Check the chunk status please!',
|
||||
code=settings.RetCode.DATA_ERROR)
|
||||
return server_error_response(e)
|
||||
|
||||
|
||||
@manager.route("/searchbots/related_questions", methods=["POST"]) # noqa: F821
|
||||
@validate_request("question")
|
||||
def related_questions_embedded():
|
||||
token = request.headers.get("Authorization").split()
|
||||
if len(token) != 2:
|
||||
return get_error_data_result(message='Authorization is not valid!"')
|
||||
token = token[1]
|
||||
objs = APIToken.query(beta=token)
|
||||
if not objs:
|
||||
return get_error_data_result(message='Authentication error: API key is invalid!"')
|
||||
|
||||
req = request.json
|
||||
tenant_id = objs[0].tenant_id
|
||||
if not tenant_id:
|
||||
return get_error_data_result(message="permission denined.")
|
||||
|
||||
search_id = req.get("search_id", "")
|
||||
search_config = {}
|
||||
if search_id:
|
||||
if search_app := SearchService.get_detail(search_id):
|
||||
search_config = search_app.get("search_config", {})
|
||||
|
||||
question = req["question"]
|
||||
|
||||
chat_id = search_config.get("chat_id", "")
|
||||
chat_mdl = LLMBundle(tenant_id, LLMType.CHAT, chat_id)
|
||||
|
||||
gen_conf = search_config.get("llm_setting", {"temperature": 0.9})
|
||||
prompt = load_prompt("related_question")
|
||||
ans = chat_mdl.chat(
|
||||
prompt,
|
||||
[
|
||||
{
|
||||
"role": "user",
|
||||
"content": f"""
|
||||
Keywords: {question}
|
||||
Related search terms:
|
||||
""",
|
||||
}
|
||||
],
|
||||
gen_conf,
|
||||
)
|
||||
return get_json_result(data=[re.sub(r"^[0-9]\. ", "", a) for a in ans.split("\n") if re.match(r"^[0-9]\. ", a)])
|
||||
|
||||
|
||||
@manager.route("/searchbots/detail", methods=["GET"]) # noqa: F821
|
||||
def detail_share_embedded():
|
||||
token = request.headers.get("Authorization").split()
|
||||
if len(token) != 2:
|
||||
return get_error_data_result(message='Authorization is not valid!"')
|
||||
token = token[1]
|
||||
objs = APIToken.query(beta=token)
|
||||
if not objs:
|
||||
return get_error_data_result(message='Authentication error: API key is invalid!"')
|
||||
|
||||
search_id = request.args["search_id"]
|
||||
tenant_id = objs[0].tenant_id
|
||||
if not tenant_id:
|
||||
return get_error_data_result(message="permission denined.")
|
||||
try:
|
||||
tenants = UserTenantService.query(user_id=tenant_id)
|
||||
for tenant in tenants:
|
||||
if SearchService.query(tenant_id=tenant.tenant_id, id=search_id):
|
||||
break
|
||||
else:
|
||||
return get_json_result(data=False, message="Has no permission for this operation.", code=settings.RetCode.OPERATING_ERROR)
|
||||
|
||||
search = SearchService.get_detail(search_id)
|
||||
if not search:
|
||||
return get_error_data_result(message="Can't find this Search App!")
|
||||
return get_json_result(data=search)
|
||||
except Exception as e:
|
||||
return server_error_response(e)
|
||||
|
||||
|
||||
@manager.route("/searchbots/mindmap", methods=["POST"]) # noqa: F821
|
||||
@validate_request("question", "kb_ids")
|
||||
def mindmap():
|
||||
token = request.headers.get("Authorization").split()
|
||||
if len(token) != 2:
|
||||
return get_error_data_result(message='Authorization is not valid!"')
|
||||
token = token[1]
|
||||
objs = APIToken.query(beta=token)
|
||||
if not objs:
|
||||
return get_error_data_result(message='Authentication error: API key is invalid!"')
|
||||
|
||||
tenant_id = objs[0].tenant_id
|
||||
req = request.json
|
||||
|
||||
search_id = req.get("search_id", "")
|
||||
search_app = SearchService.get_detail(search_id) if search_id else {}
|
||||
|
||||
mind_map = gen_mindmap(req["question"], req["kb_ids"], tenant_id, search_app.get("search_config", {}))
|
||||
if "error" in mind_map:
|
||||
return server_error_response(Exception(mind_map["error"]))
|
||||
return get_json_result(data=mind_map)
|
||||
|
||||
@ -22,7 +22,6 @@ from api.constants import DATASET_NAME_LIMIT
|
||||
from api.db import StatusEnum
|
||||
from api.db.db_models import DB
|
||||
from api.db.services import duplicate_name
|
||||
from api.db.services.knowledgebase_service import KnowledgebaseService
|
||||
from api.db.services.search_service import SearchService
|
||||
from api.db.services.user_service import TenantService, UserTenantService
|
||||
from api.utils import get_uuid
|
||||
@ -47,7 +46,7 @@ def create():
|
||||
return get_data_error_result(message="Authorizationd identity.")
|
||||
|
||||
search_name = search_name.strip()
|
||||
search_name = duplicate_name(KnowledgebaseService.query, name=search_name, tenant_id=current_user.id, status=StatusEnum.VALID.value)
|
||||
search_name = duplicate_name(SearchService.query, name=search_name, tenant_id=current_user.id, status=StatusEnum.VALID.value)
|
||||
|
||||
req["id"] = get_uuid()
|
||||
req["name"] = search_name
|
||||
|
||||
@ -872,7 +872,7 @@ class Search(DataBaseModel):
|
||||
default={
|
||||
"kb_ids": [],
|
||||
"doc_ids": [],
|
||||
"similarity_threshold": 0.0,
|
||||
"similarity_threshold": 0.2,
|
||||
"vector_similarity_weight": 0.3,
|
||||
"use_kg": False,
|
||||
# rerank settings
|
||||
|
||||
@ -22,6 +22,7 @@ from datetime import datetime
|
||||
from functools import partial
|
||||
from timeit import default_timer as timer
|
||||
|
||||
import trio
|
||||
from langfuse import Langfuse
|
||||
from peewee import fn
|
||||
|
||||
@ -36,11 +37,12 @@ from api.db.services.langfuse_service import TenantLangfuseService
|
||||
from api.db.services.llm_service import LLMBundle
|
||||
from api.db.services.tenant_llm_service import TenantLLMService
|
||||
from api.utils import current_timestamp, datetime_format
|
||||
from graphrag.general.mind_map_extractor import MindMapExtractor
|
||||
from rag.app.resume import forbidden_select_fields4resume
|
||||
from rag.app.tag import label_question
|
||||
from rag.nlp.search import index_name
|
||||
from rag.prompts import chunks_format, citation_prompt, cross_languages, full_question, kb_prompt, keyword_extraction, message_fit_in
|
||||
from rag.prompts.prompts import gen_meta_filter
|
||||
from rag.prompts.prompts import gen_meta_filter, PROMPT_JINJA_ENV, ASK_SUMMARY
|
||||
from rag.utils import num_tokens_from_string, rmSpace
|
||||
from rag.utils.tavily_conn import Tavily
|
||||
|
||||
@ -687,7 +689,14 @@ def tts(tts_mdl, text):
|
||||
return binascii.hexlify(bin).decode("utf-8")
|
||||
|
||||
|
||||
def ask(question, kb_ids, tenant_id, chat_llm_name=None):
|
||||
def ask(question, kb_ids, tenant_id, chat_llm_name=None, search_config={}):
|
||||
doc_ids = search_config.get("doc_ids", [])
|
||||
rerank_mdl = None
|
||||
kb_ids = search_config.get("kb_ids", kb_ids)
|
||||
chat_llm_name = search_config.get("chat_id", chat_llm_name)
|
||||
rerank_id = search_config.get("rerank_id", "")
|
||||
meta_data_filter = search_config.get("meta_data_filter")
|
||||
|
||||
kbs = KnowledgebaseService.get_by_ids(kb_ids)
|
||||
embedding_list = list(set([kb.embd_id for kb in kbs]))
|
||||
|
||||
@ -696,30 +705,46 @@ def ask(question, kb_ids, tenant_id, chat_llm_name=None):
|
||||
|
||||
embd_mdl = LLMBundle(tenant_id, LLMType.EMBEDDING, embedding_list[0])
|
||||
chat_mdl = LLMBundle(tenant_id, LLMType.CHAT, chat_llm_name)
|
||||
if rerank_id:
|
||||
rerank_mdl = LLMBundle(tenant_id, LLMType.RERANK, rerank_id)
|
||||
max_tokens = chat_mdl.max_length
|
||||
tenant_ids = list(set([kb.tenant_id for kb in kbs]))
|
||||
kbinfos = retriever.retrieval(question, embd_mdl, tenant_ids, kb_ids, 1, 12, 0.1, 0.3, aggs=False, rank_feature=label_question(question, kbs))
|
||||
|
||||
if meta_data_filter:
|
||||
metas = DocumentService.get_meta_by_kbs(kb_ids)
|
||||
if meta_data_filter.get("method") == "auto":
|
||||
filters = gen_meta_filter(chat_mdl, metas, question)
|
||||
doc_ids.extend(meta_filter(metas, filters))
|
||||
if not doc_ids:
|
||||
doc_ids = None
|
||||
elif meta_data_filter.get("method") == "manual":
|
||||
doc_ids.extend(meta_filter(metas, meta_data_filter["manual"]))
|
||||
if not doc_ids:
|
||||
doc_ids = None
|
||||
|
||||
kbinfos = retriever.retrieval(
|
||||
question = question,
|
||||
embd_mdl=embd_mdl,
|
||||
tenant_ids=tenant_ids,
|
||||
kb_ids=kb_ids,
|
||||
page=1,
|
||||
page_size=12,
|
||||
similarity_threshold=search_config.get("similarity_threshold", 0.1),
|
||||
vector_similarity_weight=search_config.get("vector_similarity_weight", 0.3),
|
||||
top=search_config.get("top_k", 1024),
|
||||
doc_ids=doc_ids,
|
||||
aggs=False,
|
||||
rerank_mdl=rerank_mdl,
|
||||
rank_feature=label_question(question, kbs)
|
||||
)
|
||||
|
||||
knowledges = kb_prompt(kbinfos, max_tokens)
|
||||
prompt = """
|
||||
Role: You're a smart assistant. Your name is Miss R.
|
||||
Task: Summarize the information from knowledge bases and answer user's question.
|
||||
Requirements and restriction:
|
||||
- DO NOT make things up, especially for numbers.
|
||||
- If the information from knowledge is irrelevant with user's question, JUST SAY: Sorry, no relevant information provided.
|
||||
- Answer with markdown format text.
|
||||
- Answer in language of user's question.
|
||||
- DO NOT make things up, especially for numbers.
|
||||
sys_prompt = PROMPT_JINJA_ENV.from_string(ASK_SUMMARY).render(knowledge="\n".join(knowledges))
|
||||
|
||||
### Information from knowledge bases
|
||||
%s
|
||||
|
||||
The above is information from knowledge bases.
|
||||
|
||||
""" % "\n".join(knowledges)
|
||||
msg = [{"role": "user", "content": question}]
|
||||
|
||||
def decorate_answer(answer):
|
||||
nonlocal knowledges, kbinfos, prompt
|
||||
nonlocal knowledges, kbinfos, sys_prompt
|
||||
answer, idx = retriever.insert_citations(answer, [ck["content_ltks"] for ck in kbinfos["chunks"]], [ck["vector"] for ck in kbinfos["chunks"]], embd_mdl, tkweight=0.7, vtweight=0.3)
|
||||
idx = set([kbinfos["chunks"][int(i)]["doc_id"] for i in idx])
|
||||
recall_docs = [d for d in kbinfos["doc_aggs"] if d["doc_id"] in idx]
|
||||
@ -737,7 +762,55 @@ def ask(question, kb_ids, tenant_id, chat_llm_name=None):
|
||||
return {"answer": answer, "reference": refs}
|
||||
|
||||
answer = ""
|
||||
for ans in chat_mdl.chat_streamly(prompt, msg, {"temperature": 0.1}):
|
||||
for ans in chat_mdl.chat_streamly(sys_prompt, msg, {"temperature": 0.1}):
|
||||
answer = ans
|
||||
yield {"answer": answer, "reference": {}}
|
||||
yield decorate_answer(answer)
|
||||
|
||||
|
||||
def gen_mindmap(question, kb_ids, tenant_id, search_config={}):
|
||||
meta_data_filter = search_config.get("meta_data_filter", {})
|
||||
doc_ids = search_config.get("doc_ids", [])
|
||||
rerank_id = search_config.get("rerank_id", "")
|
||||
rerank_mdl = None
|
||||
kbs = KnowledgebaseService.get_by_ids(kb_ids)
|
||||
if not kbs:
|
||||
return {"error": "No KB selected"}
|
||||
embedding_list = list(set([kb.embd_id for kb in kbs]))
|
||||
tenant_ids = list(set([kb.tenant_id for kb in kbs]))
|
||||
|
||||
embd_mdl = LLMBundle(tenant_id, LLMType.EMBEDDING, llm_name=embedding_list[0])
|
||||
chat_mdl = LLMBundle(tenant_id, LLMType.CHAT, llm_name=search_config.get("chat_id", ""))
|
||||
if rerank_id:
|
||||
rerank_mdl = LLMBundle(tenant_id, LLMType.RERANK, rerank_id)
|
||||
|
||||
if meta_data_filter:
|
||||
metas = DocumentService.get_meta_by_kbs(kb_ids)
|
||||
if meta_data_filter.get("method") == "auto":
|
||||
filters = gen_meta_filter(chat_mdl, metas, question)
|
||||
doc_ids.extend(meta_filter(metas, filters))
|
||||
if not doc_ids:
|
||||
doc_ids = None
|
||||
elif meta_data_filter.get("method") == "manual":
|
||||
doc_ids.extend(meta_filter(metas, meta_data_filter["manual"]))
|
||||
if not doc_ids:
|
||||
doc_ids = None
|
||||
|
||||
ranks = settings.retrievaler.retrieval(
|
||||
question=question,
|
||||
embd_mdl=embd_mdl,
|
||||
tenant_ids=tenant_ids,
|
||||
kb_ids=kb_ids,
|
||||
page=1,
|
||||
page_size=12,
|
||||
similarity_threshold=search_config.get("similarity_threshold", 0.2),
|
||||
vector_similarity_weight=search_config.get("vector_similarity_weight", 0.3),
|
||||
top=search_config.get("top_k", 1024),
|
||||
doc_ids=doc_ids,
|
||||
aggs=False,
|
||||
rerank_mdl=rerank_mdl,
|
||||
rank_feature=label_question(question, kbs),
|
||||
)
|
||||
mindmap = MindMapExtractor(chat_mdl)
|
||||
mind_map = trio.run(mindmap, [c["content_with_weight"] for c in ranks["chunks"]])
|
||||
return mind_map.output
|
||||
@ -71,6 +71,8 @@ class SearchService(CommonService):
|
||||
.first()
|
||||
.to_dict()
|
||||
)
|
||||
if not search:
|
||||
return {}
|
||||
return search
|
||||
|
||||
@classmethod
|
||||
|
||||
@ -59,11 +59,14 @@ def update_progress():
|
||||
if redis_lock.acquire():
|
||||
DocumentService.update_progress()
|
||||
redis_lock.release()
|
||||
stop_event.wait(6)
|
||||
except Exception:
|
||||
logging.exception("update_progress exception")
|
||||
finally:
|
||||
redis_lock.release()
|
||||
try:
|
||||
redis_lock.release()
|
||||
except Exception:
|
||||
logging.exception("update_progress exception")
|
||||
stop_event.wait(6)
|
||||
|
||||
def signal_handler(sig, frame):
|
||||
logging.info("Received interrupt signal, shutting down...")
