Docs: How to use MinerU to parse pdf documents (#10763)

### What problem does this PR solve?



### Type of change

- [x] Documentation Update

README.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.1">
     </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">
@@ -187,7 +187,7 @@ releases! 🌟
 > All Docker images are built for x86 platforms. We don't currently offer Docker images for ARM64.
 > If you are on an ARM64 platform, follow [this guide](https://ragflow.io/docs/dev/build_docker_image) to build a Docker image compatible with your system.
 
-   > The command below downloads the `v0.21.0-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.21.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0` for the full edition `v0.21.0`.
+   > The command below downloads the `v0.21.1-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.21.1-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1` for the full edition `v0.21.1`.
 
    ```bash
    $ cd ragflow/docker
@@ -200,8 +200,8 @@ releases! 🌟
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    |-------------------|-----------------|-----------------------|--------------------------|
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                   | Stable release            |
+   | v0.21.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.21.1-slim      | &approx;2       | ❌                   | Stable release            |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                   | _Unstable_ nightly build  |
 

README_id.md

@@ -22,7 +22,7 @@
         <img alt="Lencana Daring" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.1">
     </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 v0.21.0-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.21.0-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0 untuk edisi lengkap v0.21.0.
+> Perintah di bawah ini mengunduh edisi v0.21.1-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.21.1-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1 untuk edisi lengkap v0.21.1.
 
 ```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?                  |
 | ----------------- | --------------- | --------------------- | ------------------------ |
-| v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-| v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+| v0.21.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
 | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
 | nightly-slim      | &approx;2       | ❌                    | _Unstable_ nightly build |
 

README_ja.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.1">
     </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 v0.21.0-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。v0.21.0-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 v0.21.0 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0 と設定します。
+   > 以下のコマンドは、RAGFlow Docker イメージの v0.21.1-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。v0.21.1-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 v0.21.1 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1 と設定します。
 
    ```bash
    $ cd ragflow/docker
@@ -173,8 +173,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.21.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

README_ko.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.1">
     </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 v0.21.0-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.21.0-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.21.0을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0로 설정합니다.
+   > 아래 명령어는 RAGFlow Docker 이미지의 v0.21.1-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.21.1-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.21.1을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1로 설정합니다.
 
    ```bash
    $ cd ragflow/docker
@@ -173,8 +173,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.21.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

README_pt_br.md

@@ -22,7 +22,7 @@
         <img alt="Badge Estático" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.1">
     </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 `v0.21.0-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 `v0.21.0-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:v0.21.0` para a edição completa `v0.21.0`.
+    > O comando abaixo baixa a edição `v0.21.1-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 `v0.21.1-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:v0.21.1` para a edição completa `v0.21.1`.
 
     ```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?                 |
     | --------------------- | ---------------------- | ------------------------------- | ------------------------ |
-    | v0.21.0               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
-    | v0.21.0-slim          | ~2                     | ❌                              | Lançamento estável       |
+    | v0.21.1               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
+    | v0.21.1-slim          | ~2                     | ❌                              | Lançamento estável       |
     | nightly               | ~9                     | :heavy_check_mark:              | _Instável_ build noturno |
     | nightly-slim          | ~2                     | ❌                               | _Instável_ build noturno |
 

README_tzh.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.1">
     </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 `v0.21.0-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.21.0-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:v0.21.0` 來下載 RAGFlow 鏡像的 `v0.21.0` 完整發行版。
+   > 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.21.1-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.21.1-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:v0.21.1` 來下載 RAGFlow 鏡像的 `v0.21.1` 完整發行版。
 
    ```bash
    $ cd ragflow/docker
@@ -196,8 +196,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.21.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

README_zh.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.21.1">
     </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 `v0.21.0-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.21.0-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:v0.21.0` 来下载 RAGFlow 镜像的 `v0.21.0` 完整发行版。
+   > 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.21.1-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.21.1-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:v0.21.1` 来下载 RAGFlow 镜像的 `v0.21.1` 完整发行版。
 
    ```bash
    $ cd ragflow/docker
@@ -196,8 +196,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.21.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.21.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.21.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.21.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

admin/client/README.md

@@ -48,7 +48,7 @@ It consists of a server-side Service and a command-line client (CLI), both imple
 1.  Ensure the Admin Service is running.
 2.  Install ragflow-cli.
     ```bash
-    pip install ragflow-cli==0.21.0
+    pip install ragflow-cli==0.21.1
     ```
 3.  Launch the CLI client:
     ```bash

admin/client/admin_client.py

@@ -370,7 +370,7 @@ class AdminCLI(Cmd):
                         self.session.headers.update({
                             'Content-Type': 'application/json',
                             'Authorization': response.headers['Authorization'],
-                            'User-Agent': 'RAGFlow-CLI/0.21.0'
+                            'User-Agent': 'RAGFlow-CLI/0.21.1'
                         })
                         print("Authentication successful.")
                         return True

admin/client/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragflow-cli"
-version = "0.21.0"
+version = "0.21.1"
 description = "Admin Service's client of [RAGFlow](https://github.com/infiniflow/ragflow). The Admin Service provides user management and system monitoring. "
 authors = [{ name = "Lynn", email = "lynn_inf@hotmail.com" }]
 license = { text = "Apache License, Version 2.0" }

admin/pyproject.toml

@@ -1,24 +0,0 @@
-[project]
-name = "ragflow-cli"
-version = "0.21.0.dev2"
-description = "Admin Service's client of [RAGFlow](https://github.com/infiniflow/ragflow). The Admin Service provides user management and system monitoring. "
-authors = [{ name = "Lynn", email = "lynn_inf@hotmail.com" }]
-license = { text = "Apache License, Version 2.0" }
-readme = "README.md"
-requires-python = ">=3.10,<3.13"
-dependencies = [
-    "requests>=2.30.0,<3.0.0",
-    "beartype>=0.18.5,<0.19.0",
-    "pycryptodomex>=3.10.0",
-    "lark>=1.1.0",
-]
-
-[dependency-groups]
-test = [
-    "pytest>=8.3.5",
-    "requests>=2.32.3",
-    "requests-toolbelt>=1.0.0",
-]
-
-[project.scripts]
-ragflow-cli = "ragflow_cli.admin_client:main"

admin/server/auth.py

@@ -32,6 +32,7 @@ from api.utils.crypt import decrypt
 from api.utils import (
     current_timestamp,
     datetime_format,
+    get_format_time,
     get_uuid,
 )
 from api.utils.api_utils import (
@@ -131,6 +132,7 @@ def login_admin(email: str, password: str):
     login_user(user)
     user.update_time = (current_timestamp(),)
     user.update_date = (datetime_format(datetime.now()),)
+    user.last_login_time = get_format_time()
     user.save()
     msg = "Welcome back!"
     return construct_response(data=resp, auth=user.get_id(), message=msg)

admin/server/routes.py

@@ -32,18 +32,24 @@ admin_bp = Blueprint('admin', __name__, url_prefix='/api/v1/admin')
 def login():
     if not request.json:
         return error_response('Authorize admin failed.' ,400)
-    email = request.json.get("email", "")
-    password = request.json.get("password", "")
-    return login_admin(email, password)
+    try:
+        email = request.json.get("email", "")
+        password = request.json.get("password", "")
+        return login_admin(email, password)
+    except Exception as e:
+        return error_response(str(e), 500)
 
 
 @admin_bp.route('/logout', methods=['GET'])
 @login_required
 def logout():
-    current_user.access_token = f"INVALID_{secrets.token_hex(16)}"
-    current_user.save()
-    logout_user()
-    return success_response(True)
+    try:
+        current_user.access_token = f"INVALID_{secrets.token_hex(16)}"
+        current_user.save()
+        logout_user()
+        return success_response(True)
+    except Exception as e:
+        return error_response(str(e), 500)
 
 
 @admin_bp.route('/auth', methods=['GET'])

admin/server/services.py

@@ -36,8 +36,13 @@ class UserMgr:
         users = UserService.get_all_users()
         result = []
         for user in users:
-            result.append({'email': user.email, 'nickname': user.nickname, 'create_date': user.create_date,
-                           'is_active': user.is_active})
+            result.append({
+                'email': user.email,
+                'nickname': user.nickname,
+                'create_date': user.create_date,
+                'is_active': user.is_active,
+                'is_superuser': user.is_superuser,
+            })
         return result
 
     @staticmethod
@@ -50,7 +55,6 @@ class UserMgr:
                 'email': user.email,
                 'language': user.language,
                 'last_login_time': user.last_login_time,
-                'is_authenticated': user.is_authenticated,
                 'is_active': user.is_active,
                 'is_anonymous': user.is_anonymous,
                 'login_channel': user.login_channel,
@@ -166,7 +170,7 @@ class UserServiceMgr:
         return [{
             'title': r['title'],
             'permission': r['permission'],
-            'canvas_category': r['canvas_category'].split('-')[0]
+            'canvas_category': r['canvas_category'].split('_')[0]
         } for r in res]
 
 

agent/templates/chunk_summary.json

@@ -350,7 +350,7 @@
                             ]
                         },
                         "label": "Tokenizer",
-                        "name": "Tokenizer"
+                        "name": "Indexer"
                     },
                     "dragging": false,
                     "id": "Tokenizer:EightRocketsAppear",

agent/tools/retrieval.py

@@ -18,12 +18,14 @@ import re
 from abc import ABC
 from agent.tools.base import ToolParamBase, ToolBase, ToolMeta
 from api.db import LLMType
+from api.db.services.document_service import DocumentService
+from api.db.services.dialog_service import meta_filter
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.llm_service import LLMBundle
 from api import settings
 from api.utils.api_utils import timeout
 from rag.app.tag import label_question
-from rag.prompts.generator import cross_languages, kb_prompt
+from rag.prompts.generator import cross_languages, kb_prompt, gen_meta_filter
 
 
 class RetrievalParam(ToolParamBase):
@@ -58,6 +60,7 @@ class RetrievalParam(ToolParamBase):
         self.use_kg = False
         self.cross_languages = []
         self.toc_enhance = False
+        self.meta_data_filter={}
 
     def check(self):
         self.check_decimal_float(self.similarity_threshold, "[Retrieval] Similarity threshold")
@@ -117,6 +120,21 @@ class Retrieval(ToolBase, ABC):
         vars = self.get_input_elements_from_text(kwargs["query"])
         vars = {k:o["value"] for k,o in vars.items()}
         query = self.string_format(kwargs["query"], vars)
+        
+        doc_ids=[]
+        if self._param.meta_data_filter!={}:
+            metas = DocumentService.get_meta_by_kbs(kb_ids)
+            if self._param.meta_data_filter.get("method") == "auto":
+                chat_mdl = LLMBundle(self._canvas.get_tenant_id(), LLMType.CHAT)
+                filters = gen_meta_filter(chat_mdl, metas, query)
+                doc_ids.extend(meta_filter(metas, filters))
+                if not doc_ids:
+                    doc_ids = None
+            elif self._param.meta_data_filter.get("method") == "manual":
+                doc_ids.extend(meta_filter(metas, self._param.meta_data_filter["manual"]))
+                if not doc_ids:
+                    doc_ids = None
+
         if self._param.cross_languages:
             query = cross_languages(kbs[0].tenant_id, None, query, self._param.cross_languages)
 
@@ -131,6 +149,7 @@ class Retrieval(ToolBase, ABC):
                 self._param.top_n,
                 self._param.similarity_threshold,
                 1 - self._param.keywords_similarity_weight,
+                doc_ids=doc_ids,
                 aggs=False,
                 rerank_mdl=rerank_mdl,
                 rank_feature=label_question(query, kbs),

api/apps/document_app.py

@@ -45,7 +45,7 @@ from api.utils.api_utils import (
 from api.utils.file_utils import filename_type, get_project_base_directory, thumbnail
 from api.utils.web_utils import CONTENT_TYPE_MAP, html2pdf, is_valid_url
 from deepdoc.parser.html_parser import RAGFlowHtmlParser
-from rag.nlp import search
+from rag.nlp import search, rag_tokenizer
 from rag.utils.storage_factory import STORAGE_IMPL
 
 
@@ -524,6 +524,21 @@ def rename():
             e, file = FileService.get_by_id(informs[0].file_id)
             FileService.update_by_id(file.id, {"name": req["name"]})
 
+        tenant_id = DocumentService.get_tenant_id(req["doc_id"])
+        title_tks = rag_tokenizer.tokenize(req["name"])
+        es_body = {
+            "docnm_kwd": req["name"],
+            "title_tks": title_tks,
+            "title_sm_tks": rag_tokenizer.fine_grained_tokenize(title_tks),
+        }
+        if settings.docStoreConn.indexExist(search.index_name(tenant_id), doc.kb_id):
+            settings.docStoreConn.update(
+                {"doc_id": req["doc_id"]},
+                es_body,
+                search.index_name(tenant_id),
+                doc.kb_id,
+            )
+
         return get_json_result(data=True)
     except Exception as e:
         return server_error_response(e)

api/apps/kb_app.py

@@ -70,6 +70,7 @@ def create():
         e, t = TenantService.get_by_id(current_user.id)
         if not e:
             return get_data_error_result(message="Tenant not found.")
+
         req["parser_config"] = {
             "layout_recognize": "DeepDOC",
             "chunk_token_num": 512,
@@ -579,7 +580,7 @@ def run_graphrag():
     sample_document = documents[0]
     document_ids = [document["id"] for document in documents]
 
-    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="graphrag", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
+    task_id = queue_raptor_o_graphrag_tasks(sample_doc_id=sample_document, ty="graphrag", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
 
     if not KnowledgebaseService.update_by_id(kb.id, {"graphrag_task_id": task_id}):
         logging.warning(f"Cannot save graphrag_task_id for kb {kb_id}")
@@ -648,7 +649,7 @@ def run_raptor():
     sample_document = documents[0]
     document_ids = [document["id"] for document in documents]
 
-    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="raptor", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
+    task_id = queue_raptor_o_graphrag_tasks(sample_doc_id=sample_document, ty="raptor", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
 
     if not KnowledgebaseService.update_by_id(kb.id, {"raptor_task_id": task_id}):
         logging.warning(f"Cannot save raptor_task_id for kb {kb_id}")
@@ -717,7 +718,7 @@ def run_mindmap():
     sample_document = documents[0]
     document_ids = [document["id"] for document in documents]
 
-    task_id = queue_raptor_o_graphrag_tasks(doc=sample_document, ty="mindmap", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
+    task_id = queue_raptor_o_graphrag_tasks(sample_doc_id=sample_document, ty="mindmap", priority=0, fake_doc_id=GRAPH_RAPTOR_FAKE_DOC_ID, doc_ids=list(document_ids))
 
     if not KnowledgebaseService.update_by_id(kb.id, {"mindmap_task_id": task_id}):
         logging.warning(f"Cannot save mindmap_task_id for kb {kb_id}")

api/apps/sdk/doc.py

@@ -470,6 +470,20 @@ def list_docs(dataset_id, tenant_id):
         required: false
         default: 0
         description: Unix timestamp for filtering documents created before this time. 0 means no filter.
+      - in: query
+        name: suffix
+        type: array
+        items:
+          type: string
+        required: false
+        description: Filter by file suffix (e.g., ["pdf", "txt", "docx"]).
+      - in: query
+        name: run
+        type: array
+        items:
+          type: string
+        required: false
+        description: Filter by document run status. Supports both numeric ("0", "1", "2", "3", "4") and text formats ("UNSTART", "RUNNING", "CANCEL", "DONE", "FAIL").
       - in: header
         name: Authorization
         type: string
@@ -512,63 +526,62 @@ def list_docs(dataset_id, tenant_id):
                     description: Processing status.
     """
     if not KnowledgebaseService.accessible(kb_id=dataset_id, user_id=tenant_id):
-        return get_error_data_result(message=f"You don't own the dataset {dataset_id}. ")
-    id = request.args.get("id")
-    name = request.args.get("name")
+      return get_error_data_result(message=f"You don't own the dataset {dataset_id}. ")
 
-    if id and not DocumentService.query(id=id, kb_id=dataset_id):
-        return get_error_data_result(message=f"You don't own the document {id}.")
+    q = request.args
+    document_id = q.get("id")  
+    name        = q.get("name")
+
+    if document_id and not DocumentService.query(id=document_id, kb_id=dataset_id):
+        return get_error_data_result(message=f"You don't own the document {document_id}.")
     if name and not DocumentService.query(name=name, kb_id=dataset_id):
         return get_error_data_result(message=f"You don't own the document {name}.")
 
-    page = int(request.args.get("page", 1))
-    keywords = request.args.get("keywords", "")
-    page_size = int(request.args.get("page_size", 30))
-    orderby = request.args.get("orderby", "create_time")
-    if request.args.get("desc") == "False":
-        desc = False
-    else:
-        desc = True
-    docs, tol = DocumentService.get_list(dataset_id, page, page_size, orderby, desc, keywords, id, name)
+    page        = int(q.get("page", 1))
+    page_size   = int(q.get("page_size", 30))  
+    orderby     = q.get("orderby", "create_time")
+    desc        = str(q.get("desc", "true")).strip().lower() != "false"
+    keywords    = q.get("keywords", "")
 
-    create_time_from = int(request.args.get("create_time_from", 0))
-    create_time_to = int(request.args.get("create_time_to", 0))
+    # filters - align with OpenAPI parameter names
+    suffix               = q.getlist("suffix") 
+    run_status           = q.getlist("run")   
+    create_time_from     = int(q.get("create_time_from", 0))  
+    create_time_to       = int(q.get("create_time_to", 0))    
 
+    # map run status (accept text or numeric) - align with API parameter
+    run_status_text_to_numeric = {"UNSTART": "0", "RUNNING": "1", "CANCEL": "2", "DONE": "3", "FAIL": "4"}
+    run_status_converted = [run_status_text_to_numeric.get(v, v) for v in run_status]
+
+    docs, total = DocumentService.get_list(
+        dataset_id, page, page_size, orderby, desc, keywords, document_id, name, suffix, run_status_converted
+    )
+
+    # time range filter (0 means no bound)
     if create_time_from or create_time_to:
-        filtered_docs = []
-        for doc in docs:
-            doc_create_time = doc.get("create_time", 0)
-            if (create_time_from == 0 or doc_create_time >= create_time_from) and (create_time_to == 0 or doc_create_time <= create_time_to):
-                filtered_docs.append(doc)
-        docs = filtered_docs
+        docs = [
+            d for d in docs
+            if (create_time_from == 0 or d.get("create_time", 0) >= create_time_from)
+            and (create_time_to == 0 or d.get("create_time", 0) <= create_time_to)
+        ]
 
-    # rename key's name
-    renamed_doc_list = []
+    # rename keys + map run status back to text for output
     key_mapping = {
         "chunk_num": "chunk_count",
-        "kb_id": "dataset_id",
+        "kb_id": "dataset_id", 
         "token_num": "token_count",
         "parser_id": "chunk_method",
     }
-    run_mapping = {
-        "0": "UNSTART",
-        "1": "RUNNING",
-        "2": "CANCEL",
-        "3": "DONE",
-        "4": "FAIL",
-    }
-    for doc in docs:
-        renamed_doc = {}
-        for key, value in doc.items():
-            if key == "run":
-                renamed_doc["run"] = run_mapping.get(str(value))
-            new_key = key_mapping.get(key, key)
-            renamed_doc[new_key] = value
-            if key == "run":
-                renamed_doc["run"] = run_mapping.get(value)
-        renamed_doc_list.append(renamed_doc)
-    return get_result(data={"total": tol, "docs": renamed_doc_list})
+    run_status_numeric_to_text = {"0": "UNSTART", "1": "RUNNING", "2": "CANCEL", "3": "DONE", "4": "FAIL"}
 
+    output_docs = []
+    for d in docs:
+        renamed_doc = {key_mapping.get(k, k): v for k, v in d.items()}
+        if "run" in d:
+            renamed_doc["run"] = run_status_numeric_to_text.get(str(d["run"]), d["run"])
+        output_docs.append(renamed_doc)
+
+    return get_result(data={"total": total, "docs": output_docs})
 
 @manager.route("/datasets/<dataset_id>/documents", methods=["DELETE"])  # noqa: F821
 @token_required

api/apps/user_app.py

@@ -22,7 +22,7 @@ import secrets
 import time
 from datetime import datetime
 
-from flask import redirect, request, session, Response
+from flask import redirect, request, session, make_response
 from flask_login import current_user, login_required, login_user, logout_user
 from werkzeug.security import check_password_hash, generate_password_hash
 
@@ -866,7 +866,9 @@ def forget_get_captcha():
     from captcha.image import ImageCaptcha
     image = ImageCaptcha(width=300, height=120, font_sizes=[50, 60, 70])
     img_bytes = image.generate(captcha_text).read()
-    return Response(img_bytes, mimetype="image/png")
+    response = make_response(img_bytes)
+    response.headers.set("Content-Type", "image/JPEG")
+    return response
 
 
 @manager.route("/forget/otp", methods=["POST"])  # noqa: F821

api/db/services/document_service.py

@@ -79,7 +79,7 @@ class DocumentService(CommonService):
     @classmethod
     @DB.connection_context()
     def get_list(cls, kb_id, page_number, items_per_page,
-                 orderby, desc, keywords, id, name):
+                 orderby, desc, keywords, id, name, suffix=None, run = None):
         fields = cls.get_cls_model_fields()
         docs = cls.model.select(*[*fields, UserCanvas.title]).join(File2Document, on = (File2Document.document_id == cls.model.id))\
             .join(File, on = (File.id == File2Document.file_id))\
@@ -96,6 +96,10 @@ class DocumentService(CommonService):
             docs = docs.where(
                 fn.LOWER(cls.model.name).contains(keywords.lower())
             )
+        if suffix:
+            docs = docs.where(cls.model.suffix.in_(suffix))
+        if run:
+            docs = docs.where(cls.model.run.in_(run))
         if desc:
             docs = docs.order_by(cls.model.getter_by(orderby).desc())
         else:
@@ -667,9 +671,11 @@ class DocumentService(CommonService):
     @classmethod
     @DB.connection_context()
     def _sync_progress(cls, docs:list[dict]):
+        from api.db.services.task_service import TaskService
+
         for d in docs:
             try:
-                tsks = Task.query(doc_id=d["id"], order_by=Task.create_time)
+                tsks = TaskService.query(doc_id=d["id"], order_by=Task.create_time)
                 if not tsks:
                     continue
                 msg = []
@@ -787,21 +793,23 @@ class DocumentService(CommonService):
             "cancelled": int(cancelled),
         }
 
-def queue_raptor_o_graphrag_tasks(doc, ty, priority, fake_doc_id="", doc_ids=[]):
+def queue_raptor_o_graphrag_tasks(sample_doc_id, ty, priority, fake_doc_id="", doc_ids=[]):
     """
     You can provide a fake_doc_id to bypass the restriction of tasks at the knowledgebase level.
     Optionally, specify a list of doc_ids to determine which documents participate in the task.
     """
-    chunking_config = DocumentService.get_chunking_config(doc["id"])
+    assert ty in ["graphrag", "raptor", "mindmap"], "type should be graphrag, raptor or mindmap"
+
+    chunking_config = DocumentService.get_chunking_config(sample_doc_id["id"])
     hasher = xxhash.xxh64()
     for field in sorted(chunking_config.keys()):
         hasher.update(str(chunking_config[field]).encode("utf-8"))
 
     def new_task():
-        nonlocal doc
+        nonlocal sample_doc_id
         return {
             "id": get_uuid(),
-            "doc_id": fake_doc_id if fake_doc_id else doc["id"],
+            "doc_id": sample_doc_id["id"],
             "from_page": 100000000,
             "to_page": 100000000,
             "task_type": ty,
@@ -816,9 +824,9 @@ def queue_raptor_o_graphrag_tasks(doc, ty, priority, fake_doc_id="", doc_ids=[])
     task["digest"] = hasher.hexdigest()
     bulk_insert_into_db(Task, [task], True)
 
-    if ty in ["graphrag", "raptor", "mindmap"]:
-        task["doc_ids"] = doc_ids
-        DocumentService.begin2parse(doc["id"])
+    task["doc_id"] = fake_doc_id
+    task["doc_ids"] = doc_ids
+    DocumentService.begin2parse(sample_doc_id["id"])
     assert REDIS_CONN.queue_product(get_svr_queue_name(priority), message=task), "Can't access Redis. Please check the Redis' status."
     return task["id"]
 

api/db/services/llm_service.py

@@ -210,19 +210,18 @@ class LLMBundle(LLM4Tenant):
     def _clean_param(chat_partial, **kwargs):
         func = chat_partial.func
         sig = inspect.signature(func)
-        keyword_args = []
         support_var_args = False
+        allowed_params = set()
+
         for param in sig.parameters.values():
-            if param.kind == inspect.Parameter.VAR_KEYWORD or param.kind == inspect.Parameter.VAR_POSITIONAL:
+            if param.kind == inspect.Parameter.VAR_KEYWORD:
                 support_var_args = True
-            elif param.kind == inspect.Parameter.KEYWORD_ONLY:
-                keyword_args.append(param.name)
-
-        use_kwargs = kwargs
-        if not support_var_args:
-            use_kwargs = {k: v for k, v in kwargs.items() if k in keyword_args}
-        return use_kwargs
-
+            elif param.kind in (inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.KEYWORD_ONLY):
+                allowed_params.add(param.name)
+        if support_var_args:
+            return kwargs
+        else:
+            return {k: v for k, v in kwargs.items() if k in allowed_params}
     def chat(self, system: str, history: list, gen_conf: dict = {}, **kwargs) -> str:
         if self.langfuse:
             generation = self.langfuse.start_generation(trace_context=self.trace_context, name="chat", model=self.llm_name, input={"system": system, "history": history})

api/utils/file_utils.py

@@ -173,7 +173,7 @@ def filename_type(filename):
     if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):
         return FileType.AURAL.value
 
-    if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4)$", filename):
+    if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4|avi|mkv)$", filename):
         return FileType.VISUAL.value
 
     return FileType.OTHER.value

conf/llm_factories.json

@@ -2987,7 +2987,7 @@
                     "tags": "LLM,CHAT,IMAGE2TEXT,32k",
                     "max_tokens": 32000,
                     "model_type": "image2text",
-                    "is_tools": true
+                    "is_tools": false
                 },
                 {
                     "llm_name": "THUDM/GLM-Z1-32B-0414",

deepdoc/parser/excel_parser.py

@@ -54,8 +54,8 @@ class RAGFlowExcelParser:
             try:
                 file_like_object.seek(0)
                 try:
-                    df = pd.read_excel(file_like_object)
-                    return RAGFlowExcelParser._dataframe_to_workbook(df)
+                    dfs = pd.read_excel(file_like_object, sheet_name=None)
+                    return RAGFlowExcelParser._dataframe_to_workbook(dfs)
                 except Exception as ex:
                     logging.info(f"pandas with default engine load error: {ex}, try calamine instead")
                     file_like_object.seek(0)
@@ -75,6 +75,10 @@ class RAGFlowExcelParser:
 
     @staticmethod
     def _dataframe_to_workbook(df):
+        # if contains multiple sheets use _dataframes_to_workbook
+        if isinstance(df, dict) and len(df) > 1:
+            return RAGFlowExcelParser._dataframes_to_workbook(df)
+
         df = RAGFlowExcelParser._clean_dataframe(df)
         wb = Workbook()
         ws = wb.active
@@ -88,6 +92,22 @@ class RAGFlowExcelParser:
                 ws.cell(row=row_num, column=col_num, value=value)
 
         return wb
+    
+    @staticmethod
+    def _dataframes_to_workbook(dfs: dict):
+        wb = Workbook()
+        default_sheet = wb.active
+        wb.remove(default_sheet)
+        
+        for sheet_name, df in dfs.items():
+            df = RAGFlowExcelParser._clean_dataframe(df)
+            ws = wb.create_sheet(title=sheet_name)
+            for col_num, column_name in enumerate(df.columns, 1):
+                ws.cell(row=1, column=col_num, value=column_name)
+            for row_num, row in enumerate(df.values, 2):
+                for col_num, value in enumerate(row, 1):
+                    ws.cell(row=row_num, column=col_num, value=value)
+        return wb
 
     def html(self, fnm, chunk_rows=256):
         from html import escape

deepdoc/parser/figure_parser.py

@@ -17,6 +17,8 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from PIL import Image
 
+from api.db import LLMType
+from api.db.services.llm_service import LLMBundle
 from api.utils.api_utils import timeout
 from rag.app.picture import vision_llm_chunk as picture_vision_llm_chunk
 from rag.prompts.generator import vision_llm_figure_describe_prompt
@@ -32,6 +34,43 @@ def vision_figure_parser_figure_data_wrapper(figures_data_without_positions):
         if isinstance(figure_data[1], Image.Image)
     ]
 
+def vision_figure_parser_docx_wrapper(sections,tbls,callback=None,**kwargs):
+    try:
+        vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT)
+        callback(0.7, "Visual model detected. Attempting to enhance figure extraction...")
+    except Exception:
+        vision_model = None
+    if vision_model:
+        figures_data = vision_figure_parser_figure_data_wrapper(sections)
+        try:
+            docx_vision_parser = VisionFigureParser(vision_model=vision_model, figures_data=figures_data, **kwargs)
+            boosted_figures = docx_vision_parser(callback=callback)
+            tbls.extend(boosted_figures)
+        except Exception as e:
+            callback(0.8, f"Visual model error: {e}. Skipping figure parsing enhancement.")
+    return tbls
+
+def vision_figure_parser_pdf_wrapper(tbls,callback=None,**kwargs):
+    try:
+        vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT)
+        callback(0.7, "Visual model detected. Attempting to enhance figure extraction...")
+    except Exception:
+        vision_model = None
+    if vision_model:
+        def is_figure_item(item):
+            return (
+                isinstance(item[0][0], Image.Image) and
+                isinstance(item[0][1], list)
+            )
+        figures_data = [item for item in tbls if is_figure_item(item)]
+        try:
+            docx_vision_parser = VisionFigureParser(vision_model=vision_model, figures_data=figures_data, **kwargs)
+            boosted_figures = docx_vision_parser(callback=callback)
+            tbls = [item for item in tbls if not is_figure_item(item)]
+            tbls.extend(boosted_figures)
+        except Exception as e:
+            callback(0.8, f"Visual model error: {e}. Skipping figure parsing enhancement.")
+    return tbls
 
 shared_executor = ThreadPoolExecutor(max_workers=10)
 

docker/.env

@@ -97,13 +97,13 @@ SVR_HTTP_PORT=9380
 ADMIN_SVR_HTTP_PORT=9381
 
 # The RAGFlow Docker image to download.
-# Defaults to the v0.21.0-slim edition, which is the RAGFlow Docker image without embedding models.
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0-slim
+# Defaults to the v0.21.1-slim edition, which is the RAGFlow Docker image without embedding models.
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1-slim
 #
 # To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
-# RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0
+# RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1
 #
-# The Docker image of the v0.21.0 edition includes built-in embedding models:
+# The Docker image of the v0.21.1 edition includes built-in embedding models:
 #   - BAAI/bge-large-zh-v1.5
 #   - maidalun1020/bce-embedding-base_v1
 #

docker/README.md

@@ -79,8 +79,8 @@ The [.env](./.env) file contains important environment variables for Docker.
 - `RAGFLOW-IMAGE`  
   The Docker image edition. Available editions:  
   
-  - `infiniflow/ragflow:v0.21.0-slim` (default): The RAGFlow Docker image without embedding models.  
-  - `infiniflow/ragflow:v0.21.0`: The RAGFlow Docker image with embedding models including:
+  - `infiniflow/ragflow:v0.21.1-slim` (default): The RAGFlow Docker image without embedding models.  
+  - `infiniflow/ragflow:v0.21.1`: The RAGFlow Docker image with embedding models including:
     - Built-in embedding models:
       - `BAAI/bge-large-zh-v1.5` 
       - `maidalun1020/bce-embedding-base_v1`

docker/docker-compose-base.yml

@@ -77,7 +77,7 @@ services:
     container_name: ragflow-infinity
     profiles:
       - infinity
-    image: infiniflow/infinity:v0.6.0
+    image: infiniflow/infinity:v0.6.1
     volumes:
       - infinity_data:/var/infinity
       - ./infinity_conf.toml:/infinity_conf.toml

docker/infinity_conf.toml

@@ -1,5 +1,5 @@
 [general]
-version                  = "0.6.0"
+version                  = "0.6.1"
 time_zone                = "utc-8"
 
 [network]

docs/configurations.md

@@ -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:v0.21.0-slim` (default): The RAGFlow Docker image without embedding models.  
-  - `infiniflow/ragflow:v0.21.0`: The RAGFlow Docker image with embedding models including:
+  - `infiniflow/ragflow:v0.21.1-slim` (default): The RAGFlow Docker image without embedding models.  
+  - `infiniflow/ragflow:v0.21.1`: The RAGFlow Docker image with embedding models including:
     - Built-in embedding models:
       - `BAAI/bge-large-zh-v1.5` 
       - `maidalun1020/bce-embedding-base_v1`

docs/develop/build_docker_image.mdx

@@ -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:v0.21.0-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:v0.21.1-slim` to `infiniflow/ragflow:nightly-slim` to use the pre-built image.
 
 
 2. Launch the Service

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:v0.21.0-slim`
-- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.21.0`
+- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1-slim`
+- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1`
 
 ---
 
 ### Which embedding models can be deployed locally?
 
-RAGFlow offers two Docker image editions, `v0.21.0-slim` and `v0.21.0`:  
+RAGFlow offers two Docker image editions, `v0.21.1-slim` and `v0.21.1`:  
   
-- `infiniflow/ragflow:v0.21.0-slim` (default): The RAGFlow Docker image without embedding models.  
-- `infiniflow/ragflow:v0.21.0`: The RAGFlow Docker image with the following built-in embedding models:
+- `infiniflow/ragflow:v0.21.1-slim` (default): The RAGFlow Docker image without embedding models.  
+- `infiniflow/ragflow:v0.21.1`: The RAGFlow Docker image with the following built-in embedding models:
   - `BAAI/bge-large-zh-v1.5`
   - `maidalun1020/bce-embedding-base_v1`
 
@@ -510,3 +510,27 @@ See [here](./guides/agent/best_practices/accelerate_agent_question_answering.md)
 
 ---
 
+### How to use MinerU to parse PDF documents?
+
+MinerU PDF document parsing is available starting from v0.21.1. To use this feature, follow these steps:
+
+1. Before deploying ragflow-server, update your **docker/.env** file:  
+   - Enable `HF_ENDPOINT=https://hf-mirror.com`
+   - Add a MinerU entry: `MINERU_EXECUTABLE=/ragflow/uv_tools/.venv/bin/mineru`
+
+2. Start the ragflow-server and run the following commands inside the container:  
+
+```bash
+mkdir uv_tools
+cd uv_tools
+uv venv .venv
+source .venv/bin/activate
+uv pip install -U "mineru[core]" -i https://mirrors.aliyun.com/pypi/simple
+```
+
+3. Restart the ragflow-server.
+4. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and slect **MinerU** in **PDF parser**.
+5. If you use a custom ingestion pipeline instead, you must also complete the first three steps before selecting **MinerU** in the **Parsing method** section of the **Parser** component.
+
+
+

docs/guides/agent/agent_component_reference/chunker_title.md

@@ -0,0 +1,40 @@
+---
+sidebar_position: 31
+slug: /chunker_title_component
+---
+
+# Title chunker component
+
+A component that splits texts into chunks by heading level.
+
+---
+
+A **Token chunker** component is a text splitter that uses specified heading level as delimiter to define chunk boundaries and create chunks.
+
+## Scenario
+
+A **Title chunker** component is optional, usually placed immediately after **Parser**.
+
+:::caution WARNING
+Placing a **Title chunker** after a **Token chunker** is invalid and will cause an error. Please note that this restriction is not currently system-enforced and requires your attention.
+:::
+
+## Configurations
+
+### Hierarchy
+
+Specifies the heading level to define chunk boundaries: 
+
+- H1
+- H2
+- H3 (Default)
+- H4
+
+Click **+ Add** to add heading levels here or update the corresponding **Regular Expressions** fields for custom heading patterns.
+
+### Output
+
+The global variable name for the output of the **Title chunker** component, which can be referenced by subsequent components in the ingestion pipeline.
+
+- Default: `chunks`
+- Type: `Array<Object>`

docs/guides/agent/agent_component_reference/chunker_token.md

@@ -0,0 +1,43 @@
+---
+sidebar_position: 32
+slug: /chunker_token_component
+---
+
+# Token chunker component
+
+A component that splits texts into chunks, respecting a maximum token limit and using delimiters to find optimal breakpoints.
+
+---
+
+A **Token chunker** component is a text splitter that creates chunks by respecting a recommended maximum token length, using delimiters to ensure logical chunk breakpoints. It splits long texts into appropriately-sized, semantically related chunks.
+
+
+## Scenario
+
+A **Token chunker** component is optional, usually placed immediately after **Parser** or **Title chunker**.
+
+## Configurations
+
+### Recommended chunk size
+
+The recommended maximum token limit for each created chunk. The **Token chunker** component creates chunks at specified delimiters. If this token limit is reached before a delimiter, a chunk is created at that point.
+
+### Overlapped percent (%)
+
+This defines the overlap percentage between chunks. An appropriate degree of overlap ensures semantic coherence without creating excessive, redundant tokens for the LLM.
+
+- Default: 0
+- Maximum: 30%
+
+
+### Delimiters
+
+Defaults to `\n`. Click the right-hand **Recycle bin** button to remove it, or click **+ Add** to add a delimiter.
+
+
+### Output
+
+The global variable name for the output of the **Token chunker** component, which can be referenced by subsequent components in the ingestion pipeline.
+
+- Default: `chunks`
+- Type: `Array<Object>`

docs/guides/chat/start_chat.md

@@ -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 v0.21.0, if you add custom variables here, the only way you can pass in their values is to call:
+      - As of v0.21.1, 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).
 

docs/guides/dataset/configure_knowledge_base.md

@@ -59,7 +59,7 @@ You can also change a file's chunking method on the **Files** page.
 ![change chunking method](https://raw.githubusercontent.com/infiniflow/ragflow-docs/main/images/change_chunking_method.jpg)
 
 <details>
-  <summary>From v0.21.0 onward, RAGFlow supports ingestion pipeline for customized data ingestion and cleansing workflows.</summary>
+  <summary>From v0.21.1 onward, RAGFlow supports ingestion pipeline for customized data ingestion and cleansing workflows.</summary>
    
   To use a customized data pipeline:
 
@@ -138,7 +138,7 @@ See [Run retrieval test](./run_retrieval_test.md) for details.
 
 ## Search for dataset
 
-As of RAGFlow v0.21.0, the search feature is still in a rudimentary form, supporting only dataset search by name.
+As of RAGFlow v0.21.1, the search feature is still in a rudimentary form, supporting only dataset search by name.
 
 ![search dataset](https://raw.githubusercontent.com/infiniflow/ragflow-docs/main/images/search_datasets.jpg)
 

docs/guides/dataset/select_pdf_parser.md

@@ -35,8 +35,31 @@ RAGFlow isn't one-size-fits-all. It is built for flexibility and supports deeper
 
   - DeepDoc: (Default) The default visual model performing OCR, TSR, and DLR tasks on PDFs, which can be time-consuming.
   - Naive: Skip OCR, TSR, and DLR tasks if *all* your PDFs are plain text.
+  - MinerU: An experimental feature.
   - A third-party visual model provided by a specific model provider.
 
+:::danger IMPORTANG
+MinerU PDF document parsing is available starting from v0.21.1. To use this feature, follow these steps:
+
+1. Before deploying ragflow-server, update your **docker/.env** file:  
+   - Enable `HF_ENDPOINT=https://hf-mirror.com`
+   - Add a MinerU entry: `MINERU_EXECUTABLE=/ragflow/uv_tools/.venv/bin/mineru`
+
+2. Start the ragflow-server and run the following commands inside the container:  
+
+```bash
+mkdir uv_tools
+cd uv_tools
+uv venv .venv
+source .venv/bin/activate
+uv pip install -U "mineru[core]" -i https://mirrors.aliyun.com/pypi/simple
+```
+
+3. Restart the ragflow-server.
+4. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and slect **MinerU** in **PDF parser**.
+5. If you use a custom ingestion pipeline instead, you must also complete the first three steps before selecting **MinerU** in the **Parsing method** section of the **Parser** component.
+:::
+
 :::caution WARNING
 Third-party visual models are marked **Experimental**, because we have not fully tested these models for the aforementioned data extraction tasks.
 :::

docs/guides/manage_files.md

@@ -87,4 +87,4 @@ RAGFlow's file management allows you to download an uploaded file:
 
 ![download_file](https://github.com/infiniflow/ragflow/assets/93570324/cf3b297f-7d9b-4522-bf5f-4f45743e4ed5)
 
-> As of RAGFlow v0.21.0, bulk download is not supported, nor can you download an entire folder. 
+> As of RAGFlow v0.21.1, bulk download is not supported, nor can you download an entire folder. 

docs/guides/manage_users_and_services.md

@@ -46,7 +46,7 @@ The Admin CLI and Admin Service form a client-server architectural suite for RAG
 2. Install ragflow-cli.
 
    ```bash
-   pip install ragflow-cli==0.21.0
+   pip install ragflow-cli==0.21.1
    ```
 
 3. Launch the CLI client:
@@ -348,7 +348,7 @@ Listing all agents of user: lynn_inf@hotmail.com
 +-----------------+-------------+------------+-----------------+
 | canvas_category | canvas_type | permission | title           |
 +-----------------+-------------+------------+-----------------+
-| agent_canvas    | None        | team       | research_helper |
+| agent           | None        | team       | research_helper |
 +-----------------+-------------+------------+-----------------+
 ```
 

