Fix: search list permission (#9767 )

### What problem does this PR solve? Search list permission. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
Revert: broken agent completion by #9631 (#9760 )
2026-01-04 03:25:30 +08:00 · 2025-08-27 18:50:02 +08:00 · 2025-08-27 17:16:55 +08:00 · 2025-08-27 16:56:55 +08:00 · 2025-08-27 15:29:09 +08:00 · 2025-08-27 15:15:24 +08:00
135 changed files with 2430 additions and 626 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:v0.20.3">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
    </a>
    <a href="https://github.com/infiniflow/ragflow/releases/latest">
        <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@ -190,7 +190,7 @@ releases! 🌟
 > All Docker images are built for x86 platforms. We don't currently offer Docker images for ARM64.
 > If you are on an ARM64 platform, follow [this guide](https://ragflow.io/docs/dev/build_docker_image) to build a Docker image compatible with your system.

-   > The command below downloads the `v0.20.3-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.3-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3` for the full edition `v0.20.3`.
+   > The command below downloads the `v0.20.4-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.4-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4` for the full edition `v0.20.4`.

   ```bash
   $ cd ragflow/docker
@ -203,8 +203,8 @@ releases! 🌟

   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
   |-------------------|-----------------|-----------------------|--------------------------|
-   | v0.20.3           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.3-slim      | &approx;2       | ❌                   | Stable release            |
+   | v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.4-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:v0.20.3">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
    </a>
    <a href="https://github.com/infiniflow/ragflow/releases/latest">
        <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Rilis%20Terbaru" alt="Rilis Terbaru">
@ -181,7 +181,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 > Semua gambar Docker dibangun untuk platform x86. Saat ini, kami tidak menawarkan gambar Docker untuk ARM64.
 > Jika Anda menggunakan platform ARM64, [silakan gunakan panduan ini untuk membangun gambar Docker yang kompatibel dengan sistem Anda](https://ragflow.io/docs/dev/build_docker_image).

-> Perintah di bawah ini mengunduh edisi v0.20.3-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.3-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3 untuk edisi lengkap v0.20.3.
+> Perintah di bawah ini mengunduh edisi v0.20.4-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.4-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4 untuk edisi lengkap v0.20.4.

 ```bash
 $ cd ragflow/docker
@ -194,8 +194,8 @@ $ docker compose -f docker-compose.yml up -d

 | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
 | ----------------- | --------------- | --------------------- | ------------------------ |
-| v0.20.3           | &approx;9       | :heavy_check_mark:    | Stable release           |
-| v0.20.3-slim      | &approx;2       | ❌                    | Stable release           |
+| v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| v0.20.4-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:v0.20.3">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
    </a>
    <a href="https://github.com/infiniflow/ragflow/releases/latest">
        <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@ -160,7 +160,7 @@
 > 現在、公式に提供されているすべての Docker イメージは x86 アーキテクチャ向けにビルドされており、ARM64 用の Docker イメージは提供されていません。
 > ARM64 アーキテクチャのオペレーティングシステムを使用している場合は、[このドキュメント](https://ragflow.io/docs/dev/build_docker_image)を参照して Docker イメージを自分でビルドしてください。

-   > 以下のコマンドは、RAGFlow Docker イメージの v0.20.3-slim エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.20.3-slim とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。例えば、完全版 v0.20.3 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3 と設定します。
+   > 以下のコマンドは、RAGFlow Docker イメージの v0.20.4-slim エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.20.4-slim とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。例えば、完全版 v0.20.4 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4 と設定します。

   ```bash
   $ cd ragflow/docker
@ -173,8 +173,8 @@

   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
   | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.3           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.3-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.4-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:v0.20.3">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
    </a>
    <a href="https://github.com/infiniflow/ragflow/releases/latest">
        <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@ -160,7 +160,7 @@
 > 모든 Docker 이미지는 x86 플랫폼을 위해 빌드되었습니다. 우리는 현재 ARM64 플랫폼을 위한 Docker 이미지를 제공하지 않습니다.
 > ARM64 플랫폼을 사용 중이라면, [시스템과 호환되는 Docker 이미지를 빌드하려면 이 가이드를 사용해 주세요](https://ragflow.io/docs/dev/build_docker_image).

-   > 아래 명령어는 RAGFlow Docker 이미지의 v0.20.3-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.20.3-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.20.3을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3로 설정합니다.
+   > 아래 명령어는 RAGFlow Docker 이미지의 v0.20.4-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.20.4-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.20.4을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4로 설정합니다.

   ```bash
   $ cd ragflow/docker
@ -173,8 +173,8 @@

   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
   | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.3           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.3-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.4-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:v0.20.3">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
    </a>
    <a href="https://github.com/infiniflow/ragflow/releases/latest">
        <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Última%20Relese" alt="Última Versão">
@ -180,7 +180,7 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 > Todas as imagens Docker são construídas para plataformas x86. Atualmente, não oferecemos imagens Docker para ARM64.
 > Se você estiver usando uma plataforma ARM64, por favor, utilize [este guia](https://ragflow.io/docs/dev/build_docker_image) para construir uma imagem Docker compatível com o seu sistema.

-    > O comando abaixo baixa a edição `v0.20.3-slim` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.20.3-slim`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor. Por exemplo: defina `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3` para a edição completa `v0.20.3`.
+    > O comando abaixo baixa a edição `v0.20.4-slim` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.20.4-slim`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor. Por exemplo: defina `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4` para a edição completa `v0.20.4`.

    ```bash
    $ cd ragflow/docker
@ -193,8 +193,8 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).

    | Tag da imagem RAGFlow | Tamanho da imagem (GB) | Possui modelos de incorporação? | Estável?                 |
    | --------------------- | ---------------------- | ------------------------------- | ------------------------ |
-    | v0.20.3               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
-    | v0.20.3-slim          | ~2                     | ❌                              | Lançamento estável       |
+    | v0.20.4               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
+    | v0.20.4-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:v0.20.3">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
    </a>
    <a href="https://github.com/infiniflow/ragflow/releases/latest">
        <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@ -183,7 +183,7 @@
 > 所有 Docker 映像檔都是為 x86 平台建置的。目前，我們不提供 ARM64 平台的 Docker 映像檔。
 > 如果您使用的是 ARM64 平台，請使用 [這份指南](https://ragflow.io/docs/dev/build_docker_image) 來建置適合您系統的 Docker 映像檔。

-   > 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.20.3-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.20.3-slim` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。例如，你可以透過設定 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3` 來下載 RAGFlow 鏡像的 `v0.20.3` 完整發行版。
+   > 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.20.4-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.20.4-slim` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。例如，你可以透過設定 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4` 來下載 RAGFlow 鏡像的 `v0.20.4` 完整發行版。

   ```bash
   $ cd ragflow/docker
@ -196,8 +196,8 @@

   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
   | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.3           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.3-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.4-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:v0.20.3">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.4">
    </a>
    <a href="https://github.com/infiniflow/ragflow/releases/latest">
        <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@ -183,7 +183,7 @@
 > 请注意，目前官方提供的所有 Docker 镜像均基于 x86 架构构建，并不提供基于 ARM64 的 Docker 镜像。
 > 如果你的操作系统是 ARM64 架构，请参考[这篇文档](https://ragflow.io/docs/dev/build_docker_image)自行构建 Docker 镜像。

-   > 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.20.3-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.20.3-slim` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。比如，你可以通过设置 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3` 来下载 RAGFlow 镜像的 `v0.20.3` 完整发行版。
+   > 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.20.4-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.20.4-slim` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。比如，你可以通过设置 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4` 来下载 RAGFlow 镜像的 `v0.20.4` 完整发行版。

   ```bash
   $ cd ragflow/docker
@ -196,8 +196,8 @@

   | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
   | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.3           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.3-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.4           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.4-slim      | &approx;2       | ❌                    | Stable release           |
   | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
   | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |

--- a/agent/canvas.py
+++ b/agent/canvas.py
@ -469,6 +469,9 @@ class Canvas:
    def get_prologue(self):
        return self.components["begin"]["obj"]._param.prologue

+    def get_mode(self):
+        return self.components["begin"]["obj"]._param.mode
+
    def set_global_param(self, **kwargs):
        self.globals.update(kwargs)