|
||||
|
||||
@ -505,6 +505,24 @@
|
||||
"tags": "RE-RANK,4k",
|
||||
"max_tokens": 4000,
|
||||
"model_type": "rerank"
|
||||
},
|
||||
{
|
||||
"llm_name": "qwen-audio-asr",
|
||||
"tags": "SPEECH2TEXT,8k",
|
||||
"max_tokens": 8000,
|
||||
"model_type": "speech2text"
|
||||
},
|
||||
{
|
||||
"llm_name": "qwen-audio-asr-latest",
|
||||
"tags": "SPEECH2TEXT,8k",
|
||||
"max_tokens": 8000,
|
||||
"model_type": "speech2text"
|
||||
},
|
||||
{
|
||||
"llm_name": "qwen-audio-asr-1204",
|
||||
"tags": "SPEECH2TEXT,8k",
|
||||
"max_tokens": 8000,
|
||||
"model_type": "speech2text"
|
||||
}
|
||||
]
|
||||
},
|
||||
@ -1146,60 +1164,35 @@
|
||||
"llm_name": "gemini-2.5-flash",
|
||||
"tags": "LLM,CHAT,1024K,IMAGE2TEXT",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "image2text",
|
||||
"model_type": "chat",
|
||||
"is_tools": true
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-2.5-pro",
|
||||
"tags": "LLM,CHAT,IMAGE2TEXT,1024K",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "image2text",
|
||||
"model_type": "chat",
|
||||
"is_tools": true
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-2.5-flash-preview-05-20",
|
||||
"llm_name": "gemini-2.5-flash-lite",
|
||||
"tags": "LLM,CHAT,1024K,IMAGE2TEXT",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "image2text",
|
||||
"model_type": "chat",
|
||||
"is_tools": true
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-2.0-flash-001",
|
||||
"tags": "LLM,CHAT,1024K",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "image2text",
|
||||
"is_tools": true
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-2.0-flash-thinking-exp-01-21",
|
||||
"llm_name": "gemini-2.0-flash",
|
||||
"tags": "LLM,CHAT,1024K",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "chat",
|
||||
"is_tools": true
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-1.5-flash",
|
||||
"tags": "LLM,IMAGE2TEXT,1024K",
|
||||
"llm_name": "gemini-2.0-flash-lite",
|
||||
"tags": "LLM,CHAT,1024K",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "image2text"
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-2.5-pro-preview-05-06",
|
||||
"tags": "LLM,IMAGE2TEXT,1024K",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "image2text"
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-1.5-pro",
|
||||
"tags": "LLM,IMAGE2TEXT,2048K",
|
||||
"max_tokens": 2097152,
|
||||
"model_type": "image2text"
|
||||
},
|
||||
{
|
||||
"llm_name": "gemini-1.5-flash-8b",
|
||||
"tags": "LLM,IMAGE2TEXT,1024K",
|
||||
"max_tokens": 1048576,
|
||||
"model_type": "image2text",
|
||||
"model_type": "chat",
|
||||
"is_tools": true
|
||||
},
|
||||
{
|
||||
|
||||
@ -94,7 +94,7 @@ SVR_HTTP_PORT=9380
|
||||
|
||||
# The RAGFlow Docker image to download.
|
||||
# Defaults to the v0.20.1-slim edition, which is the RAGFlow Docker image without embedding models.
|
||||
RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1-slim
|
||||
RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2-slim
|
||||
#
|
||||
# To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
|
||||
# RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1
|
||||
|
||||
@ -79,8 +79,8 @@ The [.env](./.env) file contains important environment variables for Docker.
|
||||
- `RAGFLOW-IMAGE`
|
||||
The Docker image edition. Available editions:
|
||||
|
||||
- `infiniflow/ragflow:v0.20.1-slim` (default): The RAGFlow Docker image without embedding models.
|
||||
- `infiniflow/ragflow:v0.20.1`: The RAGFlow Docker image with embedding models including:
|
||||
- `infiniflow/ragflow:v0.20.2-slim` (default): The RAGFlow Docker image without embedding models.
|
||||
- `infiniflow/ragflow:v0.20.2`: The RAGFlow Docker image with embedding models including:
|
||||
- Built-in embedding models:
|
||||
- `BAAI/bge-large-zh-v1.5`
|
||||
- `maidalun1020/bce-embedding-base_v1`
|
||||
|
||||
@ -6,3 +6,7 @@ proxy_set_header Connection "";
|
||||
proxy_buffering off;
|
||||
proxy_read_timeout 3600s;
|
||||
proxy_send_timeout 3600s;
|
||||
proxy_buffer_size 1024k;
|
||||
proxy_buffers 16 1024k;
|
||||
proxy_busy_buffers_size 2048k;
|
||||
proxy_temp_file_write_size 2048k;
|
||||
@ -99,8 +99,8 @@ RAGFlow utilizes MinIO as its object storage solution, leveraging its scalabilit
|
||||
- `RAGFLOW-IMAGE`
|
||||
The Docker image edition. Available editions:
|
||||
|
||||
- `infiniflow/ragflow:v0.20.1-slim` (default): The RAGFlow Docker image without embedding models.
|
||||
- `infiniflow/ragflow:v0.20.1`: The RAGFlow Docker image with embedding models including:
|
||||
- `infiniflow/ragflow:v0.20.2-slim` (default): The RAGFlow Docker image without embedding models.
|
||||
- `infiniflow/ragflow:v0.20.2`: The RAGFlow Docker image with embedding models including:
|
||||
- Built-in embedding models:
|
||||
- `BAAI/bge-large-zh-v1.5`
|
||||
- `maidalun1020/bce-embedding-base_v1`
|
||||
|
||||
@ -77,7 +77,7 @@ After building the infiniflow/ragflow:nightly-slim image, you are ready to launc
|
||||
|
||||
1. Edit Docker Compose Configuration
|
||||
|
||||
Open the `docker/.env` file. Find the `RAGFLOW_IMAGE` setting and change the image reference from `infiniflow/ragflow:v0.20.1-slim` to `infiniflow/ragflow:nightly-slim` to use the pre-built image.
|
||||
Open the `docker/.env` file. Find the `RAGFLOW_IMAGE` setting and change the image reference from `infiniflow/ragflow:v0.20.2-slim` to `infiniflow/ragflow:nightly-slim` to use the pre-built image.
|
||||
|
||||
|
||||
2. Launch the Service
|
||||
|
||||
10
docs/faq.mdx
10
docs/faq.mdx
@ -30,17 +30,17 @@ The "garbage in garbage out" status quo remains unchanged despite the fact that
|
||||
|
||||
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:v0.20.1-slim`
|
||||
- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.20.1`
|
||||
- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.20.2-slim`
|
||||
- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.20.2`
|
||||
|
||||
---
|
||||
|
||||
### Which embedding models can be deployed locally?
|
||||
|
||||
RAGFlow offers two Docker image editions, `v0.20.1-slim` and `v0.20.1`:
|
||||
RAGFlow offers two Docker image editions, `v0.20.2-slim` and `v0.20.2`:
|
||||
|
||||
- `infiniflow/ragflow:v0.20.1-slim` (default): The RAGFlow Docker image without embedding models.
|
||||
- `infiniflow/ragflow:v0.20.1`: The RAGFlow Docker image with embedding models including:
|
||||
- `infiniflow/ragflow:v0.20.2-slim` (default): The RAGFlow Docker image without embedding models.
|
||||
- `infiniflow/ragflow:v0.20.2`: The RAGFlow Docker image with embedding models including:
|
||||
- Built-in embedding models:
|
||||
- `BAAI/bge-large-zh-v1.5`
|
||||
- `maidalun1020/bce-embedding-base_v1`
|
||||
|
||||
@ -9,7 +9,7 @@ The component equipped with reasoning, tool usage, and multi-agent collaboration
|
||||
|
||||
---
|
||||
|
||||
An **Agent** component fine-tunes the LLM and sets its prompt. From v0.20.1 onwards, an **Agent** component is able to work independently and with the following capabilities:
|
||||
An **Agent** component fine-tunes the LLM and sets its prompt. From v0.20.2 onwards, an **Agent** component is able to work independently and with the following capabilities:
|
||||
|
||||
- Autonomous reasoning with reflection and adjustment based on environmental feedback.
|
||||
- Use of tools or subagents to complete tasks.
|
||||
|
||||
@ -9,7 +9,7 @@ A component that retrieves information from specified datasets.
|
||||
|
||||
## Scenarios
|
||||
|
||||
A **Retrieval** component is essential in most RAG scenarios, where information is extracted from designated knowledge bases before being sent to the LLM for content generation. As of v0.20.1, a **Retrieval** component can operate either as a workflow component or as a tool of an **Agent**, enabling the Agent to control its invocation and search queries.
|
||||
A **Retrieval** component is essential in most RAG scenarios, where information is extracted from designated knowledge bases before being sent to the LLM for content generation. As of v0.20.2, a **Retrieval** component can operate either as a workflow component or as a tool of an **Agent**, enabling the Agent to control its invocation and search queries.
|
||||
|
||||
## Configurations
|
||||
|
||||
|
||||
@ -48,7 +48,7 @@ You start an AI conversation by creating an assistant.
|
||||
- If no target language is selected, the system will search only in the language of your query, which may cause relevant information in other languages to be missed.
|
||||
- **Variable** refers to the variables (keys) to be used in the system prompt. `{knowledge}` is a reserved variable. Click **Add** to add more variables for the system prompt.
|
||||
- If you are uncertain about the logic behind **Variable**, leave it *as-is*.
|
||||
- As of v0.20.1, if you add custom variables here, the only way you can pass in their values is to call:
|
||||
- As of v0.20.2, if you add custom variables here, the only way you can pass in their values is to call:
|
||||
- HTTP method [Converse with chat assistant](../../references/http_api_reference.md#converse-with-chat-assistant), or
|
||||
- Python method [Converse with chat assistant](../../references/python_api_reference.md#converse-with-chat-assistant).
|
||||
|
||||
|
||||
@ -128,7 +128,7 @@ See [Run retrieval test](./run_retrieval_test.md) for details.
|
||||
|
||||
## Search for knowledge base
|
||||
|
||||
As of RAGFlow v0.20.1, the search feature is still in a rudimentary form, supporting only knowledge base search by name.
|
||||
As of RAGFlow v0.20.2, the search feature is still in a rudimentary form, supporting only knowledge base search by name.
|
||||
|
||||
|
||||
|
||||
|
||||
@ -87,4 +87,4 @@ RAGFlow's file management allows you to download an uploaded file:
|
||||
|
||||
|
||||
|
||||
> As of RAGFlow v0.20.1, bulk download is not supported, nor can you download an entire folder.
|
||||
> As of RAGFlow v0.20.2, bulk download is not supported, nor can you download an entire folder.
|
||||
|
||||
@ -18,7 +18,7 @@ RAGFlow ships with a built-in [Langfuse](https://langfuse.com) integration so th
|
||||
Langfuse stores traces, spans and prompt payloads in a purpose-built observability backend and offers filtering and visualisations on top.
|
||||
|
||||
:::info NOTE
|
||||
• RAGFlow **≥ 0.20.1** (contains the Langfuse connector)
|
||||
• RAGFlow **≥ 0.20.2** (contains the Langfuse connector)
|
||||
• A Langfuse workspace (cloud or self-hosted) with a _Project Public Key_ and _Secret Key_
|
||||
:::
|
||||
|
||||
|
||||
@ -66,10 +66,10 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
|
||||
git clone https://github.com/infiniflow/ragflow.git
|
||||
```
|
||||
|
||||
2. Switch to the latest, officially published release, e.g., `v0.20.1`:
|
||||
2. Switch to the latest, officially published release, e.g., `v0.20.2`:
|
||||
|
||||
```bash
|
||||
git checkout -f v0.20.1
|
||||
git checkout -f v0.20.2
|
||||
```
|
||||
|
||||
3. Update **ragflow/docker/.env**:
|
||||
@ -83,14 +83,14 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
|
||||
<TabItem value="slim">
|
||||
|
||||
```bash
|
||||
RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1-slim
|
||||
RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2-slim
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
<TabItem value="full">
|
||||
|
||||
```bash
|
||||
RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1
|
||||
RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
@ -114,10 +114,10 @@ No, you do not need to. Upgrading RAGFlow in itself will *not* remove your uploa
|
||||
1. From an environment with Internet access, pull the required Docker image.
|
||||
2. Save the Docker image to a **.tar** file.
|
||||
```bash
|
||||
docker save -o ragflow.v0.20.1.tar infiniflow/ragflow:v0.20.1
|
||||
docker save -o ragflow.v0.20.2.tar infiniflow/ragflow:v0.20.2
|
||||
```
|
||||
3. Copy the **.tar** file to the target server.
|
||||
4. Load the **.tar** file into Docker:
|
||||
```bash
|
||||
docker load -i ragflow.v0.20.1.tar
|
||||
docker load -i ragflow.v0.20.2.tar
|
||||
```
|
||||
|
||||
@ -44,7 +44,7 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
|
||||
|
||||
`vm.max_map_count`. This value sets the maximum number of memory map areas a process may have. Its default value is 65530. While most applications require fewer than a thousand maps, reducing this value can result in abnormal behaviors, and the system will throw out-of-memory errors when a process reaches the limitation.
|
||||
|
||||
RAGFlow v0.20.1 uses Elasticsearch or [Infinity](https://github.com/infiniflow/infinity) for multiple recall. Setting the value of `vm.max_map_count` correctly is crucial to the proper functioning of the Elasticsearch component.
|
||||
RAGFlow v0.20.2 uses Elasticsearch or [Infinity](https://github.com/infiniflow/infinity) for multiple recall. Setting the value of `vm.max_map_count` correctly is crucial to the proper functioning of the Elasticsearch component.
|
||||
|
||||
<Tabs
|
||||
defaultValue="linux"
|
||||
@ -184,13 +184,13 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
|
||||
```bash
|
||||
$ git clone https://github.com/infiniflow/ragflow.git
|
||||
$ cd ragflow/docker
|
||||
$ git checkout -f v0.20.1
|
||||
$ git checkout -f v0.20.2
|
||||
```
|
||||
|
||||
3. Use the pre-built Docker images and start up the server:
|
||||
|
||||
:::tip NOTE
|
||||
The command below downloads the `v0.20.1-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 `v0.20.1-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:v0.20.1` for the full edition `v0.20.1`.
|
||||
The command below downloads the `v0.20.2-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 `v0.20.2-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.2` for the full edition `v0.20.2`.
|
||||
:::
|
||||
|
||||
```bash
|
||||
@ -207,8 +207,8 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
|
||||
|
||||
| RAGFlow image tag | Image size (GB) | Has embedding models and Python packages? | Stable? |
|
||||
| ------------------- | --------------- | ----------------------------------------- | ------------------------ |
|
||||
| `v0.20.1` | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| `v0.20.1-slim` | ≈2 | ❌ | Stable release |
|
||||
| `v0.20.2` | ≈9 | :heavy_check_mark: | Stable release |
|
||||
| `v0.20.2-slim` | ≈2 | ❌ | Stable release |
|
||||
| `nightly` | ≈9 | :heavy_check_mark: | *Unstable* nightly build |
|
||||
| `nightly-slim` | ≈2 | ❌ | *Unstable* nightly build |
|
||||
|
||||
@ -217,7 +217,7 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
|
||||
```
|
||||
|
||||
:::danger IMPORTANT
|
||||
The embedding models included in `v0.20.1` and `nightly` are:
|
||||
The embedding models included in `v0.20.2` and `nightly` are:
|
||||
|
||||
- BAAI/bge-large-zh-v1.5
|
||||
- maidalun1020/bce-embedding-base_v1
|
||||
|
||||
@ -19,7 +19,7 @@ import TOCInline from '@theme/TOCInline';
|
||||
|
||||
### Cross-language search
|
||||
|
||||
Cross-language search (also known as cross-lingual retrieval) is a feature introduced in version 0.20.1. It enables users to submit queries in one language (for example, English) and retrieve relevant documents written in other languages such as Chinese or Spanish. This feature is enabled by the system’s default chat model, which translates queries to ensure accurate matching of semantic meaning across languages.
|
||||
Cross-language search (also known as cross-lingual retrieval) is a feature introduced in version 0.20.2. It enables users to submit queries in one language (for example, English) and retrieve relevant documents written in other languages such as Chinese or Spanish. This feature is enabled by the system’s default chat model, which translates queries to ensure accurate matching of semantic meaning across languages.
|
||||
|
||||
By enabling cross-language search, users can effortlessly access a broader range of information regardless of language barriers, significantly enhancing the system’s usability and inclusiveness.