docs/guides/tracing.mdx

@@ -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 **≥ 0.21.0** (contains the Langfuse connector)  
+• RAGFlow **≥ 0.21.1** (contains the Langfuse connector)  
 • A Langfuse workspace (cloud or self-hosted) with a _Project Public Key_ and _Secret Key_
 :::
 

docs/guides/upgrade_ragflow.mdx

@@ -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., `v0.21.0`:
+2. Switch to the latest, officially published release, e.g., `v0.21.1`:
 
    ```bash
-   git checkout -f v0.21.0
+   git checkout -f v0.21.1
    ```
 
 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:v0.21.0-slim
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1-slim
 ```
 
   </TabItem>
   <TabItem value="full">
 
 ```bash
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1
 ```
 
   </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.v0.21.0.tar infiniflow/ragflow:v0.21.0
+   docker save -o ragflow.v0.21.1.tar infiniflow/ragflow:v0.21.1
    ```
 3. Copy the **.tar** file to the target server.
 4. Load the **.tar** file into Docker:
    ```bash
-   docker load -i ragflow.v0.21.0.tar
+   docker load -i ragflow.v0.21.1.tar
    ```

docs/quickstart.mdx

@@ -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 v0.21.0 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 v0.21.1 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.
 
 <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 v0.21.0
+   $ git checkout -f v0.21.1
    ```
 
 3. Use the pre-built Docker images and start up the server:
 
    :::tip NOTE
-   The command below downloads the `v0.21.0-slim` edition of the RAGFlow Docker image. Refer to the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.21.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.0` for the full edition `v0.21.0`.
+   The command below downloads the `v0.21.1-slim` edition of the RAGFlow Docker image. Refer to the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.21.1-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.21.1` for the full edition `v0.21.1`.
    :::
 
    ```bash
@@ -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?                  |
 | ------------------- | --------------- | ----------------------------------------- | ------------------------ |
-| `v0.21.0`           | &approx;9       | :heavy_check_mark:                        | Stable release           |
-| `v0.21.0-slim`      | &approx;2       | ❌                                        | Stable release           |
+| `v0.21.1`           | &approx;9       | :heavy_check_mark:                        | Stable release           |
+| `v0.21.1-slim`      | &approx;2       | ❌                                        | Stable release           |
 | `nightly`           | &approx;9       | :heavy_check_mark:                        | *Unstable* nightly build |
 | `nightly-slim`      | &approx;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 `v0.21.0` and `nightly` are:
+The embedding models included in `v0.21.1` and `nightly` are:
 
 - BAAI/bge-large-zh-v1.5
 - maidalun1020/bce-embedding-base_v1

docs/references/glossary.mdx

@@ -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 0.21.0. 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 0.21.1. 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.
 
 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.
 

docs/references/http_api_reference.md

@@ -1198,23 +1198,24 @@ Failure:
 
 ### List documents
 
-**GET** `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp}`
+**GET** `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp}&suffix={file_suffix}&run={run_status}`
 
 Lists documents in a specified dataset.
 
 #### Request
 
 - Method: GET
-- URL: `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp}`
+- URL: `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp}&suffix={file_suffix}&run={run_status}`
 - Headers:
   - `'content-Type: application/json'`
   - `'Authorization: Bearer <YOUR_API_KEY>'`
 
-##### Request example
+##### Request examples
 
+**A basic request with pagination:**
 ```bash
 curl --request GET \
-     --url http://{address}/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp} \
+     --url http://{address}/api/v1/datasets/{dataset_id}/documents?page=1&page_size=10 \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
@@ -1236,10 +1237,34 @@ curl --request GET \
   Indicates whether the retrieved documents should be sorted in descending order. Defaults to `true`.
 - `id`: (*Filter parameter*), `string`  
   The ID of the document to retrieve.
-- `create_time_from`: (*Filter parameter*), `integer`
+- `create_time_from`: (*Filter parameter*), `integer`  
   Unix timestamp for filtering documents created after this time. 0 means no filter. Defaults to `0`.
-- `create_time_to`: (*Filter parameter*), `integer`
+- `create_time_to`: (*Filter parameter*), `integer`  
   Unix timestamp for filtering documents created before this time. 0 means no filter. Defaults to `0`.
+- `suffix`: (*Filter parameter*), `array[string]`  
+  Filter by file suffix. Supports multiple values, e.g., `pdf`, `txt`, and `docx`. Defaults to all suffixes.
+- `run`: (*Filter parameter*), `array[string]`  
+  Filter by document processing status. Supports numeric, text, and mixed formats:  
+  - Numeric format: `["0", "1", "2", "3", "4"]`
+  - Text format: `[UNSTART, RUNNING, CANCEL, DONE, FAIL]`
+  - Mixed format: `[UNSTART, 1, DONE]` (mixing numeric and text formats)
+  - Status mapping:
+    - `0` / `UNSTART`: Document not yet processed
+    - `1` / `RUNNING`: Document is currently being processed
+    - `2` / `CANCEL`: Document processing was cancelled
+    - `3` / `DONE`: Document processing completed successfully
+    - `4` / `FAIL`: Document processing failed  
+  Defaults to all statuses.
+
+##### Usage examples
+
+**A request with multiple filtering parameters**
+
+```bash
+curl --request GET \
+     --url 'http://{address}/api/v1/datasets/{dataset_id}/documents?suffix=pdf&run=DONE&page=1&page_size=10' \
+     --header 'Authorization: Bearer <YOUR_API_KEY>'
+```
 
 #### Response
 
@@ -1270,7 +1295,7 @@ Success:
                 "process_duration": 0.0,
                 "progress": 0.0,
                 "progress_msg": "",
-                "run": "0",
+                "run": "UNSTART",
                 "size": 7,
                 "source_type": "local",
                 "status": "1",

docs/release_notes.md

@@ -9,8 +9,8 @@ Key features, improvements and bug fixes in the latest releases.
 
