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

### What problem does this PR solve? ### Type of change - [x] Documentation Update
Docs: Update version references to v0.21.1 in READMEs and docs (#10761 )
2026-01-04 03:25:30 +08:00 · 2025-10-23 18:56:09 +08:00 · 2025-10-23 18:55:41 +08:00 · 2025-10-23 17:38:54 +08:00 · 2025-10-23 17:25:29 +08:00 · 2025-10-23 16:17:43 +08:00
112 changed files with 2128 additions and 1213 deletions
--- a/README.md
+++ b/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  |

--- a/README_id.md
+++ b/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 |

--- a/README_ja.md
+++ b/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 |

--- a/README_ko.md
+++ b/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 |

--- a/README_pt_br.md
+++ b/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 |

--- a/README_tzh.md
+++ b/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 |

--- a/README_zh.md
+++ b/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 |

--- a/admin/client/README.md
+++ b/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
--- a/admin/client/admin_client.py
+++ b/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
--- a/admin/client/pyproject.toml
+++ b/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" }
--- a/admin/pyproject.toml
+++ b/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"
--- a/admin/server/auth.py
+++ b/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)
--- a/admin/server/routes.py
+++ b/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'])
--- a/admin/server/services.py
+++ b/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]


--- a/agent/templates/chunk_summary.json
+++ b/agent/templates/chunk_summary.json
@ -350,7 +350,7 @@
                            ]
                        },
                        "label": "Tokenizer",
-                        "name": "Tokenizer"
+                        "name": "Indexer"
                    },
                    "dragging": false,
                    "id": "Tokenizer:EightRocketsAppear",
--- a/api/apps/kb_app.py
+++ b/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}")
--- a/api/apps/user_app.py
+++ b/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
--- a/api/db/services/document_service.py
+++ b/api/db/services/document_service.py
@ -671,9 +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 = []
@ -791,21 +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,
@ -820,9 +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"]

--- a/api/db/services/llm_service.py
+++ b/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})
--- a/api/utils/file_utils.py
+++ b/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
--- a/conf/llm_factories.json
+++ b/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",
--- a/deepdoc/parser/figure_parser.py
+++ b/deepdoc/parser/figure_parser.py
@ -41,13 +41,13 @@ def vision_figure_parser_docx_wrapper(sections,tbls,callback=None,**kwargs):
    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.")
+        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):
--- a/docker/.env
+++ b/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
 #
--- a/docker/README.md
+++ b/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`
--- a/docker/docker-compose-base.yml
+++ b/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
--- a/docker/infinity_conf.toml
+++ b/docker/infinity_conf.toml
@ -1,5 +1,5 @@
 [general]
-version                  = "0.6.0"
+version                  = "0.6.1"
 time_zone                = "utc-8"

 [network]
--- a/docs/configurations.md
+++ b/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`
--- a/docs/develop/build_docker_image.mdx
+++ b/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
--- a/docs/faq.mdx
+++ b/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.
+
+
+
--- a/docs/guides/agent/agent_component_reference/chunker_title.md
+++ b/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>`
--- a/docs/guides/agent/agent_component_reference/chunker_token.md
+++ b/docs/guides/agent/agent_component_reference/chunker_token.md
@ -3,15 +3,41 @@ sidebar_position: 32
 slug: /chunker_token_component
 ---

-# Parser component
+# Token chunker component

-A component that sets the parsing rules for your dataset.
+A component that splits texts into chunks, respecting a maximum token limit and using delimiters to find optimal breakpoints.

 ---

-A **Parser** component defines how various file types should be parsed, including parsing methods for PDFs , fields to parse for Emails, and OCR methods for images.
+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 **Parser** component is auto-populated on the ingestion pipeline canvas and required in all ingestion pipeline workflows.
+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>`
--- a/docs/guides/chat/start_chat.md
+++ b/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).

--- a/docs/guides/dataset/configure_knowledge_base.md
+++ b/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)

--- a/docs/guides/dataset/select_pdf_parser.md
+++ b/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.
 :::
--- a/docs/guides/manage_files.md
+++ b/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. 
--- a/docs/guides/manage_users_and_services.md
+++ b/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 |
 +-----------------+-------------+------------+-----------------+
 ```

--- a/docs/guides/tracing.mdx
+++ b/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_
 :::

--- a/docs/guides/upgrade_ragflow.mdx
+++ b/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
   ```
--- a/docs/quickstart.mdx
+++ b/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
--- a/docs/references/glossary.mdx
+++ b/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.

--- a/docs/release_notes.md
+++ b/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.
--- a/graphrag/general/extractor.py
+++ b/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")
--- a/helm/values.yaml
+++ b/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:
--- a/pyproject.toml
+++ b/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",
--- a/rag/app/manual.py
+++ b/rag/app/manual.py
@ -262,7 +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=sections,tbls=tbls,callback=callback,**kwargs)
+        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)
--- a/rag/app/picture.py
+++ b/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):
--- a/rag/flow/parser/parser.py
+++ b/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:
--- a/rag/llm/chat_model.py
+++ b/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"""

--- a/rag/llm/cv_model.py
+++ b/rag/llm/cv_model.py
@ -50,7 +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})
@ -78,7 +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,
@ -89,7 +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:
@ -228,7 +228,7 @@ 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=[], 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)
@ -506,7 +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})
@ -547,7 +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,
@ -561,7 +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(
@ -596,7 +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"]]})
@ -633,7 +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)
@ -651,7 +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:
@ -782,7 +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 (
@ -792,7 +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)
@ -858,7 +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:
@ -879,7 +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:
@ -963,13 +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
--- a/rag/nlp/search.py
+++ b/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
--- a/rag/svr/task_executor.py
+++ b/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"])