|
||||
|
||||
|
||||
@ -2656,7 +2656,7 @@ Creates a session with an agent.
|
||||
- Body:
|
||||
- the required parameters:`str`
|
||||
- other parameters:
|
||||
The parameters specified in the **Begin** component.
|
||||
The variables specified in the **Begin** component.
|
||||
|
||||
##### Request example
|
||||
|
||||
@ -3000,13 +3000,19 @@ curl --request POST \
|
||||
- `"session_id"`: (*Body Parameter*)
|
||||
The ID of the session. If it is not provided, a new session will be generated.
|
||||
- `"inputs"`: (*Body Parameter*)
|
||||
Parameters specified in the **Begin** component.
|
||||
Variables specified in the **Begin** component.
|
||||
- `"user_id"`: (*Body parameter*), `string`
|
||||
The optional user-defined ID. Valid *only* when no `session_id` is provided.
|
||||
|
||||
:::tip NOTE
|
||||
For now, this method does *not* support a file type input/variable. As a workaround, use the following to upload a file to an agent:
|
||||
`http://{address}/v1/canvas/upload/{agent_id}`
|
||||
*You will get a corresponding file ID from its response body.*
|
||||
:::
|
||||
|
||||
#### Response
|
||||
|
||||
success without `session_id` provided and with no parameters specified in the **Begin** component:
|
||||
success without `session_id` provided and with no variables specified in the **Begin** component:
|
||||
|
||||
Stream:
|
||||
|
||||
@ -3074,7 +3080,7 @@ Non-stream:
|
||||
}
|
||||
```
|
||||
|
||||
Success without `session_id` provided and with parameters specified in the **Begin** component:
|
||||
Success without `session_id` provided and with variables specified in the **Begin** component:
|
||||
|
||||
Stream:
|
||||
|
||||
@ -3163,7 +3169,7 @@ Non-stream:
|
||||
}
|
||||
```
|
||||
|
||||
Success with parameters specified in the **Begin** component:
|
||||
Success with variables specified in the **Begin** component:
|
||||
|
||||
Stream:
|
||||
|
||||
|
||||
@ -22,13 +22,14 @@ The embedding models included in a full edition are:
|
||||
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.
|
||||
:::
|
||||
|
||||
## v0.20.2 (Ongoing🔨)
|
||||
## v0.20.2
|
||||
|
||||
Released on August ??, 2025.
|
||||
Released on August 19, 2025.
|
||||
|
||||
### Improvements
|
||||
|
||||
- Revamps the user interface for the **Datasets**, **Chat**, and **Search** pages.
|
||||
- Search and Chat: Introduces document-level metadata filtering, allowing automatic or manual filtering during chats or searches.
|
||||
- Search: Supports creating search apps tailored to various business scenarios
|
||||
- Chat: Supports comparing answer performance of up to three chat model settings on a single **Chat** page.
|
||||
- Agent:
|
||||
@ -42,6 +43,7 @@ Released on August ??, 2025.
|
||||
|
||||
### Fixed issues
|
||||
|
||||
- The timeout mechanism introduced in v0.20.0 caused tasks like GraphRAG to halt.
|
||||
- Predefined opening greeting in the **Agent** component was missing during conversations.
|
||||
- An automatic line break issue in the prompt editor.
|
||||
- A memory leak issue caused by PyPDF. [#9469](https://github.com/infiniflow/ragflow/pull/9469)
|
||||
|
||||
@ -57,7 +57,7 @@ async def run_graphrag(
|
||||
):
|
||||
chunks.append(d["content_with_weight"])
|
||||
|
||||
with trio.fail_after(len(chunks)*60):
|
||||
with trio.fail_after(max(120, len(chunks)*120)):
|
||||
subgraph = await generate_subgraph(
|
||||
LightKGExt
|
||||
if "method" not in row["kb_parser_config"].get("graphrag", {}) or row["kb_parser_config"]["graphrag"]["method"] != "general"
|
||||
|
||||
@ -56,7 +56,7 @@ env:
|
||||
ragflow:
|
||||
image:
|
||||
repository: infiniflow/ragflow
|
||||
tag: v0.20.1-slim
|
||||
tag: v0.20.2-slim
|
||||
pullPolicy: IfNotPresent
|
||||
pullSecrets: []
|
||||
# Optional service configuration overrides
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "ragflow"
|
||||
version = "0.20.1"
|
||||
version = "0.20.2"
|
||||
description = "[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data."
|
||||
authors = [{ name = "Zhichang Yu", email = "yuzhichang@gmail.com" }]
|
||||
license-files = ["LICENSE"]
|
||||
@ -43,7 +43,7 @@ dependencies = [
|
||||
"groq==0.9.0",
|
||||
"hanziconv==0.3.2",
|
||||
"html-text==0.6.2",
|
||||
"httpx==0.27.2",
|
||||
"httpx[socks]==0.27.2",
|
||||
"huggingface-hub>=0.25.0,<0.26.0",
|
||||
"infinity-sdk==0.6.0-dev4",
|
||||
"infinity-emb>=0.0.66,<0.0.67",
|
||||
|
||||
@ -14,31 +14,48 @@
|
||||
# limitations under the License.
|
||||
#
|
||||
|
||||
import os
|
||||
import re
|
||||
import tempfile
|
||||
|
||||
from api.db import LLMType
|
||||
from rag.nlp import rag_tokenizer
|
||||
from api.db.services.llm_service import LLMBundle
|
||||
from rag.nlp import tokenize
|
||||
from rag.nlp import rag_tokenizer, tokenize
|
||||
|
||||
|
||||
def chunk(filename, binary, tenant_id, lang, callback=None, **kwargs):
|
||||
doc = {
|
||||
"docnm_kwd": filename,
|
||||
"title_tks": rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", filename))
|
||||
}
|
||||
doc = {"docnm_kwd": filename, "title_tks": rag_tokenizer.tokenize(re.sub(r"\.[a-zA-Z]+$", "", filename))}
|
||||
doc["title_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["title_tks"])
|
||||
|
||||
# is it English
|
||||
eng = lang.lower() == "english" # is_english(sections)
|
||||
try:
|
||||
_, ext = os.path.splitext(filename)
|
||||
if not ext:
|
||||
raise RuntimeError("No extension detected.")
|
||||
|
||||
if ext not in [".da", ".wave", ".wav", ".mp3", ".wav", ".aac", ".flac", ".ogg", ".aiff", ".au", ".midi", ".wma", ".realaudio", ".vqf", ".oggvorbis", ".aac", ".ape"]:
|
||||
raise RuntimeError(f"Extension {ext} is not supported yet.")
|
||||
|
||||
tmp_path = ""
|
||||
with tempfile.NamedTemporaryFile(suffix=ext, delete=False) as tmpf:
|
||||
tmpf.write(binary)
|
||||
tmpf.flush()
|
||||
tmp_path = os.path.abspath(tmpf.name)
|
||||
|
||||
callback(0.1, "USE Sequence2Txt LLM to transcription the audio")
|
||||
seq2txt_mdl = LLMBundle(tenant_id, LLMType.SPEECH2TEXT, lang=lang)
|
||||
ans = seq2txt_mdl.transcription(binary)
|
||||
ans = seq2txt_mdl.transcription(tmp_path)
|
||||
callback(0.8, "Sequence2Txt LLM respond: %s ..." % ans[:32])
|
||||
|
||||
tokenize(doc, ans, eng)
|
||||
return [doc]
|
||||
except Exception as e:
|
||||
callback(prog=-1, msg=str(e))
|
||||
|
||||
finally:
|
||||
if tmp_path and os.path.exists(tmp_path):
|
||||
try:
|
||||
os.unlink(tmp_path)
|
||||
except Exception:
|
||||
pass
|
||||
return []
|
||||
|
||||
@ -539,24 +539,24 @@ class GeminiCV(Base):
|
||||
return res.text, res.usage_metadata.total_token_count
|
||||
|
||||
def chat(self, system, history, gen_conf, images=[]):
|
||||
from transformers import GenerationConfig
|
||||
generation_config = dict(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7))
|
||||
try:
|
||||
response = self.model.generate_content(
|
||||
self._form_history(system, history, images),
|
||||
generation_config=GenerationConfig(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7)))
|
||||
generation_config=generation_config)
|
||||
ans = response.text
|
||||
return ans, response.usage_metadata.total_token_count
|
||||
except Exception as e:
|
||||
return "**ERROR**: " + str(e), 0
|
||||
|
||||
def chat_streamly(self, system, history, gen_conf, images=[]):
|
||||
from transformers import GenerationConfig
|
||||
ans = ""
|
||||
response = None
|
||||
try:
|
||||
generation_config = dict(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7))
|
||||
response = self.model.generate_content(
|
||||
self._form_history(system, history, images),
|
||||
generation_config=GenerationConfig(temperature=gen_conf.get("temperature", 0.3), top_p=gen_conf.get("top_p", 0.7)),
|
||||
generation_config=generation_config,
|
||||
stream=True,
|
||||
)
|
||||
|
||||
@ -572,7 +572,7 @@ class GeminiCV(Base):
|
||||
yield response.usage_metadata.total_token_count
|
||||
else:
|
||||
yield 0
|
||||
|
||||
|
||||
|
||||
class NvidiaCV(Base):
|
||||
_FACTORY_NAME = "NVIDIA"
|
||||
|
||||
@ -100,7 +100,7 @@ class DefaultRerank(Base):
|
||||
old_dynamic_batch_size = self._dynamic_batch_size
|
||||
if max_batch_size is not None:
|
||||
self._dynamic_batch_size = max_batch_size
|
||||
res = np.array([], dtype=float)
|
||||
res = np.array(len(pairs), dtype=float)
|
||||
i = 0
|
||||
while i < len(pairs):
|
||||
cur_i = i
|
||||
@ -111,7 +111,7 @@ class DefaultRerank(Base):
|
||||
try:
|
||||
# call subclass implemented batch processing calculation
|
||||
batch_scores = self._compute_batch_scores(pairs[i : i + current_batch])
|
||||
res = np.append(res, batch_scores)
|
||||
res[i : i + current_batch] = batch_scores
|
||||
i += current_batch
|
||||
self._dynamic_batch_size = min(self._dynamic_batch_size * 2, 8)
|
||||
break
|
||||
@ -125,8 +125,8 @@ class DefaultRerank(Base):
|
||||
raise
|
||||
if retry_count >= max_retries:
|
||||
raise RuntimeError("max retry times, still cannot process batch, please check your GPU memory")
|
||||
self.torch_empty_cache()
|
||||
|
||||
|
||||
self.torch_empty_cache()
|
||||
self._dynamic_batch_size = old_dynamic_batch_size
|
||||
return np.array(res)
|
||||
|
||||
@ -482,9 +482,10 @@ class VoyageRerank(Base):
|
||||
self.model_name = model_name
|
||||
|
||||
def similarity(self, query: str, texts: list):
|
||||
rank = np.zeros(len(texts), dtype=float)
|
||||
if not texts:
|
||||
return rank, 0
|
||||
return np.array([]), 0
|
||||
rank = np.zeros(len(texts), dtype=float)
|
||||
|
||||
res = self.client.rerank(query=query, documents=texts, model=self.model_name, top_k=len(texts))
|
||||
try:
|
||||
for r in res.results:
|
||||
|
||||
@ -35,8 +35,9 @@ class Base(ABC):
|
||||
"""
|
||||
pass
|
||||
|
||||
def transcription(self, audio, **kwargs):
|
||||
transcription = self.client.audio.transcriptions.create(model=self.model_name, file=audio, response_format="text")
|
||||
def transcription(self, audio_path, **kwargs):
|
||||
audio_file = open(audio_path, "rb")
|
||||
transcription = self.client.audio.transcriptions.create(model=self.model_name, file=audio_file)
|
||||
return transcription.text.strip(), num_tokens_from_string(transcription.text.strip())
|
||||
|
||||
def audio2base64(self, audio):
|
||||
@ -50,7 +51,7 @@ class Base(ABC):
|
||||
class GPTSeq2txt(Base):
|
||||
_FACTORY_NAME = "OpenAI"
|
||||
|
||||
def __init__(self, key, model_name="whisper-1", base_url="https://api.openai.com/v1"):
|
||||
def __init__(self, key, model_name="whisper-1", base_url="https://api.openai.com/v1", **kwargs):
|
||||
if not base_url:
|
||||
base_url = "https://api.openai.com/v1"
|
||||
self.client = OpenAI(api_key=key, base_url=base_url)
|
||||
@ -60,27 +61,38 @@ class GPTSeq2txt(Base):
|
||||
class QWenSeq2txt(Base):
|
||||
_FACTORY_NAME = "Tongyi-Qianwen"
|
||||
|
||||
def __init__(self, key, model_name="paraformer-realtime-8k-v1", **kwargs):
|
||||
def __init__(self, key, model_name="qwen-audio-asr", **kwargs):
|
||||
import dashscope
|
||||
|
||||
dashscope.api_key = key
|
||||
self.model_name = model_name
|
||||
|
||||
def transcription(self, audio, format):
|
||||
from http import HTTPStatus
|
||||
def transcription(self, audio_path):
|
||||
if "paraformer" in self.model_name or "sensevoice" in self.model_name:
|
||||
return f"**ERROR**: model {self.model_name} is not suppported yet.", 0
|
||||
|
||||
from dashscope.audio.asr import Recognition
|
||||
from dashscope import MultiModalConversation
|
||||
|
||||
recognition = Recognition(model=self.model_name, format=format, sample_rate=16000, callback=None)
|
||||
result = recognition.call(audio)
|
||||
audio_path = f"file://{audio_path}"
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [{"audio": audio_path}],
|
||||
}
|
||||
]
|
||||
|
||||
ans = ""
|
||||
if result.status_code == HTTPStatus.OK:
|
||||
for sentence in result.get_sentence():
|
||||
ans += sentence.text.decode("utf-8") + "\n"
|
||||
return ans, num_tokens_from_string(ans)
|
||||
|
||||
return "**ERROR**: " + result.message, 0
|
||||
response = None
|
||||
full_content = ""
|
||||
try:
|
||||
response = MultiModalConversation.call(model="qwen-audio-asr", messages=messages, result_format="message", stream=True)
|
||||
for response in response:
|
||||
try:
|
||||
full_content += response["output"]["choices"][0]["message"].content[0]["text"]
|
||||
except Exception:
|
||||
pass
|
||||
return full_content, num_tokens_from_string(full_content)
|
||||
except Exception as e:
|
||||
return "**ERROR**: " + str(e), 0
|
||||
|
||||
|
||||
class AzureSeq2txt(Base):
|
||||
@ -212,6 +224,7 @@ class GiteeSeq2txt(Base):
|
||||
self.client = OpenAI(api_key=key, base_url=base_url)
|
||||
self.model_name = model_name
|
||||
|
||||
|
||||
class DeepInfraSeq2txt(Base):
|
||||
_FACTORY_NAME = "DeepInfra"
|
||||
|
||||
|
||||
@ -611,10 +611,6 @@ def naive_merge_with_images(texts, images, chunk_token_num=128, delimiter="\n。
|
||||
if re.match(f"^{dels}$", sub_sec):
|
||||
continue
|
||||
add_chunk(sub_sec, image)
|
||||
|
||||
for img in images:
|
||||
if isinstance(img, Image.Image):
|
||||
img.close()
|
||||
|
||||
return cks, result_images
|
||||
|
||||
|
||||
14
rag/prompts/ask_summary.md
Normal file
14
rag/prompts/ask_summary.md
Normal file
@ -0,0 +1,14 @@
|
||||
Role: You're a smart assistant. Your name is Miss R.
|
||||
Task: Summarize the information from knowledge bases and answer user's question.
|
||||
Requirements and restriction:
|
||||
- DO NOT make things up, especially for numbers.
|
||||
- If the information from knowledge is irrelevant with user's question, JUST SAY: Sorry, no relevant information provided.
|
||||
- Answer with markdown format text.
|
||||
- Answer in language of user's question.
|
||||
- DO NOT make things up, especially for numbers.
|
||||
|
||||
### Information from knowledge bases
|
||||
|
||||
{{ knowledge }}
|
||||
|
||||
The above is information from knowledge bases.