 :::info
 Each RAGFlow release is available in two editions:
-- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.21.0-slim`
-- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.21.0`
+- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1-slim`
+- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1`
 :::
 
 :::danger IMPORTANT
@@ -22,6 +22,23 @@ 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.
 :::
 
+## v0.21.1
+
+Released on October 23, 2025.
+
+### New features
+
+- Experimental: Adds support for PDF document parsing using MinerU. See [here](./faq.mdx#how-to-use-mineru-to-parse-pdf-documents).
+
+### Improvements
+
+- Enhances UI/UX for the dataset and personal center pages.
+- Upgrades RAGFlow's document engine, [Infinity](https://github.com/infiniflow/infinity), to v0.6.1.
+
+### Fixed issues
+
+- An issue with video parsing.
+
 ## v0.21.0
 
 Released on October 15, 2025.

graphrag/general/extractor.py

@@ -105,16 +105,36 @@ class Extractor:
 
         async def extract_all(doc_id, chunks, max_concurrency=MAX_CONCURRENT_PROCESS_AND_EXTRACT_CHUNK):
             out_results = []
+            error_count = 0
+            max_errors = 3
+
             limiter = trio.Semaphore(max_concurrency)
 
             async def worker(chunk_key_dp: tuple[str, str], idx: int, total: int):
+                nonlocal error_count
                 async with limiter:
-                    await self._process_single_content(chunk_key_dp, idx, total, out_results)
+                    try:
+                        await self._process_single_content(chunk_key_dp, idx, total, out_results)
+                    except Exception as e:
+                        error_count += 1
+                        error_msg = f"Error processing chunk {idx+1}/{total}: {str(e)}"
+                        logging.warning(error_msg)
+                        if self.callback:
+                            self.callback(msg=error_msg)
+
+                        if error_count > max_errors:
+                            raise Exception(f"Maximum error count ({max_errors}) reached. Last errors: {str(e)}")
 
             async with trio.open_nursery() as nursery:
                 for i, ck in enumerate(chunks):
                     nursery.start_soon(worker, (doc_id, ck), i, len(chunks))
 
+            if error_count > 0:
+                warning_msg = f"Completed with {error_count} errors (out of {len(chunks)} chunks processed)"
+                logging.warning(warning_msg)
+                if self.callback:
+                    self.callback(msg=warning_msg)
+
             return out_results
 
         out_results = await extract_all(doc_id, chunks, max_concurrency=MAX_CONCURRENT_PROCESS_AND_EXTRACT_CHUNK)
@@ -129,8 +149,8 @@ class Extractor:
                 maybe_edges[tuple(sorted(k))].extend(v)
             sum_token_count += token_count
         now = trio.current_time()
-        if callback:
-            callback(msg=f"Entities and relationships extraction done, {len(maybe_nodes)} nodes, {len(maybe_edges)} edges, {sum_token_count} tokens, {now - start_ts:.2f}s.")
+        if self.callback:
+            self.callback(msg=f"Entities and relationships extraction done, {len(maybe_nodes)} nodes, {len(maybe_edges)} edges, {sum_token_count} tokens, {now - start_ts:.2f}s.")
         start_ts = now
         logging.info("Entities merging...")
         all_entities_data = []
@@ -138,8 +158,8 @@ class Extractor:
             for en_nm, ents in maybe_nodes.items():
                 nursery.start_soon(self._merge_nodes, en_nm, ents, all_entities_data)
         now = trio.current_time()
-        if callback:
-            callback(msg=f"Entities merging done, {now - start_ts:.2f}s.")
+        if self.callback:
+            self.callback(msg=f"Entities merging done, {now - start_ts:.2f}s.")
 
         start_ts = now
         logging.info("Relationships merging...")
@@ -148,8 +168,8 @@ class Extractor:
             for (src, tgt), rels in maybe_edges.items():
                 nursery.start_soon(self._merge_edges, src, tgt, rels, all_relationships_data)
         now = trio.current_time()
-        if callback:
-            callback(msg=f"Relationships merging done, {now - start_ts:.2f}s.")
+        if self.callback:
+            self.callback(msg=f"Relationships merging done, {now - start_ts:.2f}s.")
 
         if not len(all_entities_data) and not len(all_relationships_data):
             logging.warning("Didn't extract any entities and relationships, maybe your LLM is not working")

helm/values.yaml

@@ -56,7 +56,7 @@ env:
 ragflow:
   image:
     repository: infiniflow/ragflow
-    tag: v0.21.0-slim
+    tag: v0.21.1-slim
     pullPolicy: IfNotPresent
     pullSecrets: []
   # Optional service configuration overrides
@@ -96,7 +96,7 @@ ragflow:
 infinity:
   image:
     repository: infiniflow/infinity
-    tag: v0.6.0
+    tag: v0.6.1
     pullPolicy: IfNotPresent
     pullSecrets: []
   storage:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragflow"
-version = "0.21.0"
+version = "0.21.1"
 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"]
@@ -46,7 +46,7 @@ dependencies = [
     "html-text==0.6.2",
     "httpx[socks]>=0.28.1,<0.29.0",
     "huggingface-hub>=0.25.0,<0.26.0",
-    "infinity-sdk==0.6.0",
+    "infinity-sdk==0.6.1",
     "infinity-emb>=0.0.66,<0.0.67",
     "itsdangerous==2.1.2",
     "json-repair==0.35.0",

rag/app/book.py

@@ -20,11 +20,14 @@ import re
 from io import BytesIO
 
 from deepdoc.parser.utils import get_text
+from rag.app import naive
 from rag.nlp import bullets_category, is_english,remove_contents_table, \
     hierarchical_merge, make_colon_as_title, naive_merge, random_choices, tokenize_table, \
     tokenize_chunks
 from rag.nlp import rag_tokenizer
-from deepdoc.parser import PdfParser, DocxParser, PlainParser, HtmlParser
+from deepdoc.parser import PdfParser, PlainParser, HtmlParser
+from deepdoc.parser.figure_parser import vision_figure_parser_pdf_wrapper,vision_figure_parser_docx_wrapper
+from PIL import Image
 
 
 class Pdf(PdfParser):
@@ -81,13 +84,15 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     sections, tbls = [], []
     if re.search(r"\.docx$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        doc_parser = DocxParser()
+        doc_parser = naive.Docx()
         # TODO: table of contents need to be removed
         sections, tbls = doc_parser(
-            binary if binary else filename, from_page=from_page, to_page=to_page)
+            filename, binary=binary, from_page=from_page, to_page=to_page)
         remove_contents_table(sections, eng=is_english(
             random_choices([t for t, _ in sections], k=200)))
-        tbls = [((None, lns), None) for lns in tbls]
+        tbls=vision_figure_parser_docx_wrapper(sections=sections,tbls=tbls,callback=callback,**kwargs)
+        # tbls = [((None, lns), None) for lns in tbls]
+        sections=[(item[0],item[1] if item[1] is not None else "") for item in sections if not isinstance(item[1], Image.Image)]
         callback(0.8, "Finish parsing.")
 
     elif re.search(r"\.pdf$", filename, re.IGNORECASE):
@@ -96,6 +101,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             pdf_parser = PlainParser()
         sections, tbls = pdf_parser(filename if not binary else binary,
                                     from_page=from_page, to_page=to_page, callback=callback)
+        tbls=vision_figure_parser_pdf_wrapper(tbls=tbls,callback=callback,**kwargs)
 
     elif re.search(r"\.txt$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")

rag/app/manual.py

@@ -23,6 +23,7 @@ from io import BytesIO
 from rag.nlp import rag_tokenizer, tokenize, tokenize_table, bullets_category, title_frequency, tokenize_chunks, docx_question_level
 from rag.utils import num_tokens_from_string
 from deepdoc.parser import PdfParser, PlainParser, DocxParser
+from deepdoc.parser.figure_parser import vision_figure_parser_pdf_wrapper,vision_figure_parser_docx_wrapper
 from docx import Document
 from PIL import Image
 
@@ -252,7 +253,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             tk_cnt = num_tokens_from_string(txt)
             if sec_id > -1:
                 last_sid = sec_id
-
+        tbls=vision_figure_parser_pdf_wrapper(tbls=tbls,callback=callback,**kwargs)
         res = tokenize_table(tbls, doc, eng)
         res.extend(tokenize_chunks(chunks, doc, eng, pdf_parser))
         return res
@@ -261,6 +262,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         docx_parser = Docx()
         ti_list, tbls = docx_parser(filename, binary,
                                     from_page=0, to_page=10000, callback=callback)
+        tbls=vision_figure_parser_docx_wrapper(sections=ti_list,tbls=tbls,callback=callback,**kwargs)
         res = tokenize_table(tbls, doc, eng)
         for text, image in ti_list:
             d = copy.deepcopy(doc)

rag/app/naive.py

@@ -32,7 +32,7 @@ from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from api.utils.file_utils import extract_embed_file
 from deepdoc.parser import DocxParser, ExcelParser, HtmlParser, JsonParser, MarkdownElementExtractor, MarkdownParser, PdfParser, TxtParser
-from deepdoc.parser.figure_parser import VisionFigureParser, vision_figure_parser_figure_data_wrapper
+from deepdoc.parser.figure_parser import VisionFigureParser,vision_figure_parser_docx_wrapper,vision_figure_parser_pdf_wrapper
 from deepdoc.parser.pdf_parser import PlainParser, VisionParser
 from deepdoc.parser.mineru_parser import MinerUParser
 from rag.nlp import concat_img, find_codec, naive_merge, naive_merge_with_images, naive_merge_docx, rag_tokenizer, tokenize_chunks, tokenize_chunks_with_images, tokenize_table
@@ -475,24 +475,13 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     if re.search(r"\.docx$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
 
-        try:
-            vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT)
-            callback(0.15, "Visual model detected. Attempting to enhance figure extraction...")
-        except Exception:
-            vision_model = None
+        
 
         # fix "There is no item named 'word/NULL' in the archive", referring to https://github.com/python-openxml/python-docx/issues/1105#issuecomment-1298075246
         _SerializedRelationships.load_from_xml = load_from_xml_v2
         sections, tables = Docx()(filename, binary)
 
-        if vision_model:
-            figures_data = vision_figure_parser_figure_data_wrapper(sections)
-            try:
-                docx_vision_parser = VisionFigureParser(vision_model=vision_model, figures_data=figures_data, **kwargs)
-                boosted_figures = docx_vision_parser(callback=callback)
-                tables.extend(boosted_figures)
-            except Exception as e:
-                callback(0.6, f"Visual model error: {e}. Skipping figure parsing enhancement.")
+        tables=vision_figure_parser_docx_wrapper(sections=sections,tbls=tables,callback=callback,**kwargs)
 
         res = tokenize_table(tables, doc, is_english)
         callback(0.8, "Finish parsing.")
@@ -521,25 +510,8 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
         if layout_recognizer == "DeepDOC":
             pdf_parser = Pdf()
-
-            try:
-                vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT)
-                callback(0.15, "Visual model detected. Attempting to enhance figure extraction...")
-            except Exception:
-                vision_model = None
-
-            if vision_model:
-                sections, tables, figures = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback, separate_tables_figures=True)
-                callback(0.5, "Basic parsing complete. Proceeding with figure enhancement...")
-                try:
-                    pdf_vision_parser = VisionFigureParser(vision_model=vision_model, figures_data=figures, **kwargs)
-                    boosted_figures = pdf_vision_parser(callback=callback)
-                    tables.extend(boosted_figures)
-                except Exception as e:
-                    callback(0.6, f"Visual model error: {e}. Skipping figure parsing enhancement.")
-                    tables.extend(figures)
-            else:
-                sections, tables = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback)
+            sections, tables = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback)
+            tables=vision_figure_parser_pdf_wrapper(tbls=tables,callback=callback,**kwargs)
 
             res = tokenize_table(tables, doc, is_english)
             callback(0.8, "Finish parsing.")

rag/app/one.py

@@ -23,6 +23,7 @@ from deepdoc.parser.utils import get_text
 from rag.app import naive
 from rag.nlp import rag_tokenizer, tokenize
 from deepdoc.parser import PdfParser, ExcelParser, PlainParser, HtmlParser
+from deepdoc.parser.figure_parser import vision_figure_parser_pdf_wrapper,vision_figure_parser_docx_wrapper
 
 
 class Pdf(PdfParser):
@@ -57,13 +58,8 @@ class Pdf(PdfParser):
 
         sections = [(b["text"], self.get_position(b, zoomin))
                     for i, b in enumerate(self.boxes)]
-        for (img, rows), poss in tbls:
-            if not rows:
-                continue
-            sections.append((rows if isinstance(rows, str) else rows[0],
-                             [(p[0] + 1 - from_page, p[1], p[2], p[3], p[4]) for p in poss]))
         return [(txt, "") for txt, _ in sorted(sections, key=lambda x: (
-            x[-1][0][0], x[-1][0][3], x[-1][0][1]))], None
+            x[-1][0][0], x[-1][0][3], x[-1][0][1]))], tbls
 
 
 def chunk(filename, binary=None, from_page=0, to_page=100000,
@@ -80,6 +76,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     if re.search(r"\.docx$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
         sections, tbls = naive.Docx()(filename, binary)
+        tbls=vision_figure_parser_docx_wrapper(sections=sections,tbls=tbls,callback=callback,**kwargs)
         sections = [s for s, _ in sections if s]
         for (_, html), _ in tbls:
             sections.append(html)
@@ -89,8 +86,14 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         pdf_parser = Pdf()
         if parser_config.get("layout_recognize", "DeepDOC") == "Plain Text":
             pdf_parser = PlainParser()
-        sections, _ = pdf_parser(
+        sections, tbls = pdf_parser(
             filename if not binary else binary, to_page=to_page, callback=callback)
+        tbls=vision_figure_parser_pdf_wrapper(tbls=tbls,callback=callback,**kwargs)
+        for (img, rows), poss in tbls:
+            if not rows:
+                continue
+            sections.append((rows if isinstance(rows, str) else rows[0],
+                             [(p[0] + 1 - from_page, p[1], p[2], p[3], p[4]) for p in poss]))
         sections = [s for s, _ in sections if s]
 
     elif re.search(r"\.xlsx?$", filename, re.IGNORECASE):

rag/app/paper.py

@@ -18,12 +18,12 @@ import logging
 import copy
 import re
 
+from deepdoc.parser.figure_parser import vision_figure_parser_pdf_wrapper
 from api.db import ParserType
 from rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, title_frequency, tokenize_chunks
 from deepdoc.parser import PdfParser, PlainParser
 import numpy as np
 
-
 class Pdf(PdfParser):
     def __init__(self):
         self.model_speciess = ParserType.PAPER.value
@@ -160,6 +160,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             pdf_parser = Pdf()
             paper = pdf_parser(filename if not binary else binary,
                                from_page=from_page, to_page=to_page, callback=callback)
+        tbls=paper["tables"]
+        tbls=vision_figure_parser_pdf_wrapper(tbls=tbls,callback=callback,**kwargs)
+        paper["tables"] = tbls
     else:
         raise NotImplementedError("file type not supported yet(pdf supported)")
 

rag/app/picture.py

@@ -29,7 +29,7 @@ from rag.utils import clean_markdown_block
 ocr = OCR()
 
 # Gemini supported MIME types
-VIDEO_EXTS = [".mp4", ".mov", ".avi", ".flv", ".mpeg", ".mpg", ".webm", ".wmv", ".3gp", ".3gpp"]
+VIDEO_EXTS = [".mp4", ".mov", ".avi", ".flv", ".mpeg", ".mpg", ".webm", ".wmv", ".3gp", ".3gpp", ".mkv"]
 
 
 def chunk(filename, binary, tenant_id, lang, callback=None, **kwargs):

rag/flow/parser/parser.py

@@ -29,6 +29,7 @@ from api.db.services.llm_service import LLMBundle
 from api.utils import get_uuid
 from api.utils.base64_image import image2id
 from deepdoc.parser import ExcelParser
+from deepdoc.parser.mineru_parser import MinerUParser
 from deepdoc.parser.pdf_parser import PlainParser, RAGFlowPdfParser, VisionParser
 from rag.app.naive import Docx
 from rag.flow.base import ProcessBase, ProcessParamBase
@@ -138,9 +139,16 @@ class ParserParam(ProcessParamBase):
                     "oggvorbis",
                     "ape"
                 ],
-                "output_format": "json",
+                "output_format": "text",
+            },
+            "video": {
+                "suffix":[
+                    "mp4",
+                    "avi",
+                    "mkv"
+                ],
+                "output_format": "text",
             },
-            "video": {},
         }
 
     def check(self):
@@ -149,7 +157,7 @@ class ParserParam(ProcessParamBase):
             pdf_parse_method = pdf_config.get("parse_method", "")
             self.check_empty(pdf_parse_method, "Parse method abnormal.")
 
-            if pdf_parse_method.lower() not in ["deepdoc", "plain_text"]:
+            if pdf_parse_method.lower() not in ["deepdoc", "plain_text", "mineru"]:
                 self.check_empty(pdf_config.get("lang", ""), "PDF VLM language")
 
             pdf_output_format = pdf_config.get("output_format", "")
@@ -185,6 +193,10 @@ class ParserParam(ProcessParamBase):
         if audio_config:
             self.check_empty(audio_config.get("llm_id"), "Audio VLM")
 
+        video_config = self.setups.get("video", "")
+        if video_config:
+            self.check_empty(video_config.get("llm_id"), "Video VLM")
+
         email_config = self.setups.get("email", "")
         if email_config:
             email_output_format = email_config.get("output_format", "")
@@ -207,13 +219,34 @@ class Parser(ProcessBase):
         elif conf.get("parse_method").lower() == "plain_text":
             lines, _ = PlainParser()(blob)
             bboxes = [{"text": t} for t, _ in lines]
+        elif conf.get("parse_method").lower() == "mineru":
+            mineru_executable = os.environ.get("MINERU_EXECUTABLE", "mineru")
+            pdf_parser = MinerUParser(mineru_path=mineru_executable)
+            if not pdf_parser.check_installation():
+                raise RuntimeError("MinerU not found. Please install it via: pip install -U 'mineru[core]'.")
+
+            lines, _ = pdf_parser.parse_pdf(
+                filepath=name,
+                binary=blob,
+                callback=self.callback,
+                output_dir=os.environ.get("MINERU_OUTPUT_DIR", ""),
+                delete_output=bool(int(os.environ.get("MINERU_DELETE_OUTPUT", 1))),
+            )
+            bboxes = []
+            for t, poss in lines:
+                box = {
+                    "image": pdf_parser.crop(poss, 1),
+                    "positions": [[pos[0][-1], *pos[1:]] for pos in pdf_parser.extract_positions(poss)],
+                    "text": t,
+                }
+                bboxes.append(box)
         else:
             vision_model = LLMBundle(self._canvas._tenant_id, LLMType.IMAGE2TEXT, llm_name=conf.get("parse_method"), lang=self._param.setups["pdf"].get("lang"))
             lines, _ = VisionParser(vision_model=vision_model)(blob, callback=self.callback)
             bboxes = []
             for t, poss in lines:
-                pn, x0, x1, top, bott = poss.split(" ")
-                bboxes.append({"page_number": int(pn), "x0": float(x0), "x1": float(x1), "top": float(top), "bottom": float(bott), "text": t})
+                for pn, x0, x1, top, bott in RAGFlowPdfParser.extract_positions(poss):
+                    bboxes.append({"page_number": int(pn[0]), "x0": float(x0), "x1": float(x1), "top": float(top), "bottom": float(bott), "text": t})
 
         if conf.get("output_format") == "json":
             self.set_output("json", bboxes)
@@ -357,6 +390,17 @@ class Parser(ProcessBase):
 
             self.set_output("text", txt)
 
+    def _video(self, name, blob):
+        self.callback(random.randint(1, 5) / 100.0, "Start to work on an video.")
+
+        conf = self._param.setups["video"]
+        self.set_output("output_format", conf["output_format"])
+
+        cv_mdl = LLMBundle(self._canvas.get_tenant_id(), LLMType.IMAGE2TEXT)
+        txt = cv_mdl.chat(system="", history=[], gen_conf={}, video_bytes=blob, filename=name)
+
+        self.set_output("text", txt)
+
     def _email(self, name, blob):
         self.callback(random.randint(1, 5) / 100.0, "Start to work on an email.")
 