--- a/agent/templates/ecommerce_customer_service_workflow.json
+++ b/agent/templates/ecommerce_customer_service_workflow.json
--- a/agent/tools/code_exec.py
+++ b/agent/tools/code_exec.py
@ -79,7 +79,7 @@ def main() -> dict:
    return {
        "result": fibonacci_recursive(100),
    }
-    
+
 Here's a code example for Javascript(`main` function MUST be included and exported):
 const axios = require('axios');
 async function main(args) {
@ -156,7 +156,7 @@ class CodeExec(ToolBase, ABC):
            self.set_output("_ERROR", "construct code request error: " + str(e))

        try:
-            resp = requests.post(url=f"http://{settings.SANDBOX_HOST}:9385/run", json=code_req, timeout=10)
+            resp = requests.post(url=f"http://{settings.SANDBOX_HOST}:9385/run", json=code_req, timeout=os.environ.get("COMPONENT_EXEC_TIMEOUT", 10*60))
            logging.info(f"http://{settings.SANDBOX_HOST}:9385/run", code_req, resp.status_code)
            if resp.status_code != 200:
                resp.raise_for_status()
--- a/api/apps/sdk/session.py
+++ b/api/apps/sdk/session.py
@ -16,8 +16,10 @@
 import json
 import re
 import time
+
 import tiktoken
 from flask import Response, jsonify, request
+
 from agent.canvas import Canvas
 from api import settings
 from api.db import LLMType, StatusEnum
@ -27,7 +29,8 @@ from api.db.services.canvas_service import UserCanvasService, completionOpenAI
 from api.db.services.canvas_service import completion as agent_completion
 from api.db.services.conversation_service import ConversationService, iframe_completion
 from api.db.services.conversation_service import completion as rag_completion
-from api.db.services.dialog_service import DialogService, ask, chat, gen_mindmap
+from api.db.services.dialog_service import DialogService, ask, chat, gen_mindmap, meta_filter
+from api.db.services.document_service import DocumentService
 from api.db.services.knowledgebase_service import KnowledgebaseService
 from api.db.services.llm_service import LLMBundle
 from api.db.services.search_service import SearchService
@ -37,7 +40,7 @@ from api.utils.api_utils import check_duplicate_ids, get_data_openai, get_error_
 from rag.app.tag import label_question
 from rag.prompts import chunks_format
 from rag.prompts.prompt_template import load_prompt
-from rag.prompts.prompts import cross_languages, keyword_extraction
+from rag.prompts.prompts import cross_languages, gen_meta_filter, keyword_extraction


@manager.route("/chats/<chat_id>/sessions", methods=["POST"])  # noqa: F821
@ -81,21 +84,13 @@ def create_agent_session(tenant_id, agent_id):
    if not isinstance(cvs.dsl, str):
        cvs.dsl = json.dumps(cvs.dsl, ensure_ascii=False)

-    session_id=get_uuid()
+    session_id = get_uuid()
    canvas = Canvas(cvs.dsl, tenant_id, agent_id)
    canvas.reset()
-    conv = {
-        "id": session_id,
-        "dialog_id": cvs.id,
-        "user_id": user_id,
-        "message": [],
-        "source": "agent",
-        "dsl": cvs.dsl
-    }
-    API4ConversationService.save(**conv)

    cvs.dsl = json.loads(str(canvas))
    conv = {"id": session_id, "dialog_id": cvs.id, "user_id": user_id, "message": [{"role": "assistant", "content": canvas.get_prologue()}], "source": "agent", "dsl": cvs.dsl}
+    API4ConversationService.save(**conv)
    conv["agent_id"] = conv.pop("dialog_id")
    return get_result(data=conv)

@ -450,26 +445,46 @@ def agents_completion_openai_compatibility(tenant_id, agent_id):
 def agent_completions(tenant_id, agent_id):
    req = request.json

+    ans = {}
+    if req.get("stream", True):
+
+        def generate():
+            for answer in agent_completion(tenant_id=tenant_id, agent_id=agent_id, **req):
+                if isinstance(answer, str):
+                    try:
+                        ans = json.loads(answer[5:])  # remove "data:"
+                    except Exception:
+                        continue
+
+                if ans.get("event") != "message" or not ans.get("data", {}).get("reference", None):
+                    continue
+
+                yield answer
+
+            yield "data:[DONE]\n\n"

    if req.get("stream", True):
-        resp = Response(agent_completion(tenant_id=tenant_id, agent_id=agent_id, **req), mimetype="text/event-stream")
+        resp = Response(generate(), mimetype="text/event-stream")
        resp.headers.add_header("Cache-control", "no-cache")
        resp.headers.add_header("Connection", "keep-alive")
        resp.headers.add_header("X-Accel-Buffering", "no")
        resp.headers.add_header("Content-Type", "text/event-stream; charset=utf-8")
        return resp
-    result = {}
+
+    full_content = ""
    for answer in agent_completion(tenant_id=tenant_id, agent_id=agent_id, **req):
        try:
-            ans = json.loads(answer[5:])  # remove "data:"
-            if not result:
-                result = ans.copy()
-            else:
-                result["data"]["answer"] += ans["data"]["answer"]
-                result["data"]["reference"] = ans["data"].get("reference", [])
+            ans = json.loads(answer[5:])
+
+            if ans["event"] == "message":
+                full_content += ans["data"]["content"]
+
+            if ans.get("data", {}).get("reference", None):
+                ans["data"]["content"] = full_content
+                return get_result(data=ans)
        except Exception as e:
-            return get_error_data_result(str(e))
-    return result
+            return get_result(data=f"**ERROR**: {str(e)}")
+    return get_result(data=ans)


@manager.route("/chats/<chat_id>/sessions", methods=["GET"])  # noqa: F821
@ -564,12 +579,12 @@ def list_agent_session(tenant_id, agent_id):
                if message_num != 0 and messages[message_num]["role"] != "user":
                    chunk_list = []
                    # Add boundary and type checks to prevent KeyError
-                    if (chunk_num < len(conv["reference"]) and
-                            conv["reference"][chunk_num] is not None and
-                            isinstance(conv["reference"][chunk_num], dict) and
-                            "chunks" in conv["reference"][chunk_num]):
+                    if chunk_num < len(conv["reference"]) and conv["reference"][chunk_num] is not None and isinstance(conv["reference"][chunk_num], dict) and "chunks" in conv["reference"][chunk_num]:
                        chunks = conv["reference"][chunk_num]["chunks"]
                        for chunk in chunks:
+                            # Ensure chunk is a dictionary before calling get method
+                            if not isinstance(chunk, dict):
+                                continue
                            new_chunk = {
                                "id": chunk.get("chunk_id", chunk.get("id")),
                                "content": chunk.get("content_with_weight", chunk.get("content")),
@ -865,14 +880,7 @@ def begin_inputs(agent_id):
        return get_error_data_result(f"Can't find agent by ID: {agent_id}")

    canvas = Canvas(json.dumps(cvs.dsl), objs[0].tenant_id)
-    return get_result(
-        data={
-            "title": cvs.title,
-            "avatar": cvs.avatar,
-            "inputs": canvas.get_component_input_form("begin"),
-            "prologue": canvas.get_prologue()
-        }
-    )
+    return get_result(data={"title": cvs.title, "avatar": cvs.avatar, "inputs": canvas.get_component_input_form("begin"), "prologue": canvas.get_prologue(), "mode": canvas.get_mode()})


@manager.route("/searchbots/ask", methods=["POST"])  # noqa: F821
@ -912,7 +920,7 @@ def ask_about_embedded():
    return resp


-@manager.route("/searchbots/retrieval_test", methods=['POST'])  # noqa: F821
+@manager.route("/searchbots/retrieval_test", methods=["POST"])  # noqa: F821
@validate_request("kb_id", "question")
 def retrieval_test_embedded():
    token = request.headers.get("Authorization").split()
@ -942,18 +950,30 @@ def retrieval_test_embedded():
    if not tenant_id:
        return get_error_data_result(message="permission denined.")

+    if req.get("search_id", ""):
+        search_config = SearchService.get_detail(req.get("search_id", "")).get("search_config", {})
+        meta_data_filter = search_config.get("meta_data_filter", {})
+        metas = DocumentService.get_meta_by_kbs(kb_ids)
+        if meta_data_filter.get("method") == "auto":
+            chat_mdl = LLMBundle(tenant_id, LLMType.CHAT, llm_name=search_config.get("chat_id", ""))
+            filters = gen_meta_filter(chat_mdl, metas, question)
+            doc_ids.extend(meta_filter(metas, filters))
+            if not doc_ids:
+                doc_ids = None
+        elif meta_data_filter.get("method") == "manual":
+            doc_ids.extend(meta_filter(metas, meta_data_filter["manual"]))
+            if not doc_ids:
+                doc_ids = None
+
    try:
        tenants = UserTenantService.query(user_id=tenant_id)
        for kb_id in kb_ids:
            for tenant in tenants:
-                if KnowledgebaseService.query(
-                        tenant_id=tenant.tenant_id, id=kb_id):
+                if KnowledgebaseService.query(tenant_id=tenant.tenant_id, id=kb_id):
                    tenant_ids.append(tenant.tenant_id)
                    break
            else:
-                return get_json_result(
-                    data=False, message='Only owner of knowledgebase authorized for this operation.',
-                    code=settings.RetCode.OPERATING_ERROR)
+                return get_json_result(data=False, message="Only owner of knowledgebase authorized for this operation.", code=settings.RetCode.OPERATING_ERROR)

        e, kb = KnowledgebaseService.get_by_id(kb_ids[0])
        if not e:
@ -973,17 +993,11 @@ def retrieval_test_embedded():
            question += keyword_extraction(chat_mdl, question)

        labels = label_question(question, [kb])
-        ranks = settings.retrievaler.retrieval(question, embd_mdl, tenant_ids, kb_ids, page, size,
-                               similarity_threshold, vector_similarity_weight, top,
-                               doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"),
-                               rank_feature=labels
-                               )
+        ranks = settings.retrievaler.retrieval(
+            question, embd_mdl, tenant_ids, kb_ids, page, size, similarity_threshold, vector_similarity_weight, top, doc_ids, rerank_mdl=rerank_mdl, highlight=req.get("highlight"), rank_feature=labels
+        )
        if use_kg:
-            ck = settings.kg_retrievaler.retrieval(question,
-                                                   tenant_ids,
-                                                   kb_ids,
-                                                   embd_mdl,
-                                                   LLMBundle(kb.tenant_id, LLMType.CHAT))
+            ck = settings.kg_retrievaler.retrieval(question, tenant_ids, kb_ids, embd_mdl, LLMBundle(kb.tenant_id, LLMType.CHAT))
            if ck["content_with_weight"]:
                ranks["chunks"].insert(0, ck)