|
||||
@ -150,6 +150,7 @@ REFLECT = load_prompt("reflect")
|
||||
SUMMARY4MEMORY = load_prompt("summary4memory")
|
||||
RANK_MEMORY = load_prompt("rank_memory")
|
||||
META_FILTER = load_prompt("meta_filter")
|
||||
ASK_SUMMARY = load_prompt("ask_summary")
|
||||
|
||||
PROMPT_JINJA_ENV = jinja2.Environment(autoescape=False, trim_blocks=True, lstrip_blocks=True)
|
||||
|
||||
|
||||
55
rag/prompts/related_question.md
Normal file
55
rag/prompts/related_question.md
Normal file
@ -0,0 +1,55 @@
|
||||
# Role
|
||||
You are an AI language model assistant tasked with generating **5-10 related questions** based on a user’s original query.
|
||||
These questions should help **expand the search query scope** and **improve search relevance**.
|
||||
|
||||
---
|
||||
|
||||
## Instructions
|
||||
|
||||
**Input:**
|
||||
You are provided with a **user’s question**.
|
||||
|
||||
**Output:**
|
||||
Generate **5-10 alternative questions** that are **related** to the original user question.
|
||||
These alternatives should help retrieve a **broader range of relevant documents** from a vector database.
|
||||
|
||||
**Context:**
|
||||
Focus on **rephrasing** the original question in different ways, ensuring the alternative questions are **diverse but still connected** to the topic of the original query.
|
||||
Do **not** create overly obscure, irrelevant, or unrelated questions.
|
||||
|
||||
**Fallback:**
|
||||
If you cannot generate any relevant alternatives, do **not** return any questions.
|
||||
|
||||
---
|
||||
|
||||
## Guidance
|
||||
|
||||
1. Each alternative should be **unique** but still **relevant** to the original query.
|
||||
2. Keep the phrasing **clear, concise, and easy to understand**.
|
||||
3. Avoid overly technical jargon or specialized terms **unless directly relevant**.
|
||||
4. Ensure that each question **broadens** the search angle, **not narrows** it.
|
||||
|
||||
---
|
||||
|
||||
## Example
|
||||
|
||||
**Original Question:**
|
||||
> What are the benefits of electric vehicles?
|
||||
|
||||
**Alternative Questions:**
|
||||
1. How do electric vehicles impact the environment?
|
||||
2. What are the advantages of owning an electric car?
|
||||
3. What is the cost-effectiveness of electric vehicles?
|
||||
4. How do electric vehicles compare to traditional cars in terms of fuel efficiency?
|
||||
5. What are the environmental benefits of switching to electric cars?
|
||||
6. How do electric vehicles help reduce carbon emissions?
|
||||
7. Why are electric vehicles becoming more popular?
|
||||
8. What are the long-term savings of using electric vehicles?
|
||||
9. How do electric vehicles contribute to sustainability?
|
||||
10. What are the key benefits of electric vehicles for consumers?
|
||||
|
||||
---
|
||||
|
||||
## Reason
|
||||
Rephrasing the original query into multiple alternative questions helps the user explore **different aspects** of their search topic, improving the **quality of search results**.
|
||||
These questions guide the search engine to provide a **more comprehensive set** of relevant documents.
|
||||
@ -302,7 +302,7 @@ async def build_chunks(task, progress_callback):
|
||||
# If the image is in RGBA mode, convert it to RGB mode before saving it in JPEG format.
|
||||
if d["image"].mode in ("RGBA", "P"):
|
||||
converted_image = d["image"].convert("RGB")
|
||||
d["image"].close() # Close original image
|
||||
#d["image"].close() # Close original image
|
||||
d["image"] = converted_image
|
||||
try:
|
||||
d["image"].save(output_buffer, format='JPEG')
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "ragflow-sdk"
|
||||
version = "0.20.1"
|
||||
version = "0.20.2"
|
||||
description = "Python client sdk of [RAGFlow](https://github.com/infiniflow/ragflow). RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding."
|
||||
authors = [{ name = "Zhichang Yu", email = "yuzhichang@gmail.com" }]
|
||||
license = { text = "Apache License, Version 2.0" }
|
||||
|
||||
2
sdk/python/uv.lock
generated
2
sdk/python/uv.lock
generated
@ -342,7 +342,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "ragflow-sdk"
|
||||
version = "0.20.1"
|
||||
version = "0.20.2"
|
||||
source = { virtual = "." }
|
||||
dependencies = [
|
||||
{ name = "beartype" },
|
||||
|
||||
20
uv.lock
generated
20
uv.lock
generated
@ -2422,6 +2422,11 @@ wheels = [
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/56/95/9377bcb415797e44274b51d46e3249eba641711cf3348050f76ee7b15ffc/httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0" },
|
||||
]
|
||||
|
||||
[package.optional-dependencies]
|
||||
socks = [
|
||||
{ name = "socksio" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "httpx-sse"
|
||||
version = "0.4.1"
|
||||
@ -5263,7 +5268,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "ragflow"
|
||||
version = "0.20.1"
|
||||
version = "0.20.2"
|
||||
source = { virtual = "." }
|
||||
dependencies = [
|
||||
{ name = "akshare" },
|
||||
@ -5308,7 +5313,7 @@ dependencies = [
|
||||
{ name = "groq" },
|
||||
{ name = "hanziconv" },
|
||||
{ name = "html-text" },
|
||||
{ name = "httpx" },
|
||||
{ name = "httpx", extra = ["socks"] },
|
||||
{ name = "huggingface-hub" },
|
||||
{ name = "infinity-emb" },
|
||||
{ name = "infinity-sdk" },
|
||||
@ -5463,7 +5468,7 @@ requires-dist = [
|
||||
{ name = "groq", specifier = "==0.9.0" },
|
||||
{ name = "hanziconv", specifier = "==0.3.2" },
|
||||
{ name = "html-text", specifier = "==0.6.2" },
|
||||
{ name = "httpx", specifier = "==0.27.2" },
|
||||
{ name = "httpx", extras = ["socks"], specifier = "==0.27.2" },
|
||||
{ name = "huggingface-hub", specifier = ">=0.25.0,<0.26.0" },
|
||||
{ name = "infinity-emb", specifier = ">=0.0.66,<0.0.67" },
|
||||
{ name = "infinity-sdk", specifier = "==0.6.0.dev4" },
|
||||
@ -6216,6 +6221,15 @@ wheels = [
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/ed/dc/c02e01294f7265e63a7315fe086dd1df7dacb9f840a804da846b96d01b96/snowballstemmer-2.2.0-py2.py3-none-any.whl", hash = "sha256:c8e1716e83cc398ae16824e5572ae04e0d9fc2c6b985fb0f900f5f0c96ecba1a" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "socksio"
|
||||
version = "1.0.0"
|
||||
source = { registry = "https://mirrors.aliyun.com/pypi/simple" }
|
||||
sdist = { url = "https://mirrors.aliyun.com/pypi/packages/f8/5c/48a7d9495be3d1c651198fd99dbb6ce190e2274d0f28b9051307bdec6b85/socksio-1.0.0.tar.gz", hash = "sha256:f88beb3da5b5c38b9890469de67d0cb0f9d494b78b106ca1845f96c10b91c4ac" }
|
||||
wheels = [
|
||||
{ url = "https://mirrors.aliyun.com/pypi/packages/37/c3/6eeb6034408dac0fa653d126c9204ade96b819c936e136c5e8a6897eee9c/socksio-1.0.0-py3-none-any.whl", hash = "sha256:95dc1f15f9b34e8d7b16f06d74b8ccf48f609af32ab33c608d08761c5dcbb1f3" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "sortedcontainers"
|
||||
version = "2.4.0"
|
||||
|
||||
@ -317,7 +317,11 @@ export function ChunkMethodDialog({
|
||||
</FormContainer>
|
||||
)}
|
||||
{showGraphRagItems(selectedTag as DocumentParserType) &&
|
||||
useGraphRag && <UseGraphRagFormField></UseGraphRagFormField>}
|
||||
useGraphRag && (
|
||||
<FormContainer>
|
||||
<UseGraphRagFormField></UseGraphRagFormField>
|
||||
</FormContainer>
|
||||
)}
|
||||
{showEntityTypes && <EntityTypesFormField></EntityTypesFormField>}
|
||||
</form>
|
||||
</Form>
|
||||
|
||||
@ -50,10 +50,10 @@ export function DelimiterFormField() {
|
||||
}
|
||||
return (
|
||||
<FormItem className=" items-center space-y-0 ">
|
||||
<div className="flex items-center">
|
||||
<div className="flex items-center gap-1">
|
||||
<FormLabel
|
||||
tooltip={t('knowledgeDetails.delimiterTip')}
|
||||
className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
|
||||
className="text-sm text-muted-foreground whitespace-break-spaces w-1/4"
|
||||
>
|
||||
{t('knowledgeDetails.delimiter')}
|
||||
</FormLabel>
|
||||
|
||||
48
web/src/components/embed-container.tsx
Normal file
48
web/src/components/embed-container.tsx
Normal file
@ -0,0 +1,48 @@
|
||||
import { useFetchAppConf } from '@/hooks/logic-hooks';
|
||||
import { RefreshCcw } from 'lucide-react';
|
||||
import { PropsWithChildren } from 'react';
|
||||
import { RAGFlowAvatar } from './ragflow-avatar';
|
||||
import { Button } from './ui/button';
|
||||
|
||||
type EmbedContainerProps = {
|
||||
title: string;
|
||||
avatar?: string;
|
||||
handleReset?(): void;
|
||||
} & PropsWithChildren;
|
||||
|
||||
export function EmbedContainer({
|
||||
title,
|
||||
avatar,
|
||||
children,
|
||||
handleReset,
|
||||
}: EmbedContainerProps) {
|
||||
const appConf = useFetchAppConf();
|
||||
|
||||
return (
|
||||
<section className="h-[100vh] flex justify-center items-center">
|
||||
<div className="w-40 flex gap-2 absolute left-3 top-12 items-center">
|
||||
<img src="/logo.svg" alt="" />
|
||||
<span className="text-2xl font-bold">{appConf.appName}</span>
|
||||
</div>
|
||||
<div className=" w-[80vw] border rounded-lg">
|
||||
<div className="flex justify-between items-center border-b p-3">
|
||||
<div className="flex gap-2 items-center">
|
||||
<RAGFlowAvatar avatar={avatar} name={title} isPerson />
|
||||
<div className="text-xl text-foreground">{title}</div>
|
||||
</div>
|
||||
<Button
|
||||
variant={'secondary'}
|
||||
className="text-sm text-foreground cursor-pointer"
|
||||
onClick={handleReset}
|
||||
>
|
||||
<div className="flex gap-1 items-center">
|
||||
<RefreshCcw size={14} />
|
||||
<span className="text-lg ">Reset</span>
|
||||
</div>
|
||||
</Button>
|
||||
</div>
|
||||
{children}
|
||||
</div>
|
||||
</section>
|
||||
);
|
||||
}
|
||||
@ -23,6 +23,7 @@ import {
|
||||
} from '@/constants/common';
|
||||
import { useTranslate } from '@/hooks/common-hooks';
|
||||
import { IModalProps } from '@/interfaces/common';
|
||||
import { Routes } from '@/routes';
|
||||
import { zodResolver } from '@hookform/resolvers/zod';
|
||||
import { memo, useCallback, useMemo } from 'react';
|
||||
import { useForm, useWatch } from 'react-hook-form';
|
||||
@ -68,7 +69,7 @@ function EmbedDialog({
|
||||
|
||||
const generateIframeSrc = useCallback(() => {
|
||||
const { visibleAvatar, locale } = values;
|
||||
let src = `${location.origin}/next-chat/share?shared_id=${token}&from=${from}&auth=${beta}`;
|
||||
let src = `${location.origin}${from === SharedFrom.Agent ? Routes.AgentShare : Routes.ChatShare}?shared_id=${token}&from=${from}&auth=${beta}`;
|
||||
if (visibleAvatar) {
|
||||
src += '&visible_avatar=1';
|
||||
}
|
||||
87
web/src/components/embed-dialog/use-show-embed-dialog.ts
Normal file
87
web/src/components/embed-dialog/use-show-embed-dialog.ts
Normal file
@ -0,0 +1,87 @@
|
||||
import { useSetModalState, useTranslate } from '@/hooks/common-hooks';
|
||||
import { useFetchManualSystemTokenList } from '@/hooks/user-setting-hooks';
|
||||
import { useCallback } from 'react';
|
||||
import message from '../ui/message';
|
||||
|
||||
export const useShowTokenEmptyError = () => {
|
||||
const { t } = useTranslate('chat');
|
||||
|
||||
const showTokenEmptyError = useCallback(() => {
|
||||
message.error(t('tokenError'));
|
||||
}, [t]);
|
||||
return { showTokenEmptyError };
|
||||
};
|
||||
|
||||
export const useShowBetaEmptyError = () => {
|
||||
const { t } = useTranslate('chat');
|
||||
|
||||
const showBetaEmptyError = useCallback(() => {
|
||||
message.error(t('betaError'));
|
||||
}, [t]);
|
||||
return { showBetaEmptyError };
|
||||
};
|
||||
|
||||
export const useFetchTokenListBeforeOtherStep = () => {
|
||||
const { showTokenEmptyError } = useShowTokenEmptyError();
|
||||
const { showBetaEmptyError } = useShowBetaEmptyError();
|
||||
|
||||
const { data: tokenList, fetchSystemTokenList } =
|
||||
useFetchManualSystemTokenList();
|
||||
|
||||
let token = '',
|
||||
beta = '';
|
||||
|
||||
if (Array.isArray(tokenList) && tokenList.length > 0) {
|
||||
token = tokenList[0].token;
|
||||
beta = tokenList[0].beta;
|
||||
}
|
||||
|
||||
token =
|
||||
Array.isArray(tokenList) && tokenList.length > 0 ? tokenList[0].token : '';
|
||||
|
||||
const handleOperate = useCallback(async () => {
|
||||
const ret = await fetchSystemTokenList();
|
||||
const list = ret;
|
||||
if (Array.isArray(list) && list.length > 0) {
|
||||
if (!list[0].beta) {
|
||||
showBetaEmptyError();
|
||||
return false;
|
||||
}
|
||||
return list[0]?.token;
|
||||
} else {
|
||||
showTokenEmptyError();
|
||||
return false;
|
||||
}
|
||||
}, [fetchSystemTokenList, showBetaEmptyError, showTokenEmptyError]);
|
||||
|
||||
return {
|
||||
token,
|
||||
beta,
|
||||
handleOperate,
|
||||
};
|
||||
};
|
||||
|
||||
export const useShowEmbedModal = () => {
|
||||
const {
|
||||
visible: embedVisible,
|
||||
hideModal: hideEmbedModal,
|
||||
showModal: showEmbedModal,
|
||||
} = useSetModalState();
|
||||
|
||||
const { handleOperate, token, beta } = useFetchTokenListBeforeOtherStep();
|
||||
|
||||
const handleShowEmbedModal = useCallback(async () => {
|
||||
const succeed = await handleOperate();
|
||||
if (succeed) {
|
||||
showEmbedModal();
|
||||
}
|
||||
}, [handleOperate, showEmbedModal]);
|
||||
|
||||
return {
|
||||
showEmbedModal: handleShowEmbedModal,
|
||||
hideEmbedModal,
|
||||
embedVisible,
|
||||