@@ -483,6 +527,7 @@ class Parser(ProcessBase):
             "word": self._word,
             "image": self._image,
             "audio": self._audio,
+            "video": self._video,
             "email": self._email,
         }
         try:

rag/llm/chat_model.py

@@ -167,7 +167,7 @@ class Base(ABC):
         ans = response.choices[0].message.content.strip()
         if response.choices[0].finish_reason == "length":
             ans = self._length_stop(ans)
-        return ans, self.total_token_count(response)
+        return ans, total_token_count_from_response(response)
 
     def _chat_streamly(self, history, gen_conf, **kwargs):
         logging.info("[HISTORY STREAMLY]" + json.dumps(history, ensure_ascii=False, indent=4))
@@ -193,7 +193,7 @@ class Base(ABC):
                 reasoning_start = False
                 ans = resp.choices[0].delta.content
 
-            tol = self.total_token_count(resp)
+            tol = total_token_count_from_response(resp)
             if not tol:
                 tol = num_tokens_from_string(resp.choices[0].delta.content)
 
@@ -283,7 +283,7 @@ class Base(ABC):
                 for _ in range(self.max_rounds + 1):
                     logging.info(f"{self.tools=}")
                     response = self.client.chat.completions.create(model=self.model_name, messages=history, tools=self.tools, tool_choice="auto", **gen_conf)
-                    tk_count += self.total_token_count(response)
+                    tk_count += total_token_count_from_response(response)
                     if any([not response.choices, not response.choices[0].message]):
                         raise Exception(f"500 response structure error. Response: {response}")
 
@@ -401,7 +401,7 @@ class Base(ABC):
                             answer += resp.choices[0].delta.content
                             yield resp.choices[0].delta.content
 
-                        tol = self.total_token_count(resp)
+                        tol = total_token_count_from_response(resp)
                         if not tol:
                             total_tokens += num_tokens_from_string(resp.choices[0].delta.content)
                         else:
@@ -437,7 +437,7 @@ class Base(ABC):
                     if not resp.choices[0].delta.content:
                         resp.choices[0].delta.content = ""
                         continue
-                    tol = self.total_token_count(resp)
+                    tol = total_token_count_from_response(resp)
                     if not tol:
                         total_tokens += num_tokens_from_string(resp.choices[0].delta.content)
                     else:
@@ -472,9 +472,6 @@ class Base(ABC):
 
         yield total_tokens
 
-    def total_token_count(self, resp):
-        return total_token_count_from_response(resp)
-
     def _calculate_dynamic_ctx(self, history):
         """Calculate dynamic context window size"""
 
@@ -604,7 +601,7 @@ class BaiChuanChat(Base):
                 ans += LENGTH_NOTIFICATION_CN
             else:
                 ans += LENGTH_NOTIFICATION_EN
-        return ans, self.total_token_count(response)
+        return ans, total_token_count_from_response(response)
 
     def chat_streamly(self, system, history, gen_conf={}, **kwargs):
         if system and history and history[0].get("role") != "system":
@@ -627,7 +624,7 @@ class BaiChuanChat(Base):
                 if not resp.choices[0].delta.content:
                     resp.choices[0].delta.content = ""
                 ans = resp.choices[0].delta.content
-                tol = self.total_token_count(resp)
+                tol = total_token_count_from_response(resp)
                 if not tol:
                     total_tokens += num_tokens_from_string(resp.choices[0].delta.content)
                 else:
@@ -691,9 +688,9 @@ class ZhipuChat(Base):
                         ans += LENGTH_NOTIFICATION_CN
                     else:
                         ans += LENGTH_NOTIFICATION_EN
-                    tk_count = self.total_token_count(resp)
+                    tk_count = total_token_count_from_response(resp)
                 if resp.choices[0].finish_reason == "stop":
-                    tk_count = self.total_token_count(resp)
+                    tk_count = total_token_count_from_response(resp)
                 yield ans
         except Exception as e:
             yield ans + "\n**ERROR**: " + str(e)
@@ -812,7 +809,7 @@ class MiniMaxChat(Base):
                 ans += LENGTH_NOTIFICATION_CN
             else:
                 ans += LENGTH_NOTIFICATION_EN
-        return ans, self.total_token_count(response)
+        return ans, total_token_count_from_response(response)
 
     def chat_streamly(self, system, history, gen_conf):
         if system and history and history[0].get("role") != "system":
@@ -847,7 +844,7 @@ class MiniMaxChat(Base):
                 if "choices" in resp and "delta" in resp["choices"][0]:
                     text = resp["choices"][0]["delta"]["content"]
                 ans = text
-                tol = self.total_token_count(resp)
+                tol = total_token_count_from_response(resp)
                 if not tol:
                     total_tokens += num_tokens_from_string(text)
                 else:
@@ -886,7 +883,7 @@ class MistralChat(Base):
                 ans += LENGTH_NOTIFICATION_CN
             else:
                 ans += LENGTH_NOTIFICATION_EN
-        return ans, self.total_token_count(response)
+        return ans, total_token_count_from_response(response)
 
     def chat_streamly(self, system, history, gen_conf={}, **kwargs):
         if system and history and history[0].get("role") != "system":
@@ -1110,7 +1107,7 @@ class BaiduYiyanChat(Base):
         system = history[0]["content"] if history and history[0]["role"] == "system" else ""
         response = self.client.do(model=self.model_name, messages=[h for h in history if h["role"] != "system"], system=system, **gen_conf).body
         ans = response["result"]
-        return ans, self.total_token_count(response)
+        return ans, total_token_count_from_response(response)
 
     def chat_streamly(self, system, history, gen_conf={}, **kwargs):
         gen_conf["penalty_score"] = ((gen_conf.get("presence_penalty", 0) + gen_conf.get("frequency_penalty", 0)) / 2) + 1
@@ -1124,7 +1121,7 @@ class BaiduYiyanChat(Base):
             for resp in response:
                 resp = resp.body
                 ans = resp["result"]
-                total_tokens = self.total_token_count(resp)
+                total_tokens = total_token_count_from_response(resp)
 
                 yield ans
 
@@ -1478,7 +1475,7 @@ class LiteLLMBase(ABC):
         if response.choices[0].finish_reason == "length":
             ans = self._length_stop(ans)
 
-        return ans, self.total_token_count(response)
+        return ans, total_token_count_from_response(response)
 
     def _chat_streamly(self, history, gen_conf, **kwargs):
         logging.info("[HISTORY STREAMLY]" + json.dumps(history, ensure_ascii=False, indent=4))
@@ -1512,7 +1509,7 @@ class LiteLLMBase(ABC):
                 reasoning_start = False
                 ans = delta.content
 
-            tol = self.total_token_count(resp)
+            tol = total_token_count_from_response(resp)
             if not tol:
                 tol = num_tokens_from_string(delta.content)
 
@@ -1665,7 +1662,7 @@ class LiteLLMBase(ABC):
                         timeout=self.timeout,
                     )
 
-                    tk_count += self.total_token_count(response)
+                    tk_count += total_token_count_from_response(response)
 
                     if not hasattr(response, "choices") or not response.choices or not response.choices[0].message:
                         raise Exception(f"500 response structure error. Response: {response}")
@@ -1797,7 +1794,7 @@ class LiteLLMBase(ABC):
                             answer += delta.content
                             yield delta.content
 
-                        tol = self.total_token_count(resp)
+                        tol = total_token_count_from_response(resp)
                         if not tol:
                             total_tokens += num_tokens_from_string(delta.content)
                         else:
@@ -1846,7 +1843,7 @@ class LiteLLMBase(ABC):
                     delta = resp.choices[0].delta
                     if not hasattr(delta, "content") or delta.content is None:
                         continue
-                    tol = self.total_token_count(resp)
+                    tol = total_token_count_from_response(resp)
                     if not tol:
                         total_tokens += num_tokens_from_string(delta.content)
                     else:
@@ -1880,17 +1877,6 @@ class LiteLLMBase(ABC):
 
         yield total_tokens
 
-    def total_token_count(self, resp):
-        try:
-            return resp.usage.total_tokens
-        except Exception:
-            pass
-        try:
-            return resp["usage"]["total_tokens"]
-        except Exception:
-            pass
-        return 0
-
     def _calculate_dynamic_ctx(self, history):
         """Calculate dynamic context window size"""
 

rag/llm/cv_model.py

@@ -13,13 +13,16 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+
 import base64
 import json
 import os
+import tempfile
 import logging
 from abc import ABC
 from copy import deepcopy
 from io import BytesIO
+from pathlib import Path
 from urllib.parse import urljoin
 import requests
 from openai import OpenAI
@@ -47,7 +50,7 @@ class Base(ABC):
     def describe_with_prompt(self, image, prompt=None):
         raise NotImplementedError("Please implement encode method!")
 
-    def _form_history(self, system, history, images=[]):
+    def _form_history(self, system, history, images=None):
         hist = []
         if system:
             hist.append({"role": "system", "content": system})
@@ -75,7 +78,7 @@ class Base(ABC):
             })
         return pmpt
 
-    def chat(self, system, history, gen_conf, images=[], **kwargs):
+    def chat(self, system, history, gen_conf, images=None, **kwargs):
         try:
             response = self.client.chat.completions.create(
                 model=self.model_name,
@@ -86,7 +89,7 @@ class Base(ABC):
         except Exception as e:
             return "**ERROR**: " + str(e), 0
 
-    def chat_streamly(self, system, history, gen_conf, images=[], **kwargs):
+    def chat_streamly(self, system, history, gen_conf, images=None, **kwargs):
         ans = ""
         tk_count = 0
         try:
@@ -171,6 +174,7 @@ class GptV4(Base):
     def __init__(self, key, model_name="gpt-4-vision-preview", lang="Chinese", base_url="https://api.openai.com/v1", **kwargs):
         if not base_url:
             base_url = "https://api.openai.com/v1"
+        self.api_key = key
         self.client = OpenAI(api_key=key, base_url=base_url)
         self.model_name = model_name
         self.lang = lang
@@ -224,6 +228,61 @@ class QWenCV(GptV4):
             base_url = "https://dashscope.aliyuncs.com/compatible-mode/v1"
         super().__init__(key, model_name, lang=lang, base_url=base_url, **kwargs)
 
+    def chat(self, system, history, gen_conf, images=None, video_bytes=None, filename=""):
+        if video_bytes:
+            try:
+                summary, summary_num_tokens = self._process_video(video_bytes, filename)
+                return summary, summary_num_tokens
+            except Exception as e:
+                return "**ERROR**: " + str(e), 0
+
+        return "**ERROR**: Method chat not supported yet.", 0
+
+    def _process_video(self, video_bytes, filename):
+        from dashscope import MultiModalConversation
+
+        video_suffix = Path(filename).suffix or ".mp4"
+        with tempfile.NamedTemporaryFile(delete=False, suffix=video_suffix) as tmp:
+            tmp.write(video_bytes)
+            tmp_path = tmp.name
+
+        video_path = f"file://{tmp_path}"
+        messages = [
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "video": video_path,
+                        "fps": 2,
+                    },
+                    {
+                        "text": "Please summarize this video in proper sentences.",
+                    },
+                ],
+            }
+        ]
+
+        def call_api():
+            response = MultiModalConversation.call(
+                api_key=self.api_key,
+                model=self.model_name,
+                messages=messages,
+            )
+            summary = response["output"]["choices"][0]["message"].content[0]["text"]
+            return summary, num_tokens_from_string(summary)
+
+        try:
+            return call_api()
+        except Exception as e1:
+            import dashscope
+
+            dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1"
+            try:
+                return call_api()
+            except Exception as e2:
+                raise RuntimeError(f"Both default and intl endpoint failed.\nFirst error: {e1}\nSecond error: {e2}")
+
+
 
 class HunyuanCV(GptV4):
     _FACTORY_NAME = "Tencent Hunyuan"
@@ -447,7 +506,7 @@ class OllamaCV(Base):
             options["frequency_penalty"] = gen_conf["frequency_penalty"]
         return options
 
-    def _form_history(self, system, history, images=[]):
+    def _form_history(self, system, history, images=None):
         hist = deepcopy(history)
         if system and hist[0]["role"] == "user":
             hist.insert(0, {"role": "system", "content": system})
@@ -488,7 +547,7 @@ class OllamaCV(Base):
         except Exception as e:
             return "**ERROR**: " + str(e), 0
 
-    def chat(self, system, history, gen_conf, images=[]):
+    def chat(self, system, history, gen_conf, images=None):
         try:
             response = self.client.chat(
                 model=self.model_name,
@@ -502,7 +561,7 @@ class OllamaCV(Base):
         except Exception as e:
             return "**ERROR**: " + str(e), 0
 
-    def chat_streamly(self, system, history, gen_conf, images=[]):
+    def chat_streamly(self, system, history, gen_conf, images=None):
         ans = ""
         try:
             response = self.client.chat(
@@ -537,7 +596,7 @@ class GeminiCV(Base):
         self.lang = lang
         Base.__init__(self, **kwargs)
 
-    def _form_history(self, system, history, images=[]):
+    def _form_history(self, system, history, images=None):
         hist = []
         if system:
             hist.append({"role": "user", "parts": [system, history[0]["content"]]})
@@ -574,7 +633,7 @@ class GeminiCV(Base):
                 return res.text, total_token_count_from_response(res)
 
 
-    def chat(self, system, history, gen_conf, images=[], video_bytes=None, filename=""):
+    def chat(self, system, history, gen_conf, images=None, video_bytes=None, filename=""):
         if video_bytes:
             try:
                 summary, summary_num_tokens = self._process_video(video_bytes, filename)
@@ -592,7 +651,7 @@ class GeminiCV(Base):
         except Exception as e:
             return "**ERROR**: " + str(e), 0
 
-    def chat_streamly(self, system, history, gen_conf, images=[]):
+    def chat_streamly(self, system, history, gen_conf, images=None):
         ans = ""
         response = None
         try:
@@ -616,8 +675,6 @@ class GeminiCV(Base):
     def _process_video(self, video_bytes, filename):
         from google import genai
         from google.genai import types
-        import tempfile
-        from pathlib import Path
 
         video_size_mb = len(video_bytes) / (1024 * 1024)
         client = genai.Client(api_key=self.api_key)
@@ -725,7 +782,7 @@ class NvidiaCV(Base):
             total_token_count_from_response(response)
         )
 
-    def chat(self, system, history, gen_conf, images=[], **kwargs):
+    def chat(self, system, history, gen_conf, images=None, **kwargs):
         try:
             response = self._request(self._form_history(system, history, images), gen_conf)
             return (
@@ -735,7 +792,7 @@ class NvidiaCV(Base):
         except Exception as e:
             return "**ERROR**: " + str(e), 0
 
-    def chat_streamly(self, system, history, gen_conf, images=[], **kwargs):
+    def chat_streamly(self, system, history, gen_conf, images=None, **kwargs):
         total_tokens = 0
         try:
             response = self._request(self._form_history(system, history, images), gen_conf)
@@ -801,7 +858,7 @@ class AnthropicCV(Base):
             gen_conf["max_tokens"] = self.max_tokens
         return gen_conf
 
-    def chat(self, system, history, gen_conf, images=[]):
+    def chat(self, system, history, gen_conf, images=None):
         gen_conf = self._clean_conf(gen_conf)
         ans = ""
         try:
@@ -822,7 +879,7 @@ class AnthropicCV(Base):
         except Exception as e:
             return ans + "\n**ERROR**: " + str(e), 0
 
-    def chat_streamly(self, system, history, gen_conf, images=[]):
+    def chat_streamly(self, system, history, gen_conf, images=None):
         gen_conf = self._clean_conf(gen_conf)
         total_tokens = 0
         try:
@@ -906,13 +963,13 @@ class GoogleCV(AnthropicCV, GeminiCV):
         else:
             return GeminiCV.describe_with_prompt(self, image, prompt)
 
-    def chat(self, system, history, gen_conf, images=[]):
+    def chat(self, system, history, gen_conf, images=None):
         if "claude" in self.model_name:
             return AnthropicCV.chat(self, system, history, gen_conf, images)
         else:
             return GeminiCV.chat(self, system, history, gen_conf, images)
 
-    def chat_streamly(self, system, history, gen_conf, images=[]):
+    def chat_streamly(self, system, history, gen_conf, images=None):
         if "claude" in self.model_name:
             for ans in AnthropicCV.chat_streamly(self, system, history, gen_conf, images):
                 yield ans

rag/nlp/__init__.py

@@ -459,12 +459,10 @@ def tree_merge(bull, sections, depth):
                 return len(BULLET_PATTERN[bull])+1, text
             else:
                 return len(BULLET_PATTERN[bull])+2, text
-    
     level_set = set()
     lines = []
     for section in sections:
         level, text = get_level(bull, section)
-
         if not text.strip("\n"):
             continue
             
@@ -797,8 +795,8 @@ class Node:
     def __init__(self, level, depth=-1, texts=None):
         self.level = level
         self.depth = depth
-        self.texts = texts if texts is not None else []  # 存放内容
-        self.children = []  # 子节点
+        self.texts = texts or []
+        self.children = [] 
 
     def add_child(self, child_node):
         self.children.append(child_node)
@@ -825,35 +823,51 @@ class Node:
         return f"Node(level={self.level}, texts={self.texts}, children={len(self.children)})"
 
     def build_tree(self, lines):
-        stack = [self]  
-        for line in lines:
-            level, text = line
-            node = Node(level=level, texts=[text])
-
-            if level <= self.depth or self.depth == -1:
-                while stack and level <= stack[-1].get_level():
-                    stack.pop()
-
-                stack[-1].add_child(node)
-                stack.append(node)
-            else:
+        stack = [self]
+        for level, text in lines:
+            if self.depth != -1 and level > self.depth:
+                # Beyond target depth: merge content into the current leaf instead of creating deeper nodes
                 stack[-1].add_text(text)
-        return self  
+                continue
+
+            # Move up until we find the proper parent whose level is strictly smaller than current
+            while len(stack) > 1 and level <= stack[-1].get_level():
+                stack.pop()
+
+            node = Node(level=level, texts=[text])
+            # Attach as child of current parent and descend
+            stack[-1].add_child(node)
+            stack.append(node)
+
+        return self
 
     def get_tree(self):
         tree_list = []  
-        self._dfs(self, tree_list, 0, [])
+        self._dfs(self, tree_list, [])
         return tree_list
 
-    def _dfs(self, node, tree_list, current_depth, titles):
+    def _dfs(self, node, tree_list, titles):
+        level = node.get_level()
+        texts = node.get_texts()
+        child = node.get_children()
 
-        if node.get_texts():
-            if 0 < node.get_level() < self.depth:
-                titles.extend(node.get_texts())
-            else:
-                combined_text = ["\n".join(titles + node.get_texts())]
-                tree_list.append(combined_text)
+        if level == 0 and texts:
+            tree_list.append("\n".join(titles+texts))
 
+        # Titles within configured depth are accumulated into the current path
+        if 1 <= level <= self.depth:
+            path_titles = titles + texts
+        else:
+            path_titles = titles
 
-        for child in node.get_children():
-            self._dfs(child, tree_list, current_depth + 1, titles.copy())
+        # Body outside the depth limit becomes its own chunk under the current title path
+        if level > self.depth and texts:
+            tree_list.append("\n".join(path_titles + texts))
+
+        # A leaf title within depth emits its title path as a chunk (header-only section)
+        elif not child and (1 <= level <= self.depth):
+            tree_list.append("\n".join(path_titles))
+        
+        # Recurse into children with the updated title path
+        for c in child:
+            self._dfs(c, tree_list, path_titles)

rag/nlp/search.py

@@ -388,6 +388,7 @@ class Dealer:
             else:
                 # Don't need rerank here since Infinity normalizes each way score before fusion.
                 sim = [sres.field[id].get("_score", 0.0) for id in sres.ids]
+                sim = [s if s is not None else 0. for s in sim]
                 tsim = sim
                 vsim = sim
         # Already paginated in search function

rag/raptor.py

@@ -114,7 +114,7 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
                             ),
                         }
                     ],
-                    {"max_tokens": self._max_token},
+                    {"max_tokens": max(self._max_token, 512)}, # fix issue:  #10235
                 )
                 cnt = re.sub(
                     "(······\n由于长度的原因，回答被截断了，要继续吗？|For the content length reason, it stopped, continue?)",

rag/svr/task_executor.py

@@ -228,9 +228,10 @@ async def collect():
     canceled = False
     if msg.get("doc_id", "") in [GRAPH_RAPTOR_FAKE_DOC_ID, CANVAS_DEBUG_DOC_ID]:
         task = msg
-        if task["task_type"] in ["graphrag", "raptor", "mindmap"] and msg.get("doc_ids", []):
+        if task["task_type"] in ["graphrag", "raptor", "mindmap"]:
             task = TaskService.get_task(msg["id"], msg["doc_ids"])
-            task["doc_ids"] = msg["doc_ids"]
+            task["doc_id"] = msg["doc_id"]
+            task["doc_ids"] = msg.get("doc_ids", []) or []
     else:
         task = TaskService.get_task(msg["id"])
 
@@ -1052,13 +1053,14 @@ async def task_manager():
 
 async def main():
     logging.info(r"""
-  ______           __      ______                     __
- /_  __/___ ______/ /__   / ____/  _____  _______  __/ /_____  _____
-  / / / __ `/ ___/ //_/  / __/ | |/_/ _ \/ ___/ / / / __/ __ \/ ___/
- / / / /_/ (__  ) ,<    / /____>  </  __/ /__/ /_/ / /_/ /_/ / /
-/_/  \__,_/____/_/|_|  /_____/_/|_|\___/\___/\__,_/\__/\____/_/
+    ____                      __  _
+   /  _/___  ____ ____  _____/ /_(_)___  ____     ________  ______   _____  _____
+   / // __ \/ __ `/ _ \/ ___/ __/ / __ \/ __ \   / ___/ _ \/ ___/ | / / _ \/ ___/
+ _/ // / / / /_/ /  __(__  ) /_/ / /_/ / / / /  (__  )  __/ /   | |/ /  __/ /
+/___/_/ /_/\__, /\___/____/\__/_/\____/_/ /_/  /____/\___/_/    |___/\___/_/
+          /____/
     """)
-    logging.info(f'TaskExecutor: RAGFlow version: {get_ragflow_version()}')
+    logging.info(f'RAGFlow version: {get_ragflow_version()}')
     settings.init_settings()
     print_rag_settings()
     if sys.platform != "win32":

rag/utils/oss_conn.py

@@ -106,7 +106,7 @@ class RAGFlowOSS:
 
     @use_prefix_path
     @use_default_bucket
-    def put(self, bucket, fnm, binary):
+    def put(self, bucket, fnm, binary, tenant_id=None):
         logging.debug(f"bucket name {bucket}; filename :{fnm}:")
         for _ in range(1):
             try:
@@ -123,7 +123,7 @@ class RAGFlowOSS:
 
     @use_prefix_path
     @use_default_bucket
-    def rm(self, bucket, fnm):
+    def rm(self, bucket, fnm, tenant_id=None):
         try:
             self.conn.delete_object(Bucket=bucket, Key=fnm)
         except Exception:
@@ -131,7 +131,7 @@ class RAGFlowOSS:
 
     @use_prefix_path
     @use_default_bucket
-    def get(self, bucket, fnm):
+    def get(self, bucket, fnm, tenant_id=None):
         for _ in range(1):
             try:
                 r = self.conn.get_object(Bucket=bucket, Key=fnm)
@@ -145,7 +145,7 @@ class RAGFlowOSS:
 
     @use_prefix_path
     @use_default_bucket
-    def obj_exist(self, bucket, fnm):
+    def obj_exist(self, bucket, fnm, tenant_id=None):
         try:
             if self.conn.head_object(Bucket=bucket, Key=fnm):
                 return True
@@ -157,7 +157,7 @@ class RAGFlowOSS:
 
     @use_prefix_path
     @use_default_bucket
-    def get_presigned_url(self, bucket, fnm, expires):
+    def get_presigned_url(self, bucket, fnm, expires, tenant_id=None):
         for _ in range(10):
             try:
                 r = self.conn.generate_presigned_url('get_object',

sdk/python/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragflow-sdk"
-version = "0.21.0"
+version = "0.21.1"
 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" }

sdk/python/uv.lock

@@ -342,7 +342,7 @@ wheels = [
 
 [[package]]
 name = "ragflow-sdk"
-version = "0.21.0"
+version = "0.21.1"
 source = { virtual = "." }
 dependencies = [
     { name = "beartype" },

test/testcases/test_http_api/test_chunk_management_within_dataset/test_retrieval_chunks.py