@ -994,8 +1008,7 @@ def retrieval_test_embedded():
        return get_json_result(data=ranks)
    except Exception as e:
        if str(e).find("not_found") > 0:
-            return get_json_result(data=False, message='No chunk found! Check the chunk status please!',
-                                   code=settings.RetCode.DATA_ERROR)
+            return get_json_result(data=False, message="No chunk found! Check the chunk status please!", code=settings.RetCode.DATA_ERROR)
        return server_error_response(e)


--- a/api/apps/search_app.py
+++ b/api/apps/search_app.py
@ -155,8 +155,9 @@ def list_search_app():
    owner_ids = req.get("owner_ids", [])
    try:
        if not owner_ids:
-            tenants = TenantService.get_joined_tenants_by_user_id(current_user.id)
-            tenants = [m["tenant_id"] for m in tenants]
+            # tenants = TenantService.get_joined_tenants_by_user_id(current_user.id)
+            # tenants = [m["tenant_id"] for m in tenants]
+            tenants = []
            search_apps, total = SearchService.get_by_tenant_ids(tenants, current_user.id, page_number, items_per_page, orderby, desc, keywords)
        else:
            tenants = owner_ids
--- a/api/db/services/canvas_service.py
+++ b/api/db/services/canvas_service.py
@ -135,24 +135,6 @@ class UserCanvasService(CommonService):
        return True


-def structure_answer(conv, ans, message_id, session_id):
-    if not conv:
-        return ans
-    content = ""
-    if ans["event"] == "message":
-        if ans["data"].get("start_to_think") is True:
-            content = "<think>"
-        elif ans["data"].get("end_to_think") is True:
-            content = "</think>"
-        else:
-            content = ans["data"]["content"]
-
-    reference = ans["data"].get("reference")
-    result = {"id": message_id, "session_id": session_id, "answer": content}
-    if reference:
-        result["reference"] = [reference]
-    return result
-
 def completion(tenant_id, agent_id, session_id=None, **kwargs):
    query = kwargs.get("query", "") or kwargs.get("question", "")
    files = kwargs.get("files", [])
@ -182,7 +164,8 @@ def completion(tenant_id, agent_id, session_id=None, **kwargs):
            "user_id": user_id,
            "message": [],
            "source": "agent",
-            "dsl": cvs.dsl
+            "dsl": cvs.dsl,
+            "reference": []
        }
        API4ConversationService.save(**conv)
        conv = API4Conversation(**conv)
@ -195,14 +178,13 @@ def completion(tenant_id, agent_id, session_id=None, **kwargs):
    })
    txt = ""
    for ans in canvas.run(query=query, files=files, user_id=user_id, inputs=inputs):
-        ans = structure_answer(conv, ans, message_id, session_id)
-        txt += ans["answer"]
-        if ans.get("answer") or ans.get("reference"):
-            yield "data:" + json.dumps({"code": 0, "data": ans},
-                                       ensure_ascii=False) + "\n\n"
+        ans["session_id"] = session_id
+        if ans["event"] == "message":
+            txt += ans["data"]["content"]
+        yield "data:" + json.dumps(ans, ensure_ascii=False) + "\n\n"

    conv.message.append({"role": "assistant", "content": txt, "created_at": time.time(), "id": message_id})
-    conv.reference.append(canvas.get_reference())
+    conv.reference = canvas.get_reference()
    conv.errors = canvas.error
    conv.dsl = str(canvas)
    conv = conv.to_dict()
@ -231,9 +213,9 @@ def completionOpenAI(tenant_id, agent_id, question, session_id=None, stream=True
                    except Exception as e:
                        logging.exception(f"Agent OpenAI-Compatible completionOpenAI parse answer failed: {e}")
                        continue
-                if not ans["data"]["answer"]:
+                if ans.get("event") != "message" or not ans.get("data", {}).get("reference", None):
                    continue
-                content_piece = ans["data"]["answer"]
+                content_piece = ans["data"]["content"]
                completion_tokens += len(tiktokenenc.encode(content_piece))

                yield "data: " + json.dumps(
@ -278,9 +260,9 @@ def completionOpenAI(tenant_id, agent_id, question, session_id=None, stream=True
            ):
                if isinstance(ans, str):
                    ans = json.loads(ans[5:])
-                if not ans["data"]["answer"]:
+                if ans.get("event") != "message" or not ans.get("data", {}).get("reference", None):
                    continue
-                all_content += ans["data"]["answer"]
+                all_content += ans["data"]["content"]

            completion_tokens = len(tiktokenenc.encode(all_content))

--- a/api/db/services/dialog_service.py
+++ b/api/db/services/dialog_service.py
@ -256,10 +256,10 @@ def repair_bad_citation_formats(answer: str, kbinfos: dict, idx: set):


 def meta_filter(metas: dict, filters: list[dict]):
-    doc_ids = []
+    doc_ids = set([])

    def filter_out(v2docs, operator, value):
-        nonlocal doc_ids
+        ids = []
        for input, docids in v2docs.items():
            try:
                input = float(input)
@ -284,16 +284,24 @@ def meta_filter(metas: dict, filters: list[dict]):
                ]:
                try:
                    if all(conds):
-                        doc_ids.extend(docids)
+                        ids.extend(docids)
+                        break
                except Exception:
                    pass
+        return ids

    for k, v2docs in metas.items():
        for f in filters:
            if k != f["key"]:
                continue
-            filter_out(v2docs, f["op"], f["value"])
-    return doc_ids
+            ids = filter_out(v2docs, f["op"], f["value"])
+            if not doc_ids:
+                doc_ids = set(ids)
+            else:
+                doc_ids = doc_ids & set(ids)
+            if not doc_ids:
+                return []
+    return list(doc_ids)


 def chat(dialog, messages, stream=True, **kwargs):
--- a/api/db/services/llm_service.py
+++ b/api/db/services/llm_service.py
@ -152,7 +152,7 @@ class LLMBundle(LLM4Tenant):

    def describe_with_prompt(self, image, prompt):
        if self.langfuse:
-            generation = self.language.start_generation(trace_context=self.trace_context, name="describe_with_prompt", metadata={"model": self.llm_name, "prompt": prompt})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="describe_with_prompt", metadata={"model": self.llm_name, "prompt": prompt})

        txt, used_tokens = self.mdl.describe_with_prompt(image, prompt)
        if not TenantLLMService.increase_usage(self.tenant_id, self.llm_type, used_tokens):
--- a/api/utils/api_utils.py
+++ b/api/utils/api_utils.py
@ -17,6 +17,7 @@ import asyncio
 import functools
 import json
 import logging
+import os
 import queue
 import random
 import threading
@ -353,7 +354,7 @@ def get_parser_config(chunk_method, parser_config):
    if not chunk_method:
        chunk_method = "naive"