embedToken: token,
|
||||
beta,
|
||||
};
|
||||
};
|
||||
@ -25,10 +25,10 @@ export function ExcelToHtmlFormField() {
|
||||
|
||||
return (
|
||||
<FormItem defaultChecked={false} className=" items-center space-y-0 ">
|
||||
<div className="flex items-center">
|
||||
<div className="flex items-center gap-1">
|
||||
<FormLabel
|
||||
tooltip={t('html4excelTip')}
|
||||
className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
|
||||
className="text-sm text-muted-foreground whitespace-break-spaces w-1/4"
|
||||
>
|
||||
{t('html4excel')}
|
||||
</FormLabel>
|
||||
|
||||
54
web/src/components/home-card.tsx
Normal file
54
web/src/components/home-card.tsx
Normal file
@ -0,0 +1,54 @@
|
||||
import { RAGFlowAvatar } from '@/components/ragflow-avatar';
|
||||
import { Card, CardContent } from '@/components/ui/card';
|
||||
import { formatDate } from '@/utils/date';
|
||||
|
||||
interface IProps {
|
||||
data: {
|
||||
name: string;
|
||||
description?: string;
|
||||
avatar?: string;
|
||||
update_time?: string | number;
|
||||
};
|
||||
onClick?: () => void;
|
||||
moreDropdown: React.ReactNode;
|
||||
}
|
||||
export function HomeCard({ data, onClick, moreDropdown }: IProps) {
|
||||
return (
|
||||
<Card
|
||||
className="bg-bg-card border-colors-outline-neutral-standard"
|
||||
onClick={() => {
|
||||
// navigateToSearch(data?.id);
|
||||
onClick?.();
|
||||
}}
|
||||
>
|
||||
<CardContent className="p-4 flex gap-2 items-start group h-full">
|
||||
<div className="flex justify-between mb-4">
|
||||
<RAGFlowAvatar
|
||||
className="w-[32px] h-[32px]"
|
||||
avatar={data.avatar}
|
||||
name={data.name}
|
||||
/>
|
||||
</div>
|
||||
<div className="flex flex-col justify-between gap-1 flex-1 h-full w-[calc(100%-50px)]">
|
||||
<section className="flex justify-between">
|
||||
<div className="text-[20px] font-bold w-80% leading-5">
|
||||
{data.name}
|
||||
</div>
|
||||
{moreDropdown}
|
||||
</section>
|
||||
|
||||
<section className="flex flex-col gap-1 mt-1">
|
||||
<div className="whitespace-nowrap overflow-hidden text-ellipsis">
|
||||
{data.description}
|
||||
</div>
|
||||
<div>
|
||||
<p className="text-sm opacity-80">
|
||||
{formatDate(data.update_time)}
|
||||
</p>
|
||||
</div>
|
||||
</section>
|
||||
</div>
|
||||
</CardContent>
|
||||
</Card>
|
||||
);
|
||||
}
|
||||
@ -16,7 +16,7 @@ import { Funnel } from 'lucide-react';
|
||||
import { useFormContext, useWatch } from 'react-hook-form';
|
||||
import { useTranslation } from 'react-i18next';
|
||||
import { z } from 'zod';
|
||||
import { NextLLMSelect } from './llm-select/next';
|
||||
import { NextInnerLLMSelectProps, NextLLMSelect } from './llm-select/next';
|
||||
import { Button } from './ui/button';
|
||||
|
||||
const ModelTypes = [
|
||||
@ -38,7 +38,13 @@ export const LargeModelFilterFormSchema = {
|
||||
llm_filter: z.string().optional(),
|
||||
};
|
||||
|
||||
export function LargeModelFormField() {
|
||||
type LargeModelFormFieldProps = Pick<
|
||||
NextInnerLLMSelectProps,
|
||||
'showSpeech2TextModel'
|
||||
>;
|
||||
export function LargeModelFormField({
|
||||
showSpeech2TextModel: showTTSModel,
|
||||
}: LargeModelFormFieldProps) {
|
||||
const form = useFormContext();
|
||||
const { t } = useTranslation();
|
||||
const filter = useWatch({ control: form.control, name: 'llm_filter' });
|
||||
@ -85,7 +91,11 @@ export function LargeModelFormField() {
|
||||
/>
|
||||
|
||||
<FormControl>
|
||||
<NextLLMSelect {...field} filter={filter} />
|
||||
<NextLLMSelect
|
||||
{...field}
|
||||
filter={filter}
|
||||
showSpeech2TextModel={showTTSModel}
|
||||
/>
|
||||
</FormControl>
|
||||
</section>
|
||||
|
||||
|
||||
@ -1,29 +1,41 @@
|
||||
import { LlmModelType } from '@/constants/knowledge';
|
||||
import { useComposeLlmOptionsByModelTypes } from '@/hooks/llm-hooks';
|
||||
import * as SelectPrimitive from '@radix-ui/react-select';
|
||||
import { forwardRef, memo, useState } from 'react';
|
||||
import { forwardRef, memo, useMemo, useState } from 'react';
|
||||
import { LlmSettingFieldItems } from '../llm-setting-items/next';
|
||||
import { Popover, PopoverContent, PopoverTrigger } from '../ui/popover';
|
||||
import { Select, SelectTrigger, SelectValue } from '../ui/select';
|
||||
|
||||
interface IProps {
|
||||
export interface NextInnerLLMSelectProps {
|
||||
id?: string;
|
||||
value?: string;
|
||||
onInitialValue?: (value: string, option: any) => void;
|
||||
onChange?: (value: string) => void;
|
||||
disabled?: boolean;
|
||||
filter?: string;
|
||||
showSpeech2TextModel?: boolean;
|
||||
}
|
||||
|
||||
const NextInnerLLMSelect = forwardRef<
|
||||
React.ElementRef<typeof SelectPrimitive.Trigger>,
|
||||
IProps
|
||||
>(({ value, disabled, filter }, ref) => {
|
||||
NextInnerLLMSelectProps
|
||||
>(({ value, disabled, filter, showSpeech2TextModel = false }, ref) => {
|
||||
const [isPopoverOpen, setIsPopoverOpen] = useState(false);
|
||||
const modelTypes =
|
||||
filter === 'all' || filter === undefined
|
||||
? [LlmModelType.Chat, LlmModelType.Image2text]
|
||||
: [filter as LlmModelType];
|
||||
|
||||
const ttsModel = useMemo(() => {
|
||||
return showSpeech2TextModel ? [LlmModelType.Speech2text] : [];
|
||||
}, [showSpeech2TextModel]);
|
||||
|
||||
const modelTypes = useMemo(() => {
|
||||
if (filter === LlmModelType.Chat) {
|
||||
return [LlmModelType.Chat];
|
||||
} else if (filter === LlmModelType.Image2text) {
|
||||
return [LlmModelType.Image2text, ...ttsModel];
|
||||
} else {
|
||||
return [LlmModelType.Chat, LlmModelType.Image2text, ...ttsModel];
|
||||
}
|
||||
}, [filter, ttsModel]);
|
||||
|
||||
const modelOptions = useComposeLlmOptionsByModelTypes(modelTypes);
|
||||
|
||||
return (
|
||||
|
||||
@ -28,20 +28,32 @@ interface LlmSettingFieldItemsProps {
|
||||
options?: any[];
|
||||
}
|
||||
|
||||
export const LlmSettingSchema = {
|
||||
export const LLMIdFormField = {
|
||||
llm_id: z.string(),
|
||||
temperature: z.coerce.number().optional(),
|
||||
top_p: z.number().optional(),
|
||||
presence_penalty: z.coerce.number().optional(),
|
||||
frequency_penalty: z.coerce.number().optional(),
|
||||
};
|
||||
|
||||
export const LlmSettingEnabledSchema = {
|
||||
temperatureEnabled: z.boolean().optional(),
|
||||
topPEnabled: z.boolean().optional(),
|
||||
presencePenaltyEnabled: z.boolean().optional(),
|
||||
frequencyPenaltyEnabled: z.boolean().optional(),
|
||||
maxTokensEnabled: z.boolean().optional(),
|
||||
};
|
||||
|
||||
export const LlmSettingFieldSchema = {
|
||||
temperature: z.coerce.number().optional(),
|
||||
top_p: z.number().optional(),
|
||||
presence_penalty: z.coerce.number().optional(),
|
||||
frequency_penalty: z.coerce.number().optional(),
|
||||
max_tokens: z.number().optional(),
|
||||
};
|
||||
|
||||
export const LlmSettingSchema = {
|
||||
...LLMIdFormField,
|
||||
...LlmSettingFieldSchema,
|
||||
...LlmSettingEnabledSchema,
|
||||
};
|
||||
|
||||
export function LlmSettingFieldItems({
|
||||
prefix,
|
||||
options,
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
import { settledModelVariableMap } from '@/constants/knowledge';
|
||||
import { AgentFormContext } from '@/pages/agent/context';
|
||||
import useGraphStore from '@/pages/agent/store';
|
||||
import { setChatVariableEnabledFieldValuePage } from '@/utils/chat';
|
||||
import { useCallback, useContext } from 'react';
|
||||
import { useFormContext } from 'react-hook-form';
|
||||
|
||||
@ -11,6 +12,20 @@ export function useHandleFreedomChange(
|
||||
const node = useContext(AgentFormContext);
|
||||
const updateNodeForm = useGraphStore((state) => state.updateNodeForm);
|
||||
|
||||
const setLLMParameters = useCallback(
|
||||
(values: Record<string, any>, withPrefix: boolean) => {
|
||||
for (const key in values) {
|
||||
if (Object.prototype.hasOwnProperty.call(values, key)) {
|
||||
const realKey = getFieldWithPrefix(key);
|
||||
const element = values[key as keyof typeof values];
|
||||
|
||||
form.setValue(withPrefix ? realKey : key, element);
|
||||
}
|
||||
}
|
||||
},
|
||||
[form, getFieldWithPrefix],
|
||||
);
|
||||
|
||||
const handleChange = useCallback(
|
||||
(parameter: string) => {
|
||||
const currentValues = { ...form.getValues() };
|
||||
@ -25,16 +40,12 @@ export function useHandleFreedomChange(
|
||||
updateNodeForm(node?.id, nextValues);
|
||||
}
|
||||
|
||||
for (const key in values) {
|
||||
if (Object.prototype.hasOwnProperty.call(values, key)) {
|
||||
const realKey = getFieldWithPrefix(key);
|
||||
const element = values[key as keyof typeof values];
|
||||
const variableCheckBoxFieldMap = setChatVariableEnabledFieldValuePage();
|
||||
|
||||
form.setValue(realKey, element);
|
||||
}
|
||||
}
|
||||
setLLMParameters(values, true);
|
||||
setLLMParameters(variableCheckBoxFieldMap, false);
|
||||
},
|
||||
[form, getFieldWithPrefix, node?.id, updateNodeForm],
|
||||
[form, node?.id, setLLMParameters, updateNodeForm],
|
||||
);
|
||||
|
||||
return handleChange;
|
||||
|
||||
@ -14,6 +14,7 @@ import {
|
||||
} from '@/components/file-upload';
|
||||
import { Button } from '@/components/ui/button';
|
||||
import { Textarea } from '@/components/ui/textarea';
|
||||
import { cn } from '@/lib/utils';
|
||||
import { CircleStop, Paperclip, Send, Upload, X } from 'lucide-react';
|
||||
import * as React from 'react';
|
||||
import { toast } from 'sonner';
|
||||
@ -135,7 +136,11 @@ export function NextMessageInput({
|
||||
disabled={isUploading || disabled || sendLoading}
|
||||
onKeyDown={handleKeyDown}
|
||||
/>
|
||||
<div className="flex items-center justify-between gap-1.5">
|
||||
<div
|
||||
className={cn('flex items-center justify-between gap-1.5', {
|
||||
'justify-end': !showUploadIcon,
|
||||
})}
|
||||
>
|
||||
{showUploadIcon && (
|
||||
<FileUploadTrigger asChild>
|
||||
<Button
|
||||
|
||||
@ -24,7 +24,7 @@
|
||||
.messageText {
|
||||
.chunkText();
|
||||
.messageTextBase();
|
||||
background-color: #e6f4ff;
|
||||
// background-color: #e6f4ff;
|
||||
word-break: break-word;
|
||||
}
|
||||
.messageTextDark {
|
||||
|
||||
@ -9,6 +9,7 @@ import {
|
||||
useFetchDocumentThumbnailsByIds,
|
||||
} from '@/hooks/document-hooks';
|
||||
import { IRegenerateMessage, IRemoveMessageById } from '@/hooks/logic-hooks';
|
||||
import { cn } from '@/lib/utils';
|
||||
import { IMessage } from '@/pages/chat/interface';
|
||||
import MarkdownContent from '@/pages/chat/markdown-content';
|
||||
import { Avatar, Flex, Space } from 'antd';
|
||||
@ -129,13 +130,14 @@ const MessageItem = ({
|
||||
{/* <b>{isAssistant ? '' : nickname}</b> */}
|
||||
</Space>
|
||||
<div
|
||||
className={
|
||||
className={cn(
|
||||
isAssistant
|
||||
? theme === 'dark'
|
||||
? styles.messageTextDark
|
||||
: styles.messageText
|
||||
: styles.messageUserText
|
||||
}
|
||||
: styles.messageUserText,
|
||||
{ '!bg-bg-card': !isAssistant },
|
||||
)}
|
||||
>
|
||||
<MarkdownContent
|
||||
loading={loading}
|
||||
|
||||
72
web/src/components/metadata-filter/index.tsx
Normal file
72
web/src/components/metadata-filter/index.tsx
Normal file
@ -0,0 +1,72 @@
|
||||
import { DatasetMetadata } from '@/constants/chat';
|
||||
import { useTranslate } from '@/hooks/common-hooks';
|
||||
import { useFormContext, useWatch } from 'react-hook-form';
|
||||
import { z } from 'zod';
|
||||
import { SelectWithSearch } from '../originui/select-with-search';
|
||||
import { RAGFlowFormItem } from '../ragflow-form';
|
||||
import { MetadataFilterConditions } from './metadata-filter-conditions';
|
||||
|
||||
type MetadataFilterProps = {
|
||||
prefix?: string;
|
||||
};
|
||||
|
||||
export const MetadataFilterSchema = {
|
||||
meta_data_filter: z
|
||||
.object({
|
||||
method: z.string().optional(),
|
||||
manual: z
|
||||
.array(
|
||||
z.object({
|
||||
key: z.string(),
|
||||
op: z.string(),
|
||||
value: z.string(),
|
||||
}),
|
||||
)
|
||||
.optional(),
|
||||
})
|
||||
.optional(),
|
||||
};
|
||||
|
||||
export function MetadataFilter({ prefix = '' }: MetadataFilterProps) {
|
||||
const { t } = useTranslate('chat');
|
||||
const form = useFormContext();
|
||||
|
||||
const methodName = prefix + 'meta_data_filter.method';
|
||||
|
||||
const kbIds: string[] = useWatch({
|
||||
control: form.control,
|
||||
name: prefix + 'kb_ids',
|
||||
});
|
||||
const metadata = useWatch({
|
||||
control: form.control,
|
||||
name: methodName,
|
||||
});
|
||||
const hasKnowledge = Array.isArray(kbIds) && kbIds.length > 0;
|
||||
|
||||
const MetadataOptions = Object.values(DatasetMetadata).map((x) => {
|
||||
return {
|
||||
value: x,
|
||||
label: t(`meta.${x}`),
|
||||
};
|
||||
});
|
||||
|
||||
return (
|
||||
<>
|
||||
{hasKnowledge && (
|
||||
<RAGFlowFormItem
|
||||
label={t('metadata')}
|
||||
name={methodName}
|
||||
tooltip={t('metadataTip')}
|
||||
>
|
||||
<SelectWithSearch options={MetadataOptions} />
|
||||
</RAGFlowFormItem>
|
||||
)}
|
||||
{hasKnowledge && metadata === DatasetMetadata.Manual && (
|
||||
<MetadataFilterConditions
|
||||
kbIds={kbIds}
|
||||
prefix={prefix}
|
||||
></MetadataFilterConditions>
|
||||
)}
|
||||
</>
|
||||
);
|
||||
}
|
||||
@ -0,0 +1,135 @@
|
||||
import { SelectWithSearch } from '@/components/originui/select-with-search';