@@ -83,7 +83,7 @@ class TestChunksRetrieval:
                 "ValueError('Search does not support negative slicing.')",
                 marks=pytest.mark.skip,
             ),
-            pytest.param({"page": 2, "page_size": 2}, 0, 2, "", marks=pytest.mark.skip(reason="issues/6646")),
+            ({"page": 2, "page_size": 2}, 0, 2, ""),
             ({"page": 3, "page_size": 2}, 0, 0, ""),
             ({"page": "3", "page_size": 2}, 0, 0, ""),
             pytest.param(
@@ -124,9 +124,9 @@ class TestChunksRetrieval:
                 marks=pytest.mark.skip,
             ),
             # ({"page_size": 0}, 0, 0, ""),
-            ({"page_size": 1}, 0, 1, ""),
+            pytest.param({"page_size": 1}, 0, 1, "", marks=pytest.mark.skip(reason="issues/10692")),
             ({"page_size": 5}, 0, 4, ""),
-            ({"page_size": "1"}, 0, 1, ""),
+            pytest.param({"page_size": "1"}, 0, 1, "", marks=pytest.mark.skip(reason="issues/10692")),
             # ({"page_size": -1}, 0, 0, ""),
             pytest.param(
                 {"page_size": "a"},

uv.lock

@@ -31,15 +31,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/9f/1c/a17fb513aeb684fb83bef5f395910f53103ab30308bbdd77fd66d6698c46/accelerate-1.9.0-py3-none-any.whl", hash = "sha256:c24739a97ade1d54af4549a65f8b6b046adc87e2b3e4d6c66516e32c53d5a8f1", size = 367073, upload-time = "2025-07-16T16:24:52.957Z" },
 ]
 
-[[package]]
-name = "acres"
-version = "0.5.0"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ec/ba/94b63a9af588fbf7bde25ce44d55456199654a92fb7b2337767198a824b0/acres-0.5.0.tar.gz", hash = "sha256:128b6447bf5df3b6210264feccbfa018b4ac5bd337358319aec6563f99db8f3a", size = 57750, upload-time = "2025-06-04T12:40:30.329Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/39/e8/806475fe4cdfd8635535d3fa11bd61d19b7cc94b61b9147ebdd2ab4cbbee/acres-0.5.0-py3-none-any.whl", hash = "sha256:fcc32b974b510897de0f041609b4234f9ff03e2e960aea088f63973fb106c772", size = 12703, upload-time = "2025-06-04T12:40:28.745Z" },
-]
-
 [[package]]
 name = "aiofiles"
 version = "24.1.0"
@@ -300,9 +291,9 @@ dependencies = [
     { name = "python-dateutil" },
     { name = "types-python-dateutil" },
 ]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/2e/00/0f6e8fcdb23ea632c866620cc872729ff43ed91d284c866b515c6342b173/arrow-1.3.0.tar.gz", hash = "sha256:d4540617648cb5f895730f1ad8c82a65f2dad0166f57b75f3ca54759c4d67a85" }
+sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/2e/00/0f6e8fcdb23ea632c866620cc872729ff43ed91d284c866b515c6342b173/arrow-1.3.0.tar.gz", hash = "sha256:d4540617648cb5f895730f1ad8c82a65f2dad0166f57b75f3ca54759c4d67a85", size = 131960, upload-time = "2023-09-30T22:11:18.25Z" }
 wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f8/ed/e97229a566617f2ae958a6b13e7cc0f585470eac730a73e9e82c32a3cdd2/arrow-1.3.0-py3-none-any.whl", hash = "sha256:c728b120ebc00eb84e01882a6f5e7927a53960aa990ce7dd2b10f39005a67f80" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f8/ed/e97229a566617f2ae958a6b13e7cc0f585470eac730a73e9e82c32a3cdd2/arrow-1.3.0-py3-none-any.whl", hash = "sha256:c728b120ebc00eb84e01882a6f5e7927a53960aa990ce7dd2b10f39005a67f80", size = 66419, upload-time = "2023-09-30T22:11:16.072Z" },
 ]
 
 [[package]]
@@ -827,15 +818,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/20/94/c5790835a017658cbfabd07f3bfb549140c3ac458cfc196323996b10095a/charset_normalizer-3.4.2-py3-none-any.whl", hash = "sha256:7f56930ab0abd1c45cd15be65cc741c28b1c9a34876ce8c17a2fa107810c0af0", size = 52626, upload-time = "2025-05-02T08:34:40.053Z" },
 ]
 
-[[package]]
-name = "ci-info"
-version = "0.3.0"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/11/27/938d6ef93df09c686dcee1c7334578274320e98e7bf912a6409cf2c8c3e5/ci-info-0.3.0.tar.gz", hash = "sha256:1fd50cbd401f29adffeeb18b0489e232d16ac1a7458ac6bc316deab6ae535fb0", size = 25169, upload-time = "2022-07-27T17:22:49.365Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/13/c3/8ac768b389d5b6dda1c3ce7992b3acd2b46401f9b71439123858b17b1a2c/ci_info-0.3.0-py3-none-any.whl", hash = "sha256:e9e05d262a6c48aa03cd904475de5ce8c4da8a5435e516631c795d0487dc9e07", size = 7764, upload-time = "2022-07-27T17:22:47.196Z" },
-]
-
 [[package]]
 name = "click"
 version = "8.2.1"
@@ -930,24 +912,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/07/1d/62f5bf92e12335eb63517f42671ed78512d48bbc69e02a942dd7b90f03f0/compressed_rtf-1.0.7-py3-none-any.whl", hash = "sha256:b7904921d78c67a0a4b7fff9fb361a00ae2b447b6edca010ce321cd98fa0fcc0", size = 7968, upload-time = "2025-03-24T23:03:57.433Z" },
 ]
 
-[[package]]
-name = "configobj"
-version = "5.0.9"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f5/c4/c7f9e41bc2e5f8eeae4a08a01c91b2aea3dfab40a3e14b25e87e7db8d501/configobj-5.0.9.tar.gz", hash = "sha256:03c881bbf23aa07bccf1b837005975993c4ab4427ba57f959afdd9d1a2386848", size = 101518, upload-time = "2024-09-21T12:47:46.315Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a6/c4/0679472c60052c27efa612b4cd3ddd2a23e885dcdc73461781d2c802d39e/configobj-5.0.9-py2.py3-none-any.whl", hash = "sha256:1ba10c5b6ee16229c79a05047aeda2b55eb4e80d7c7d8ecf17ec1ca600c79882", size = 35615, upload-time = "2024-11-26T14:03:32.972Z" },
-]
-
-[[package]]
-name = "configparser"
-version = "7.2.0"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/8b/ac/ea19242153b5e8be412a726a70e82c7b5c1537c83f61b20995b2eda3dcd7/configparser-7.2.0.tar.gz", hash = "sha256:b629cc8ae916e3afbd36d1b3d093f34193d851e11998920fdcfc4552218b7b70", size = 51273, upload-time = "2025-03-08T16:04:09.339Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/09/fe/f61e7129e9e689d9e40bbf8a36fb90f04eceb477f4617c02c6a18463e81f/configparser-7.2.0-py3-none-any.whl", hash = "sha256:fee5e1f3db4156dcd0ed95bc4edfa3580475537711f67a819c966b389d09ce62", size = 17232, upload-time = "2025-03-08T16:04:07.743Z" },
-]
-
 [[package]]
 name = "contourpy"
 version = "1.3.2"
@@ -1507,19 +1471,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c1/8b/5fe2cc11fee489817272089c4203e679c63b570a5aaeb18d852ae3cbba6a/et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa", size = 18059, upload-time = "2024-10-25T17:25:39.051Z" },
 ]
 
-[[package]]
-name = "etelemetry"
-version = "0.3.1"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-dependencies = [
-    { name = "ci-info" },
-    { name = "packaging" },
-    { name = "requests" },
-]
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/83/27/f997c9da0e179986fadd6c8474d16743f1b3697c129c2fcd1e739cd038c2/etelemetry-0.3.1-py3-none-any.whl", hash = "sha256:a64f09bcd55cbfa5684e4d9fb6d1d6a018ab99d2ea28e638435c4c26e6814a6b" },
-]
-
 [[package]]
 name = "events"
 version = "0.5"
@@ -2742,15 +2693,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/20/b0/36bd937216ec521246249be3bf9855081de4c5e06a0c9b4219dbeda50373/importlib_metadata-8.7.0-py3-none-any.whl", hash = "sha256:e5dd1551894c77868a30651cef00984d50e1002d06942a7101d34870c5f02afd", size = 27656, upload-time = "2025-04-27T15:29:00.214Z" },
 ]
 
-[[package]]
-name = "importlib-resources"
-version = "6.5.2"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/cf/8c/f834fbf984f691b4f7ff60f50b514cc3de5cc08abfc3295564dd89c5e2e7/importlib_resources-6.5.2.tar.gz", hash = "sha256:185f87adef5bcc288449d98fb4fba07cea78bc036455dd44c5fc4a2fe78fed2c", size = 44693, upload-time = "2025-01-03T18:51:56.698Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a4/ed/1f1afb2e9e7f38a545d628f864d562a5ae64fe6f7a10e28ffb9b185b4e89/importlib_resources-6.5.2-py3-none-any.whl", hash = "sha256:789cfdc3ed28c78b67a06acb8126751ced69a3d5f79c095a98298cd8a760ccec", size = 37461, upload-time = "2025-01-03T18:51:54.306Z" },
-]
-
 [[package]]
 name = "infinity-emb"
 version = "0.0.66"
@@ -2767,7 +2709,7 @@ wheels = [
 
 [[package]]
 name = "infinity-sdk"
-version = "0.6.0"
+version = "0.6.1"
 source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
 dependencies = [
     { name = "numpy" },
@@ -2784,7 +2726,7 @@ dependencies = [
     { name = "thrift" },
 ]
 wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f4/12/1ce243cbede6da5fc28e5462d90d96b13995446b3a90889287d31255b36e/infinity_sdk-0.6.0-py3-none-any.whl", hash = "sha256:e379853ffc44acba428572d633032e6c9bb842d1f08e9cad690916f52a8c6ba8", size = 75256, upload-time = "2025-10-14T12:05:13.918Z" },
+    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/44/0e/7a596a41a79d15bb6c87e76862aa287bb98243a40fa7a31096b57df01613/infinity_sdk-0.6.1-py3-none-any.whl", hash = "sha256:b9cb1f7fee28569de8b763c353aa299fa141af70e67ceadc70562c84237229e4", size = 75260, upload-time = "2025-10-21T13:11:06.265Z" },
 ]
 
 [[package]]
@@ -3133,15 +3075,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl", hash = "sha256:31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c", size = 61595, upload-time = "2024-12-06T11:20:54.538Z" },
 ]
 
-[[package]]
-name = "looseversion"
-version = "1.3.0"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/64/7e/f13dc08e0712cc2eac8e56c7909ce2ac280dbffef2ffd87bd5277ce9d58b/looseversion-1.3.0.tar.gz", hash = "sha256:ebde65f3f6bb9531a81016c6fef3eb95a61181adc47b7f949e9c0ea47911669e", size = 8799, upload-time = "2023-07-05T16:07:51.173Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/4e/74/d5405b9b3b12e9176dff223576d7090bc161092878f533fd0dc23dd6ae1d/looseversion-1.3.0-py2.py3-none-any.whl", hash = "sha256:781ef477b45946fc03dd4c84ea87734b21137ecda0e1e122bcb3c8d16d2a56e0", size = 8237, upload-time = "2023-07-05T16:07:49.782Z" },
-]
-
 [[package]]
 name = "lxml"
 version = "5.3.0"
@@ -3748,50 +3681,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/eb/8d/776adee7bbf76365fdd7f2552710282c79a4ead5d2a46408c9043a2b70ba/networkx-3.5-py3-none-any.whl", hash = "sha256:0030d386a9a06dee3565298b4a734b68589749a544acbb6c412dc9e2489ec6ec", size = 2034406, upload-time = "2025-05-29T11:35:04.961Z" },
 ]
 
-[[package]]
-name = "nibabel"
-version = "5.3.2"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-dependencies = [
-    { name = "importlib-resources", marker = "python_full_version < '3.12'" },
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d9/61/33036cb89f1ec1fedbc4039602345d830b27cbd8a5c7bf28c2e5b5de3ea2/nibabel-5.3.2.tar.gz", hash = "sha256:0bdca6503b1c784b446c745a4542367de7756cfba0d72143b91f9ffb78be569b", size = 4504842, upload-time = "2024-10-23T14:19:55.866Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/43/b2/dc384197be44e2a640bb43311850e23c2c30f3b82ce7c8cdabbf0e53045e/nibabel-5.3.2-py3-none-any.whl", hash = "sha256:52970a5a8a53b1b55249cba4d9bcfaa8cc57e3e5af35a29d7352237e8680a6f8", size = 3293839, upload-time = "2024-10-23T14:19:52.65Z" },
-]
-
-[[package]]
-name = "nipype"
-version = "1.10.0"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-dependencies = [
-    { name = "acres" },
-    { name = "click" },
-    { name = "etelemetry" },
-    { name = "filelock" },
-    { name = "looseversion" },
-    { name = "networkx", version = "3.4.2", source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "networkx", version = "3.5", source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }, marker = "python_full_version >= '3.11'" },
-    { name = "nibabel" },
-    { name = "numpy" },
-    { name = "packaging" },
-    { name = "prov" },
-    { name = "puremagic" },
-    { name = "pydot" },
-    { name = "python-dateutil" },
-    { name = "rdflib" },
-    { name = "scipy" },
-    { name = "simplejson" },
-    { name = "traits" },
-]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/e1/1a/7ff53f5802d37085a55d7c6df7c6ebebbc8a044930628ca21f7e661c1983/nipype-1.10.0.tar.gz", hash = "sha256:19e5d6cefa70997198f78bc665ef4d3d3cb53325b5b98a72e51aefadaf6b3e0e", size = 2919807, upload-time = "2025-03-19T23:30:07.473Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/91/53/c5ad0140e2e4c4d92ae45558587e26b2ebc62e39eafa30b74cb052d9375b/nipype-1.10.0-py3-none-any.whl", hash = "sha256:56ced3272e77952e330f13e28328a8fe2e8a69587ca89bc34234f7d06f8319bb", size = 3200685, upload-time = "2025-03-19T23:30:05.357Z" },
-]
-
 [[package]]
 name = "nltk"
 version = "3.9.1"
@@ -4473,15 +4362,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/00/2f/804f58f0b856ab3bf21617cccf5b39206e6c4c94c2cd227bde125ea6105f/parameterized-0.9.0-py2.py3-none-any.whl", hash = "sha256:4e0758e3d41bea3bbd05ec14fc2c24736723f243b28d702081aef438c9372b1b", size = 20475, upload-time = "2023-03-27T02:01:09.31Z" },
 ]
 
-[[package]]
-name = "pathlib"
-version = "1.0.1"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ac/aa/9b065a76b9af472437a0059f77e8f962fe350438b927cb80184c32f075eb/pathlib-1.0.1.tar.gz", hash = "sha256:6940718dfc3eff4258203ad5021090933e5c04707d5ca8cc9e73c94a7894ea9f", size = 49298, upload-time = "2014-09-03T15:41:57.18Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/78/f9/690a8600b93c332de3ab4a344a4ac34f00c8f104917061f779db6a918ed6/pathlib-1.0.1-py3-none-any.whl", hash = "sha256:f35f95ab8b0f59e6d354090350b44a80a80635d22efdedfa84c7ad1cf0a74147", size = 14363, upload-time = "2022-05-04T13:37:20.585Z" },
-]
-
 [[package]]
 name = "patsy"
 version = "1.0.1"
@@ -4817,21 +4697,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/3a/fa/4c3ac5527ed2e5f3577167ecd5f8180ffcdc8bdd59c9f143409c19706456/protobuf-5.27.2-py3-none-any.whl", hash = "sha256:54330f07e4949d09614707c48b06d1a22f8ffb5763c159efd5c0928326a91470", size = 164772, upload-time = "2024-06-25T20:54:52.196Z" },
 ]
 
-[[package]]
-name = "prov"
-version = "2.1.1"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-dependencies = [
-    { name = "networkx", version = "3.4.2", source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "networkx", version = "3.5", source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }, marker = "python_full_version >= '3.11'" },
-    { name = "pydot" },
-    { name = "python-dateutil" },
-]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c6/bb/442f2e478061543c9c229f48c2d3a43cb0a77642584edecac126bc1ade99/prov-2.1.1.tar.gz", hash = "sha256:7d012b164f5bbb42e118ed9d25788ab012d09082b722bc9dd4e811a309ea57f5", size = 136802, upload-time = "2025-06-24T22:01:50.767Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/76/17/5703ad2380e57ecceb2700e30646ba0d856d9b90c9f33b01c68a3e298e3a/prov-2.1.1-py3-none-any.whl", hash = "sha256:04f74f9151b68f0bda68c943e111b1275207b19e197689043644a1b355a9d035", size = 425860, upload-time = "2025-06-24T22:01:49.485Z" },
-]
-
 [[package]]
 name = "psutil"
 version = "7.0.0"
@@ -4891,15 +4756,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/7b/08/9c66c269b0d417a0af9fb969535f0371b8c538633535a7a6a5ca3f9231e2/psycopg2_binary-2.9.9-cp312-cp312-win_amd64.whl", hash = "sha256:81ff62668af011f9a48787564ab7eded4e9fb17a4a6a74af5ffa6a457400d2ab", size = 1163864, upload-time = "2023-10-28T09:37:28.155Z" },
 ]
 
-[[package]]
-name = "puremagic"
-version = "1.30"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/dd/7f/9998706bc516bdd664ccf929a1da6c6e5ee06e48f723ce45aae7cf3ff36e/puremagic-1.30.tar.gz", hash = "sha256:f9ff7ac157d54e9cf3bff1addfd97233548e75e685282d84ae11e7ffee1614c9", size = 314785, upload-time = "2025-07-04T18:48:36.061Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/91/ed/1e347d85d05b37a8b9a039ca832e5747e1e5248d0bd66042783ef48b4a37/puremagic-1.30-py3-none-any.whl", hash = "sha256:5eeeb2dd86f335b9cfe8e205346612197af3500c6872dffebf26929f56e9d3c1", size = 43304, upload-time = "2025-07-04T18:48:34.801Z" },
-]
-
 [[package]]
 name = "py"
 version = "1.11.0"
@@ -5156,18 +5012,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ca/8f/86d7931c62013a5a7ebf4e1642a87d4a6050c0f570e714f61b0df1984c62/pydivert-2.1.0-py2.py3-none-any.whl", hash = "sha256:382db488e3c37c03ec9ec94e061a0b24334d78dbaeebb7d4e4d32ce4355d9da1", size = 104718, upload-time = "2017-10-20T21:36:56.726Z" },
 ]
 
-[[package]]
-name = "pydot"
-version = "4.0.1"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-dependencies = [
-    { name = "pyparsing" },
-]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/50/35/b17cb89ff865484c6a20ef46bf9d95a5f07328292578de0b295f4a6beec2/pydot-4.0.1.tar.gz", hash = "sha256:c2148f681c4a33e08bf0e26a9e5f8e4099a82e0e2a068098f32ce86577364ad5", size = 162594, upload-time = "2025-06-17T20:09:56.454Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/7e/32/a7125fb28c4261a627f999d5fb4afff25b523800faed2c30979949d6facd/pydot-4.0.1-py3-none-any.whl", hash = "sha256:869c0efadd2708c0be1f916eb669f3d664ca684bc57ffb7ecc08e70d5e93fee6", size = 37087, upload-time = "2025-06-17T20:09:55.25Z" },
-]
-
 [[package]]
 name = "pyee"
 version = "13.0.0"
@@ -5560,20 +5404,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ba/3a/2ae996277b4b50f17d61f0603efd8253cb2d79cc7ae159468007b586396d/pywin32-311-cp312-cp312-win_arm64.whl", hash = "sha256:e286f46a9a39c4a18b319c28f59b61de793654af2f395c102b4f819e584b5852", size = 8710102, upload-time = "2025-07-14T20:13:24.682Z" },
 ]
 
-[[package]]
-name = "pyxnat"
-version = "1.6.3"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-dependencies = [
-    { name = "lxml" },
-    { name = "pathlib" },
-    { name = "requests" },
-]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/7f/24/c8737985e65d8adbbf51970b2a75cf54b5376d68d251159d9b7c5c9673b6/pyxnat-1.6.3.tar.gz", hash = "sha256:ddd074f35f7b35b5dccb6f713b20cf083c79d6e0d3d9cafbcaabb7c661b0cc68", size = 82466, upload-time = "2025-02-04T19:03:53.801Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1c/df/257c0f0af8e624daa924a3899f88e6465f162d72ada3fb0b96df9e61a2d6/pyxnat-1.6.3-py3-none-any.whl", hash = "sha256:a6d84dd24486eab9731a5de5df4fb486021b095665083c2fb1d33ac1e719d3c5", size = 95408, upload-time = "2025-02-04T19:03:51.707Z" },
-]
-
 [[package]]
 name = "pyyaml"
 version = "6.0.2"
@@ -5637,7 +5467,7 @@ wheels = [
 
 [[package]]
 name = "ragflow"
-version = "0.21.0"
+version = "0.21.1"
 source = { virtual = "." }
 dependencies = [
     { name = "akshare" },
@@ -5849,7 +5679,7 @@ requires-dist = [
     { name = "httpx", extras = ["socks"], specifier = ">=0.28.1,<0.29.0" },
     { 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" },
+    { name = "infinity-sdk", specifier = "==0.6.1" },
     { name = "itsdangerous", specifier = "==2.1.2" },
     { name = "json-repair", specifier = "==0.35.0" },
     { name = "langfuse", specifier = ">=2.60.0" },
@@ -5985,19 +5815,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1e/30/53f41b7b728a48da8974075f56c57200d7b11e4e9fa93be3cabf8218dc0c/ranx-0.3.20-py3-none-any.whl", hash = "sha256:e056e4d5981b0328b045868cc7064fc57a545f36009fbe9bb602295ec33335de", size = 99318, upload-time = "2024-07-01T17:40:27.095Z" },
 ]
 
-[[package]]
-name = "rdflib"
-version = "7.2.1"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-dependencies = [
-    { name = "isodate", marker = "python_full_version < '3.11'" },
-    { name = "pyparsing" },
-]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/8d/99/d2fec85e5f6bdfe4367dea143119cb4469bf48710487939df0abf7e22003/rdflib-7.2.1.tar.gz", hash = "sha256:cf9b7fa25234e8925da8b1fb09700f8349b5f0f100e785fb4260e737308292ac", size = 4873802, upload-time = "2025-09-19T02:33:36.492Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/31/98/7fa830bb4b9da21905683a5352aa0a01a1f3082328ae976aad341e980c23/rdflib-7.2.1-py3-none-any.whl", hash = "sha256:1a175bc1386a167a42fbfaba003bfa05c164a2a3ca3cb9c0c97f9c9638ca6ac2", size = 565423, upload-time = "2025-09-19T02:33:30.889Z" },
-]
-
 [[package]]
 name = "readability-lxml"
 version = "0.8.1"
@@ -6595,54 +6412,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/e0/f9/0595336914c5619e5f28a1fb793285925a8cd4b432c9da0a987836c7f822/shellingham-1.5.4-py2.py3-none-any.whl", hash = "sha256:7ecfff8f2fd72616f7481040475a65b2bf8af90a56c89140852d1120324e8686", size = 9755, upload-time = "2023-10-24T04:13:38.866Z" },
 ]
 