-    # Define default configurations for each chunk method
+    # Define default configurations for each chunking method
    key_mapping = {
        "naive": {"chunk_token_num": 512, "delimiter": r"\n", "html4excel": False, "layout_recognize": "DeepDOC", "raptor": {"use_raptor": False}, "graphrag": {"use_graphrag": False}},
        "qa": {"raptor": {"use_raptor": False}, "graphrag": {"use_graphrag": False}},
@ -667,7 +668,10 @@ def timeout(seconds: float | int = None, attempts: int = 2, *, exception: Option

            for a in range(attempts):
                try:
-                    result = result_queue.get(timeout=seconds)
+                    if os.environ.get("ENABLE_TIMEOUT_ASSERTION"):
+                        result = result_queue.get(timeout=seconds)
+                    else:
+                        result = result_queue.get()
                    if isinstance(result, Exception):
                        raise result
                    return result
@ -682,7 +686,10 @@ def timeout(seconds: float | int = None, attempts: int = 2, *, exception: Option

            for a in range(attempts):
                try:
-                    with trio.fail_after(seconds):
+                    if os.environ.get("ENABLE_TIMEOUT_ASSERTION"):
+                        with trio.fail_after(seconds):
+                            return await func(*args, **kwargs)
+                    else:
                        return await func(*args, **kwargs)
                except trio.TooSlowError:
                    if a < attempts - 1:
--- a/conf/llm_factories.json
+++ b/conf/llm_factories.json
@ -532,23 +532,65 @@
            "tags": "LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION",
            "status": "1",
            "llm": [
+                {
+                    "llm_name": "glm-4.5",
+                    "tags": "LLM,CHAT,128K",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "glm-4.5-x",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "glm-4.5-air",
+                    "tags": "LLM,CHAT,128K",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "glm-4.5-airx",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "glm-4.5-flash",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "glm-4.5v",
+                    "tags": "LLM,IMAGE2TEXT,64,",
+                    "max_tokens": 64000,
+                    "model_type": "image2text",
+                    "is_tools": false
+                },
                {
                    "llm_name": "glm-4-plus",
-                    "tags": "LLM,CHAT,",
+                    "tags": "LLM,CHAT,128K",
                    "max_tokens": 128000,
                    "model_type": "chat",
                    "is_tools": true
                },
                {
                    "llm_name": "glm-4-0520",
-                    "tags": "LLM,CHAT,",
+                    "tags": "LLM,CHAT,128K",
                    "max_tokens": 128000,
                    "model_type": "chat",
                    "is_tools": true
                },
                {
                    "llm_name": "glm-4",
-                    "tags": "LLM,CHAT,",
+                    "tags":"LLM,CHAT,128K",
                    "max_tokens": 128000,
                    "model_type": "chat",
                    "is_tools": true
--- a/deepdoc/parser/html_parser.py
+++ b/deepdoc/parser/html_parser.py
@ -15,35 +15,200 @@
 #  limitations under the License.
 #

-from rag.nlp import find_codec
-import readability
-import html_text
+from rag.nlp import find_codec, rag_tokenizer
+import uuid
 import chardet
-
+from bs4 import BeautifulSoup, NavigableString, Tag, Comment
+import html

 def get_encoding(file):
    with open(file,'rb') as f:
        tmp = chardet.detect(f.read())
        return tmp['encoding']

+BLOCK_TAGS = [
+    "h1", "h2", "h3", "h4", "h5", "h6",
+    "p", "div", "article", "section", "aside",
+    "ul", "ol", "li",
+    "table", "pre", "code", "blockquote",
+    "figure", "figcaption"
+]
+TITLE_TAGS = {"h1": "#", "h2": "##", "h3": "###", "h4": "#####", "h5": "#####", "h6": "######"}
+

 class RAGFlowHtmlParser:
-    def __call__(self, fnm, binary=None):
+    def __call__(self, fnm, binary=None, chunk_token_num=None):
        if binary:
            encoding = find_codec(binary)
            txt = binary.decode(encoding, errors="ignore")
        else:
            with open(fnm, "r",encoding=get_encoding(fnm)) as f:
                txt = f.read()
-        return self.parser_txt(txt)
+        return self.parser_txt(txt, chunk_token_num)

    @classmethod
-    def parser_txt(cls, txt):
+    def parser_txt(cls, txt, chunk_token_num):
        if not isinstance(txt, str):
            raise TypeError("txt type should be string!")
-        html_doc = readability.Document(txt)
-        title = html_doc.title()
-        content = html_text.extract_text(html_doc.summary(html_partial=True))
-        txt = f"{title}\n{content}"
-        sections = txt.split("\n")
+
+        temp_sections = []
+        soup = BeautifulSoup(txt, "html5lib")
+        # delete <style> tag
+        for style_tag in soup.find_all(["style", "script"]):
+            style_tag.decompose()
+        # delete <script> tag in <div>
+        for div_tag in soup.find_all("div"):
+            for script_tag in div_tag.find_all("script"):
+                script_tag.decompose()
+        # delete inline style
+        for tag in soup.find_all(True):
+            if 'style' in tag.attrs:
+                del tag.attrs['style']
+        # delete HTML comment
+        for comment in soup.find_all(string=lambda text: isinstance(text, Comment)):
+            comment.extract()
+
+        cls.read_text_recursively(soup.body, temp_sections, chunk_token_num=chunk_token_num)
+        block_txt_list, table_list = cls.merge_block_text(temp_sections)
+        sections = cls.chunk_block(block_txt_list, chunk_token_num=chunk_token_num)
+        for table in table_list:
+            sections.append(table.get("content", ""))
        return sections
+
+    @classmethod
+    def split_table(cls, html_table, chunk_token_num=512):
+        soup = BeautifulSoup(html_table, "html.parser")
+        rows = soup.find_all("tr")
+        tables = []
+        current_table = []
+        current_count = 0
+        table_str_list = []
+        for row in rows:
+            tks_str = rag_tokenizer.tokenize(str(row))
+            token_count = len(tks_str.split(" ")) if tks_str else 0
+            if current_count + token_count > chunk_token_num:
+                tables.append(current_table)
+                current_table = []
+                current_count = 0
+            current_table.append(row)
+            current_count += token_count
+        if current_table:
+            tables.append(current_table)
+
+        for table_rows in tables:
+            new_table = soup.new_tag("table")
+            for row in table_rows:
+                new_table.append(row)
+            table_str_list.append(str(new_table))
+
+        return table_str_list
+
+    @classmethod
+    def read_text_recursively(cls, element, parser_result, chunk_token_num=512, parent_name=None, block_id=None):
+        if isinstance(element, NavigableString):
+            content = element.strip()
+
+            def is_valid_html(content):
+                try:
+                    soup = BeautifulSoup(content, "html.parser")
+                    return bool(soup.find())
+                except Exception:
+                    return False
+
+            return_info = []
+            if content:
+                if is_valid_html(content):
+                    soup = BeautifulSoup(content, "html.parser")
+                    child_info = cls.read_text_recursively(soup, parser_result, chunk_token_num, element.name, block_id)
+                    parser_result.extend(child_info)
+                else:
+                    info = {"content": element.strip(), "tag_name": "inner_text", "metadata": {"block_id": block_id}}
+                    if parent_name:
+                        info["tag_name"] = parent_name
+                    return_info.append(info)
+            return return_info
+        elif isinstance(element, Tag):
+
+            if str.lower(element.name) == "table":
+                table_info_list = []
+                table_id = str(uuid.uuid1())
+                table_list = [html.unescape(str(element))]
+                for t in table_list:
+                    table_info_list.append({"content": t, "tag_name": "table",
+                                            "metadata": {"table_id": table_id, "index": table_list.index(t)}})
+                return table_info_list
+            else:
+                block_id = None
+                if str.lower(element.name) in BLOCK_TAGS:
+                    block_id = str(uuid.uuid1())
+                for child in element.children:
+                    child_info = cls.read_text_recursively(child, parser_result, chunk_token_num, element.name,
+                                                           block_id)
+                    parser_result.extend(child_info)
+        return []
+
+    @classmethod
+    def merge_block_text(cls, parser_result):
+        block_content = []
+        current_content = ""
+        table_info_list = []
+        lask_block_id = None
+        for item in parser_result:
+            content = item.get("content")
+            tag_name = item.get("tag_name")
+            title_flag = tag_name in TITLE_TAGS
+            block_id = item.get("metadata", {}).get("block_id")
+            if block_id:
+                if title_flag:
+                    content = f"{TITLE_TAGS[tag_name]} {content}"
+                if lask_block_id != block_id:
+                    if lask_block_id is not None:
+                        block_content.append(current_content)
+                    current_content = content
+                    lask_block_id = block_id
+                else:
+                    current_content += (" " if current_content else "") + content
+            else:
+                if tag_name == "table":
+                    table_info_list.append(item)
+                else:
+                    current_content += (" " if current_content else "" + content)
+        if current_content:
+            block_content.append(current_content)
+        return block_content, table_info_list
+
+    @classmethod
+    def chunk_block(cls, block_txt_list, chunk_token_num=512):
+        chunks = []
+        current_block = ""
+        current_token_count = 0
+
+        for block in block_txt_list:
+            tks_str = rag_tokenizer.tokenize(block)
+            block_token_count = len(tks_str.split(" ")) if tks_str else 0
+            if block_token_count > chunk_token_num:
+                if current_block:
+                    chunks.append(current_block)
+                start = 0
+                tokens = tks_str.split(" ")
+                while start < len(tokens):
+                    end = start + chunk_token_num
+                    split_tokens = tokens[start:end]
+                    chunks.append(" ".join(split_tokens))
+                    start = end
+                current_block = ""
+                current_token_count = 0
+            else:
+                if current_token_count + block_token_count <= chunk_token_num:
+                    current_block += ("\n" if current_block else "") + block
+                    current_token_count += block_token_count
+                else:
+                    chunks.append(current_block)
+                    current_block = block
+                    current_token_count = block_token_count
+
+        if current_block:
+            chunks.append(current_block)
+
+        return chunks
+
--- a/docker/.env
+++ b/docker/.env
@ -93,13 +93,13 @@ REDIS_PASSWORD=infini_rag_flow
 SVR_HTTP_PORT=9380