@ -1052,12 +1053,12 @@ async def task_manager():

 async def main():
    logging.info(r"""
-    ____                      __  _                                              
+    ____                      __  _
   /  _/___  ____ ____  _____/ /_(_)___  ____     ________  ______   _____  _____
   / // __ \/ __ `/ _ \/ ___/ __/ / __ \/ __ \   / ___/ _ \/ ___/ | / / _ \/ ___/
- _/ // / / / /_/ /  __(__  ) /_/ / /_/ / / / /  (__  )  __/ /   | |/ /  __/ /    
-/___/_/ /_/\__, /\___/____/\__/_/\____/_/ /_/  /____/\___/_/    |___/\___/_/     
-          /____/        
+ _/ // / / / /_/ /  __(__  ) /_/ / /_/ / / / /  (__  )  __/ /   | |/ /  __/ /
+/___/_/ /_/\__, /\___/____/\__/_/\____/_/ /_/  /____/\___/_/    |___/\___/_/
+          /____/
    """)
    logging.info(f'RAGFlow version: {get_ragflow_version()}')
    settings.init_settings()
--- a/rag/utils/oss_conn.py
+++ b/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',
--- a/sdk/python/pyproject.toml
+++ b/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" }
--- a/sdk/python/uv.lock
+++ b/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" },
--- a/uv.lock
+++ b/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"
--- a/web/src/components/avatar-upload.tsx
+++ b/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>
    );
--- a/web/src/components/card-container.tsx
+++ b/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>
+  );
+}
--- a/web/src/components/collapse.tsx
+++ b/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
--- a/web/src/components/confirm-delete-dialog.tsx
+++ b/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>
--- a/web/src/components/home-card.tsx
+++ b/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?.();
--- a/web/src/components/theme-toggle.tsx
+++ b/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;
--- a/web/src/components/ui/card.tsx
+++ b/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}
  />
 ));
--- a/web/src/components/ui/dialog.tsx
+++ b/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}
--- a/web/src/components/ui/form.tsx
+++ b/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>
  );
--- a/web/src/components/ui/label.tsx
+++ b/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<
--- a/web/src/components/ui/modal/modal.tsx
+++ b/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 */}
--- a/web/src/hooks/common-hooks.tsx
+++ b/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?.();
--- a/web/src/hooks/logic-hooks.ts
+++ b/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;
            }
          }
        }
--- a/web/src/hooks/use-send-message.ts
+++ b/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;
            }
          }
        }
--- a/web/src/interfaces/database/agent.ts
+++ b/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 {
--- a/web/src/locales/en.ts
+++ b/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.',
@ -1632,6 +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',
@ -1744,6 +1746,7 @@ Important structured information may include: names, dates, locations, events, k
      toolsAvailable: 'tools available',
      mcpServers: 'MCP Servers',
      customizeTheListOfMcpServers: 'Customize the list of MCP servers',
+      cachedTools: 'cached tools',
    },
    search: {
      searchApps: 'Search Apps',
@ -1790,6 +1793,8 @@ Important structured information may include: names, dates, locations, events, k
      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',
--- a/web/src/locales/zh.ts
+++ b/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：
@ -1631,6 +1633,7 @@ Tokenizer 会根据所选方式将内容存储为对应的数据结构。`,
      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',
@ -1677,6 +1680,8 @@ Tokenizer 会根据所选方式将内容存储为对应的数据结构。`,
      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',
--- a/web/src/pages/add-knowledge/components/knowledge-file/parsing-status-cell/index.tsx
+++ b/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)}
--- a/web/src/pages/agent/chat/chat-sheet.tsx
+++ b/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>
--- a/web/src/pages/agent/chat/use-send-agent-message.ts
+++ b/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,
      });
--- a/web/src/pages/agent/constant/pipeline.tsx
+++ b/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',
--- a/web/src/pages/agent/form/parser-form/index.tsx
+++ b/web/src/pages/agent/form/parser-form/index.tsx
@ -35,14 +35,14 @@ import { EmailFormFields } from './email-form-fields';
 import { ImageFormFields } from './image-form-fields';
 import { PdfFormFields } from './pdf-form-fields';
 import { buildFieldNameWithPrefix } from './utils';
-import { VideoFormFields } from './video-form-fields';
+import { AudioFormFields, VideoFormFields } from './video-form-fields';

 const outputList = buildOutputList(initialParserValues.outputs);

 const FileFormatWidgetMap = {
  [FileType.PDF]: PdfFormFields,
  [FileType.Video]: VideoFormFields,
-  [FileType.Audio]: VideoFormFields,
+  [FileType.Audio]: AudioFormFields,
  [FileType.Email]: EmailFormFields,
  [FileType.Image]: ImageFormFields,
 };
@ -162,13 +162,7 @@ const ParserForm = ({ node }: INextOperatorForm) => {
  const { t } = useTranslation();
  const defaultValues = useFormValues(initialParserValues, node);

-  const FileFormatOptions = buildOptions(
-    FileType,
-    t,
-    'flow.fileFormatOptions',
-  ).filter(
-    (x) => x.value !== FileType.Video, // Temporarily hide the video option
-  );
+  const FileFormatOptions = buildOptions(FileType, t, 'flow.fileFormatOptions');

  const form = useForm<z.infer<typeof FormSchema>>({
    defaultValues,
--- a/web/src/pages/agent/form/parser-form/video-form-fields.tsx
+++ b/web/src/pages/agent/form/parser-form/video-form-fields.tsx
@ -5,7 +5,7 @@ import {
  OutputFormatFormFieldProps,
 } from './common-form-fields';

-export function VideoFormFields({ prefix }: OutputFormatFormFieldProps) {
+export function AudioFormFields({ prefix }: OutputFormatFormFieldProps) {
  const modelOptions = useComposeLlmOptionsByModelTypes([
    LlmModelType.Speech2text,
  ]);
@ -20,3 +20,19 @@ export function VideoFormFields({ prefix }: OutputFormatFormFieldProps) {
    </>
  );
 }
+
+export function VideoFormFields({ prefix }: OutputFormatFormFieldProps) {
+  const modelOptions = useComposeLlmOptionsByModelTypes([
+    LlmModelType.Image2text,
+  ]);
+
+  return (
+    <>
+      {/* Multimodal Model */}
+      <LargeModelFormField
+        prefix={prefix}
+        options={modelOptions}
+      ></LargeModelFormField>
+    </>
+  );
+}
--- a/web/src/pages/agents/agent-templates.tsx
+++ b/web/src/pages/agents/agent-templates.tsx
@ -10,9 +10,10 @@ import {
 import { useSetModalState } from '@/hooks/common-hooks';
 import { useNavigatePage } from '@/hooks/logic-hooks/navigate-hooks';
 import { useFetchAgentTemplates, useSetAgent } from '@/hooks/use-agent-request';
-import { IFlowTemplate } from '@/interfaces/database/flow';