-[[package]]
-name = "simplejson"
-version = "3.20.2"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/41/f4/a1ac5ed32f7ed9a088d62a59d410d4c204b3b3815722e2ccfb491fa8251b/simplejson-3.20.2.tar.gz", hash = "sha256:5fe7a6ce14d1c300d80d08695b7f7e633de6cd72c80644021874d985b3393649", size = 85784, upload-time = "2025-09-26T16:29:36.64Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/78/09/2bf3761de89ea2d91bdce6cf107dcd858892d0adc22c995684878826cc6b/simplejson-3.20.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:6d7286dc11af60a2f76eafb0c2acde2d997e87890e37e24590bb513bec9f1bc5", size = 94039, upload-time = "2025-09-26T16:27:29.283Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/0f/33/c3277db8931f0ae9e54b9292668863365672d90fb0f632f4cf9829cb7d68/simplejson-3.20.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c01379b4861c3b0aa40cba8d44f2b448f5743999aa68aaa5d3ef7049d4a28a2d", size = 75894, upload-time = "2025-09-26T16:27:30.378Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/fa/ea/ae47b04d03c7c8a7b7b1a8b39a6e27c3bd424e52f4988d70aca6293ff5e5/simplejson-3.20.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a16b029ca25645b3bc44e84a4f941efa51bf93c180b31bd704ce6349d1fc77c1", size = 76116, upload-time = "2025-09-26T16:27:31.42Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/4b/42/6c9af551e5a8d0f171d6dce3d9d1260068927f7b80f1f09834e07887c8c4/simplejson-3.20.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e22a5fb7b1437ffb057e02e1936a3bfb19084ae9d221ec5e9f4cf85f69946b6", size = 138827, upload-time = "2025-09-26T16:27:32.486Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/2b/22/5e268bbcbe9f75577491e406ec0a5536f5b2fa91a3b52031fea51cd83e1d/simplejson-3.20.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d8b6ff02fc7b8555c906c24735908854819b0d0dc85883d453e23ca4c0445d01", size = 146772, upload-time = "2025-09-26T16:27:34.036Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/71/b4/800f14728e2ad666f420dfdb57697ca128aeae7f991b35759c09356b829a/simplejson-3.20.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2bfc1c396ad972ba4431130b42307b2321dba14d988580c1ac421ec6a6b7cee3", size = 134497, upload-time = "2025-09-26T16:27:35.211Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c1/b9/c54eef4226c6ac8e9a389bbe5b21fef116768f97a2dc1a683c716ffe66ef/simplejson-3.20.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a97249ee1aee005d891b5a211faf58092a309f3d9d440bc269043b08f662eda", size = 138172, upload-time = "2025-09-26T16:27:36.44Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/09/36/4e282f5211b34620f1b2e4b51d9ddaab5af82219b9b7b78360a33f7e5387/simplejson-3.20.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:f1036be00b5edaddbddbb89c0f80ed229714a941cfd21e51386dc69c237201c2", size = 140272, upload-time = "2025-09-26T16:27:37.605Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/aa/b0/94ad2cf32f477c449e1f63c863d8a513e2408d651c4e58fe4b6a7434e168/simplejson-3.20.2-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:5d6f5bacb8cdee64946b45f2680afa3f54cd38e62471ceda89f777693aeca4e4", size = 140468, upload-time = "2025-09-26T16:27:39.015Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/e5/46/827731e4163be3f987cb8ee90f5d444161db8f540b5e735355faa098d9bc/simplejson-3.20.2-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:8db6841fb796ec5af632f677abf21c6425a1ebea0d9ac3ef1a340b8dc69f52b8", size = 148700, upload-time = "2025-09-26T16:27:40.171Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c7/28/c32121064b1ec2fb7b5d872d9a1abda62df064d35e0160eddfa907118343/simplejson-3.20.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:c0a341f7cc2aae82ee2b31f8a827fd2e51d09626f8b3accc441a6907c88aedb7", size = 141323, upload-time = "2025-09-26T16:27:41.324Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/46/b6/c897c54326fe86dd12d101981171a49361949f4728294f418c3b86a1af77/simplejson-3.20.2-cp310-cp310-win32.whl", hash = "sha256:27f9c01a6bc581d32ab026f515226864576da05ef322d7fc141cd8a15a95ce53", size = 74377, upload-time = "2025-09-26T16:27:42.533Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ad/87/a6e03d4d80cca99c1fee4e960f3440e2f21be9470e537970f960ca5547f1/simplejson-3.20.2-cp310-cp310-win_amd64.whl", hash = "sha256:c0a63ec98a4547ff366871bf832a7367ee43d047bcec0b07b66c794e2137b476", size = 76081, upload-time = "2025-09-26T16:27:43.945Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b9/3e/96898c6c66d9dca3f9bd14d7487bf783b4acc77471b42f979babbb68d4ca/simplejson-3.20.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:06190b33cd7849efc413a5738d3da00b90e4a5382fd3d584c841ac20fb828c6f", size = 92633, upload-time = "2025-09-26T16:27:45.028Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/6b/a2/cd2e10b880368305d89dd540685b8bdcc136df2b3c76b5ddd72596254539/simplejson-3.20.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4ad4eac7d858947a30d2c404e61f16b84d16be79eb6fb316341885bdde864fa8", size = 75309, upload-time = "2025-09-26T16:27:46.142Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/5d/02/290f7282eaa6ebe945d35c47e6534348af97472446951dce0d144e013f4c/simplejson-3.20.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:b392e11c6165d4a0fde41754a0e13e1d88a5ad782b245a973dd4b2bdb4e5076a", size = 75308, upload-time = "2025-09-26T16:27:47.542Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/43/91/43695f17b69e70c4b0b03247aa47fb3989d338a70c4b726bbdc2da184160/simplejson-3.20.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51eccc4e353eed3c50e0ea2326173acdc05e58f0c110405920b989d481287e51", size = 143733, upload-time = "2025-09-26T16:27:48.673Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/9b/4b/fdcaf444ac1c3cbf1c52bf00320c499e1cf05d373a58a3731ae627ba5e2d/simplejson-3.20.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:306e83d7c331ad833d2d43c76a67f476c4b80c4a13334f6e34bb110e6105b3bd", size = 153397, upload-time = "2025-09-26T16:27:49.89Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c4/83/21550f81a50cd03599f048a2d588ffb7f4c4d8064ae091511e8e5848eeaa/simplejson-3.20.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f820a6ac2ef0bc338ae4963f4f82ccebdb0824fe9caf6d660670c578abe01013", size = 141654, upload-time = "2025-09-26T16:27:51.168Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/cf/54/d76c0e72ad02450a3e723b65b04f49001d0e73218ef6a220b158a64639cb/simplejson-3.20.2-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21e7a066528a5451433eb3418184f05682ea0493d14e9aae690499b7e1eb6b81", size = 144913, upload-time = "2025-09-26T16:27:52.331Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/3f/49/976f59b42a6956d4aeb075ada16ad64448a985704bc69cd427a2245ce835/simplejson-3.20.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:438680ddde57ea87161a4824e8de04387b328ad51cfdf1eaf723623a3014b7aa", size = 144568, upload-time = "2025-09-26T16:27:53.41Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/60/c7/30bae30424ace8cd791ca660fed454ed9479233810fe25c3f3eab3d9dc7b/simplejson-3.20.2-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:cac78470ae68b8d8c41b6fca97f5bf8e024ca80d5878c7724e024540f5cdaadb", size = 146239, upload-time = "2025-09-26T16:27:54.502Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/79/3e/7f3b7b97351c53746e7b996fcd106986cda1954ab556fd665314756618d2/simplejson-3.20.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:7524e19c2da5ef281860a3d74668050c6986be15c9dd99966034ba47c68828c2", size = 154497, upload-time = "2025-09-26T16:27:55.885Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/1d/48/7241daa91d0bf19126589f6a8dcbe8287f4ed3d734e76fd4a092708947be/simplejson-3.20.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:0e9b6d845a603b2eef3394eb5e21edb8626cd9ae9a8361d14e267eb969dbe413", size = 148069, upload-time = "2025-09-26T16:27:57.039Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/e6/f4/ef18d2962fe53e7be5123d3784e623859eec7ed97060c9c8536c69d34836/simplejson-3.20.2-cp311-cp311-win32.whl", hash = "sha256:47d8927e5ac927fdd34c99cc617938abb3624b06ff86e8e219740a86507eb961", size = 74158, upload-time = "2025-09-26T16:27:58.265Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/35/fd/3d1158ecdc573fdad81bf3cc78df04522bf3959758bba6597ba4c956c74d/simplejson-3.20.2-cp311-cp311-win_amd64.whl", hash = "sha256:ba4edf3be8e97e4713d06c3d302cba1ff5c49d16e9d24c209884ac1b8455520c", size = 75911, upload-time = "2025-09-26T16:27:59.292Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/9d/9e/1a91e7614db0416885eab4136d49b7303de20528860ffdd798ce04d054db/simplejson-3.20.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:4376d5acae0d1e91e78baeba4ee3cf22fbf6509d81539d01b94e0951d28ec2b6", size = 93523, upload-time = "2025-09-26T16:28:00.356Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/5e/2b/d2413f5218fc25608739e3d63fe321dfa85c5f097aa6648dbe72513a5f12/simplejson-3.20.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:f8fe6de652fcddae6dec8f281cc1e77e4e8f3575249e1800090aab48f73b4259", size = 75844, upload-time = "2025-09-26T16:28:01.756Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ad/f1/efd09efcc1e26629e120fef59be059ce7841cc6e1f949a4db94f1ae8a918/simplejson-3.20.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:25ca2663d99328d51e5a138f22018e54c9162438d831e26cfc3458688616eca8", size = 75655, upload-time = "2025-09-26T16:28:03.037Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/97/ec/5c6db08e42f380f005d03944be1af1a6bd501cc641175429a1cbe7fb23b9/simplejson-3.20.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:12a6b2816b6cab6c3fd273d43b1948bc9acf708272074c8858f579c394f4cbc9", size = 150335, upload-time = "2025-09-26T16:28:05.027Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/81/f5/808a907485876a9242ec67054da7cbebefe0ee1522ef1c0be3bfc90f96f6/simplejson-3.20.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ac20dc3fcdfc7b8415bfc3d7d51beccd8695c3f4acb7f74e3a3b538e76672868", size = 158519, upload-time = "2025-09-26T16:28:06.5Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/66/af/b8a158246834645ea890c36136584b0cc1c0e4b83a73b11ebd9c2a12877c/simplejson-3.20.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:db0804d04564e70862ef807f3e1ace2cc212ef0e22deb1b3d6f80c45e5882c6b", size = 148571, upload-time = "2025-09-26T16:28:07.715Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/20/05/ed9b2571bbf38f1a2425391f18e3ac11cb1e91482c22d644a1640dea9da7/simplejson-3.20.2-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:979ce23ea663895ae39106946ef3d78527822d918a136dbc77b9e2b7f006237e", size = 152367, upload-time = "2025-09-26T16:28:08.921Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/81/2c/bad68b05dd43e93f77994b920505634d31ed239418eb6a88997d06599983/simplejson-3.20.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a2ba921b047bb029805726800819675249ef25d2f65fd0edb90639c5b1c3033c", size = 150205, upload-time = "2025-09-26T16:28:10.086Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/69/46/90c7fc878061adafcf298ce60cecdee17a027486e9dce507e87396d68255/simplejson-3.20.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:12d3d4dc33770069b780cc8f5abef909fe4a3f071f18f55f6d896a370fd0f970", size = 151823, upload-time = "2025-09-26T16:28:11.329Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ab/27/b85b03349f825ae0f5d4f780cdde0bbccd4f06c3d8433f6a3882df887481/simplejson-3.20.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:aff032a59a201b3683a34be1169e71ddda683d9c3b43b261599c12055349251e", size = 158997, upload-time = "2025-09-26T16:28:12.917Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/71/ad/d7f3c331fb930638420ac6d236db68e9f4c28dab9c03164c3cd0e7967e15/simplejson-3.20.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:30e590e133b06773f0dc9c3f82e567463df40598b660b5adf53eb1c488202544", size = 154367, upload-time = "2025-09-26T16:28:14.393Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f0/46/5c67324addd40fa2966f6e886cacbbe0407c03a500db94fb8bb40333fcdf/simplejson-3.20.2-cp312-cp312-win32.whl", hash = "sha256:8d7be7c99939cc58e7c5bcf6bb52a842a58e6c65e1e9cdd2a94b697b24cddb54", size = 74285, upload-time = "2025-09-26T16:28:15.931Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/fa/c9/5cc2189f4acd3a6e30ffa9775bf09b354302dbebab713ca914d7134d0f29/simplejson-3.20.2-cp312-cp312-win_amd64.whl", hash = "sha256:2c0b4a67e75b945489052af6590e7dca0ed473ead5d0f3aad61fa584afe814ab", size = 75969, upload-time = "2025-09-26T16:28:17.017Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/05/5b/83e1ff87eb60ca706972f7e02e15c0b33396e7bdbd080069a5d1b53cf0d8/simplejson-3.20.2-py3-none-any.whl", hash = "sha256:3b6bb7fb96efd673eac2e4235200bfffdc2353ad12c54117e1e4e2fc485ac017", size = 57309, upload-time = "2025-09-26T16:29:35.312Z" },
-]
-
 [[package]]
 name = "six"
 version = "1.16.0"
@@ -7248,38 +7017,6 @@ wheels = [
     { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2", size = 78540, upload-time = "2024-11-24T20:12:19.698Z" },
 ]
 
-[[package]]
-name = "traits"
-version = "7.0.2"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/9e/ba/33e199bfae748e802f68a857035fb003089c176897bf43e2cf38ff167740/traits-7.0.2.tar.gz", hash = "sha256:a563515809cb3911975de5a54209855f0b6fdb7ca6912a5e81de26529f70428c", size = 9534785, upload-time = "2025-01-24T20:52:59.954Z" }
-wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/06/5c/6aa6aef1472a79accd4c077cc8eccf3c3a2acc4b42ece2c48f5651f2f915/traits-7.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cb59a033260dfa3aacfe484307a91f318a1fa801f5e8c8293fe22834fa4b30a7", size = 5034452, upload-time = "2025-01-24T20:55:25.02Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/73/0a/8387ff6f32898c334b2a96b465a8790633cec3c2270893210946d43de0d3/traits-7.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f5c18d5f4aea2988b15bc10e2ac9f4eb49531d1ec380857f3046a7ba14509e4b", size = 5034825, upload-time = "2025-01-24T20:56:04.238Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/8f/15/a04a5e1cd0c2e2979365e1ac3a674ec0f16a5af36d19809c869985e63f7a/traits-7.0.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:11950d519b113e9a34d5a99fca112866d8c36aa8fce85edadf52995ad03de07e", size = 5110401, upload-time = "2025-01-24T20:57:19.172Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/b3/da/58d58c3495b2bfee03975d95799d5a8ac771a2f510d579935122c02d26dc/traits-7.0.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d50b42061cb8f34119b6b7abe703982c6fa157a2fe4e10a5b9ab9f93c340d5e3", size = 5121856, upload-time = "2025-01-24T20:57:20.949Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/fe/74/66ed1b2511c0a457f716f6c718abf807db58c76292cbd69ecf4390519fea/traits-7.0.2-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:53fbd8a0adf42d235e6a73bd3fbb3f7190a28302d151c9a25967ff6f12b918cd", size = 5109296, upload-time = "2025-01-24T20:57:23.835Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/9e/30/60efe8a3fe454fd7b939695d556cdee7943b1ced19fc40f9b4f2a240211c/traits-7.0.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:0b48be9fb0b9e5a733e9fa5a542b0751237822e20b52fac80b5796cc606af509", size = 5117788, upload-time = "2025-01-24T20:57:27.096Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/62/ef/e884bd2c05d52415acb0344ed3847f1c3835d1651a4189a17e06fa2363fa/traits-7.0.2-cp310-cp310-win32.whl", hash = "sha256:5b98600b9f40e980e0cc5b1f0ade5fb1c1f1c19d25afc2b33ea30773015eb3e5", size = 5033760, upload-time = "2025-01-24T21:01:04.683Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/d2/71/a630ee815843e3d87484c9a0368f81eb993e862aa4cb9c20822deee7e9a3/traits-7.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:def3ab01e7d636aceda9dc6ca2abf71f2a992f9ec993c7ea200157c1ca983ae7", size = 5036225, upload-time = "2025-01-24T21:01:07.817Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/73/db/da628e34564a89f68d6b3ff5caee8a0a932858a4a3e1bf0d077d9f6d053c/traits-7.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:33fd20c3bc29fbb1f51ddb23f63173bf59a2fdafd300e5f4790352d76e4cf68e", size = 5034488, upload-time = "2025-01-24T20:55:26.853Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/e9/4e/d64ad9fb725ff1b943432c5df32c64abb28ad17f66e976d6ce6aaa1b54d5/traits-7.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:018d4f7cbd5e18cb34bafc915134c29aa8568bccd35d9aa9102e2af9ef66cb80", size = 5034832, upload-time = "2025-01-24T20:56:06.125Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/3f/80/f32ade6b131c69d2a3451edfa5c9f23056c3c9889b1d7918890ff6dad273/traits-7.0.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fa323b634abd9c7f049892d86296bc1c46bad6ad80121fefeaf12039002d58ff", size = 5119215, upload-time = "2025-01-24T20:57:31.594Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/be/d6/0c7c2c12a53698906e86a0076d13ee3d529a5c0a44468e89cb8a91186f22/traits-7.0.2-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:209bfb95c094cd315f77fc610ae65af86ec0de075be2d84e6e6290ff2f860715", size = 5130753, upload-time = "2025-01-24T20:57:34.737Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/8b/09/070aef46f818eaab7afdada8647b303facb14d4d5f931c1fb560cfc24e1b/traits-7.0.2-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:4f38eee0b94f9fbab2f086200e35f835ad1563ba7e078a044cb268ce50542565", size = 5117762, upload-time = "2025-01-24T20:57:36.764Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/85/99/fb239d5fe1ac2931c284496995998abc72f6af0ca32cfdb70095b883fab9/traits-7.0.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:135dc11da393f5dec1ecaf6981f0608976354435f7be53b9e9175a9c8a118127", size = 5126325, upload-time = "2025-01-24T20:57:38.638Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/73/48/6c1484be7d5b322c57415c9b6d39c7419ad4ee1eb52b288ddfa3893caf31/traits-7.0.2-cp311-cp311-win32.whl", hash = "sha256:c588571d981d1254d9abf8bd2f8e449f82f31ebe8f951853290910ae2f03dc84", size = 5033773, upload-time = "2025-01-24T21:01:09.598Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/73/f4/d8cb863aaacfe1633d2b636647bcc70b1cd2e258e4a83e71eae995a34ed4/traits-7.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:98a880b6adab40d66ce0eda1c6f4fdcf178bb182d28d0fb71d3755c36065dd39", size = 5036235, upload-time = "2025-01-24T21:01:12.296Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/7e/6c/9b3be8e459627267de56029a0c91e9a9c9a082353cd5b9ec1edd2f4738a5/traits-7.0.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:bccfafbda22346f0278f010458e819f0a58a95f242f91e14014b055580a15cd8", size = 5035260, upload-time = "2025-01-24T20:55:28.536Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/35/0c/990486e972614dd0173ea647b80c30c30d3ad4819befa9ec94f4a8a421b6/traits-7.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d9899ee203fd379fb0e07aebc178940d62d5790dc311263d5c3a577f3baf7dfa", size = 5035240, upload-time = "2025-01-24T20:56:08.856Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/11/7c/458041d4b345ddd351451303353acbc72a36cbc47649eedb29863a37f119/traits-7.0.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2938cccfea2da2fdce6cc7ec1e605c923e66610df1b223cf24a4b23ba97375de", size = 5121555, upload-time = "2025-01-24T20:57:41.688Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/77/f3/7736bf1bee46c6fd1c488e180236067c91490cf2aea235ed851bcf2151e2/traits-7.0.2-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f696c4d4d03b333e8f8beec206d80d4998ce6b4801deb74c258dbc4415f92345", size = 5135379, upload-time = "2025-01-24T20:57:45.797Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f0/07/e80f6663d460f80f09b443175cb8118b74ca3b7bd164f1ec5c44e1da2047/traits-7.0.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:c49384b12ecaf39b9ab156e1c7d31960206e15071a9917596ab3c265d7bb99aa", size = 5120513, upload-time = "2025-01-24T20:57:49.354Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f2/8b/0716f7b8f34e1b57b39f81472460f4e02491dde02fbc114bac42cf0acd85/traits-7.0.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6932e5a784000368aa3948890bf55c4aba10494d4a45e9bb6c2b228644f2e67c", size = 5130509, upload-time = "2025-01-24T20:57:51.933Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/c5/bf/e0135ce54d5604c57caad8866ac56a05265943a1b3a438277fb6ee10b0f6/traits-7.0.2-cp312-cp312-win32.whl", hash = "sha256:f434da460be8b3eb9f9f35143af116622cd313fa346c0df37b026d318c88ad29", size = 5034118, upload-time = "2025-01-24T21:01:14.04Z" },
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/a7/2b/49423d5b269dfc095e09ecbb41b987b224f4154716d91da063cebaf963a0/traits-7.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:497463a437cb8cd4bb2ed27ae4e4491a8ed3d4d8515803476c94ce952a17af54", size = 5036464, upload-time = "2025-01-24T21:01:16.256Z" },
-]
-
 [[package]]
 name = "transformers"
 version = "4.36.2"

web/src/components/avatar-upload.tsx

@@ -1,5 +1,5 @@
 import { transformFile2Base64 } from '@/utils/file-util';
-import { Pencil, Upload, XIcon } from 'lucide-react';
+import { Pencil, Plus, XIcon } from 'lucide-react';
 import {
   ChangeEventHandler,
   forwardRef,
@@ -12,10 +12,14 @@ import { Avatar, AvatarFallback, AvatarImage } from './ui/avatar';
 import { Button } from './ui/button';
 import { Input } from './ui/input';
 
-type AvatarUploadProps = { value?: string; onChange?: (value: string) => void };
+type AvatarUploadProps = {
+  value?: string;
+  onChange?: (value: string) => void;
+  tips?: string;
+};
 
 export const AvatarUpload = forwardRef<HTMLInputElement, AvatarUploadProps>(
-  function AvatarUpload({ value, onChange }, ref) {
+  function AvatarUpload({ value, onChange, tips }, ref) {
     const { t } = useTranslation();
     const [avatarBase64Str, setAvatarBase64Str] = useState(''); // Avatar Image base64
 