|
||||
import { Button } from '@/components/ui/button';
|
||||
import {
|
||||
DropdownMenu,
|
||||
DropdownMenuContent,
|
||||
DropdownMenuItem,
|
||||
DropdownMenuTrigger,
|
||||
} from '@/components/ui/dropdown-menu';
|
||||
import {
|
||||
FormControl,
|
||||
FormField,
|
||||
FormItem,
|
||||
FormLabel,
|
||||
FormMessage,
|
||||
} from '@/components/ui/form';
|
||||
import { Input } from '@/components/ui/input';
|
||||
import { Separator } from '@/components/ui/separator';
|
||||
import { useFetchKnowledgeMetadata } from '@/hooks/use-knowledge-request';
|
||||
import { SwitchOperatorOptions } from '@/pages/agent/constant';
|
||||
import { useBuildSwitchOperatorOptions } from '@/pages/agent/form/switch-form';
|
||||
import { Plus, X } from 'lucide-react';
|
||||
import { useCallback } from 'react';
|
||||
import { useFieldArray, useFormContext } from 'react-hook-form';
|
||||
import { useTranslation } from 'react-i18next';
|
||||
|
||||
export function MetadataFilterConditions({
|
||||
kbIds,
|
||||
prefix = '',
|
||||
}: {
|
||||
kbIds: string[];
|
||||
prefix?: string;
|
||||
}) {
|
||||
const { t } = useTranslation();
|
||||
const form = useFormContext();
|
||||
const name = prefix + 'meta_data_filter.manual';
|
||||
const metadata = useFetchKnowledgeMetadata(kbIds);
|
||||
|
||||
const switchOperatorOptions = useBuildSwitchOperatorOptions();
|
||||
|
||||
const { fields, remove, append } = useFieldArray({
|
||||
name,
|
||||
control: form.control,
|
||||
});
|
||||
|
||||
const add = useCallback(
|
||||
(key: string) => () => {
|
||||
append({
|
||||
key,
|
||||
value: '',
|
||||
op: SwitchOperatorOptions[0].value,
|
||||
});
|
||||
},
|
||||
[append],
|
||||
);
|
||||
|
||||
return (
|
||||
<section className="flex flex-col gap-2">
|
||||
<div className="flex items-center justify-between">
|
||||
<FormLabel>{t('chat.conditions')}</FormLabel>
|
||||
<DropdownMenu>
|
||||
<DropdownMenuTrigger>
|
||||
<Button variant={'ghost'} type="button">
|
||||
<Plus />
|
||||
</Button>
|
||||
</DropdownMenuTrigger>
|
||||
<DropdownMenuContent>
|
||||
{Object.keys(metadata.data).map((key, idx) => {
|
||||
return (
|
||||
<DropdownMenuItem key={idx} onClick={add(key)}>
|
||||
{key}
|
||||
</DropdownMenuItem>
|
||||
);
|
||||
})}
|
||||
</DropdownMenuContent>
|
||||
</DropdownMenu>
|
||||
</div>
|
||||
<div className="space-y-5">
|
||||
{fields.map((field, index) => {
|
||||
const typeField = `${name}.${index}.key`;
|
||||
return (
|
||||
<div key={field.id} className="flex w-full items-center gap-2">
|
||||
<FormField
|
||||
control={form.control}
|
||||
name={typeField}
|
||||
render={({ field }) => (
|
||||
<FormItem className="flex-1 overflow-hidden">
|
||||
<FormControl>
|
||||
<Input
|
||||
{...field}
|
||||
placeholder={t('common.pleaseInput')}
|
||||
></Input>
|
||||
</FormControl>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
<Separator className="w-3 text-text-secondary" />
|
||||
<FormField
|
||||
control={form.control}
|
||||
name={`${name}.${index}.op`}
|
||||
render={({ field }) => (
|
||||
<FormItem className="flex-1 overflow-hidden">
|
||||
<FormControl>
|
||||
<SelectWithSearch
|
||||
{...field}
|
||||
options={switchOperatorOptions}
|
||||
></SelectWithSearch>
|
||||
</FormControl>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
<Separator className="w-3 text-text-secondary" />
|
||||
<FormField
|
||||
control={form.control}
|
||||
name={`${name}.${index}.value`}
|
||||
render={({ field }) => (
|
||||
<FormItem className="flex-1 overflow-hidden">
|
||||
<FormControl>
|
||||
<Input placeholder={t('common.pleaseInput')} {...field} />
|
||||
</FormControl>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
<Button variant={'ghost'} onClick={() => remove(index)}>
|
||||
<X className="text-text-sub-title-invert " />
|
||||
</Button>
|
||||
</div>
|
||||
);
|
||||
})}
|
||||
</div>
|
||||
</section>
|
||||
);
|
||||
}
|
||||
@ -59,10 +59,10 @@ export function UseGraphRagFormField() {
|
||||
name="parser_config.graphrag.use_graphrag"
|
||||
render={({ field }) => (
|
||||
<FormItem defaultChecked={false} className=" items-center space-y-0 ">
|
||||
<div className="flex items-center">
|
||||
<div className="flex items-center gap-1">
|
||||
<FormLabel
|
||||
tooltip={t('useGraphRagTip')}
|
||||
className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
|
||||
className="text-sm text-muted-foreground whitespace-break-spaces w-1/4"
|
||||
>
|
||||
{t('useGraphRag')}
|
||||
</FormLabel>
|
||||
|
||||
@ -86,10 +86,10 @@ const RaptorFormFields = () => {
|
||||
defaultChecked={false}
|
||||
className="items-center space-y-0 "
|
||||
>
|
||||
<div className="flex items-center">
|
||||
<div className="flex items-center gap-1">
|
||||
<FormLabel
|
||||
tooltip={t('useRaptorTip')}
|
||||
className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
|
||||
className="text-sm text-muted-foreground w-1/4 whitespace-break-spaces"
|
||||
>
|
||||
{t('useRaptor')}
|
||||
</FormLabel>
|
||||
|
||||
@ -3,6 +3,13 @@ import * as AvatarPrimitive from '@radix-ui/react-avatar';
|
||||
import { forwardRef, memo, useEffect, useRef, useState } from 'react';
|
||||
import { Avatar, AvatarFallback, AvatarImage } from './ui/avatar';
|
||||
|
||||
const PREDEFINED_COLORS = [
|
||||
{ from: '#4F6DEE', to: '#67BDF9' },
|
||||
{ from: '#38A04D', to: '#93DCA2' },
|
||||
{ from: '#C35F2B', to: '#EDB395' },
|
||||
{ from: '#633897', to: '#CBA1FF' },
|
||||
];
|
||||
|
||||
const getStringHash = (str: string): number => {
|
||||
const normalized = str.trim().toLowerCase();
|
||||
let hash = 104729;
|
||||
@ -17,16 +24,12 @@ const getStringHash = (str: string): number => {
|
||||
return Math.abs(hash);
|
||||
};
|
||||
|
||||
// Generate a hash function with a fixed color
|
||||
const getColorForName = (name: string): { from: string; to: string } => {
|
||||
const hash = getStringHash(name);
|
||||
const hue = hash % 360;
|
||||
|
||||
return {
|
||||
to: `hsl(${hue}, 70%, 80%)`,
|
||||
from: `hsl(${hue}, 60%, 30%)`,
|
||||
};
|
||||
const index = hash % PREDEFINED_COLORS.length;
|
||||
return PREDEFINED_COLORS[index];
|
||||
};
|
||||
|
||||
export const RAGFlowAvatar = memo(
|
||||
forwardRef<
|
||||
React.ElementRef<typeof AvatarPrimitive.Root>,
|
||||
@ -43,13 +46,13 @@ export const RAGFlowAvatar = memo(
|
||||
if (parts.length === 1) {
|
||||
return parts[0][0].toUpperCase();
|
||||
}
|
||||
return parts[0][0].toUpperCase() + parts[1][0].toUpperCase();
|
||||
return parts[0][0].toUpperCase();
|
||||
};
|
||||
|
||||
const initials = getInitials(name);
|
||||
const { from, to } = name
|
||||
? getColorForName(name)
|
||||
: { from: 'hsl(0, 0%, 80%)', to: 'hsl(0, 0%, 30%)' };
|
||||
: { from: 'hsl(0, 0%, 30%)', to: 'hsl(0, 0%, 80%)' };
|
||||
|
||||
const fallbackRef = useRef<HTMLElement>(null);
|
||||
const [fontSize, setFontSize] = useState('0.875rem');
|
||||
@ -98,7 +101,7 @@ export const RAGFlowAvatar = memo(
|
||||
'bg-gradient-to-b',
|
||||
`from-[${from}] to-[${to}]`,
|
||||
'flex items-center justify-center',
|
||||
'text-white font-bold',
|
||||
'text-white ',
|
||||
{ 'rounded-md': !isPerson },
|
||||
)}
|
||||
style={{
|
||||
|
||||
@ -49,12 +49,12 @@ export function SliderInputFormField({
|
||||
defaultValue={defaultValue || 0}
|
||||
render={({ field }) => (
|
||||
<FormItem
|
||||
className={cn({ 'flex items-center space-y-0': isHorizontal })}
|
||||
className={cn({ 'flex items-center gap-1 space-y-0': isHorizontal })}
|
||||
>
|
||||
<FormLabel
|
||||
tooltip={tooltip}
|
||||
className={cn({
|
||||
'text-sm text-muted-foreground whitespace-nowrap w-1/4':
|
||||
'text-sm text-muted-foreground whitespace-break-spaces w-1/4':
|
||||
isHorizontal,
|
||||
})}
|
||||
>
|
||||
|
||||
@ -32,3 +32,9 @@ export enum ChatSearchParams {
|
||||
}
|
||||
|
||||
export const EmptyConversationId = 'empty';
|
||||
|
||||
export enum DatasetMetadata {
|
||||
Disabled = 'disabled',
|
||||
Automatic = 'automatic',
|
||||
Manual = 'manual',
|
||||
}
|
||||
|
||||
@ -369,22 +369,28 @@ export const useScrollToBottom = (
|
||||
return () => container.removeEventListener('scroll', handleScroll);
|
||||
}, [containerRef, checkIfUserAtBottom]);
|
||||
|
||||
// Imperative scroll function
|
||||
const scrollToBottom = useCallback(() => {
|
||||
if (containerRef?.current) {
|
||||
const container = containerRef.current;
|
||||
container.scrollTo({
|
||||
top: container.scrollHeight - container.clientHeight,
|
||||
behavior: 'smooth',
|
||||
});
|
||||
}
|
||||
}, [containerRef]);
|
||||
|
||||
useEffect(() => {
|
||||
if (!messages) return;
|
||||
if (!containerRef?.current) return;
|
||||
requestAnimationFrame(() => {
|
||||
setTimeout(() => {
|
||||
if (isAtBottomRef.current) {
|
||||
ref.current?.scrollIntoView({ behavior: 'smooth' });
|
||||
scrollToBottom();
|
||||
}
|
||||
}, 30);
|
||||
}, 100);
|
||||
});
|
||||
}, [messages, containerRef]);
|
||||
|
||||
// Imperative scroll function
|
||||
const scrollToBottom = useCallback(() => {
|
||||
ref.current?.scrollIntoView({ behavior: 'smooth' });
|
||||
}, []);
|
||||
}, [messages, containerRef, scrollToBottom]);
|
||||
|
||||
return { scrollRef: ref, isAtBottom, scrollToBottom };
|
||||
};
|
||||
@ -551,6 +557,15 @@ export const useSelectDerivedMessages = () => {
|
||||
setDerivedMessages([]);
|
||||
}, [setDerivedMessages]);
|
||||
|
||||
const removeAllMessagesExceptFirst = useCallback(() => {
|
||||
setDerivedMessages((list) => {
|
||||
if (list.length <= 1) {
|
||||
return list;
|
||||
}
|
||||
return list.slice(0, 1);
|
||||
});
|
||||
}, [setDerivedMessages]);
|
||||
|
||||
return {
|
||||
scrollRef,
|
||||
messageContainerRef,
|
||||
@ -565,6 +580,7 @@ export const useSelectDerivedMessages = () => {
|
||||
removeMessagesAfterCurrentMessage,
|
||||
removeAllMessages,
|
||||
scrollToBottom,
|
||||
removeAllMessagesExceptFirst,
|
||||
};
|
||||
};
|
||||
|
||||
|
||||
@ -24,13 +24,17 @@ export const useNavigatePage = () => {
|
||||
);
|
||||
|
||||
const navigateToHome = useCallback(() => {
|
||||
navigate(Routes.Home);
|
||||
navigate(Routes.Root);
|
||||
}, [navigate]);
|
||||
|
||||
const navigateToProfile = useCallback(() => {
|
||||
navigate(Routes.ProfileSetting);
|
||||
}, [navigate]);
|
||||
|
||||
const navigateToOldProfile = useCallback(() => {
|
||||
navigate(Routes.UserSetting);
|
||||
}, [navigate]);
|
||||
|
||||
const navigateToChatList = useCallback(() => {
|
||||
navigate(Routes.Chats);
|
||||
}, [navigate]);
|
||||
@ -139,5 +143,6 @@ export const useNavigatePage = () => {
|
||||
navigateToSearch,
|
||||
navigateToFiles,
|
||||
navigateToAgentList,
|
||||
navigateToOldProfile,
|
||||
};
|
||||
};
|
||||
|
||||
@ -1,6 +1,10 @@
|
||||
import message from '@/components/ui/message';
|
||||
import { ChatSearchParams } from '@/constants/chat';
|
||||
import { IConversation, IDialog } from '@/interfaces/database/chat';
|
||||
import {
|
||||
IConversation,
|
||||
IDialog,
|
||||
IExternalChatInfo,
|
||||
} from '@/interfaces/database/chat';
|
||||
import { IAskRequestBody } from '@/interfaces/request/chat';
|
||||
import { IClientConversation } from '@/pages/next-chats/chat/interface';
|
||||
import { useGetSharedChatSearchParams } from '@/pages/next-chats/hooks/use-send-shared-message';
|
||||
@ -32,6 +36,7 @@ export const enum ChatApiAction {
|
||||
FetchMindMap = 'fetchMindMap',
|
||||
FetchRelatedQuestions = 'fetchRelatedQuestions',
|
||||
UploadAndParse = 'upload_and_parse',
|
||||
FetchExternalChatInfo = 'fetchExternalChatInfo',
|
||||
}
|
||||
|
||||
export const useGetChatSearchParams = () => {
|
||||
@ -418,6 +423,29 @@ export function useUploadAndParseFile() {
|
||||
return { data, loading, uploadAndParseFile: mutateAsync };
|
||||
}
|
||||
|
||||
export const useFetchExternalChatInfo = () => {
|
||||
const { sharedId: id } = useGetSharedChatSearchParams();
|
||||
|
||||
const {
|
||||
data,
|
||||
isFetching: loading,
|
||||
refetch,
|
||||
} = useQuery<IExternalChatInfo>({
|
||||
queryKey: [ChatApiAction.FetchExternalChatInfo, id],
|
||||
gcTime: 0,
|
||||
initialData: {} as IExternalChatInfo,
|
||||
enabled: !!id,
|
||||
refetchOnWindowFocus: false,
|
||||
queryFn: async () => {
|
||||
const { data } = await chatService.fetchExternalChatInfo(id!);
|
||||
|
||||
return data?.data;
|
||||
},
|
||||
});
|
||||
|
||||
return { data, loading, refetch };
|
||||
};
|
||||
|
||||
//#endregion
|
||||
|
||||
//#region search page
|
||||
|
||||
@ -172,3 +172,9 @@ export interface IStats {
|
||||
round: [string, number][];
|
||||
thumb_up: [string, number][];
|
||||
}
|
||||
|
||||
export interface IExternalChatInfo {
|
||||
avatar?: string;
|
||||
title: string;
|
||||
prologue?: string;
|
||||
}
|
||||
|
||||
@ -7,4 +7,5 @@ export interface IFeedbackRequestBody {
|
||||
export interface IAskRequestBody {
|
||||
question: string;
|
||||
kb_ids: string[];
|
||||
search_id?: string;
|
||||
}
|
||||
|
||||
@ -1,6 +1,5 @@
|
||||
import { RAGFlowAvatar } from '@/components/ragflow-avatar';
|
||||
import { useTheme } from '@/components/theme-provider';
|
||||
import { Badge } from '@/components/ui/badge';
|
||||
import { Button } from '@/components/ui/button';
|
||||