+import { CardContainer } from '@/components/card-container';
 import { AgentCategory } from '@/constants/agent';
+import { IFlowTemplate } from '@/interfaces/database/agent';
 import { useCallback, useEffect, useMemo, useState } from 'react';
 import { useTranslation } from 'react-i18next';
 import { CreateAgentDialog } from './create-agent-dialog';
@ -121,7 +122,7 @@ export default function AgentTemplates() {
        ></SideBar>

        <main className="flex-1 bg-text-title-invert/50 h-dvh">
-          <div className="grid gap-6 sm:grid-cols-1 md:grid-cols-2 lg:grid-cols-3 xl:grid-cols-4 2xl:grid-cols-5 max-h-[94vh] overflow-auto px-8 pt-8">
+          <CardContainer className="max-h-[94vh] overflow-auto px-8 pt-8">
            {tempListFilter?.map((x) => {
              return (
                <TemplateCard
@ -131,14 +132,13 @@ export default function AgentTemplates() {
                ></TemplateCard>
              );
            })}
-          </div>
+          </CardContainer>
          {creatingVisible && (
            <CreateAgentDialog
              loading={loading}
              visible={creatingVisible}
              hideModal={hideCreatingModal}
              onOk={handleOk}
-              canvasCategory={template?.canvas_category}
            ></CreateAgentDialog>
          )}
        </main>
--- a/web/src/pages/agents/index.tsx
+++ b/web/src/pages/agents/index.tsx
@ -1,3 +1,4 @@
+import { CardContainer } from '@/components/card-container';
 import ListFilterBar from '@/components/list-filter-bar';
 import { RenameDialog } from '@/components/rename-dialog';
 import { Button } from '@/components/ui/button';
@ -113,7 +114,7 @@ export default function Agents() {
        </ListFilterBar>
      </div>
      <div className="flex-1 overflow-auto">
-        <div className="grid gap-6 sm:grid-cols-1 md:grid-cols-2 lg:grid-cols-3 xl:grid-cols-4 2xl:grid-cols-5 max-h-[calc(100dvh-280px)] overflow-auto px-8">
+        <CardContainer className="max-h-[calc(100dvh-280px)] overflow-auto px-8">
          {data.map((x) => {
            return (
              <AgentCard
@ -123,7 +124,7 @@ export default function Agents() {
              ></AgentCard>
            );
          })}
-        </div>
+        </CardContainer>
      </div>
      <div className="mt-8 px-8 pb-8">
        <RAGFlowPagination
--- a/web/src/pages/agents/template-card.tsx
+++ b/web/src/pages/agents/template-card.tsx
@ -1,7 +1,7 @@
 import { RAGFlowAvatar } from '@/components/ragflow-avatar';
 import { Button } from '@/components/ui/button';
 import { Card, CardContent } from '@/components/ui/card';
-import { IFlowTemplate } from '@/interfaces/database/flow';
+import { IFlowTemplate } from '@/interfaces/database/agent';
 import i18n from '@/locales/config';
 import { useCallback, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
--- a/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/components/document-preview/image-preview.tsx
+++ b/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/components/document-preview/image-preview.tsx
@ -2,7 +2,7 @@ import message from '@/components/ui/message';
 import { Spin } from '@/components/ui/spin';
 import request from '@/utils/request';
 import classNames from 'classnames';
-import { useEffect, useState } from 'react';
+import { useCallback, useEffect, useState } from 'react';

 interface ImagePreviewerProps {
  className?: string;
@ -17,7 +17,7 @@ export const ImagePreviewer: React.FC<ImagePreviewerProps> = ({
  const [imageSrc, setImageSrc] = useState<string | null>(null);
  const [isLoading, setIsLoading] = useState<boolean>(true);

-  const fetchImage = async () => {
+  const fetchImage = useCallback(async () => {
    setIsLoading(true);
    const res = await request(url, {
      method: 'GET',
@ -30,12 +30,13 @@ export const ImagePreviewer: React.FC<ImagePreviewerProps> = ({
    const objectUrl = URL.createObjectURL(res.data);
    setImageSrc(objectUrl);
    setIsLoading(false);
-  };
+  }, [url]);
+
  useEffect(() => {
    if (url) {
      fetchImage();
    }
-  }, [url]);
+  }, [url, fetchImage]);

  useEffect(() => {
    return () => {
--- a/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/components/document-preview/index.tsx
+++ b/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/components/document-preview/index.tsx
@ -8,6 +8,7 @@ import styles from './index.less';
 import PdfPreviewer, { IProps } from './pdf-preview';
 import { PptPreviewer } from './ppt-preview';
 import { TxtPreviewer } from './txt-preview';
+import { VideoPreviewer } from './video-preview';