@@ -47,9 +51,9 @@ export const AvatarUpload = forwardRef<HTMLInputElement, AvatarUploadProps>(
       <div className="flex justify-start items-end space-x-2">
         <div className="relative group">
           {!avatarBase64Str ? (
-            <div className="w-[64px] h-[64px] grid place-content-center border border-dashed	rounded-md">
+            <div className="w-[64px] h-[64px] grid place-content-center border border-dashed bg-bg-input	rounded-md">
               <div className="flex flex-col items-center">
-                <Upload />
+                <Plus />
                 <p>{t('common.upload')}</p>
               </div>
             </div>
@@ -86,8 +90,8 @@ export const AvatarUpload = forwardRef<HTMLInputElement, AvatarUploadProps>(
             ref={ref}
           />
         </div>
-        <div className="margin-1 text-muted-foreground">
-          {t('knowledgeConfiguration.photoTip')}
+        <div className="margin-1 text-text-secondary">
+          {tips ?? t('knowledgeConfiguration.photoTip')}
         </div>
       </div>
     );

web/src/components/card-container.tsx

@@ -0,0 +1,17 @@
+import { cn } from '@/lib/utils';
+import { PropsWithChildren } from 'react';
+
+type CardContainerProps = { className?: string } & PropsWithChildren;
+
+export function CardContainer({ children, className }: CardContainerProps) {
+  return (
+    <section
+      className={cn(
+        'grid gap-6 sm:grid-cols-1 md:grid-cols-2 lg:grid-cols-3 xl:grid-cols-4 2xl:grid-cols-5',
+        className,
+      )}
+    >
+      {children}
+    </section>
+  );
+}

web/src/components/collapse.tsx

@@ -51,8 +51,8 @@ export function Collapse({
       onOpenChange={handleOpenChange}
       disabled={disabled}
     >
-      <CollapsibleTrigger className="w-full">
-        <section className="flex justify-between items-center pb-2">
+      <CollapsibleTrigger className={'w-full'}>
+        <section className="flex justify-between items-center">
           <div className="flex items-center gap-1">
             <IconFontFill
               name={`more`}
@@ -60,12 +60,18 @@ export function Collapse({
                 'rotate-90': !currentOpen,
               })}
             ></IconFontFill>
-            {title}
+            <div
+              className={cn('text-text-secondary', {
+                'text-text-primary': open,
+              })}
+            >
+              {title}
+            </div>
           </div>
           <div>{rightContent}</div>
         </section>
       </CollapsibleTrigger>
-      <CollapsibleContent>{children}</CollapsibleContent>
+      <CollapsibleContent className="pt-2">{children}</CollapsibleContent>
     </Collapsible>
   );
 }
@@ -94,7 +100,7 @@ export function NodeCollapsible<T extends any[]>({
     >
       {nextItems.slice(0, 3).map(children)}
       <CollapsibleContent className={nextClassName}>
-        {nextItems.slice(3).map(children)}
+        {nextItems.slice(3).map((x, idx) => children(x, idx + 3))}
       </CollapsibleContent>
       {nextItems.length > 3 && (
         <CollapsibleTrigger

web/src/components/confirm-delete-dialog.tsx

@@ -56,13 +56,13 @@ export function ConfirmDeleteDialog({
         </AlertDialogHeader>
         <AlertDialogFooter>
           <AlertDialogCancel onClick={onCancel}>
-            {t('common.cancel')}
+            {t('common.no')}
           </AlertDialogCancel>
           <AlertDialogAction
             className="bg-state-error text-text-primary"
             onClick={onOk}
           >
-            {t('common.ok')}
+            {t('common.yes')}
           </AlertDialogAction>
         </AlertDialogFooter>
       </AlertDialogContent>

web/src/components/edit-tag/index.tsx

@@ -1,5 +1,4 @@
 import { PlusOutlined } from '@ant-design/icons';
-import { TweenOneGroup } from 'rc-tween-one';
 import React, { useEffect, useRef, useState } from 'react';
 
 import { X } from 'lucide-react';
@@ -57,7 +56,7 @@ const EditTag = React.forwardRef<HTMLDivElement, EditTagsProps>(
         <HoverCard key={tag}>
           <HoverCardContent side="top">{tag}</HoverCardContent>
           <HoverCardTrigger asChild>
-            <div className="w-fit flex items-center justify-center gap-2 border-dashed border px-1 rounded-sm bg-bg-card">
+            <div className="w-fit flex items-center justify-center gap-2 border-dashed border px-2 py-1 rounded-sm bg-bg-card">
               <div className="flex gap-2 items-center">
                 <div className="max-w-80 overflow-hidden text-ellipsis">
                   {tag}
@@ -84,11 +83,11 @@ const EditTag = React.forwardRef<HTMLDivElement, EditTagsProps>(
 
     return (
       <div>
-        {inputVisible ? (
+        {inputVisible && (
           <Input
             ref={inputRef}
             type="text"
-            className="h-8 bg-bg-card"
+            className="h-8 bg-bg-card mb-1"
             value={inputValue}
             onChange={handleInputChange}
             onBlur={handleInputConfirm}
@@ -98,36 +97,20 @@ const EditTag = React.forwardRef<HTMLDivElement, EditTagsProps>(
               }
             }}
           />
-        ) : (
-          <Button
-            variant="dashed"
-            className="w-fit flex items-center justify-center gap-2 bg-bg-card"
-            onClick={showInput}
-            style={tagPlusStyle}
-          >
-            <PlusOutlined />
-          </Button>
-        )}
-        {Array.isArray(tagChild) && tagChild.length > 0 && (
-          <TweenOneGroup
-            className="flex gap-2 flex-wrap mt-2"
-            enter={{
-              scale: 0.8,
-              opacity: 0,
-              type: 'from',
-              duration: 100,
-            }}
-            onEnd={(e) => {
-              if (e.type === 'appear' || e.type === 'enter') {
-                (e.target as any).style = 'display: inline-block';
-              }
-            }}
-            leave={{ opacity: 0, width: 0, scale: 0, duration: 200 }}
-            appear={false}
-          >
-            {tagChild}
-          </TweenOneGroup>
         )}
+        <div className="flex gap-2 py-1">
+          {Array.isArray(tagChild) && tagChild.length > 0 && <>{tagChild}</>}
+          {!inputVisible && (
+            <Button
+              variant="dashed"
+              className="w-fit flex items-center justify-center gap-2 bg-bg-card"
+              onClick={showInput}
+              style={tagPlusStyle}
+            >
+              <PlusOutlined />
+            </Button>
+          )}
+        </div>
       </div>
     );
   },

web/src/components/home-card.tsx

@@ -24,7 +24,6 @@ export function HomeCard({
 }: IProps) {
   return (
     <Card
-      className="bg-bg-card  border-colors-outline-neutral-standard"
       onClick={() => {
         // navigateToSearch(data?.id);
         onClick?.();

web/src/components/theme-toggle.tsx

@@ -0,0 +1,48 @@
+import { ThemeEnum } from '@/constants/common';
+import { Moon, Sun } from 'lucide-react';
+import { FC, useCallback } from 'react';
+import { useIsDarkTheme, useTheme } from './theme-provider';
+import { Button } from './ui/button';
+
+const ThemeToggle: FC = () => {
+  const { setTheme } = useTheme();
+  const isDarkTheme = useIsDarkTheme();
+  const handleThemeChange = useCallback(
+    (checked: boolean) => {
+      setTheme(checked ? ThemeEnum.Dark : ThemeEnum.Light);
+    },
+    [setTheme],
+  );
+  return (
+    <Button
+      type="button"
+      onClick={() => handleThemeChange(!isDarkTheme)}
+      className="relative inline-flex h-6 w-14 items-center rounded-full  transition-colors p-0.5 border-none focus:border-none bg-bg-card hover:bg-bg-card"
+      //   aria-label={isDarkTheme ? 'Switch to light mode' : 'Switch to dark mode'}
+    >
+      <div className="inline-flex h-full w-full items-center">
+        <div
+          className={`inline-flex transform items-center justify-center rounded-full  transition-transform ${
+            isDarkTheme
+              ? '  text-text-disabled h-4 w-5'
+              : '  text-text-primary bg-bg-base h-full w-8 flex-1'
+          }`}
+        >
+          <Sun />
+        </div>
+
+        <div
+          className={`inline-flex  transform items-center justify-center rounded-full  transition-transform ${
+            isDarkTheme
+              ? ' text-text-primary bg-bg-base h-full w-8 flex-1'
+              : 'text-text-disabled h-4 w-5'
+          }`}
+        >
+          <Moon />
+        </div>
+      </div>
+    </Button>
+  );
+};
+
+export default ThemeToggle;

web/src/components/ui/card.tsx

@@ -8,7 +8,10 @@ const Card = React.forwardRef<
 >(({ className, ...props }, ref) => (
   <div
     ref={ref}
-    className={cn('rounded-lg  bg-bg-card  shadow-sm', className)}
+    className={cn(
+      'rounded-lg border-border-default border shadow-sm bg-bg-input',
+      className,
+    )}
     {...props}
   />
 ));

web/src/components/ui/dialog.tsx

@@ -73,7 +73,7 @@ const DialogFooter = ({
 }: React.HTMLAttributes<HTMLDivElement>) => (
   <div
     className={cn(
-      'flex flex-col-reverse sm:flex-row sm:justify-end sm:space-x-2',
+      'flex flex-col-reverse sm:flex-row sm:justify-end sm:space-x-4',
       className,
     )}
     {...props}

web/src/components/ui/form.tsx

@@ -106,8 +106,10 @@ const FormLabel = React.forwardRef<
       htmlFor={formItemId}
       {...props}
     >
-      {required && <span className="text-destructive">*</span>}
-      {props.children}
+      <section>
+        {required && <span className="text-destructive">*</span>}
+        {props.children}
+      </section>
       {tooltip && <FormTooltip tooltip={tooltip}></FormTooltip>}
     </Label>
   );

web/src/components/ui/label.tsx

@@ -7,7 +7,7 @@ import * as React from 'react';
 import { cn } from '@/lib/utils';
 
 const labelVariants = cva(
-  'text-sm font-medium leading-none peer-disabled:cursor-not-allowed peer-disabled:opacity-70',
+  'text-sm font-medium leading-none peer-disabled:cursor-not-allowed peer-disabled:opacity-70 text-text-secondary',
 );
 
 const Label = React.forwardRef<

web/src/components/ui/modal/modal.tsx

@@ -140,6 +140,7 @@ const Modal: ModalType = ({
       </div>
     );
   }, [
+    disabled,
     footer,
     cancelText,
     t,
@@ -158,7 +159,7 @@ const Modal: ModalType = ({
           onClick={() => maskClosable && onOpenChange?.(false)}
         >
           <DialogPrimitive.Content
-            className={`relative w-[700px] ${full ? 'max-w-full' : sizeClasses[size]} ${className} bg-colors-background-neutral-standard rounded-lg shadow-lg border transition-all focus-visible:!outline-none`}
+            className={`relative w-[700px] ${full ? 'max-w-full' : sizeClasses[size]} ${className} bg-bg-base rounded-lg shadow-lg border border-border-default transition-all focus-visible:!outline-none`}
             onClick={(e) => e.stopPropagation()}
           >
             {/* title */}

web/src/hooks/common-hooks.tsx

@@ -94,9 +94,9 @@ export const useShowDeleteConfirm = () => {
           title: title ?? t('common.deleteModalTitle'),
           icon: <ExclamationCircleFilled />,
           content,
-          okText: t('common.ok'),
+          okText: t('common.yes'),
           okType: 'danger',
-          cancelText: t('common.cancel'),
+          cancelText: t('common.no'),
           async onOk() {
             try {
               const ret = await onOk?.();

web/src/hooks/logic-hooks.ts

@@ -257,25 +257,32 @@ export const useSendMessageWithSse = (
           .getReader();
 
         while (true) {
-          const x = await reader?.read();
-          if (x) {
-            const { done, value } = x;
-            if (done) {
-              resetAnswer();
-              break;
-            }
-            try {
-              const val = JSON.parse(value?.data || '');
-              const d = val?.data;
-              if (typeof d !== 'boolean') {
-                setAnswer({
-                  ...d,
-                  conversationId: body?.conversation_id,
-                  chatBoxId: body.chatBoxId,
-                });
+          try {
+            const x = await reader?.read();
+            if (x) {
+              const { done, value } = x;
+              if (done) {
+                resetAnswer();
+                break;
               }
-            } catch (e) {
-              // Swallow parse errors silently
+              try {
+                const val = JSON.parse(value?.data || '');
+                const d = val?.data;
+                if (typeof d !== 'boolean') {
+                  setAnswer({
+                    ...d,
+                    conversationId: body?.conversation_id,
+                    chatBoxId: body.chatBoxId,
+                  });
+                }
+              } catch (e) {
+                // Swallow parse errors silently
+              }
+            }
+          } catch (e) {
+            if (e instanceof DOMException && e.name === 'AbortError') {
+              console.log('Request was aborted by user or logic.');
+              break;
             }
           }
         }

web/src/hooks/use-send-message.ts

@@ -126,29 +126,36 @@ export const useSendMessageBySSE = (url: string = api.completeConversation) => {
           .getReader();
 
         while (true) {
-          const x = await reader?.read();
-          if (x) {
-            const { done, value } = x;
-            if (done) {
-              console.info('done');
-              resetAnswerList();
-              break;
-            }
-            try {
-              const val = JSON.parse(value?.data || '');
-
-              console.info('data:', val);
-              if (val.code === 500) {
-                message.error(val.message);
+          try {
+            const x = await reader?.read();
+            if (x) {
+              const { done, value } = x;
+              if (done) {
+                console.info('done');
+                resetAnswerList();
+                break;
               }
+              try {
+                const val = JSON.parse(value?.data || '');
 
-              setAnswerList((list) => {
-                const nextList = [...list];
-                nextList.push(val);
-                return nextList;
-              });
-            } catch (e) {
-              console.warn(e);
+                console.info('data:', val);
+                if (val.code === 500) {
+                  message.error(val.message);
+                }
+
+                setAnswerList((list) => {
+                  const nextList = [...list];
+                  nextList.push(val);
+                  return nextList;
+                });
+              } catch (e) {
+                console.warn(e);
+              }
+            }
+          } catch (e) {
+            if (e instanceof DOMException && e.name === 'AbortError') {
+              console.log('Request was aborted by user or logic.');
+              break;
             }
           }
         }

web/src/interfaces/database/agent.ts

@@ -83,12 +83,19 @@ export interface IFlowTemplate {
   canvas_type: string;
   create_date: string;
   create_time: number;
-  description: string;
+  canvas_category?: string;
   dsl: DSL;
   id: string;
-  title: string;
   update_date: string;
   update_time: number;
+  description: {
+    en: string;
+    zh: string;
+  };
+  title: {
+    en: string;
+    zh: string;
+  };
 }
 
 export interface IGenerateForm {

web/src/locales/en.ts

@@ -6,8 +6,9 @@ export default {
       selectAll: 'Select All',
       delete: 'Delete',
       deleteModalTitle: 'Are you sure to delete this item?',
-      ok: 'Yes',
-      cancel: 'No',
+      ok: 'Ok',
+      cancel: 'Cancel',
+      yes: 'Yes',
       no: 'No',
       total: 'Total',
       rename: 'Rename',
@@ -137,7 +138,7 @@ export default {
       completed: 'Completed',
       datasetLog: 'Dataset Log',
       created: 'Created',
-      learnMore: 'Learn More',
+      learnMore: 'Built-in pipeline introduction',
       general: 'General',
       chunkMethodTab: 'Chunk Method',
       testResults: 'Test Results',
@@ -429,7 +430,7 @@ export default {
 `,
       useRaptor: 'RAPTOR',
       useRaptorTip:
-        'Enable RAPTOR for multi-hop question-answering tasks. See https://ragflow.io/docs/dev/enable_raptor for details.',
+        'RAPTOR can be used for multi-hop question-answering tasks. Navigate to the Files page, click Generate > RAPTOR to enable it. See https://ragflow.io/docs/dev/enable_raptor for details.',
       prompt: 'Prompt',
       promptTip:
         'Use the system prompt to describe the task for the LLM, specify how it should respond, and outline other miscellaneous requirements. The system prompt is often used in conjunction with keys (variables), which serve as various data inputs for the LLM. Use a forward slash `/` or the (x) button to show the keys to use.',
@@ -697,7 +698,7 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
       system: 'System',
       logout: 'Log out',
       api: 'API',
-      username: 'Username',
+      username: 'Name',
       usernameMessage: 'Please input your username!',
       photo: 'Your photo',
       photoDescription: 'This will be displayed on your profile.',
@@ -1533,8 +1534,8 @@ This delimiter is used to split the input text into several text pieces echo of
         'Your users will see this welcome message at the beginning.',
       modeTip: 'The mode defines how the workflow is initiated.',
       mode: 'Mode',
-      conversational: 'conversational',
-      task: 'task',
+      conversational: 'Conversational',
+      task: 'Task',
       beginInputTip:
         'By defining input parameters, this content can be accessed by other components in subsequent processes.',
       query: 'Query variables',
@@ -1605,107 +1606,6 @@ This delimiter is used to split the input text into several text pieces echo of
       ceateAgent: 'Agent flow',
       createPipeline: 'Ingestion pipeline',
       chooseAgentType: 'Choose Agent Type',
-    },
-    llmTools: {
-      bad_calculator: {
-        name: 'Calculator',
-        description:
-          'A tool to calculate the sum of two numbers (will give wrong answer)',
-        params: {
-          a: 'The first number',
-          b: 'The second number',
-        },
-      },
-    },
-    modal: {
-      okText: 'Confirm',
-      cancelText: 'Cancel',
-    },
-    mcp: {
-      export: 'Export',
-      import: 'Import',
-      url: 'URL',
-      serverType: 'Server Type',
-      addMCP: 'Add MCP',
-      editMCP: 'Edit MCP',
-      toolsAvailable: 'tools available',
-      mcpServers: 'MCP Servers',
-      customizeTheListOfMcpServers: 'Customize the list of MCP servers',
-    },
-    search: {
-      searchApps: 'Search Apps',
-      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',
-      descriptionValue: 'You are an intelligent assistant.',
-      okText: 'Save',
-      cancelText: 'Cancel',
-      chooseDataset: 'Please select a dataset first',
-    },
-    language: {
-      english: 'English',
-      chinese: 'Chinese',
-      spanish: 'Spanish',
-      french: 'French',
-      german: 'German',
-      japanese: 'Japanese',
-      korean: 'Korean',
-      vietnamese: 'Vietnamese',
-    },
-    pagination: {
-      total: 'Total {{total}}',
-      page: '{{page}} /Page',
-    },
-    dataflowParser: {
-      result: 'Result',
-      parseSummary: 'Parse Summary',
-      parseSummaryTip: 'Parser：deepdoc',
-      rerunFromCurrentStep: 'Rerun From Current Step',
-      rerunFromCurrentStepTip: 'Changes detected. Click to re-run.',
-      confirmRerun: 'Confirm Rerun Process',
-      confirmRerunModalContent: `
-      <p class="text-sm text-text-disabled font-medium mb-2">
-        You are about to rerun the process starting from the <strong class="text-text-primary">{{step}}</strong> step.
-      </p>
-      <p class="text-sm mb-3 text-text-secondary">This will:</p>
-      <ul class="list-disc list-inside space-y-1 text-sm text-text-secondary">
-        <li>Overwrite existing results from the current step onwards</li>
-        <li>Create a new log entry for tracking</li>
-        <li>Previous steps will remain unchanged</li>
-      </ul>`,
-      changeStepModalTitle: 'Step Switch Warning',
-      changeStepModalContent: `
-      <p>You are currently editing the results of this stage.</p> 
-      <p>If you switch to a later stage, your changes will be lost. </p> 
-      <p>To keep them, please click Rerun to re-run the current stage.</p> `,
-      changeStepModalConfirmText: 'Switch Anyway',
-      changeStepModalCancelText: 'Cancel',
-      unlinkPipelineModalTitle: 'Unlink Ingestion pipeline',
-      unlinkPipelineModalContent: `
-      <p>Once unlinked, this Dataset will no longer be connected to the current Ingestion pipeline.</p> 
-      <p>Files that are already being parsed  will continue until completion</p> 
-      <p>Files that are not yet parsed will no longer be processed</p> <br/>
-      <p>Are you sure you want to proceed?</p> `,
-      unlinkPipelineModalConfirmText: 'Unlink',
-    },
-    dataflow: {
       parser: 'Parser',
       parserDescription:
         'Extracts raw text and structure from files for downstream processing.',
@@ -1723,7 +1623,6 @@ This delimiter is used to split the input text into several text pieces echo of
       extractorDescription:
         'Use an LLM to extract structured insights from document chunks—such as summaries, classifications, etc.',
       outputFormat: 'Output format',
-      lang: 'Language',
       fileFormats: 'File format',
       fileFormatOptions: {
         pdf: 'PDF',
@@ -1734,6 +1633,7 @@ This delimiter is used to split the input text into several text pieces echo of
         word: 'Word',
         slides: 'PPT',
         audio: 'Audio',
+        video: 'Video',
       },
       fields: 'Field',
       addParser: 'Add Parser',
@@ -1743,9 +1643,9 @@ This delimiter is used to split the input text into several text pieces echo of
       searchMethod: 'Search method',
       searchMethodTip: `Defines how the content can be searched — by full-text, embedding, or both.
 The Indexer will store the content in the corresponding data structures for the selected methods.`,
-      begin: 'File',
+      // file: 'File',
       parserMethod: 'Parsing method',
-      systemPrompt: 'System Prompt',
+      // systemPrompt: 'System Prompt',
       systemPromptPlaceholder:
         'Enter system prompt for image analysis, if empty the system default value will be used',
       exportJson: 'Export JSON',
@@ -1820,9 +1720,108 @@ Important structured information may include: names, dates, locations, events, k
       imageParseMethodOptions: {
         ocr: 'OCR',
       },
-      note: 'Note',
-      noteDescription: 'Note',
-      notePlaceholder: 'Please enter a note',
+    },
+    llmTools: {
+      bad_calculator: {
+        name: 'Calculator',
+        description:
+          'A tool to calculate the sum of two numbers (will give wrong answer)',
+        params: {
+          a: 'The first number',
+          b: 'The second number',
+        },
+      },
+    },
+    modal: {
+      okText: 'Confirm',
+      cancelText: 'Cancel',
+    },
+    mcp: {
+      export: 'Export',
+      import: 'Import',
+      url: 'URL',
+      serverType: 'Server Type',
+      addMCP: 'Add MCP',
+      editMCP: 'Edit MCP',
+      toolsAvailable: 'tools available',
+      mcpServers: 'MCP Servers',
+      customizeTheListOfMcpServers: 'Customize the list of MCP servers',
+      cachedTools: 'cached tools',
+    },
+    search: {
+      searchApps: 'Search Apps',
+      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',
+      descriptionValue: 'You are an intelligent assistant.',
+      okText: 'Save',
+      cancelText: 'Cancel',
+      chooseDataset: 'Please select a dataset first',
+    },
+    language: {
+      english: 'English',
+      chinese: 'Chinese',
+      spanish: 'Spanish',
+      french: 'French',
+      german: 'German',
+      japanese: 'Japanese',
+      korean: 'Korean',
+      vietnamese: 'Vietnamese',
+    },
+    pagination: {
+      total: 'Total {{total}}',
+      page: '{{page}} /Page',
+    },
+    dataflowParser: {
+      result: 'Result',
+      parseSummary: 'Parse Summary',
+      parseSummaryTip: 'Parser：deepdoc',
+      parserMethod: 'Parser Method',
+      outputFormat: 'Output Format',
+      rerunFromCurrentStep: 'Rerun From Current Step',
+      rerunFromCurrentStepTip: 'Changes detected. Click to re-run.',
+      confirmRerun: 'Confirm Rerun Process',
+      confirmRerunModalContent: `
+      <p class="text-sm text-text-disabled font-medium mb-2">
+        You are about to rerun the process starting from the <strong class="text-text-primary">{{step}}</strong> step.
+      </p>
+      <p class="text-sm mb-3 text-text-secondary">This will:</p>
+      <ul class="list-disc list-inside space-y-1 text-sm text-text-secondary">
+        <li>Overwrite existing results from the current step onwards</li>
+        <li>Create a new log entry for tracking</li>
+        <li>Previous steps will remain unchanged</li>
+      </ul>`,
+      changeStepModalTitle: 'Step Switch Warning',
+      changeStepModalContent: `
+      <p>You are currently editing the results of this stage.</p> 
+      <p>If you switch to a later stage, your changes will be lost. </p> 
+      <p>To keep them, please click Rerun to re-run the current stage.</p> `,
+      changeStepModalConfirmText: 'Switch Anyway',
+      changeStepModalCancelText: 'Cancel',
+      unlinkPipelineModalTitle: 'Unlink Ingestion pipeline',
+      unlinkPipelineModalContent: `
+      <p>Once unlinked, this Dataset will no longer be connected to the current Ingestion pipeline.</p> 
+      <p>Files that are already being parsed  will continue until completion</p> 
+      <p>Files that are not yet parsed will no longer be processed</p> <br/>
+      <p>Are you sure you want to proceed?</p> `,
+      unlinkPipelineModalConfirmText: 'Unlink',
     },
     datasetOverview: {
       downloadTip: 'Files being downloaded from data sources. ',