 # The RAGFlow Docker image to download.
-# Defaults to the v0.20.1-slim edition, which is the RAGFlow Docker image without embedding models.
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3-slim
+# Defaults to the v0.20.4-slim edition, which is the RAGFlow Docker image without embedding models.
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4-slim
 #
 # To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
-# RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1
+# RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4
 #
-# The Docker image of the v0.20.1 edition includes built-in embedding models:
+# The Docker image of the v0.20.4 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:v0.20.3-slim` (default): The RAGFlow Docker image without embedding models.  
-  - `infiniflow/ragflow:v0.20.3`: The RAGFlow Docker image with embedding models including:
+  - `infiniflow/ragflow:v0.20.4-slim` (default): The RAGFlow Docker image without embedding models.  
+  - `infiniflow/ragflow:v0.20.4`: 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/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:v0.20.3-slim` (default): The RAGFlow Docker image without embedding models.  
-  - `infiniflow/ragflow:v0.20.3`: The RAGFlow Docker image with embedding models including:
+  - `infiniflow/ragflow:v0.20.4-slim` (default): The RAGFlow Docker image without embedding models.  
+  - `infiniflow/ragflow:v0.20.4`: 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/acquire_ragflow_api_key.md
+++ b/docs/develop/acquire_ragflow_api_key.md
@ -11,7 +11,7 @@ An API key is required for the RAGFlow server to authenticate your HTTP/Python o
 2. Click **API** to switch to the **API** page.
 3. Obtain a RAGFlow API key:

-![ragflow_api_key](https://github.com/user-attachments/assets/f461ed61-04c6-4faf-b3d8-6b5fa56be4e7)
+![ragflow_api_key](https://raw.githubusercontent.com/infiniflow/ragflow-docs/main/images/ragflow_api_key.jpg)

 :::tip NOTE
 See the [RAGFlow HTTP API reference](../references/http_api_reference.md) or the [RAGFlow Python API reference](../references/python_api_reference.md) for a complete reference of RAGFlow's HTTP or Python APIs.
--- 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:v0.20.3-slim` to `infiniflow/ragflow:nightly-slim` to use the pre-built image.
+Open the `docker/.env` file. Find the `RAGFLOW_IMAGE` setting and change the image reference from `infiniflow/ragflow:v0.20.4-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:v0.20.3-slim`
- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.20.3`
+- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.20.4-slim`
+- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.20.4`

 ---

 ### Which embedding models can be deployed locally?

-RAGFlow offers two Docker image editions, `v0.20.3-slim` and `v0.20.3`:  
+RAGFlow offers two Docker image editions, `v0.20.4-slim` and `v0.20.4`:  
  
- `infiniflow/ragflow:v0.20.3-slim` (default): The RAGFlow Docker image without embedding models.  
- `infiniflow/ragflow:v0.20.3`: The RAGFlow Docker image with embedding models including:
+- `infiniflow/ragflow:v0.20.4-slim` (default): The RAGFlow Docker image without embedding models.  
+- `infiniflow/ragflow:v0.20.4`: 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/guides/agent/agent_component_reference/agent.mdx
+++ b/docs/guides/agent/agent_component_reference/agent.mdx
@ -9,7 +9,7 @@ The component equipped with reasoning, tool usage, and multi-agent collaboration

 ---

-An **Agent** component fine-tunes the LLM and sets its prompt. From v0.20.3 onwards, an **Agent** component is able to work independently and with the following capabilities:
+An **Agent** component fine-tunes the LLM and sets its prompt. From v0.20.4 onwards, an **Agent** component is able to work independently and with the following capabilities:

 - Autonomous reasoning with reflection and adjustment based on environmental feedback.
 - Use of tools or subagents to complete tasks.
--- a/docs/guides/agent/agent_component_reference/retrieval.mdx
+++ b/docs/guides/agent/agent_component_reference/retrieval.mdx
@ -9,7 +9,7 @@ A component that retrieves information from specified datasets.

 ## Scenarios

-A **Retrieval** component is essential in most RAG scenarios, where information is extracted from designated knowledge bases before being sent to the LLM for content generation. As of v0.20.3, a **Retrieval** component can operate either as a workflow component or as a tool of an **Agent**, enabling the Agent to control its invocation and search queries.
+A **Retrieval** component is essential in most RAG scenarios, where information is extracted from designated knowledge bases before being sent to the LLM for content generation. As of v0.20.4, a **Retrieval** component can operate either as a workflow component or as a tool of an **Agent**, enabling the Agent to control its invocation and search queries.

 ## Configurations

--- 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 v0.20.3, if you add custom variables here, the only way you can pass in their values is to call:
+      - As of v0.20.4, 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
@ -128,7 +128,7 @@ See [Run retrieval test](./run_retrieval_test.md) for details.

 ## Search for knowledge base

-As of RAGFlow v0.20.3, the search feature is still in a rudimentary form, supporting only knowledge base search by name.
+As of RAGFlow v0.20.4, the search feature is still in a rudimentary form, supporting only knowledge base search by name.

 ![search knowledge base](https://github.com/infiniflow/ragflow/assets/93570324/836ae94c-2438-42be-879e-c7ad2a59693e)

--- 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 v0.20.3, bulk download is not supported, nor can you download an entire folder. 
+> As of RAGFlow v0.20.4, bulk download is not supported, nor can you download an entire folder. 
--- 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 **≥ 0.20.3** (contains the Langfuse connector)  
+• RAGFlow **≥ 0.20.4** (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., `v0.20.3`:
+2. Switch to the latest, officially published release, e.g., `v0.20.4`:

   ```bash
-   git checkout -f v0.20.3
+   git checkout -f v0.20.4
   ```

 3. Update **ragflow/docker/.env**:
@ -83,14 +83,14 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
  <TabItem value="slim">

 ```bash
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3-slim
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4-slim
 ```

  </TabItem>
  <TabItem value="full">

 ```bash
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4
 ```

  </TabItem>
@ -114,10 +114,10 @@ No, you do not need to. Upgrading RAGFlow in itself will *not* remove your uploa
 1. From an environment with Internet access, pull the required Docker image.
 2. Save the Docker image to a **.tar** file.
   ```bash
-   docker save -o ragflow.v0.20.3.tar infiniflow/ragflow:v0.20.3
+   docker save -o ragflow.v0.20.4.tar infiniflow/ragflow:v0.20.4
   ```
 3. Copy the **.tar** file to the target server.
 4. Load the **.tar** file into Docker:
   ```bash
-   docker load -i ragflow.v0.20.3.tar
+   docker load -i ragflow.v0.20.4.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 v0.20.3 uses Elasticsearch or [Infinity](https://github.com/infiniflow/infinity) for multiple recall. Setting the value of `vm.max_map_count` correctly is crucial to the proper functioning of the Elasticsearch component.
+   RAGFlow v0.20.4 uses Elasticsearch or [Infinity](https://github.com/infiniflow/infinity) for multiple recall. Setting the value of `vm.max_map_count` correctly is crucial to the proper functioning of the Elasticsearch component.

 <Tabs
  defaultValue="linux"
@ -184,13 +184,13 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
   ```bash
   $ git clone https://github.com/infiniflow/ragflow.git
   $ cd ragflow/docker
-   $ git checkout -f v0.20.3
+   $ git checkout -f v0.20.4
   ```

 3. Use the pre-built Docker images and start up the server:

   :::tip NOTE
-   The command below downloads the `v0.20.3-slim` edition of the RAGFlow Docker image. Refer to the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.3-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.3` for the full edition `v0.20.3`.
+   The command below downloads the `v0.20.4-slim` edition of the RAGFlow Docker image. Refer to the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.4-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.4` for the full edition `v0.20.4`.
   :::

   ```bash
@ -207,8 +207,8 @@ This section provides instructions on setting up the RAGFlow server on Linux. If

 | RAGFlow image tag   | Image size (GB) | Has embedding models and Python packages? | Stable?                  |
 | ------------------- | --------------- | ----------------------------------------- | ------------------------ |
-| `v0.20.3`           | &approx;9       | :heavy_check_mark:                        | Stable release           |
-| `v0.20.3-slim`      | &approx;2       | ❌                                        | Stable release           |
+| `v0.20.4`           | &approx;9       | :heavy_check_mark:                        | Stable release           |
+| `v0.20.4-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 `v0.20.3` and `nightly` are:
+The embedding models included in `v0.20.4` 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 0.20.3. It enables users to submit queries in one language (for example, English) and retrieve relevant documents written in other languages such as Chinese or Spanish. This feature is enabled by the system’s default chat model, which translates queries to ensure accurate matching of semantic meaning across languages.
+Cross-language search (also known as cross-lingual retrieval) is a feature introduced in version 0.20.4. 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/references/http_api_reference.md
+++ b/docs/references/http_api_reference.md
@ -5,7 +5,7 @@ slug: /http_api_reference

 # HTTP API

-A complete reference for RAGFlow's RESTful API. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](../develop/acquire_ragflow_api_key.md).
+A complete reference for RAGFlow's RESTful API. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](https://ragflow.io/docs/dev/acquire_ragflow_api_key).