 type PreviewProps = {
  fileType: string;
@ -42,11 +43,30 @@ const Preview = ({
          <TxtPreviewer className={className} url={url} />
        </section>
      )}
-      {['visual'].indexOf(fileType) > -1 && (
+      {['jpg', 'png', 'gif', 'jpeg', 'svg', 'bmp', 'ico', 'tif'].indexOf(
+        fileType,
+      ) > -1 && (
        <section>
          <ImagePreviewer className={className} url={url} />
        </section>
      )}
+      {[
+        'mp4',
+        'avi',
+        'mov',
+        'mkv',
+        'wmv',
+        'flv',
+        'mpeg',
+        'mpg',
+        'asf',
+        'rm',
+        'rmvb',
+      ].indexOf(fileType) > -1 && (
+        <section>
+          <VideoPreviewer className={className} url={url} />
+        </section>
+      )}
      {['pptx'].indexOf(fileType) > -1 && (
        <section>
          <PptPreviewer className={className} url={url} />
--- a/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/components/document-preview/video-preview.tsx
+++ b/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/components/document-preview/video-preview.tsx
@ -0,0 +1,74 @@
+import message from '@/components/ui/message';
+import { Spin } from '@/components/ui/spin';
+import request from '@/utils/request';
+import classNames from 'classnames';
+import { useCallback, useEffect, useState } from 'react';
+
+interface VideoPreviewerProps {
+  className?: string;
+  url: string;
+}
+
+export const VideoPreviewer: React.FC<VideoPreviewerProps> = ({
+  className,
+  url,
+}) => {
+  // const url = useGetDocumentUrl();
+  const [videoSrc, setVideoSrc] = useState<string | null>(null);
+  const [isLoading, setIsLoading] = useState<boolean>(true);
+
+  const fetchVideo = useCallback(async () => {
+    setIsLoading(true);
+    const res = await request(url, {
+      method: 'GET',
+      responseType: 'blob',
+      onError: () => {
+        message.error('Failed to load video');
+        setIsLoading(false);
+      },
+    });
+    const objectUrl = URL.createObjectURL(res.data);
+    setVideoSrc(objectUrl);
+    setIsLoading(false);
+  }, [url]);
+
+  useEffect(() => {
+    if (url) {
+      fetchVideo();
+    }
+  }, [url, fetchVideo]);
+
+  useEffect(() => {
+    return () => {
+      if (videoSrc) {
+        URL.revokeObjectURL(videoSrc);
+      }
+    };
+  }, [videoSrc]);
+
+  return (
+    <div
+      className={classNames(
+        'relative w-full h-full p-4 bg-background-paper border border-border-normal rounded-md video-previewer',
+        className,
+      )}
+    >
+      {isLoading && (
+        <div className="absolute inset-0 flex items-center justify-center">
+          <Spin />
+        </div>
+      )}
+
+      {!isLoading && videoSrc && (
+        <div className="max-h-[80vh] overflow-auto p-2">
+          <video
+            src={videoSrc}
+            controls
+            className="w-full h-auto max-w-full object-contain"
+            onLoadedData={() => URL.revokeObjectURL(videoSrc!)}
+          />
+        </div>
+      )}
+    </div>
+  );
+};
--- a/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/index.tsx
+++ b/web/src/pages/chunk/parsed-result/add-knowledge/components/knowledge-chunk/index.tsx
@ -166,6 +166,7 @@ const Chunk = () => {
      case 'doc':
        return documentInfo?.name.split('.').pop() || 'doc';
      case 'visual':
+        return documentInfo?.name.split('.').pop() || 'visual';
      case 'docx':
      case 'txt':
      case 'md':
--- a/web/src/pages/dataflow-result/hooks.ts
+++ b/web/src/pages/dataflow-result/hooks.ts
@ -345,10 +345,10 @@ export const useSummaryInfo = (
        const { output_format, parse_method } = setups;
        const res = [];
        if (parse_method) {
-          res.push(`${t('dataflow.parserMethod')}: ${parse_method}`);
+          res.push(`${t('dataflowParser.parserMethod')}: ${parse_method}`);
        }
        if (output_format) {
-          res.push(`${t('dataflow.outputFormat')}: ${output_format}`);
+          res.push(`${t('dataflowParser.outputFormat')}: ${output_format}`);
        }
        return res.join(' ');
      }
--- a/web/src/pages/dataflow-result/index.tsx
+++ b/web/src/pages/dataflow-result/index.tsx
@ -28,6 +28,7 @@ import {
 } from '@/components/ui/breadcrumb';
 import { Button } from '@/components/ui/button';
 import { Modal } from '@/components/ui/modal/modal';
+import { AgentCategory } from '@/constants/agent';
 import { Images } from '@/constants/common';
 import { useNavigatePage } from '@/hooks/logic-hooks/navigate-hooks';
 import { useGetKnowledgeSearchParams } from '@/hooks/route-hook';
@ -65,7 +66,7 @@ const Chunk = () => {
    navigateToDatasetOverview,
    navigateToDatasetList,
    navigateToAgents,
-    navigateToDataflow,
+    navigateToAgent,
  } = useNavigatePage();
  let fileUrl = useGetDocumentUrl(isAgent);

@ -178,8 +179,8 @@ const Chunk = () => {
                  if (knowledgeId) {
                    navigateToDatasetOverview(knowledgeId)();
                  }
-                  if (agentId) {
-                    navigateToDataflow(agentId)();
+                  if (isAgent) {
+                    navigateToAgent(agentId, AgentCategory.DataflowCanvas)();
                  }
                }}
              >
--- a/web/src/pages/dataset/dataset-overview/overview-table.tsx
+++ b/web/src/pages/dataset/dataset-overview/overview-table.tsx
@ -85,8 +85,8 @@ export const getFileLogsTableColumns = (
          //   row.original.kb_id,
          // )}
        >
-          <FileIcon name={row.original.fileName}></FileIcon>
-          {row.original.fileName}
+          <FileIcon name={row.original.document_name}></FileIcon>
+          {row.original.document_name}
        </div>
      ),
    },
--- a/web/src/pages/dataset/dataset/generate-button/generate.tsx
+++ b/web/src/pages/dataset/dataset/generate-button/generate.tsx
@ -83,10 +83,10 @@ const MenuItem: React.FC<{
      className={cn(
        'border cursor-pointer p-2 rounded-md focus:bg-transparent',
        {
-          'hover:border-accent-primary hover:bg-[rgba(59,160,92,0.1)]':
+          'hover:border-accent-primary hover:bg-[rgba(59,160,92,0.1)] focus:bg-[rgba(59,160,92,0.1)]':
            status === generateStatus.start ||
            status === generateStatus.completed,
-          'hover:border-border hover:bg-[rgba(59,160,92,0)]':
+          'hover:border-border hover:bg-[rgba(59,160,92,0)] focus:bg-[rgba(59,160,92,0)]':
            status !== generateStatus.start &&
            status !== generateStatus.completed,
        },
@ -177,7 +177,11 @@ const MenuItem: React.FC<{
  );
 };