web/src/locales/zh.ts

@@ -6,8 +6,10 @@ export default {
       selectAll: '全选',
       delete: '删除',
       deleteModalTitle: '确定删除吗?',
-      ok: '是',
-      cancel: '否',
+      ok: '确认',
+      cancel: '取消',
+      yes: '是',
+      no: '否',
       total: '总共',
       rename: '重命名',
       name: '名称',
@@ -125,7 +127,7 @@ export default {
       completed: '已完成',
       datasetLog: '知识库日志',
       created: '创建于',
-      learnMore: '了解更多',
+      learnMore: '内置pipeline简介',
       general: '通用',
       chunkMethodTab: '切片方法',
       testResults: '测试结果',
@@ -423,7 +425,7 @@ export default {
 `,
       useRaptor: '使用召回增强 RAPTOR 策略',
       useRaptorTip:
-        '为多跳问答任务启用 RAPTOR，详情请见 : https://ragflow.io/docs/dev/enable_raptor。',
+        'RAPTOR 常应用于复杂的多跳问答任务。如需打开，请跳转至知识库的文件页面，点击生成 > RAPTOR 开启。详见: https://ragflow.io/docs/dev/enable_raptor。',
       prompt: '提示词',
       promptMessage: '提示词是必填项',
       promptText: `请总结以下段落。 小心数字，不要编造。 段落如下：
@@ -1511,114 +1513,6 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       createFromTemplate: '从模板创建',
       importJsonFile: '导入 JSON 文件',
       chooseAgentType: '选择智能体类型',
-    },
-    footer: {
-      profile: 'All rights reserved @ React',
-    },
-    layout: {
-      file: 'file',
-      knowledge: 'knowledge',
-      chat: 'chat',
-    },
-    llmTools: {
-      bad_calculator: {
-        name: '计算器',
-        description: '用于计算两个数的和的工具（会给出错误答案）',
-        params: {
-          a: '第一个数',
-          b: '第二个数',
-        },
-      },
-    },
-    modal: {
-      okText: '确认',
-      cancelText: '取消',
-    },
-    mcp: {
-      export: '导出',
-      import: '导入',
-      url: 'URL',
-      serverType: '服务器类型',
-      addMCP: '添加 MCP',
-      editMCP: '编辑 MCP',
-      toolsAvailable: '可用的工具',
-      mcpServers: 'MCP 服务器',
-      customizeTheListOfMcpServers: '自定义 MCP 服务器列表',
-    },
-    search: {
-      searchApps: '搜索',
-      createSearch: '创建查询',
-      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: '知识库',
-      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',
-      descriptionValue: '你是一位智能助手。',
-      okText: '保存',
-      cancelText: '返回',
-      chooseDataset: '请先选择知识库',
-    },
-    language: {
-      english: '英语',
-      chinese: '中文',
-      spanish: '西班牙语',
-      french: '法语',
-      german: '德语',
-      japanese: '日语',
-      korean: '韩语',
-      vietnamese: '越南语',
-    },
-    pagination: {
-      total: '总共 {{total}} 条',
-      page: '{{page}}条/页',
-    },
-    dataflowParser: {
-      result: '结果',
-      parseSummary: '解析摘要',
-      parseSummaryTip: '解析器: deepdoc',
-      rerunFromCurrentStep: '从当前步骤重新运行',
-      rerunFromCurrentStepTip: '已修改，点击重新运行。',
-      confirmRerun: '确认重新运行流程',
-      confirmRerunModalContent: `
-      <p class="text-sm text-text-disabled font-medium mb-2">
-        您即将从 <strong class="text-text-primary">{{step}}</strong> 步骤开始重新运行该过程
-      </p>
-      <p class="text-sm mb-3 text-text-secondary">这将:</p>
-      <ul class="list-disc list-inside space-y-1 text-sm text-text-secondary">
-        <li>从当前步骤开始覆盖现有结果</li>
-        <li>创建新的日志条目进行跟踪</li>
-        <li>之前的步骤将保持不变</li>
-      </ul>`,
-      changeStepModalTitle: '切换步骤警告',
-      changeStepModalContent: `
-      <p>您目前正在编辑此阶段的结果。</p>
-      <p>如果您切换到后续阶段，您的更改将会丢失。</p>
-      <p>要保留这些更改，请点击“重新运行”以重新运行当前阶段。</p> `,
-      changeStepModalConfirmText: '继续切换',
-      changeStepModalCancelText: '取消',
-      unlinkPipelineModalTitle: '解绑pipeline',
-      unlinkPipelineModalContent: `
-      <p>一旦取消链接，该数据集将不再连接到当前数据管道。</p> 
-      <p>正在解析的文件将继续解析，直到完成。</p> 
-      <p>尚未解析的文件将不再被处理。</p> <br/>
-      <p>你确定要继续吗?</p> `,
-      unlinkPipelineModalConfirmText: '解绑',
-    },
-    dataflow: {
       parser: '解析器',
       parserDescription: '从文件中提取原始文本和结构以供下游处理。',
       tokenizer: '分词器',
@@ -1635,7 +1529,6 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       extractorDescription:
         '使用 LLM 从文档块（例如摘要、分类等）中提取结构化见解。',
       outputFormat: '输出格式',
-      lang: '语言',
       fileFormats: '文件格式',
       fields: '字段',
       addParser: '增加解析器',
@@ -1646,9 +1539,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
       searchMethodTip: `决定该数据集启用的搜索方式，可选择全文、向量，或两者兼有。
 Tokenizer 会根据所选方式将内容存储为对应的数据结构。`,
       filenameEmbdWeight: '文件名嵌入权重',
-      begin: '文件',
       parserMethod: '解析方法',
-      systemPrompt: '系统提示词',
       systemPromptPlaceholder:
         '请输入用于图像分析的系统提示词，若为空则使用系统缺省值',
       exportJson: '导出 JSON',
@@ -1709,9 +1600,115 @@ Tokenizer 会根据所选方式将内容存储为对应的数据结构。`,
       cancel: '取消',
       filenameEmbeddingWeight: '文件名嵌入权重',
       switchPromptMessage: '提示词将发生变化，请确认是否放弃已有提示词？',
-      note: '注释',
-      noteDescription: '注释',
-      notePlaceholder: '请输入注释',
+    },
+    footer: {
+      profile: 'All rights reserved @ React',
+    },
+    layout: {
+      file: 'file',
+      knowledge: 'knowledge',
+      chat: 'chat',
+    },
+    llmTools: {
+      bad_calculator: {
+        name: '计算器',
+        description: '用于计算两个数的和的工具（会给出错误答案）',
+        params: {
+          a: '第一个数',
+          b: '第二个数',
+        },
+      },
+    },
+    modal: {
+      okText: '确认',
+      cancelText: '取消',
+    },
+    mcp: {
+      export: '导出',
+      import: '导入',
+      url: 'URL',
+      serverType: '服务器类型',
+      addMCP: '添加 MCP',
+      editMCP: '编辑 MCP',
+      toolsAvailable: '可用的工具',
+      mcpServers: 'MCP 服务器',
+      customizeTheListOfMcpServers: '自定义 MCP 服务器列表',
+      cachedTools: '缓存工具',
+    },
+    search: {
+      searchApps: '搜索',
+      createSearch: '创建查询',
+      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: '知识库',
+      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',
+      descriptionValue: '你是一位智能助手。',
+      okText: '保存',
+      cancelText: '返回',
+      chooseDataset: '请先选择知识库',
+    },
+    language: {
+      english: '英语',
+      chinese: '中文',
+      spanish: '西班牙语',
+      french: '法语',
+      german: '德语',
+      japanese: '日语',
+      korean: '韩语',
+      vietnamese: '越南语',
+    },
+    pagination: {
+      total: '总共 {{total}} 条',
+      page: '{{page}}条/页',
+    },
+    dataflowParser: {
+      result: '结果',
+      parseSummary: '解析摘要',
+      parseSummaryTip: '解析器: deepdoc',
+      parserMethod: '解析方法',
+      outputFormat: '输出格式',
+      rerunFromCurrentStep: '从当前步骤重新运行',
+      rerunFromCurrentStepTip: '已修改，点击重新运行。',
+      confirmRerun: '确认重新运行流程',
+      confirmRerunModalContent: `
+      <p class="text-sm text-text-disabled font-medium mb-2">
+        您即将从 <strong class="text-text-primary">{{step}}</strong> 步骤开始重新运行该过程
+      </p>
+      <p class="text-sm mb-3 text-text-secondary">这将:</p>
+      <ul class="list-disc list-inside space-y-1 text-sm text-text-secondary">
+        <li>从当前步骤开始覆盖现有结果</li>
+        <li>创建新的日志条目进行跟踪</li>
+        <li>之前的步骤将保持不变</li>
+      </ul>`,
+      changeStepModalTitle: '切换步骤警告',
+      changeStepModalContent: `
+      <p>您目前正在编辑此阶段的结果。</p>
+      <p>如果您切换到后续阶段，您的更改将会丢失。</p>
+      <p>要保留这些更改，请点击“重新运行”以重新运行当前阶段。</p> `,
+      changeStepModalConfirmText: '继续切换',
+      changeStepModalCancelText: '取消',
+      unlinkPipelineModalTitle: '解绑pipeline',
+      unlinkPipelineModalContent: `
+      <p>一旦取消链接，该数据集将不再连接到当前数据管道。</p> 
+      <p>正在解析的文件将继续解析，直到完成。</p> 
+      <p>尚未解析的文件将不再被处理。</p> <br/>
+      <p>你确定要继续吗?</p> `,
+      unlinkPipelineModalConfirmText: '解绑',
     },
     datasetOverview: {
       downloadTip: '正在从数据源下载文件。',

web/src/pages/add-knowledge/components/knowledge-file/parsing-status-cell/index.tsx

@@ -124,8 +124,8 @@ export const ParsingStatusCell = ({ record }: IProps) => {
         onConfirm={handleOperationIconClick(true)}
         onCancel={handleOperationIconClick(false)}
         disabled={record.chunk_num === 0}
-        okText={t('common.ok')}
-        cancelText={t('common.cancel')}
+        okText={t('common.yes')}
+        cancelText={t('common.no')}
       >
         <div
           className={classNames(styles.operationIcon)}

web/src/pages/agent/canvas/node/file-node.tsx

@@ -36,7 +36,7 @@ function InnerFileNode({ data, id, selected }: NodeProps<IBeginNode>) {
       <section className="flex items-center  gap-2">
         <OperatorIcon name={data.label as Operator}></OperatorIcon>
         <div className="truncate text-center font-semibold text-sm">
-          {t(`dataflow.begin`)}
+          {t(`flow.begin`)}
         </div>
       </section>
       <section className={cn(styles.generateParameters, 'flex gap-2 flex-col')}>

web/src/pages/agent/canvas/node/handle.tsx

@@ -5,6 +5,8 @@ import { Plus } from 'lucide-react';
 import { useMemo } from 'react';
 import { NodeHandleId } from '../../constant';
 import { HandleContext } from '../../context';
+import { useIsPipeline } from '../../hooks/use-is-pipeline';
+import useGraphStore from '../../store';
 import { useDropdownManager } from '../context';
 import { NextStepDropdown } from './dropdown/next-step-dropdown';
 
@@ -14,9 +16,12 @@ export function CommonHandle({
   ...props
 }: HandleProps & { nodeId: string }) {
   const { visible, hideModal, showModal } = useSetModalState();
-
   const { canShowDropdown, setActiveDropdown, clearActiveDropdown } =
     useDropdownManager();
+  const { hasChildNode } = useGraphStore((state) => state);
+  const isPipeline = useIsPipeline();
+
+  const isConnectable = !(isPipeline && hasChildNode(nodeId)); // Using useMemo will cause isConnectable to not be updated when the subsequent connection line is deleted
 
   const value = useMemo(
     () => ({
@@ -33,6 +38,7 @@ export function CommonHandle({
     <HandleContext.Provider value={value}>
       <Handle
         {...props}
+        isConnectable={isConnectable}
         className={cn(
           'inline-flex justify-center items-center !bg-accent-primary !border-none group-hover:!size-4 group-hover:!rounded-sm',
           className,
@@ -40,6 +46,10 @@ export function CommonHandle({
         onClick={(e) => {
           e.stopPropagation();
 
+          if (!isConnectable) {
+            return;
+          }
+
           if (!canShowDropdown()) {
             return;
           }

web/src/pages/agent/canvas/node/parser-node.tsx

@@ -46,7 +46,7 @@ function ParserNode({
             className="flex flex-col text-text-primary gap-1"
           >
             <span className="text-text-secondary">Parser {idx + 1}</span>
-            {t(`dataflow.fileFormatOptions.${x.fileFormat}`)}
+            {t(`flow.fileFormatOptions.${x.fileFormat}`)}
           </LabelCard>
         )}
       </NodeCollapsible>

web/src/pages/agent/canvas/node/tokenizer-node.tsx

@@ -38,12 +38,10 @@ function TokenizerNode({
         ></CommonHandle>
         <NodeHeader id={id} name={data.name} label={data.label}></NodeHeader>
         <LabelCard className="text-text-primary flex justify-between flex-col gap-1">
-          <span className="text-text-secondary">
-            {t('dataflow.searchMethod')}
-          </span>
+          <span className="text-text-secondary">{t('flow.searchMethod')}</span>
           <ul className="space-y-1">
             {data.form?.search_method.map((x) => (
-              <li key={x}>{t(`dataflow.tokenizerSearchMethodOptions.${x}`)}</li>
+              <li key={x}>{t(`flow.tokenizerSearchMethodOptions.${x}`)}</li>
             ))}
           </ul>
         </LabelCard>

web/src/pages/agent/chat/chat-sheet.tsx

@@ -2,10 +2,13 @@ import { Sheet, SheetContent, SheetTitle } from '@/components/ui/sheet';
 import { IModalProps } from '@/interfaces/common';
 import { cn } from '@/lib/utils';
 import { useTranslation } from 'react-i18next';
+import { useIsTaskMode } from '../hooks/use-get-begin-query';
 import AgentChatBox from './box';
 
 export function ChatSheet({ hideModal }: IModalProps<any>) {
   const { t } = useTranslation();
+  const isTaskMode = useIsTaskMode();
+
   return (
     <Sheet open modal={false} onOpenChange={hideModal}>
       <SheetContent
@@ -13,7 +16,9 @@ export function ChatSheet({ hideModal }: IModalProps<any>) {
         onInteractOutside={(e) => e.preventDefault()}
       >
         <SheetTitle className="hidden"></SheetTitle>
-        <div className="pl-5 pt-2">{t('chat.chat')}</div>
+        <div className="pl-5 pt-2">
+          {t(isTaskMode ? 'flow.task' : 'chat.chat')}
+        </div>
         <AgentChatBox></AgentChatBox>
       </SheetContent>
     </Sheet>

web/src/pages/agent/chat/use-send-agent-message.ts

@@ -382,9 +382,9 @@ export const useSendAgentMessage = ({
     const { content, id } = findMessageFromList(answerList);
     const inputAnswer = findInputFromList(answerList);
     const answer = content || getLatestError(answerList);
-    if (answerList.length > 0 && answer) {
+    if (answerList.length > 0) {
       addNewestOneAnswer({
-        answer: answer,
+        answer: answer ?? '',
         id: id,
         ...inputAnswer,
       });

web/src/pages/agent/constant/pipeline.tsx

@@ -49,7 +49,7 @@ export enum PptOutputFormat {
 }
 
 export enum VideoOutputFormat {
-  Json = 'json',
+  Text = 'text',
 }
 
 export enum AudioOutputFormat {
@@ -76,7 +76,7 @@ export const InitialOutputFormatMap = {
   [FileType.TextMarkdown]: TextMarkdownOutputFormat.Text,
   [FileType.Docx]: DocxOutputFormat.Json,
   [FileType.PowerPoint]: PptOutputFormat.Json,
-  [FileType.Video]: VideoOutputFormat.Json,
+  [FileType.Video]: VideoOutputFormat.Text,
   [FileType.Audio]: AudioOutputFormat.Text,
 };
 
@@ -244,7 +244,7 @@ export const FileTypeSuffixMap = {
   [FileType.TextMarkdown]: ['md', 'markdown', 'mdx', 'txt'],
   [FileType.Docx]: ['doc', 'docx'],
   [FileType.PowerPoint]: ['pptx'],
-  [FileType.Video]: [],
+  [FileType.Video]: ['mp4', 'avi', 'mkv'],
   [FileType.Audio]: [
     'da',
     'wave',

web/src/pages/agent/context.ts

@@ -48,13 +48,3 @@ export type HandleContextType = {
 export const HandleContext = createContext<HandleContextType>(
   {} as HandleContextType,
 );
-
-export type PipelineLogContextType = {
-  messageId: string;
-  setMessageId: (messageId: string) => void;
-  setUploadedFileData: (data: Record<string, any>) => void;
-};
-
-export const PipelineLogContext = createContext<PipelineLogContextType>(
-  {} as PipelineLogContextType,
-);

web/src/pages/agent/form/extractor-form/index.tsx

@@ -47,7 +47,7 @@ const ExtractorForm = ({ node }: INextOperatorForm) => {
 
   const promptOptions = useBuildNodeOutputOptions(node?.id);
 
-  const options = buildOptions(ContextGeneratorFieldName, t, 'dataflow');
+  const options = buildOptions(ContextGeneratorFieldName, t, 'flow');
 
   const {
     handleFieldNameChange,
@@ -63,7 +63,7 @@ const ExtractorForm = ({ node }: INextOperatorForm) => {
     <Form {...form}>
       <FormWrapper>
         <LargeModelFormField></LargeModelFormField>
-        <RAGFlowFormItem label={t('dataflow.fieldName')} name="field_name">
+        <RAGFlowFormItem label={t('flow.fieldName')} name="field_name">
           {(field) => (
             <SelectWithSearch
               onChange={(value) => {
@@ -93,7 +93,7 @@ const ExtractorForm = ({ node }: INextOperatorForm) => {
       </FormWrapper>
       {visible && (
         <ConfirmDeleteDialog
-          title={t('dataflow.switchPromptMessage')}
+          title={t('flow.switchPromptMessage')}
           open
           onOpenChange={hideModal}
           onOk={confirmSwitch}

web/src/pages/agent/form/extractor-form/use-switch-prompt.ts

@@ -21,7 +21,7 @@ export function useSwitchPrompt(form: UseFormReturn<ExtractorFormSchemaType>) {
 
   const setPromptValue = useCallback(
     (field: keyof ExtractorFormSchemaType, key: string, value: string) => {
-      form.setValue(field, t(`dataflow.prompts.${key}.${value}`), {
+      form.setValue(field, t(`flow.prompts.${key}.${value}`), {
         shouldDirty: true,
         shouldValidate: true,
       });

web/src/pages/agent/form/hierarchical-merger-form/index.tsx

@@ -98,7 +98,7 @@ export function RegularExpressions({
       </CardHeader>
       <CardContent>
         <FormLabel required className="mb-2 text-text-secondary">
-          {t('dataflow.regularExpressions')}
+          {t('flow.regularExpressions')}
         </FormLabel>
         <section className="space-y-4">
           {fields.map((field, index) => (
@@ -158,7 +158,7 @@ const HierarchicalMergerForm = ({ node }: INextOperatorForm) => {
   return (
     <Form {...form}>
       <FormWrapper>
-        <RAGFlowFormItem name={'hierarchy'} label={t('dataflow.hierarchy')}>
+        <RAGFlowFormItem name={'hierarchy'} label={t('flow.hierarchy')}>
           <SelectWithSearch options={HierarchyOptions}></SelectWithSearch>
         </RAGFlowFormItem>
         {fields.map((field, index) => (

web/src/pages/agent/form/parser-form/common-form-fields.tsx

@@ -50,7 +50,7 @@ export function OutputFormatFormField({
   return (
     <RAGFlowFormItem
       name={buildFieldNameWithPrefix(`output_format`, prefix)}
-      label={t('dataflow.outputFormat')}
+      label={t('flow.outputFormat')}
     >
       <SelectWithSearch
         options={buildOutputOptionsFormatMap()[fileType]}
@@ -69,7 +69,7 @@ export function ParserMethodFormField({
       name={buildFieldNameWithPrefix(`parse_method`, prefix)}
       horizontal={false}
       optionsWithoutLLM={optionsWithoutLLM}
-      label={t('dataflow.parserMethod')}
+      label={t('flow.parserMethod')}
     ></LayoutRecognizeFormField>
   );
 }
@@ -92,7 +92,7 @@ export function LanguageFormField({ prefix }: CommonProps) {
   return (
     <RAGFlowFormItem
       name={buildFieldNameWithPrefix(`lang`, prefix)}
-      label={t('dataflow.lang')}
+      label={t('flow.lang')}
     >
       {(field) => (
         <SelectWithSearch

web/src/pages/agent/form/parser-form/email-form-fields.tsx

@@ -14,7 +14,7 @@ export function EmailFormFields({ prefix }: CommonProps) {
     <>
       <RAGFlowFormItem
         name={buildFieldNameWithPrefix(`fields`, prefix)}
-        label={t('dataflow.fields')}
+        label={t('flow.fields')}
       >
         {(field) => (
           <MultiSelect

web/src/pages/agent/form/parser-form/image-form-fields.tsx

@@ -17,7 +17,7 @@ export function ImageFormFields({ prefix }: CommonProps) {
   const options = buildOptions(
     ImageParseMethod,
     t,
-    'dataflow.imageParseMethodOptions',
+    'flow.imageParseMethodOptions',
   );
   const parseMethodName = buildFieldNameWithPrefix('parse_method', prefix);
 
@@ -50,9 +50,9 @@ export function ImageFormFields({ prefix }: CommonProps) {
       {languageShown && (
         <RAGFlowFormItem
           name={buildFieldNameWithPrefix('system_prompt', prefix)}
-          label={t('dataflow.systemPrompt')}
+          label={t('flow.systemPrompt')}
         >
-          <Textarea placeholder={t('dataflow.systemPromptPlaceholder')} />
+          <Textarea placeholder={t('flow.systemPromptPlaceholder')} />
         </RAGFlowFormItem>
       )}
     </>