 ---

@ -383,7 +383,7 @@ curl --request POST \
    - `"layout_recognize"`: `string`
      - Defaults to `DeepDOC`
    - `"tag_kb_ids"`: `array<string>` refer to [Use tag set](https://ragflow.io/docs/dev/use_tag_sets)
-      - Must include a list of dataset IDs, where each dataset is parsed using the Tag Chunk Method
+      - Must include a list of dataset IDs, where each dataset is parsed using the Tag Chunking Method
    - `"task_page_size"`: `int` For PDF only.
      - Defaults to `12`
      - Minimum: `1`
@ -604,7 +604,7 @@ curl --request PUT \
    - `"layout_recognize"`: `string`
      - Defaults to `DeepDOC`
    - `"tag_kb_ids"`: `array<string>` refer to [Use tag set](https://ragflow.io/docs/dev/use_tag_sets)
-      - Must include a list of dataset IDs, where each dataset is parsed using the Tag Chunk Method
+      - Must include a list of dataset IDs, where each dataset is parsed using the Tag Chunking Method
    - `"task_page_size"`: `int` For PDF only.
      - Defaults to `12`
      - Minimum: `1`
@ -731,7 +731,7 @@ Failure:
 ```
 ---

-## Get dataset's knowledge graph
+### Get knowledge graph

 **GET** `/api/v1/datasets/{dataset_id}/knowledge_graph`

@ -810,7 +810,7 @@ Failure:
 ```
 ---

-## Delete dataset's knowledge graph
+### Delete knowledge graph

 **DELETE** `/api/v1/datasets/{dataset_id}/knowledge_graph`

@ -3501,7 +3501,7 @@ Failure:

 ### Generate related questions

-**POST** `/v1/sessions/related_questions`
+**POST** `/api/v1/sessions/related_questions`

 Generates five to ten alternative question strings from the user's original query to retrieve more relevant search results.

@ -3516,7 +3516,7 @@ The chat model autonomously determines the number of questions to generate based
 #### Request