-const Generate: React.FC = () => {
+type GenerateProps = {
+  disabled?: boolean;
+};
+const Generate: React.FC<GenerateProps> = (props) => {
+  const { disabled = false } = props;
  const [open, setOpen] = useState(false);
  const { graphRunData, raptorRunData } = useTraceGenerate({ open });
  const { runGenerate, pauseGenerate } = useDatasetGenerate();
@ -189,16 +193,21 @@ const Generate: React.FC = () => {
  return (
    <div className="generate">
      <DropdownMenu open={open} onOpenChange={handleOpenChange}>
-        <DropdownMenuTrigger asChild>
-          <Button
-            variant={'transparent'}
-            onClick={() => {
-              handleOpenChange(!open);
-            }}
-          >
-            <WandSparkles className="mr-2" />
-            {t('knowledgeDetails.generate')}
-          </Button>
+        <DropdownMenuTrigger asChild disabled={disabled}>
+          <div className={cn({ 'cursor-not-allowed': disabled })}>
+            <Button
+              disabled={disabled}
+              variant={'transparent'}
+              onClick={() => {
+                if (!disabled) {
+                  handleOpenChange(!open);
+                }
+              }}
+            >
+              <WandSparkles className="mr-2 size-4" />
+              {t('knowledgeDetails.generate')}
+            </Button>
+          </div>
        </DropdownMenuTrigger>
        <DropdownMenuContent className="w-[380px] p-5 flex flex-col gap-2 ">
          {Object.values(GenerateType).map((name) => {
--- a/web/src/pages/dataset/dataset/index.tsx
+++ b/web/src/pages/dataset/dataset/index.tsx
@ -12,7 +12,9 @@ import {
 } from '@/components/ui/dropdown-menu';
 import { useRowSelection } from '@/hooks/logic-hooks/use-row-selection';
 import { useFetchDocumentList } from '@/hooks/use-document-request';
+import { useFetchKnowledgeBaseConfiguration } from '@/hooks/use-knowledge-request';
 import { Upload } from 'lucide-react';
+import { useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
 import { DatasetTable } from './dataset-table';
 import Generate from './generate-button/generate';
@ -41,6 +43,14 @@ export default function Dataset() {
    handleFilterSubmit,
    loading,
  } = useFetchDocumentList();
+
+  const refreshCount = useMemo(() => {
+    return documents.findIndex((doc) => doc.run === '1') + documents.length;
+  }, [documents]);
+
+  const { data: dataSetData } = useFetchKnowledgeBaseConfiguration({
+    refreshCount,
+  });
  const { filters, onOpenChange } = useSelectDatasetFilters();

  const {
@ -62,7 +72,7 @@ export default function Dataset() {
  return (
    <>
      <div className="absolute top-4 right-5">
-        <Generate />
+        <Generate disabled={!(dataSetData.chunk_num > 0)} />
      </div>
      <section className="p-5 min-w-[880px]">
        <ListFilterBar
--- a/web/src/pages/datasets/index.tsx
+++ b/web/src/pages/datasets/index.tsx
@ -1,3 +1,4 @@
+import { CardContainer } from '@/components/card-container';
 import ListFilterBar from '@/components/list-filter-bar';
 import { RenameDialog } from '@/components/rename-dialog';
 import { Button } from '@/components/ui/button';
@ -70,7 +71,7 @@ export default function Datasets() {
        </Button>
      </ListFilterBar>
      <div className="flex-1">
-        <div className="grid gap-6 sm:grid-cols-1 md:grid-cols-2 lg:grid-cols-3 xl:grid-cols-4 2xl:grid-cols-5 max-h-[calc(100dvh-280px)] overflow-auto px-8">
+        <CardContainer className="max-h-[calc(100dvh-280px)] overflow-auto px-8">
          {kbs.map((dataset) => {
            return (
              <DatasetCard
@ -80,7 +81,7 @@ export default function Datasets() {
              ></DatasetCard>
            );
          })}
-        </div>
+        </CardContainer>
      </div>
      <div className="mt-8 px-8">
        <RAGFlowPagination
--- a/web/src/pages/next-chats/hooks/use-upload-file.ts
+++ b/web/src/pages/next-chats/hooks/use-upload-file.ts
@ -20,7 +20,7 @@ export function useUploadFile() {
      if (Array.isArray(files) && files.length) {
        const file = files[0];
        const ret = await uploadAndParseFile({ file, options, conversationId });
-        if (ret.code === 0 && Array.isArray(ret.data)) {
+        if (ret?.code === 0 && Array.isArray(ret?.data)) {
          setFileIds((list) => [...list, ...ret.data]);
          setFileMap((map) => {
            map.set(files[0], ret.data[0]);
--- a/web/src/pages/next-chats/index.tsx
+++ b/web/src/pages/next-chats/index.tsx
@ -1,3 +1,4 @@
+import { CardContainer } from '@/components/card-container';
 import ListFilterBar from '@/components/list-filter-bar';
 import { RenameDialog } from '@/components/rename-dialog';
 import { Button } from '@/components/ui/button';
@ -50,7 +51,7 @@ export default function ChatList() {
        </ListFilterBar>
      </div>
      <div className="flex-1 overflow-auto">
-        <div className="grid gap-6 sm:grid-cols-1 md:grid-cols-2 lg:grid-cols-3 xl:grid-cols-4 2xl:grid-cols-5 max-h-[calc(100dvh-280px)] overflow-auto px-8">
+        <CardContainer className="max-h-[calc(100dvh-280px)] overflow-auto px-8">
          {data.dialogs.map((x) => {
            return (
              <ChatCard
@ -60,7 +61,7 @@ export default function ChatList() {
              ></ChatCard>
            );
          })}
-        </div>
+        </CardContainer>
      </div>
      <div className="mt-8 px-8 pb-8">
        <RAGFlowPagination
--- a/web/src/pages/next-searches/index.tsx
+++ b/web/src/pages/next-searches/index.tsx
@ -1,3 +1,4 @@
+import { CardContainer } from '@/components/card-container';
 import { IconFont } from '@/components/icon-font';
 import ListFilterBar from '@/components/list-filter-bar';
 import { RenameDialog } from '@/components/rename-dialog';
@ -64,7 +65,7 @@ export default function SearchList() {
        </ListFilterBar>
      </div>
      <div className="flex-1">
-        <div className="grid gap-6 sm:grid-cols-1 md:grid-cols-2 lg:grid-cols-3 xl:grid-cols-4 2xl:grid-cols-5 max-h-[calc(100dvh-280px)] overflow-auto px-8">
+        <CardContainer className="max-h-[calc(100dvh-280px)] overflow-auto px-8">
          {list?.data.search_apps.map((x) => {
            return (
              <SearchCard
@ -76,7 +77,7 @@ export default function SearchList() {
              ></SearchCard>
            );
          })}
-        </div>
+        </CardContainer>
      </div>
      {list?.data.total && list?.data.total > 0 && (
        <div className="px-8 mb-4">
--- a/web/src/pages/profile-setting/components.tsx
+++ b/web/src/pages/profile-setting/components.tsx
@ -1,5 +1,24 @@
+import { Card, CardContent, CardHeader } from '@/components/ui/card';
 import { PropsWithChildren } from 'react';