import {
|
||||
DropdownMenu,
|
||||
@ -41,7 +40,7 @@ export function Header() {
|
||||
const { t } = useTranslation();
|
||||
const { pathname } = useLocation();
|
||||
const navigate = useNavigateWithFromState();
|
||||
const { navigateToProfile } = useNavigatePage();
|
||||
const { navigateToOldProfile } = useNavigatePage();
|
||||
|
||||
const changeLanguage = useChangeLanguage();
|
||||
const { setTheme, theme } = useTheme();
|
||||
@ -75,8 +74,8 @@ export function Header() {
|
||||
|
||||
const tagsData = useMemo(
|
||||
() => [
|
||||
{ path: Routes.Home, name: t('header.home'), icon: House },
|
||||
{ path: Routes.Datasets, name: t('header.knowledgeBase'), icon: Library },
|
||||
{ path: Routes.Root, name: t('header.Root'), icon: House },
|
||||
{ path: Routes.Datasets, name: t('header.dataset'), icon: Library },
|
||||
{ path: Routes.Chats, name: t('header.chat'), icon: MessageSquareText },
|
||||
{ path: Routes.Searches, name: t('header.search'), icon: Search },
|
||||
{ path: Routes.Agents, name: t('header.flow'), icon: Cpu },
|
||||
@ -91,7 +90,7 @@ export function Header() {
|
||||
|
||||
return {
|
||||
label:
|
||||
tag.path === Routes.Home ? (
|
||||
tag.path === Routes.Root ? (
|
||||
<HeaderIcon className="size-6"></HeaderIcon>
|
||||
) : (
|
||||
<span>{tag.name}</span>
|
||||
@ -101,18 +100,18 @@ export function Header() {
|
||||
});
|
||||
}, [tagsData]);
|
||||
|
||||
const currentPath = useMemo(() => {
|
||||
return (
|
||||
tagsData.find((x) => pathname.startsWith(x.path))?.path || Routes.Home
|
||||
);
|
||||
}, [pathname, tagsData]);
|
||||
// const currentPath = useMemo(() => {
|
||||
// return (
|
||||
// tagsData.find((x) => pathname.startsWith(x.path))?.path || Routes.Root
|
||||
// );
|
||||
// }, [pathname, tagsData]);
|
||||
|
||||
const handleChange = (path: SegmentedValue) => {
|
||||
navigate(path as Routes);
|
||||
};
|
||||
|
||||
const handleLogoClick = useCallback(() => {
|
||||
navigate(Routes.Home);
|
||||
navigate(Routes.Root);
|
||||
}, [navigate]);
|
||||
|
||||
return (
|
||||
@ -124,14 +123,19 @@ export function Header() {
|
||||
className="size-10 mr-[12]"
|
||||
onClick={handleLogoClick}
|
||||
/>
|
||||
<div className="flex items-center gap-1.5 text-text-secondary">
|
||||
<Github className="size-3.5" />
|
||||
<span className=" text-base">21.5k stars</span>
|
||||
</div>
|
||||
<a
|
||||
className="flex items-center gap-1.5 text-text-secondary"
|
||||
target="_blank"
|
||||
href="https://github.com/infiniflow/ragflow"
|
||||
rel="noreferrer"
|
||||
>
|
||||
<Github className="size-4" />
|
||||
{/* <span className=" text-base">21.5k stars</span> */}
|
||||
</a>
|
||||
</div>
|
||||
<Segmented
|
||||
options={options}
|
||||
value={currentPath}
|
||||
value={pathname}
|
||||
onChange={handleChange}
|
||||
></Segmented>
|
||||
<div className="flex items-center gap-5 text-text-badge">
|
||||
@ -161,11 +165,12 @@ export function Header() {
|
||||
name={nickname}
|
||||
avatar={avatar}
|
||||
className="size-8 cursor-pointer"
|
||||
onClick={navigateToProfile}
|
||||
onClick={navigateToOldProfile}
|
||||
></RAGFlowAvatar>
|
||||
<Badge className="h-5 w-8 absolute font-normal p-0 justify-center -right-8 -top-2 text-bg-base bg-gradient-to-l from-[#42D7E7] to-[#478AF5]">
|
||||
{/* Temporarily hidden */}
|
||||
{/* <Badge className="h-5 w-8 absolute font-normal p-0 justify-center -right-8 -top-2 text-bg-base bg-gradient-to-l from-[#42D7E7] to-[#478AF5]">
|
||||
Pro
|
||||
</Badge>
|
||||
</Badge> */}
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
@ -5,6 +5,7 @@ export default {
|
||||
deleteModalTitle: 'Are you sure to delete this item?',
|
||||
ok: 'Yes',
|
||||
cancel: 'No',
|
||||
no: 'No',
|
||||
total: 'Total',
|
||||
rename: 'Rename',
|
||||
name: 'Name',
|
||||
@ -80,6 +81,7 @@ export default {
|
||||
flow: 'Agent',
|
||||
search: 'Search',
|
||||
welcome: 'Welcome to',
|
||||
dataset: 'Dataset',
|
||||
},
|
||||
knowledgeList: {
|
||||
welcome: 'Welcome back',
|
||||
@ -575,6 +577,8 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
|
||||
automatic: 'Automatic',
|
||||
manual: 'Manual',
|
||||
},
|
||||
cancel: 'Cancel',
|
||||
chatSetting: 'Chat setting',
|
||||
},
|
||||
setting: {
|
||||
profile: 'Profile',
|
||||
@ -1419,6 +1423,26 @@ This delimiter is used to split the input text into several text pieces echo of
|
||||
search: {
|
||||
createSearch: 'Create Search',
|
||||
searchGreeting: 'How can I help you today ？',
|
||||
profile: 'Hide Profile',
|
||||
locale: 'Locale',
|
||||
embedCode: 'Embed code',
|
||||
id: 'ID',
|
||||
copySuccess: 'Copy Success',
|
||||
welcomeBack: 'Welcome back',
|
||||
searchSettings: 'Search Settings',
|
||||
name: 'Name',
|
||||
avatar: 'Avatar',
|
||||
description: 'Description',
|
||||
datasets: 'Datasets',
|
||||
rerankModel: 'Rerank Model',
|
||||
AISummary: 'AI Summary',
|
||||
enableWebSearch: 'Enable Web Search',
|
||||
enableRelatedSearch: 'Enable Related Search',
|
||||
showQueryMindmap: 'Show Query Mindmap',
|
||||
embedApp: 'Embed App',
|
||||
relatedSearch: 'Related Search',
|
||||
okText: 'Save',
|
||||
cancelText: 'Cancel',
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
@ -1192,6 +1192,12 @@ export default {
|
||||
search: {
|
||||
createSearch: '新建查詢',
|
||||
searchGreeting: '今天我能為你做些什麽？',
|
||||
profile: '隱藏個人資料',
|
||||
locale: '語言',
|
||||
embedCode: '嵌入代碼',
|
||||
id: 'ID',
|
||||
copySuccess: '複製成功',
|
||||
welcomeBack: '歡迎回來',
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
@ -73,6 +73,7 @@ export default {
|
||||
flow: 'Agent',
|
||||
search: '搜索',
|
||||
welcome: '欢迎来到',
|
||||
dataset: '数据集',
|
||||
},
|
||||
knowledgeList: {
|
||||
welcome: '欢迎回来',
|
||||
@ -569,6 +570,8 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
|
||||
automatic: '自动',
|
||||
manual: '手动',
|
||||
},
|
||||
cancel: '取消',
|
||||
chatSetting: '聊天设置',
|
||||
},
|
||||
setting: {
|
||||
profile: '概要',
|
||||
@ -1323,6 +1326,26 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
|
||||
search: {
|
||||
createSearch: '新建查询',
|
||||
searchGreeting: '今天我能为你做些什么？',
|
||||
profile: '隐藏个人资料',
|
||||
locale: '语言',
|
||||
embedCode: '嵌入代码',
|
||||
id: 'ID',
|
||||
copySuccess: '复制成功',
|
||||
welcomeBack: '欢迎回来',
|
||||
searchSettings: '搜索设置',
|
||||
name: '姓名',
|
||||
avatar: '头像',
|
||||
description: '描述',
|
||||
datasets: '数据集',
|
||||
rerankModel: 'rerank 模型',
|
||||
AISummary: 'AI 总结',
|
||||
enableWebSearch: '启用网页搜索',
|
||||
enableRelatedSearch: '启用相关搜索',
|
||||
showQueryMindmap: '显示查询思维导图',
|
||||
embedApp: '嵌入网站',
|
||||
relatedSearch: '相关搜索',
|
||||
okText: '保存',
|
||||
cancelText: '返回',
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
@ -242,7 +242,7 @@ export function InnerNextStepDropdown({
|
||||
}}
|
||||
onClick={(e) => e.stopPropagation()}
|
||||
>
|
||||
<div className="w-[300px] font-semibold bg-white border border-border rounded-md shadow-lg">
|
||||
<div className="w-[300px] font-semibold bg-bg-base border border-border rounded-md shadow-lg">
|
||||
<div className="px-3 py-2 border-b border-border">
|
||||
<div className="text-sm font-medium">Next Step</div>
|
||||
</div>
|
||||
|
||||
@ -128,7 +128,7 @@ function AgentForm({ node }: INextOperatorForm) {
|
||||
<FormWrapper>
|
||||
<FormContainer>
|
||||
{isSubAgent && <DescriptionField></DescriptionField>}
|
||||
<LargeModelFormField></LargeModelFormField>
|
||||
<LargeModelFormField showSpeech2TextModel></LargeModelFormField>
|
||||
{findLlmByUuid(llmId)?.model_type === LlmModelType.Image2text && (
|
||||
<QueryVariable
|
||||
name="visual_files_var"
|
||||
|
||||
@ -3,7 +3,6 @@ import { useCallback } from 'react';
|
||||
import { z } from 'zod';
|
||||
|
||||
export const ExeSQLFormSchema = {
|
||||
sql: z.string(),
|
||||
db_type: z.string().min(1),
|
||||
database: z.string().min(1),
|
||||
username: z.string().min(1),
|
||||
@ -14,7 +13,7 @@ export const ExeSQLFormSchema = {
|
||||
};
|
||||
|
||||
export const FormSchema = z.object({
|
||||
query: z.string().optional(),
|
||||
sql: z.string().optional(),
|
||||
...ExeSQLFormSchema,
|
||||
});
|
||||
|
||||
|
||||
@ -25,11 +25,13 @@ const ExeSQLForm = () => {
|
||||
defaultValues: defaultValues as FormType,
|
||||
});
|
||||
|
||||
const onError = (error: any) => console.log(error);
|
||||
|
||||
useWatchFormChange(form);
|
||||
|
||||
return (
|
||||
<Form {...form}>
|
||||
<FormWrapper onSubmit={form.handleSubmit(onSubmit)}>
|
||||
<FormWrapper onSubmit={form.handleSubmit(onSubmit, onError)}>
|
||||
<ExeSQLFormWidgets loading={loading}></ExeSQLFormWidgets>
|
||||
</FormWrapper>
|
||||
</Form>
|
||||
|
||||
@ -54,6 +54,8 @@ export function useAgentToolInitialValues() {
|
||||
return pick(initialValues, 'top_n');
|
||||
case Operator.WenCai:
|
||||
return pick(initialValues, 'top_n', 'query_type');
|
||||
case Operator.Code:
|
||||
return {};
|
||||
|
||||
default:
|
||||
return initialValues;
|
||||
|
||||
65
web/src/pages/agent/hooks/use-send-shared-message.ts
Normal file
65
web/src/pages/agent/hooks/use-send-shared-message.ts
Normal file
@ -0,0 +1,65 @@
|
||||
import { SharedFrom } from '@/constants/chat';
|
||||
import { useSetModalState } from '@/hooks/common-hooks';
|
||||
import { IEventList } from '@/hooks/use-send-message';
|
||||
import { useSendAgentMessage } from '@/pages/agent/chat/use-send-agent-message';
|
||||
import trim from 'lodash/trim';
|
||||
import { useCallback, useState } from 'react';
|
||||
import { useSearchParams } from 'umi';
|
||||
|
||||
export const useSendButtonDisabled = (value: string) => {
|
||||
return trim(value) === '';
|
||||
};
|
||||
|
||||
export const useGetSharedChatSearchParams = () => {
|
||||
const [searchParams] = useSearchParams();
|
||||
const data_prefix = 'data_';
|
||||
const data = Object.fromEntries(
|
||||
searchParams
|
||||
.entries()
|
||||
.filter(([key]) => key.startsWith(data_prefix))
|
||||
.map(([key, value]) => [key.replace(data_prefix, ''), value]),
|
||||
);
|
||||
return {
|
||||
from: searchParams.get('from') as SharedFrom,
|
||||
sharedId: searchParams.get('shared_id'),
|
||||
locale: searchParams.get('locale'),
|
||||
data: data,
|
||||
visibleAvatar: searchParams.get('visible_avatar')
|
||||
? searchParams.get('visible_avatar') !== '1'
|
||||
: true,
|
||||
};
|
||||
};
|
||||
|
||||
export const useSendNextSharedMessage = (
|
||||
addEventList: (data: IEventList, messageId: string) => void,
|
||||
) => {
|
||||
const { from, sharedId: conversationId } = useGetSharedChatSearchParams();
|
||||
const url = `/api/v1/${from === SharedFrom.Agent ? 'agentbots' : 'chatbots'}/${conversationId}/completions`;
|
||||
|
||||
const [params, setParams] = useState<any[]>([]);
|
||||
|
||||
const {
|
||||
visible: parameterDialogVisible,
|
||||
hideModal: hideParameterDialog,
|
||||
showModal: showParameterDialog,
|
||||
} = useSetModalState();
|
||||
|
||||
const ret = useSendAgentMessage(url, addEventList, params);
|
||||
|
||||
const ok = useCallback(
|
||||
(params: any[]) => {
|
||||
setParams(params);
|
||||
hideParameterDialog();
|
||||
},
|
||||
[hideParameterDialog],
|
||||
);
|
||||
|
||||
return {
|
||||
...ret,
|
||||
hasError: false,
|
||||
parameterDialogVisible,
|
||||
hideParameterDialog,
|
||||
showParameterDialog,
|
||||
ok,
|
||||
};
|
||||
};
|
||||
@ -1,18 +1,13 @@
|
||||
import { useFetchTokenListBeforeOtherStep } from '@/components/embed-dialog/use-show-embed-dialog';
|
||||
import { SharedFrom } from '@/constants/chat';
|
||||
import {
|
||||
useSetModalState,
|
||||
useShowDeleteConfirm,
|
||||
useTranslate,
|
||||
} from '@/hooks/common-hooks';
|
||||
import { useShowDeleteConfirm } from '@/hooks/common-hooks';
|
||||
import {
|
||||
useCreateSystemToken,
|
||||
useFetchManualSystemTokenList,
|
||||
useFetchSystemTokenList,
|
||||
useRemoveSystemToken,
|
||||
} from '@/hooks/user-setting-hooks';
|
||||
import { IStats } from '@/interfaces/database/chat';
|
||||
import { useQueryClient } from '@tanstack/react-query';
|
||||
import { message } from 'antd';
|
||||
import { useCallback } from 'react';
|
||||
|
||||
export const useOperateApiKey = (idKey: string, dialogId?: string) => {
|
||||
@ -62,94 +57,11 @@ export const useSelectChartStatsList = (): ChartStatsType => {
|
||||
}, {} as ChartStatsType);
|
||||
};
|
||||
|
||||
export const useShowTokenEmptyError = () => {
|
||||
const { t } = useTranslate('chat');
|
||||
|
||||
const showTokenEmptyError = useCallback(() => {
|
||||
message.error(t('tokenError'));
|
||||
}, [t]);
|
||||
return { showTokenEmptyError };
|
||||
};
|
||||
|
||||
export const useShowBetaEmptyError = () => {
|
||||
const { t } = useTranslate('chat');
|
||||
|
||||
const showBetaEmptyError = useCallback(() => {
|
||||
message.error(t('betaError'));
|
||||
}, [t]);
|
||||
return { showBetaEmptyError };
|
||||
};
|
||||
|
||||
const getUrlWithToken = (token: string, from: string = 'chat') => {
|
||||
const { protocol, host } = window.location;
|
||||
return `${protocol}//${host}/chat/share?shared_id=${token}&from=${from}`;
|
||||
};
|
||||
|
||||
export const useFetchTokenListBeforeOtherStep = () => {
|
||||
const { showTokenEmptyError } = useShowTokenEmptyError();
|
||||