 - Method: POST
- URL: `/v1/sessions/related_questions`
+- URL: `/api/v1/sessions/related_questions`
 - Headers:
  - `'content-Type: application/json'`
  - `'Authorization: Bearer <YOUR_LOGIN_TOKEN>'`
@ -3528,7 +3528,7 @@ The chat model autonomously determines the number of questions to generate based

 ```bash
 curl --request POST \
-     --url http://{address}/v1/sessions/related_questions \
+     --url http://{address}/api/v1/sessions/related_questions \
     --header 'Content-Type: application/json' \
     --header 'Authorization: Bearer <YOUR_LOGIN_TOKEN>' \
     --data '
--- a/docs/references/python_api_reference.md
+++ b/docs/references/python_api_reference.md
@ -5,7 +5,7 @@ slug: /python_api_reference

 # Python API

-A complete reference for RAGFlow's Python APIs. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](../develop/acquire_ragflow_api_key.md).
+A complete reference for RAGFlow's Python APIs. Before proceeding, please ensure you [have your RAGFlow API key ready for authentication](https://ragflow.io/docs/dev/acquire_ragflow_api_key).

 :::tip NOTE
 Run the following command to download the Python SDK:
--- 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:v0.20.1-slim`
- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.20.1`
+- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.20.4-slim`
+- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.20.4`
 :::

 :::danger IMPORTANT
@ -22,6 +22,38 @@ The embedding models included in a full edition are:
 These two embedding models are optimized specifically for English and Chinese, so performance may be compromised if you use them to embed documents in other languages.
 :::

+## v0.20.4
+
+Released on August 27, 2025.
+
+### Improvements
+
+- Agent component: Completes Chinese localization for the Agent component.
+- Introduces the `ENABLE_TIMEOUT_ASSERTION` environment variable to enable or disable timeout assertions for file parsing tasks.
+- Dataset:
+  - Improves Markdown file parsing, with AST support to avoid unintended chunking.
+  - Enhances HTML parsing, supporting bs4-based HTML tag traversal.
+
+### Added models
+
+ZHIPU GLM-4.5
+
+### New Agent templates
+
+Ecommerce Customer Service Workflow: A template designed to handle enquiries about product features and multi-product comparisons using the internal knowledge base, as well as to manage installation appointment bookings.
+
+### Fixed issues
+
+- Dataset:  
+  - Unable to share resources with the team.
+  - Inappropriate restrictions on the number and size of uploaded files.
+- Chat:
+  - Unable to preview referenced files in responses.
+  - Unable to send out messages after file uploads.
+- An OAuth2 authentication failure.
+- A logical error in multi-conditioned metadata searches within a dataset.
+- Citations infinitely increased in multi-turn conversations.
+
 ## v0.20.3

 Released on August 20, 2025.
--- a/graphrag/entity_resolution.py
+++ b/graphrag/entity_resolution.py
@ -15,6 +15,7 @@
 #
 import logging
 import itertools
+import os
 import re
 from dataclasses import dataclass
 from typing import Any, Callable
@ -106,7 +107,8 @@ class EntityResolution(Extractor):
            nonlocal remain_candidates_to_resolve, callback
            async with semaphore:
                try:
-                    with trio.move_on_after(280) as cancel_scope:
+                    enable_timeout_assertion = os.environ.get("ENABLE_TIMEOUT_ASSERTION")
+                    with trio.move_on_after(280 if enable_timeout_assertion else 1000000000) as cancel_scope:
                        await self._resolve_candidate(candidate_batch, result_set, result_lock)
                        remain_candidates_to_resolve = remain_candidates_to_resolve - len(candidate_batch[1])
                        callback(msg=f"Resolved {len(candidate_batch[1])} pairs, {remain_candidates_to_resolve} are remained to resolve. ")
@ -169,7 +171,8 @@ class EntityResolution(Extractor):
        logging.info(f"Created resolution prompt {len(text)} bytes for {len(candidate_resolution_i[1])} entity pairs of type {candidate_resolution_i[0]}")
        async with chat_limiter:
            try:
-                with trio.move_on_after(280) as cancel_scope:
+                enable_timeout_assertion = os.environ.get("ENABLE_TIMEOUT_ASSERTION")
+                with trio.move_on_after(280 if enable_timeout_assertion else 1000000000) as cancel_scope:
                    response = await trio.to_thread.run_sync(self._chat, text, [{"role": "user", "content": "Output:"}], {})
                if cancel_scope.cancelled_caught:
                    logging.warning("_resolve_candidate._chat timeout, skipping...")
--- a/graphrag/general/community_reports_extractor.py
+++ b/graphrag/general/community_reports_extractor.py
@ -7,6 +7,7 @@ Reference:

 import logging
 import json
+import os
 import re
 from typing import Callable
 from dataclasses import dataclass
@ -51,6 +52,7 @@ class CommunityReportsExtractor(Extractor):
        self._max_report_length = max_report_length or 1500

    async def __call__(self, graph: nx.Graph, callback: Callable | None = None):
+        enable_timeout_assertion = os.environ.get("ENABLE_TIMEOUT_ASSERTION")
        for node_degree in graph.degree:
            graph.nodes[str(node_degree[0])]["rank"] = int(node_degree[1])

@ -92,7 +94,7 @@ class CommunityReportsExtractor(Extractor):
            text = perform_variable_replacements(self._extraction_prompt, variables=prompt_variables)
            async with chat_limiter:
                try:
-                    with trio.move_on_after(180) as cancel_scope:
+                    with trio.move_on_after(180 if enable_timeout_assertion else 1000000000) as cancel_scope:
                        response = await trio.to_thread.run_sync( self._chat, text, [{"role": "user", "content": "Output:"}], {})
                    if cancel_scope.cancelled_caught:
                        logging.warning("extract_community_report._chat timeout, skipping...")
--- a/graphrag/general/index.py
+++ b/graphrag/general/index.py
@ -15,6 +15,8 @@
 #
 import json
 import logging
+import os
+
 import networkx as nx
 import trio

@ -49,6 +51,7 @@ async def run_graphrag(
    embedding_model,
    callback,
 ):
+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
    start = trio.current_time()
    tenant_id, kb_id, doc_id = row["tenant_id"], str(row["kb_id"]), row["doc_id"]
    chunks = []
@ -57,7 +60,7 @@ async def run_graphrag(
    ):
        chunks.append(d["content_with_weight"])

-    with trio.fail_after(max(120, len(chunks)*120)):
+    with trio.fail_after(max(120, len(chunks)*60*10) if enable_timeout_assertion else 10000000000):
        subgraph = await generate_subgraph(
            LightKGExt
            if "method" not in row["kb_parser_config"].get("graphrag", {}) or row["kb_parser_config"]["graphrag"]["method"] != "general"
--- a/graphrag/light/graph_prompt.py
+++ b/graphrag/light/graph_prompt.py
@ -130,7 +130,36 @@ Output:

 PROMPTS[
    "entiti_continue_extraction"
-] = """MANY entities were missed in the last extraction.  Add them below using the same format:
+] = """
+MANY entities and relationships were missed in the last extraction. Please find only the missing entities and relationships from previous text.
+
+---Remember Steps---
+
+1. Identify all entities. For each identified entity, extract the following information:
+- entity_name: Name of the entity, use same language as input text. If English, capitalized the name
+- entity_type: One of the following types: [{entity_types}]
+- entity_description: Provide a comprehensive description of the entity's attributes and activities *based solely on the information present in the input text*. **Do not infer or hallucinate information not explicitly stated.** If the text provides insufficient information to create a comprehensive description, state "Description not available in text."
+Format each entity as ("entity"{tuple_delimiter}<entity_name>{tuple_delimiter}<entity_type>{tuple_delimiter}<entity_description>)
+
+2. From the entities identified in step 1, identify all pairs of (source_entity, target_entity) that are *clearly related* to each other.
+For each pair of related entities, extract the following information:
+- source_entity: name of the source entity, as identified in step 1
+- target_entity: name of the target entity, as identified in step 1
+- relationship_description: explanation as to why you think the source entity and the target entity are related to each other
+- relationship_strength: a numeric score indicating strength of the relationship between the source entity and target entity
+- relationship_keywords: one or more high-level key words that summarize the overarching nature of the relationship, focusing on concepts or themes rather than specific details
+Format each relationship as ("relationship"{tuple_delimiter}<source_entity>{tuple_delimiter}<target_entity>{tuple_delimiter}<relationship_description>{tuple_delimiter}<relationship_keywords>{tuple_delimiter}<relationship_strength>)
+
+3. Identify high-level key words that summarize the main concepts, themes, or topics of the entire text. These should capture the overarching ideas present in the document.
+Format the content-level key words as ("content_keywords"{tuple_delimiter}<high_level_keywords>)
+
+4. Return output in {language} as a single list of all the entities and relationships identified in steps 1 and 2. Use **{record_delimiter}** as the list delimiter.
+
+5. When finished, output {completion_delimiter}
+
+---Output---
+
+Add new entities and relations below using the same format, and do not include entities and relations that have been previously extracted. :
 """

 PROMPTS[
@ -252,4 +281,4 @@ When handling information with timestamps:
 - List up to 5 most important reference sources at the end under "References", clearly indicating whether each source is from Knowledge Graph (KG) or Vector Data (VD)
  Format: [KG/VD] Source content

-Add sections and commentary to the response as appropriate for the length and format. If the provided information is insufficient to answer the question, clearly state that you don't know or cannot provide an answer in the same language as the user's question."""
+Add sections and commentary to the response as appropriate for the length and format. If the provided information is insufficient to answer the question, clearly state that you don't know or cannot provide an answer in the same language as the user's question."""
--- a/graphrag/utils.py
+++ b/graphrag/utils.py
@ -307,6 +307,7 @@ def chunk_id(chunk):

 async def graph_node_to_chunk(kb_id, embd_mdl, ent_name, meta, chunks):
    global chat_limiter
+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
    chunk = {
        "id": get_uuid(),
        "important_kwd": [ent_name],
@ -324,7 +325,7 @@ async def graph_node_to_chunk(kb_id, embd_mdl, ent_name, meta, chunks):
    ebd = get_embed_cache(embd_mdl.llm_name, ent_name)
    if ebd is None:
        async with chat_limiter:
-            with trio.fail_after(3):
+            with trio.fail_after(3 if enable_timeout_assertion else 30000000):
                ebd, _ = await trio.to_thread.run_sync(lambda: embd_mdl.encode([ent_name]))
        ebd = ebd[0]
        set_embed_cache(embd_mdl.llm_name, ent_name, ebd)
@ -362,6 +363,7 @@ def get_relation(tenant_id, kb_id, from_ent_name, to_ent_name, size=1):


 async def graph_edge_to_chunk(kb_id, embd_mdl, from_ent_name, to_ent_name, meta, chunks):
+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
    chunk = {
        "id": get_uuid(),
        "from_entity_kwd": from_ent_name,
@ -380,7 +382,7 @@ async def graph_edge_to_chunk(kb_id, embd_mdl, from_ent_name, to_ent_name, meta,
    ebd = get_embed_cache(embd_mdl.llm_name, txt)
    if ebd is None:
        async with chat_limiter:
-            with trio.fail_after(3):
+            with trio.fail_after(3 if enable_timeout_assertion else 300000000):