 export function Title({ children }: PropsWithChildren) {
  return <span className="font-bold text-xl">{children}</span>;
 }
+
+type ProfileSettingWrapperCardProps = {
+  header: React.ReactNode;
+} & PropsWithChildren;
+
+export function ProfileSettingWrapperCard({
+  header,
+  children,
+}: ProfileSettingWrapperCardProps) {
+  return (
+    <Card className="w-full mb-5 border-border-button bg-transparent">
+      <CardHeader className="border-b border-border-button p-5">
+        {header}
+      </CardHeader>
+      <CardContent className="p-5">{children}</CardContent>
+    </Card>
+  );
+}
--- a/web/src/pages/profile-setting/mcp/edit-mcp-dialog.tsx
+++ b/web/src/pages/profile-setting/mcp/edit-mcp-dialog.tsx
@ -1,7 +1,9 @@
 import { Collapse } from '@/components/collapse';
 import { Button, ButtonLoading } from '@/components/ui/button';
+import { Card, CardContent } from '@/components/ui/card';
 import {
  Dialog,
+  DialogClose,
  DialogContent,
  DialogFooter,
  DialogHeader,
@ -121,36 +123,44 @@ export function EditMcpDialog({
          form={form}
          setFieldChanged={setFieldChanged}
        ></EditMcpForm>
-        <Collapse
-          title={
-            <div>
-              {nextTools?.length || 0} {t('mcp.toolsAvailable')}
-            </div>
-          }
-          open={collapseOpen}
-          onOpenChange={setCollapseOpen}
-          rightContent={
-            <Button
-              variant={'ghost'}
-              form={FormId}
-              type="submit"
-              onClick={handleTest}
+        <Card>
+          <CardContent className="p-3">
+            <Collapse
+              title={
+                <div>
+                  {nextTools?.length || 0} {t('mcp.toolsAvailable')}
+                </div>
+              }
+              open={collapseOpen}
+              onOpenChange={setCollapseOpen}
+              rightContent={
+                <Button
+                  variant={'transparent'}
+                  form={FormId}
+                  type="submit"
+                  onClick={handleTest}
+                  className="border-none p-0 hover:bg-transparent"
+                >
+                  <RefreshCw
+                    className={cn('text-text-secondary', {
+                      'animate-spin': testLoading,
+                    })}
+                  />
+                </Button>
+              }
            >
-              <RefreshCw
-                className={cn('text-accent-primary', {
-                  'animate-spin': testLoading,
-                })}
-              />
-            </Button>
-          }
-        >
-          <div className="space-y-2.5 overflow-auto max-h-80">
-            {nextTools?.map((x) => (
-              <McpToolCard key={x.name} data={x}></McpToolCard>
-            ))}
-          </div>
-        </Collapse>
+              <div className="overflow-auto max-h-80 divide-y bg-bg-card rounded-md px-2.5">
+                {nextTools?.map((x) => (
+                  <McpToolCard key={x.name} data={x}></McpToolCard>
+                ))}
+              </div>
+            </Collapse>
+          </CardContent>
+        </Card>
        <DialogFooter>
+          <DialogClose asChild>
+            <Button variant="outline">{t('common.cancel')}</Button>
+          </DialogClose>
          <ButtonLoading
            type="submit"
            form={FormId}
--- a/web/src/pages/profile-setting/mcp/edit-mcp-form.tsx
+++ b/web/src/pages/profile-setting/mcp/edit-mcp-form.tsx
@ -89,7 +89,7 @@ export function EditMcpForm({
          name="name"
          render={({ field }) => (
            <FormItem>
-              <FormLabel>{t('common.name')}</FormLabel>
+              <FormLabel required>{t('common.name')}</FormLabel>
              <FormControl>
                <Input
                  placeholder={t('common.mcp.namePlaceholder')}
@ -106,7 +106,7 @@ export function EditMcpForm({
          name="url"
          render={({ field }) => (
            <FormItem>
-              <FormLabel>{t('mcp.url')}</FormLabel>
+              <FormLabel required>{t('mcp.url')}</FormLabel>
              <FormControl>
                <Input
                  placeholder={t('common.mcp.urlPlaceholder')}
@ -127,7 +127,7 @@ export function EditMcpForm({
          name="server_type"
          render={({ field }) => (
            <FormItem>
-              <FormLabel>{t('mcp.serverType')}</FormLabel>
+              <FormLabel required>{t('mcp.serverType')}</FormLabel>
              <FormControl>
                <RAGFlowSelect
                  {...field}
--- a/web/src/pages/profile-setting/mcp/index.tsx
+++ b/web/src/pages/profile-setting/mcp/index.tsx
@ -1,12 +1,15 @@
 import { BulkOperateBar } from '@/components/bulk-operate-bar';
+import { CardContainer } from '@/components/card-container';
+import Spotlight from '@/components/spotlight';
 import { Button } from '@/components/ui/button';
 import { SearchInput } from '@/components/ui/input';
 import { RAGFlowPagination } from '@/components/ui/ragflow-pagination';
 import { useListMcpServer } from '@/hooks/use-mcp-request';
 import { pick } from 'lodash';
-import { Import, Plus } from 'lucide-react';
+import { Plus, SquareArrowOutDownLeft } from 'lucide-react';
 import { useCallback } from 'react';
 import { useTranslation } from 'react-i18next';
+import { ProfileSettingWrapperCard } from '../components';
 import { EditMcpDialog } from './edit-mcp-dialog';
 import { ImportMcpDialog } from './import-mcp-dialog';
 import { McpCard } from './mcp-card';
@ -32,27 +35,33 @@ export default function McpServer() {
  );