const { showBetaEmptyError } = useShowBetaEmptyError();
|
||||
|
||||
const { data: tokenList, fetchSystemTokenList } =
|
||||
useFetchManualSystemTokenList();
|
||||
|
||||
let token = '',
|
||||
beta = '';
|
||||
|
||||
if (Array.isArray(tokenList) && tokenList.length > 0) {
|
||||
token = tokenList[0].token;
|
||||
beta = tokenList[0].beta;
|
||||
}
|
||||
|
||||
token =
|
||||
Array.isArray(tokenList) && tokenList.length > 0 ? tokenList[0].token : '';
|
||||
|
||||
const handleOperate = useCallback(async () => {
|
||||
const ret = await fetchSystemTokenList();
|
||||
const list = ret;
|
||||
if (Array.isArray(list) && list.length > 0) {
|
||||
if (!list[0].beta) {
|
||||
showBetaEmptyError();
|
||||
return false;
|
||||
}
|
||||
return list[0]?.token;
|
||||
} else {
|
||||
showTokenEmptyError();
|
||||
return false;
|
||||
}
|
||||
}, [fetchSystemTokenList, showBetaEmptyError, showTokenEmptyError]);
|
||||
|
||||
return {
|
||||
token,
|
||||
beta,
|
||||
handleOperate,
|
||||
};
|
||||
};
|
||||
|
||||
export const useShowEmbedModal = () => {
|
||||
const {
|
||||
visible: embedVisible,
|
||||
hideModal: hideEmbedModal,
|
||||
showModal: showEmbedModal,
|
||||
} = useSetModalState();
|
||||
|
||||
const { handleOperate, token, beta } = useFetchTokenListBeforeOtherStep();
|
||||
|
||||
const handleShowEmbedModal = useCallback(async () => {
|
||||
const succeed = await handleOperate();
|
||||
if (succeed) {
|
||||
showEmbedModal();
|
||||
}
|
||||
}, [handleOperate, showEmbedModal]);
|
||||
|
||||
return {
|
||||
showEmbedModal: handleShowEmbedModal,
|
||||
hideEmbedModal,
|
||||
embedVisible,
|
||||
embedToken: token,
|
||||
beta,
|
||||
};
|
||||
};
|
||||
|
||||
export const usePreviewChat = (idKey: string) => {
|
||||
const { handleOperate } = useFetchTokenListBeforeOtherStep();
|
||||
|
||||
|
||||
@ -23,8 +23,13 @@ export const useShowFormDrawer = () => {
|
||||
|
||||
const handleShow = useCallback(
|
||||
(e: React.MouseEvent<Element>, nodeId: string) => {
|
||||
const tool = get(e.target, 'dataset.tool');
|
||||
// TODO: Operator type judgment should be used
|
||||
if (nodeId.startsWith(Operator.Tool) && !tool) {
|
||||
return;
|
||||
}
|
||||
setClickedNodeId(nodeId);
|
||||
setClickedToolId(get(e.target, 'dataset.tool'));
|
||||
setClickedToolId(tool);
|
||||
showFormDrawer();
|
||||
},
|
||||
[setClickedNodeId, setClickedToolId, showFormDrawer],
|
||||
|
||||
@ -1,3 +1,5 @@
|
||||
import EmbedDialog from '@/components/embed-dialog';
|
||||
import { useShowEmbedModal } from '@/components/embed-dialog/use-show-embed-dialog';
|
||||
import { PageHeader } from '@/components/page-header';
|
||||
import {
|
||||
Breadcrumb,
|
||||
@ -35,7 +37,6 @@ import { useTranslation } from 'react-i18next';
|
||||
import { useParams } from 'umi';
|
||||
import AgentCanvas from './canvas';
|
||||
import { DropdownProvider } from './canvas/context';
|
||||
import EmbedDialog from './embed-dialog';
|
||||
import { useHandleExportOrImportJsonFile } from './hooks/use-export-json';
|
||||
import { useFetchDataOnMount } from './hooks/use-fetch-data';
|
||||
import { useGetBeginNodeDataInputs } from './hooks/use-get-begin-query';
|
||||
@ -44,7 +45,6 @@ import {
|
||||
useSaveGraphBeforeOpeningDebugDrawer,
|
||||
useWatchAgentChange,
|
||||
} from './hooks/use-save-graph';
|
||||
import { useShowEmbedModal } from './hooks/use-show-dialog';
|
||||
import { SettingDialog } from './setting-dialog';
|
||||
import { UploadAgentDialog } from './upload-agent-dialog';
|
||||
import { useAgentHistoryManager } from './use-agent-history-manager';
|
||||
@ -63,7 +63,7 @@ function AgentDropdownMenuItem({
|
||||
|
||||
export default function Agent() {
|
||||
const { id } = useParams();
|
||||
const { navigateToAgentList } = useNavigatePage();
|
||||
const { navigateToAgents } = useNavigatePage();
|
||||
const {
|
||||
visible: chatDrawerVisible,
|
||||
hideModal: hideChatDrawer,
|
||||
@ -113,7 +113,7 @@ export default function Agent() {
|
||||
<Breadcrumb>
|
||||
<BreadcrumbList>
|
||||
<BreadcrumbItem>
|
||||
<BreadcrumbLink onClick={navigateToAgentList}>
|
||||
<BreadcrumbLink onClick={navigateToAgents}>
|
||||
Agent
|
||||
</BreadcrumbLink>
|
||||
</BreadcrumbItem>
|
||||
|
||||
@ -158,8 +158,9 @@ const ToolTimelineItem = ({
|
||||
</span>
|
||||
)}
|
||||
<span className="text-text-secondary text-xs">
|
||||
{/* 0:00
|
||||
{x.data.elapsed_time?.toString().slice(0, 6)} */}
|
||||
{/* 0:00*/}
|
||||
{tool.elapsed_time?.toString().slice(0, 6) || ''}
|
||||
{tool.elapsed_time ? 's' : ''}
|
||||
</span>
|
||||
<span
|
||||
className={cn(
|
||||
|
||||
@ -153,6 +153,22 @@ export const WorkFlowTimeline = ({
|
||||
}, []);
|
||||
}, [currentEventListWithoutMessage, sendLoading]);
|
||||
|
||||
const getElapsedTime = (nodeId: string) => {
|
||||
if (nodeId === 'begin') {
|
||||
return '';
|
||||
}
|
||||
const data = currentEventListWithoutMessage?.find((x) => {
|
||||
return (
|
||||
x.data.component_id === nodeId &&
|
||||
x.event === MessageEventType.NodeFinished
|
||||
);
|
||||
});
|
||||
if (!data || data?.data.elapsed_time < 0.000001) {
|
||||
return '';
|
||||
}
|
||||
return data?.data.elapsed_time || '';
|
||||
};
|
||||
|
||||
const hasTrace = useCallback(
|
||||
(componentId: string) => {
|
||||
if (Array.isArray(traceData)) {
|
||||
@ -272,7 +288,10 @@ export const WorkFlowTimeline = ({
|
||||
nodeLabel)}
|
||||
</span>
|
||||
<span className="text-text-secondary text-xs">
|
||||
{x.data.elapsed_time?.toString().slice(0, 6)}
|
||||
{getElapsedTime(x.data.component_id)
|
||||
.toString()
|
||||
.slice(0, 6)}
|
||||
{getElapsedTime(x.data.component_id) ? 's' : ''}
|
||||
</span>
|
||||
<span
|
||||
className={cn(
|
||||
|
||||
233
web/src/pages/agent/share/index.tsx
Normal file
233
web/src/pages/agent/share/index.tsx
Normal file
@ -0,0 +1,233 @@
|
||||
import { EmbedContainer } from '@/components/embed-container';
|
||||
import { FileUploadProps } from '@/components/file-upload';
|
||||
import { NextMessageInput } from '@/components/message-input/next';
|
||||
import MessageItem from '@/components/next-message-item';
|
||||
import PdfDrawer from '@/components/pdf-drawer';
|
||||
import { useClickDrawer } from '@/components/pdf-drawer/hooks';
|
||||
import { MessageType } from '@/constants/chat';
|
||||
import {
|
||||
useFetchExternalAgentInputs,
|
||||
useUploadCanvasFileWithProgress,
|
||||
} from '@/hooks/use-agent-request';
|
||||
import { cn } from '@/lib/utils';
|
||||
import i18n from '@/locales/config';
|
||||
import DebugContent from '@/pages/agent/debug-content';
|
||||
import { useCacheChatLog } from '@/pages/agent/hooks/use-cache-chat-log';
|
||||
import { useAwaitCompentData } from '@/pages/agent/hooks/use-chat-logic';
|
||||
import { IInputs } from '@/pages/agent/interface';
|
||||
import { useSendButtonDisabled } from '@/pages/chat/hooks';
|
||||
import { buildMessageUuidWithRole } from '@/utils/chat';
|
||||
import { isEmpty } from 'lodash';
|
||||
import React, { forwardRef, useCallback, useState } from 'react';
|
||||
import {
|
||||
useGetSharedChatSearchParams,
|
||||
useSendNextSharedMessage,
|
||||
} from '../hooks/use-send-shared-message';
|
||||
import { ParameterDialog } from './parameter-dialog';
|
||||
|
||||
const ChatContainer = () => {
|
||||
const {
|
||||
sharedId: conversationId,
|
||||
locale,
|
||||
visibleAvatar,
|
||||
} = useGetSharedChatSearchParams();
|
||||
const { visible, hideModal, documentId, selectedChunk, clickDocumentButton } =
|
||||
useClickDrawer();
|
||||
|
||||
const { uploadCanvasFile, loading } =
|
||||
useUploadCanvasFileWithProgress(conversationId);
|
||||
const {
|
||||
addEventList,
|
||||
setCurrentMessageId,
|
||||
currentEventListWithoutMessageById,
|
||||
clearEventList,
|
||||
} = useCacheChatLog();
|
||||
const {
|
||||
handlePressEnter,
|
||||
handleInputChange,
|
||||
value,
|
||||
sendLoading,
|
||||
scrollRef,
|
||||
messageContainerRef,
|
||||
derivedMessages,
|
||||
hasError,
|
||||
stopOutputMessage,
|
||||
findReferenceByMessageId,
|
||||
appendUploadResponseList,
|
||||
parameterDialogVisible,
|
||||
showParameterDialog,
|
||||
sendFormMessage,
|
||||
addNewestOneAnswer,
|
||||
ok,
|
||||
resetSession,
|
||||
} = useSendNextSharedMessage(addEventList);
|
||||
const { buildInputList, handleOk, isWaitting } = useAwaitCompentData({
|
||||
derivedMessages,
|
||||
sendFormMessage,
|
||||
canvasId: conversationId as string,
|
||||
});
|
||||
const sendDisabled = useSendButtonDisabled(value);
|
||||
const { data: inputsData } = useFetchExternalAgentInputs();
|
||||
const [agentInfo, setAgentInfo] = useState<IInputs>({
|
||||
avatar: '',
|
||||
title: '',
|
||||
inputs: {},
|
||||
prologue: '',
|
||||
});
|
||||
const handleUploadFile: NonNullable<FileUploadProps['onUpload']> =
|
||||
useCallback(
|
||||
async (files, options) => {
|
||||
const ret = await uploadCanvasFile({ files, options });
|
||||
appendUploadResponseList(ret.data, files);
|
||||
},
|
||||
[appendUploadResponseList, uploadCanvasFile],
|
||||
);
|
||||
|
||||
React.useEffect(() => {
|
||||
if (locale && i18n.language !== locale) {
|
||||
i18n.changeLanguage(locale);
|
||||
}
|
||||
}, [locale, visibleAvatar]);
|
||||
|
||||
React.useEffect(() => {
|
||||
const { avatar, title, inputs } = inputsData;
|
||||
setAgentInfo({
|
||||
avatar,
|
||||
title,
|
||||
inputs: inputs,
|
||||
prologue: '',
|
||||
});
|
||||
}, [inputsData, setAgentInfo]);
|
||||
|
||||
React.useEffect(() => {
|
||||
if (inputsData.prologue) {
|
||||
addNewestOneAnswer({
|
||||
answer: inputsData.prologue,
|
||||
});
|
||||
}
|
||||
}, [inputsData.prologue, addNewestOneAnswer]);
|
||||
|
||||
React.useEffect(() => {
|
||||
if (inputsData && inputsData.inputs && !isEmpty(inputsData.inputs)) {
|
||||
showParameterDialog();
|
||||
}
|
||||
}, [inputsData, showParameterDialog]);
|
||||
|
||||
const handleInputsModalOk = (params: any[]) => {
|
||||
ok(params);
|
||||
};
|
||||
const handleReset = () => {
|
||||
resetSession();
|
||||
clearEventList();
|
||||
};
|
||||
if (!conversationId) {
|
||||
return <div>empty</div>;
|
||||
}
|
||||
return (
|
||||
<>
|
||||
<EmbedContainer
|
||||
title={agentInfo.title}
|
||||
avatar={agentInfo.avatar}
|
||||
handleReset={handleReset}
|
||||
>
|
||||
<div className="flex flex-1 flex-col p-2.5 h-[90vh] m-3">
|
||||
<div
|
||||
className={cn(
|
||||
'flex flex-1 flex-col overflow-auto scrollbar-auto m-auto w-5/6',
|
||||
)}
|
||||
ref={messageContainerRef}
|
||||
>
|
||||
<div>
|
||||
{derivedMessages?.map((message, i) => {
|
||||
return (
|
||||
<MessageItem
|
||||
visibleAvatar={visibleAvatar}
|
||||
conversationId={conversationId}
|
||||
currentEventListWithoutMessageById={
|
||||
currentEventListWithoutMessageById
|
||||
}
|
||||
setCurrentMessageId={setCurrentMessageId}
|
||||
key={buildMessageUuidWithRole(message)}
|
||||
item={message}
|
||||
nickname="You"
|
||||
reference={findReferenceByMessageId(message.id)}
|
||||
loading={
|
||||
message.role === MessageType.Assistant &&
|
||||
sendLoading &&
|
||||
derivedMessages?.length - 1 === i
|
||||
}
|
||||
isShare={true}
|
||||
avatarDialog={agentInfo.avatar}
|
||||
agentName={agentInfo.title}
|
||||
index={i}
|
||||
clickDocumentButton={clickDocumentButton}
|
||||
showLikeButton={false}
|
||||
showLoudspeaker={false}
|
||||
showLog={false}
|
||||
sendLoading={sendLoading}
|
||||
>
|
||||
{message.role === MessageType.Assistant &&
|
||||
derivedMessages.length - 1 === i && (
|
||||
<DebugContent
|
||||
parameters={buildInputList(message)}
|
||||
message={message}
|
||||
ok={handleOk(message)}
|
||||
isNext={false}
|
||||
btnText={'Submit'}
|
||||
></DebugContent>
|
||||
)}
|
||||
{message.role === MessageType.Assistant &&
|
||||
derivedMessages.length - 1 !== i && (
|
||||
<div>
|
||||
<div>{message?.data?.tips}</div>
|
||||
|
||||
<div>
|
||||
{buildInputList(message)?.map((item) => item.value)}
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
</MessageItem>
|
||||
);
|
||||
})}
|
||||
</div>
|
||||
<div ref={scrollRef} />
|
||||
</div>
|
||||
<div className="flex w-full justify-center mb-8">
|
||||
<div className="w-5/6">
|
||||
<NextMessageInput
|
||||
isShared
|
||||
value={value}
|
||||
disabled={hasError || isWaitting}
|
||||
sendDisabled={sendDisabled || isWaitting}
|
||||
conversationId={conversationId}
|
||||
onInputChange={handleInputChange}
|
||||
onPressEnter={handlePressEnter}
|
||||
sendLoading={sendLoading}
|
||||
stopOutputMessage={stopOutputMessage}
|
||||
onUpload={handleUploadFile}
|
||||
isUploading={loading || isWaitting}
|
||||
></NextMessageInput>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</EmbedContainer>
|
||||
{visible && (
|
||||
<PdfDrawer
|
||||
visible={visible}
|
||||
hideModal={hideModal}
|
||||
documentId={documentId}
|
||||
chunk={selectedChunk}
|
||||
></PdfDrawer>
|
||||
)}
|
||||
{parameterDialogVisible && (
|
||||
<ParameterDialog
|
||||
// hideModal={hideParameterDialog}
|
||||
ok={handleInputsModalOk}
|
||||
data={agentInfo.inputs}
|
||||
></ParameterDialog>
|
||||
)}
|
||||
</>
|
||||
);
|
||||
};
|
||||
|
||||
export default forwardRef(ChatContainer);
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user