  return (
-    <section className="p-4 w-full">
-      <div className="text-text-primary text-2xl">{t('mcp.mcpServers')}</div>
-      <section className="flex items-center justify-between pb-5">
-        <div className="text-text-secondary">
-          {t('mcp.customizeTheListOfMcpServers')}
-        </div>
-        <div className="flex gap-5">
-          <SearchInput
-            className="w-40"
-            value={searchString}
-            onChange={handleInputChange}
-          ></SearchInput>
-          <Button variant={'secondary'} onClick={showImportModal}>
-            <Import /> {t('mcp.import')}
-          </Button>
-          <Button onClick={showEditModal('')}>
-            <Plus /> {t('mcp.addMCP')}
-          </Button>
-        </div>
-      </section>
-
+    <ProfileSettingWrapperCard
+      header={
+        <>
+          <div className="text-text-primary text-2xl font-semibold">
+            {t('mcp.mcpServers')}
+          </div>
+          <section className="flex items-center justify-between">
+            <div className="text-text-secondary">
+              {t('mcp.customizeTheListOfMcpServers')}
+            </div>
+            <div className="flex gap-5">
+              <SearchInput
+                className="w-40"
+                value={searchString}
+                onChange={handleInputChange}
+              ></SearchInput>
+              <Button onClick={showEditModal('')}>
+                <Plus /> {t('mcp.addMCP')}
+              </Button>
+              <Button variant={'secondary'} onClick={showImportModal}>
+                <SquareArrowOutDownLeft /> {t('mcp.import')}
+              </Button>
+            </div>
+          </section>
+        </>
+      }
+    >
      {selectedList.length > 0 && (
        <BulkOperateBar
          list={list}
@ -60,7 +69,7 @@ export default function McpServer() {
          className="mb-2.5"
        ></BulkOperateBar>
      )}
-      <section className="flex gap-5 flex-wrap">
+      <CardContainer>
        {data.mcp_servers.map((item) => (
          <McpCard
            key={item.id}
@ -70,8 +79,8 @@ export default function McpServer() {
            showEditModal={showEditModal}
          ></McpCard>
        ))}
-      </section>
-      <div className="mt-8 px-8">
+      </CardContainer>
+      <div className="mt-8">
        <RAGFlowPagination
          {...pick(pagination, 'current', 'pageSize')}
          total={pagination.total || 0}
@ -92,6 +101,7 @@ export default function McpServer() {
          onOk={onImportOk}
        ></ImportMcpDialog>
      )}
-    </section>
+      <Spotlight className="z-0" opcity={0.7} coverage={70} />
+    </ProfileSettingWrapperCard>
  );
 }
--- a/web/src/pages/profile-setting/mcp/mcp-card.tsx
+++ b/web/src/pages/profile-setting/mcp/mcp-card.tsx
@ -5,6 +5,7 @@ import { IMcpServer } from '@/interfaces/database/mcp';
 import { formatDate } from '@/utils/date';
 import { isPlainObject } from 'lodash';
 import { useMemo } from 'react';
+import { useTranslation } from 'react-i18next';
 import { McpDropdown } from './mcp-dropdown';
 import { UseBulkOperateMCPReturnType } from './use-bulk-operate-mcp';
 import { UseEditMcpReturnType } from './use-edit-mcp';
@ -20,6 +21,7 @@ export function McpCard({
  handleSelectChange,
  showEditModal,
 }: DatasetCardProps) {
+  const { t } = useTranslation();
  const toolLength = useMemo(() => {
    const tools = data.variables?.tools;
    if (isPlainObject(tools)) {
@ -33,10 +35,12 @@ export function McpCard({
    }
  };
  return (
-    <Card key={data.id} className="w-64">
+    <Card key={data.id}>
      <CardContent className="p-2.5 pt-2 group">
        <section className="flex justify-between pb-2">
-          <h3 className="text-lg font-semibold truncate flex-1">{data.name}</h3>
+          <h3 className="text-base font-normal truncate flex-1 text-text-primary">
+            {data.name}
+          </h3>
          <div className="space-x-4">
            <McpDropdown mcpId={data.id} showEditModal={showEditModal}>
              <MoreButton></MoreButton>
@ -50,14 +54,12 @@ export function McpCard({
            />
          </div>
        </section>
-        <div className="flex justify-between items-end">
+        <div className="flex justify-between items-end text-xs text-text-secondary">
          <div className="w-full">
-            <div className="text-base font-semibold mb-3 line-clamp-1 text-text-secondary">
-              {toolLength} cached tools
+            <div className="line-clamp-1 pb-1">
+              {toolLength} {t('mcp.cachedTools')}
            </div>
-            <p className="text-sm text-text-secondary">
-              {formatDate(data.update_date)}
-            </p>
+            <p>{formatDate(data.update_date)}</p>
          </div>
        </div>
      </CardContent>
--- a/web/src/pages/profile-setting/mcp/tool-card.tsx
+++ b/web/src/pages/profile-setting/mcp/tool-card.tsx
@ -1,4 +1,3 @@
-import { Card, CardContent } from '@/components/ui/card';
 import { IMCPTool } from '@/interfaces/database/mcp';

 export type McpToolCardProps = {
@ -7,13 +6,11 @@ export type McpToolCardProps = {

 export function McpToolCard({ data }: McpToolCardProps) {
  return (
-    <Card>
-      <CardContent className="p-2.5 pt-2 group">
-        <h3 className="text-sm font-semibold line-clamp-1 pb-2">{data.name}</h3>
-        <div className="text-xs font-normal mb-3 text-text-secondary">
-          {data.description}
-        </div>
-      </CardContent>
-    </Card>
+    <section className="group py-2.5">
+      <h3 className="text-sm font-semibold line-clamp-1 pb-2">{data.name}</h3>
+      <div className="text-xs font-normal text-text-secondary">
+        {data.description}
+      </div>
+    </section>
  );
 }
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
writinwaters	de24e74b4c	Docs: How to use MinerU to parse pdf documents (#10763 ) ### What problem does this PR solve? ### Type of change - [x] Documentation Update	2025-10-23 18:56:09 +08:00
Liu An	83e80e3d7f	Docs: Update version references to v0.21.1 in READMEs and docs (#10761 ) ### What problem does this PR solve? - Update version tags in README files (including translations) from v0.21.0 to v0.21.1 - Modify Docker image references and documentation to reflect new version - Update version badges and image descriptions - Maintain consistency across all language variants of README files ### Type of change - [x] Documentation Update	2025-10-23 18:55:41 +08:00
Kevin Hu	ea73f13ebf	Fix: infinity rerank error. (#10760 ) ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-23 17:38:54 +08:00
writinwaters	af6eabad0e	Docs: Added v0.21.1 release notes (#10757 ) ### What problem does this PR solve? ### Type of change - [x] Documentation Update	2025-10-23 17:25:29 +08:00
Kevin Hu	5fb5a51b2e	Fix: create KB initial embedding. (#10751 ) ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-23 16:17:43 +08:00
balibabu	37004ecfb3	Fix: Clicking "Stop receiving messages" in Firefox will cause the page to crash. #10752 (#10754 ) ### What problem does this PR solve? Fix: Clicking "Stop receiving messages" in Firefox will cause the page to crash. #10752 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-23 16:17:28 +08:00
chanx	6d333ec4bc	Fix: Add video preview #9869 (#10748 ) ### What problem does this PR solve? Fix: Add video preview ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-23 14:25:05 +08:00
balibabu	ac188b0486	Feat: The default value of the parser operator's Video output format is set to text #9869 (#10745 ) ### What problem does this PR solve? Feat: The default value of the parser operator's Video output format is set to text #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-23 14:18:51 +08:00
Zhichang Yu	adeb9d87e2	Bump infinity to 0.6.1 (#10749 ) ### What problem does this PR solve? Bump infinity to 0.6.1 #10727 missed `docker/docker-compose-base.yml`. ### Type of change - [x] Other (please describe):	2025-10-23 13:36:43 +08:00
chanx	d121033208	Fix: Resolved the issue where the Generate button must be refreshed after generating chunk to take effect #9869 (#10742 ) ### What problem does this PR solve? Fix: Resolved the issue where the Generate button must be refreshed after generating chunk to take effect ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-23 11:54:45 +08:00
balibabu	494f84cd69	Feat: Add suffix to the parser operator's video configuration #9869 (#10741 ) ### What problem does this PR solve? Feat: Add suffix to the parser operator's video configuration #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-23 11:13:21 +08:00
Kevin Hu	f24d464a53	Fix: video file suffix (#10740 ) ### What problem does this PR solve? ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-23 11:13:09 +08:00
Adrian Altermatt	484c536f2e	Fix typo (#10737 ) ### What problem does this PR solve? Chunkder to Chunker ### Type of change - [x] Documentation Update	2025-10-23 09:25:15 +08:00
Yongteng Lei	f7112acd97	Feat: pipeline supports MinerU PDF parser (#10736 ) ### What problem does this PR solve? Pipeline supports MinerU PDF parser. ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-23 09:24:31 +08:00
Kevin Hu	de4f75dcd8	Fix: add video parser (#10735 ) ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-23 09:24:16 +08:00
chanx	15fff5724e	Fix：filename is not displayed on the overview page #9869 (#10731 ) ### What problem does this PR solve? Fix: Fixed the issue that filename is not displayed on the overview page; and added the processing logic of the generate button when chunk=0 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-22 19:52:50 +08:00
Billy Bao	d616354d66	Fix: model parameter (#10730 ) ### What problem does this PR solve? Fix: fix model parameter #10729 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-22 19:52:37 +08:00
Lynn	1bad24e3ab	Feat: version 0.21.1 (#10718 ) ### What problem does this PR solve? Update version, and remove '_canvas' suffix in agent_category. ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-22 19:03:02 +08:00
balibabu	4910146149	Feat: Display the video field in the parser operator #9869 (#10728 ) ### What problem does this PR solve? Feat: Display the video field in the parser operator #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-22 18:59:20 +08:00
Zhichang Yu	0e549e96ee	bump infinity to v0.6.1 (#10727 ) ### What problem does this PR solve? bump infinity to v0.6.1 ### Type of change - [x] Other (please describe): Infinity	2025-10-22 17:36:58 +08:00
chanx	318cb7d792	Fix: Optimize the style of the personal center sidebar component #9869 (#10723 ) ### What problem does this PR solve? fix: Optimize the style of the personal center sidebar component ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-22 16:55:16 +08:00
LeonTung	4d1255b231	hotfix: Rename chunk summary's component name (#10721 ) ### What problem does this PR solve? Using Indexer instead of Tokenizer ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-22 16:55:03 +08:00
Stephen Hu	b30f0be858	Refactor: How LiteLLMBase Calculate total count (#10532 ) ### What problem does this PR solve? How LiteLLMBase Calculate total count ### Type of change - [x] Refactoring	2025-10-22 12:25:31 +08:00
Billy Bao	a82e9b3d91	Fix: can't upload image in ollama model #10447 (#10717 ) ### What problem does this PR solve? Fix: can't upload image in ollama model #10447 ### Type of change - [X] Bug Fix (non-breaking change which fixes an issue) ### Change all `image=[]` to `image = None` Changing `image=[]` to `images=None` avoids Python’s mutable default parameter issue. If you keep `images=[]`, all calls share the same list, so modifying it (e.g., images.append()) will affect later calls. Using images=None and creating a new list inside the function ensures each call is independent. This change does not affect current behavior — it simply makes the code safer and more predictable. 把 `images=[]` 改成 `images=None` 是为了避免 Python 默认参数的可变对象问题。如果保留 `images=[]`，所有调用都会共用同一个列表，一旦修改就会影响后续调用。改成 None 并在函数内部重新创建列表，可以确保每次调用都是独立的。这个修改不会影响现有运行结果，只是让代码更安全、更可控。	2025-10-22 12:24:12 +08:00
balibabu	02a452993e	Feat: Adjust the style of the mcp dialog #10703 (#10719 ) ### What problem does this PR solve? Feat: Adjust the style of the mcp dialog #10703 ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-22 12:20:19 +08:00
Stephen Hu	307cdc62ea	fix:RAGFlowOSS.put() got an unexpected keyword argument 'tenant_id' (#10712 ) ### What problem does this PR solve? https://github.com/infiniflow/ragflow/issues/10700 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-22 09:30:41 +08:00
Yongteng Lei	2d491188b8	Refa: improve flow of GraphRAG and RAPTOR (#10709 ) ### What problem does this PR solve? Improve flow of GraphRAG and RAPTOR. ### Type of change - [x] Refactoring	2025-10-22 09:29:20 +08:00
Yongteng Lei	acc0f7396e	Feat: add fault-tolerant mechanism to GraphRAG (#10708 ) ### What problem does this PR solve? Add fault-tolerant mechanism to GraphRAG. #10406. ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-22 09:29:04 +08:00
writinwaters	9a4cd81891	Docs: Added token chunker and title chunker components (#10711 ) ### What problem does this PR solve? ### Type of change - [x] Documentation Update	2025-10-21 20:11:23 +08:00
chanx	1694f32e8e	Fix: Profile page UI adjustment #9869 (#10706 ) ### What problem does this PR solve? Fix: Profile page UI adjustment ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-21 20:11:07 +08:00
buua436	41fade3fe6	Fix:wrong param in manual chunk (#10710 ) ### What problem does this PR solve? change: wrong param in manual chunk ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-10-21 20:10:54 +08:00
balibabu	8d333f3590	Feat: Change the style of all cards according to the design #10703 (#10704 ) ### What problem does this PR solve? Feat: Change the style of all cards according to the design #10703 ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-10-21 20:08:55 +08:00