                ebd, _ = await trio.to_thread.run_sync(lambda: embd_mdl.encode([txt+f": {meta['description']}"]))
        ebd = ebd[0]
        set_embed_cache(embd_mdl.llm_name, txt, ebd)
@ -514,9 +516,10 @@ async def set_graph(tenant_id: str, kb_id: str, embd_mdl, graph: nx.Graph, chang
        callback(msg=f"set_graph converted graph change to {len(chunks)} chunks in {now - start:.2f}s.")
    start = now

+    enable_timeout_assertion=os.environ.get("ENABLE_TIMEOUT_ASSERTION")
    es_bulk_size = 4
    for b in range(0, len(chunks), es_bulk_size):
-        with trio.fail_after(3):
+        with trio.fail_after(3 if enable_timeout_assertion else 30000000):
            doc_store_result = await trio.to_thread.run_sync(lambda: settings.docStoreConn.insert(chunks[b:b + es_bulk_size], search.index_name(tenant_id), kb_id))
        if b % 100 == es_bulk_size and callback:
            callback(msg=f"Insert chunks: {b}/{len(chunks)}")
--- a/helm/values.yaml
+++ b/helm/values.yaml
@ -56,7 +56,7 @@ env:
 ragflow:
  image:
    repository: infiniflow/ragflow
-    tag: v0.20.3-slim
+    tag: v0.20.4-slim
    pullPolicy: IfNotPresent
    pullSecrets: []
  # Optional service configuration overrides
--- a/pyproject.toml
+++ b/pyproject.toml
@ -1,6 +1,6 @@
 [project]
 name = "ragflow"
-version = "0.20.3"
+version = "0.20.4"
 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"]
--- a/rag/app/naive.py
+++ b/rag/app/naive.py
@ -517,7 +517,8 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,

    elif re.search(r"\.(htm|html)$", filename, re.IGNORECASE):
        callback(0.1, "Start to parse.")
-        sections = HtmlParser()(filename, binary)
+        chunk_token_num = int(parser_config.get("chunk_token_num", 128))
+        sections = HtmlParser()(filename, binary, chunk_token_num)
        sections = [(_, "") for _ in sections if _]
        callback(0.8, "Finish parsing.")

--- a/rag/llm/init.py
+++ b/rag/llm/init.py
@ -36,6 +36,7 @@ class SupportedLiteLLMProvider(StrEnum):
    Nvidia = "NVIDIA"
    TogetherAI = "TogetherAI"
    Anthropic = "Anthropic"
+    Ollama = "Ollama"


 FACTORY_DEFAULT_BASE_URL = {
@ -59,6 +60,7 @@ LITELLM_PROVIDER_PREFIX = {
    SupportedLiteLLMProvider.Nvidia: "nvidia_nim/",
    SupportedLiteLLMProvider.TogetherAI: "together_ai/",
    SupportedLiteLLMProvider.Anthropic: "",  # don't need a prefix
+    SupportedLiteLLMProvider.Ollama: "ollama_chat/",
 }

 ChatModel = globals().get("ChatModel", {})
--- a/rag/llm/chat_model.py
+++ b/rag/llm/chat_model.py
@ -29,7 +29,6 @@ import json_repair
 import litellm
 import openai
 import requests
-from ollama import Client
 from openai import OpenAI
 from openai.lib.azure import AzureOpenAI
 from strenum import StrEnum
@ -112,6 +111,32 @@ class Base(ABC):
    def _clean_conf(self, gen_conf):
        if "max_tokens" in gen_conf:
            del gen_conf["max_tokens"]
+
+        allowed_conf = {
+            "temperature",
+            "max_completion_tokens",
+            "top_p",
+            "stream",
+            "stream_options",
+            "stop",
+            "n",
+            "presence_penalty",
+            "frequency_penalty",
+            "functions",
+            "function_call",
+            "logit_bias",
+            "user",
+            "response_format",
+            "seed",
+            "tools",
+            "tool_choice",
+            "logprobs",
+            "top_logprobs",
+            "extra_headers",
+        }
+
+        gen_conf = {k: v for k, v in gen_conf.items() if k in allowed_conf}
+
        return gen_conf

    def _chat(self, history, gen_conf, **kwargs):
@ -657,73 +682,6 @@ class ZhipuChat(Base):
        return super().chat_streamly_with_tools(system, history, gen_conf)


-class OllamaChat(Base):
-    _FACTORY_NAME = "Ollama"
-
-    def __init__(self, key, model_name, base_url=None, **kwargs):
-        super().__init__(key, model_name, base_url=base_url, **kwargs)
-
-        self.client = Client(host=base_url) if not key or key == "x" else Client(host=base_url, headers={"Authorization": f"Bearer {key}"})
-        self.model_name = model_name
-        self.keep_alive = kwargs.get("ollama_keep_alive", int(os.environ.get("OLLAMA_KEEP_ALIVE", -1)))
-
-    def _clean_conf(self, gen_conf):
-        options = {}
-        if "max_tokens" in gen_conf:
-            options["num_predict"] = gen_conf["max_tokens"]
-        for k in ["temperature", "top_p", "presence_penalty", "frequency_penalty"]:
-            if k not in gen_conf:
-                continue
-            options[k] = gen_conf[k]
-        return options
-
-    def _chat(self, history, gen_conf={}, **kwargs):
-        # Calculate context size
-        ctx_size = self._calculate_dynamic_ctx(history)
-
-        gen_conf["num_ctx"] = ctx_size
-        response = self.client.chat(model=self.model_name, messages=history, options=gen_conf, keep_alive=self.keep_alive)
-        ans = response["message"]["content"].strip()
-        token_count = response.get("eval_count", 0) + response.get("prompt_eval_count", 0)
-        return ans, token_count
-
-    def chat_streamly(self, system, history, gen_conf={}, **kwargs):
-        if system:
-            history.insert(0, {"role": "system", "content": system})
-        if "max_tokens" in gen_conf:
-            del gen_conf["max_tokens"]
-        try:
-            # Calculate context size
-            ctx_size = self._calculate_dynamic_ctx(history)
-            options = {"num_ctx": ctx_size}
-            if "temperature" in gen_conf:
-                options["temperature"] = gen_conf["temperature"]
-            if "max_tokens" in gen_conf:
-                options["num_predict"] = gen_conf["max_tokens"]
-            if "top_p" in gen_conf:
-                options["top_p"] = gen_conf["top_p"]
-            if "presence_penalty" in gen_conf:
-                options["presence_penalty"] = gen_conf["presence_penalty"]
-            if "frequency_penalty" in gen_conf:
-                options["frequency_penalty"] = gen_conf["frequency_penalty"]
-
-            ans = ""
-            try:
-                response = self.client.chat(model=self.model_name, messages=history, stream=True, options=options, keep_alive=self.keep_alive)
-                for resp in response:
-                    if resp["done"]:
-                        token_count = resp.get("prompt_eval_count", 0) + resp.get("eval_count", 0)
-                        yield token_count
-                    ans = resp["message"]["content"]
-                    yield ans
-            except Exception as e:
-                yield ans + "\n**ERROR**: " + str(e)
-            yield 0
-        except Exception as e:
-            yield "**ERROR**: " + str(e)
-            yield 0
-
-
 class LocalAIChat(Base):
    _FACTORY_NAME = "LocalAI"

@ -1396,7 +1354,7 @@ class Ai302Chat(Base):


 class LiteLLMBase(ABC):
-    _FACTORY_NAME = ["Tongyi-Qianwen", "Bedrock", "Moonshot", "xAI", "DeepInfra", "Groq", "Cohere", "Gemini", "DeepSeek", "NVIDIA", "TogetherAI", "Anthropic"]
+    _FACTORY_NAME = ["Tongyi-Qianwen", "Bedrock", "Moonshot", "xAI", "DeepInfra", "Groq", "Cohere", "Gemini", "DeepSeek", "NVIDIA", "TogetherAI", "Anthropic", "Ollama"]

    def __init__(self, key, model_name, base_url=None, **kwargs):
        self.timeout = int(os.environ.get("LM_TIMEOUT_SECONDS", 600))
--- a/rag/llm/rerank_model.py
+++ b/rag/llm/rerank_model.py
@ -44,14 +44,17 @@ class Base(ABC):
        raise NotImplementedError("Please implement encode method!")

    def total_token_count(self, resp):
-        try:
-            return resp.usage.total_tokens
-        except Exception:
-            pass
-        try:
-            return resp["usage"]["total_tokens"]
-        except Exception:
-            pass
+        if hasattr(resp, "usage") and hasattr(resp.usage, "total_tokens"):
+            try:
+                return resp.usage.total_tokens
+            except Exception:
+                pass
+
+        if 'usage' in resp and 'total_tokens' in resp['usage']:
+            try:
+                return resp["usage"]["total_tokens"]
+            except Exception:
+                pass
        return 0


--- a/rag/prompts/prompts.py
+++ b/rag/prompts/prompts.py
@ -114,6 +114,8 @@ def kb_prompt(kbinfos, max_tokens, hash_id=False):
    docs = {d.id: d.meta_fields for d in docs}

    def draw_node(k, line):
+        if line is not None and not isinstance(line, str):
+            line = str(line)
        if not line:
            return ""
        return f"\n├── {k}: " + re.sub(r"\n+", " ", line, flags=re.DOTALL)
--- a/rag/svr/task_executor.py
+++ b/rag/svr/task_executor.py
@ -21,7 +21,7 @@ import sys
 import threading
 import time

-from api.utils.api_utils import timeout, is_strong_enough
+from api.utils.api_utils import timeout
 from api.utils.log_utils import init_root_logger, get_project_base_directory
 from graphrag.general.index import run_graphrag
 from graphrag.utils import get_llm_cache, set_llm_cache, get_tags_from_cache, set_tags_to_cache
@ -478,8 +478,6 @@ async def embedding(docs, mdl, parser_config=None, callback=None):

@timeout(3600)
 async def run_raptor(row, chat_mdl, embd_mdl, vector_size, callback=None):
-    # Pressure test for GraphRAG task
-    await is_strong_enough(chat_mdl, embd_mdl)
    chunks = []
    vctr_nm = "q_%d_vec"%vector_size
    for d in settings.retrievaler.chunk_list(row["doc_id"], row["tenant_id"], [str(row["kb_id"])],
@ -553,7 +551,6 @@ async def do_handle_task(task):
    try:
        # bind embedding model
        embedding_model = LLMBundle(task_tenant_id, LLMType.EMBEDDING, llm_name=task_embedding_id, lang=task_language)
-        await is_strong_enough(None, embedding_model)
        vts, _ = embedding_model.encode(["ok"])
        vector_size = len(vts[0])
    except Exception as e:
@ -568,7 +565,6 @@ async def do_handle_task(task):
    if task.get("task_type", "") == "raptor":
        # bind LLM for raptor
        chat_model = LLMBundle(task_tenant_id, LLMType.CHAT, llm_name=task_llm_id, lang=task_language)
-        await is_strong_enough(chat_model, None)
        # run RAPTOR
        async with kg_limiter:
            chunks, token_count = await run_raptor(task, chat_model, embedding_model, vector_size, progress_callback)
@ -580,7 +576,6 @@ async def do_handle_task(task):
        graphrag_conf = task["kb_parser_config"].get("graphrag", {})
        start_ts = timer()
        chat_model = LLMBundle(task_tenant_id, LLMType.CHAT, llm_name=task_llm_id, lang=task_language)
-        await is_strong_enough(chat_model, None)
        with_resolution = graphrag_conf.get("resolution", False)
        with_community = graphrag_conf.get("community", False)
        async with kg_limiter:
--- a/sandbox/executor_manager/core/config.py
+++ b/sandbox/executor_manager/core/config.py
@ -22,7 +22,7 @@ from util import format_timeout_duration, parse_timeout_duration
 from core.container import init_containers, teardown_containers
 from core.logger import logger

-TIMEOUT = 10
+TIMEOUT = parse_timeout_duration(os.getenv("SANDBOX_TIMEOUT", "10s"))


@asynccontextmanager
@ -39,6 +39,5 @@ async def _lifespan(app: FastAPI):


 def init():
-    TIMEOUT = parse_timeout_duration(os.getenv("SANDBOX_TIMEOUT"))
    logger.info(f"Global timeout: {format_timeout_duration(TIMEOUT)}")
    return _lifespan
--- a/sdk/python/pyproject.toml
+++ b/sdk/python/pyproject.toml
@ -1,6 +1,6 @@
 [project]
 name = "ragflow-sdk"
-version = "0.20.3"
+version = "0.20.4"
 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 = "0.20.3"
+version = "0.20.4"
 source = { virtual = "." }
 dependencies = [
    { name = "beartype" },
--- a/uv.lock
+++ b/uv.lock
@ -5268,7 +5268,7 @@ wheels = [

 [[package]]
 name = "ragflow"
-version = "0.20.3"
+version = "0.20.4"
 source = { virtual = "." }
 dependencies = [
    { name = "akshare" },
--- a/web/src/app.tsx
+++ b/web/src/app.tsx
@ -2,7 +2,6 @@ import { Toaster as Sonner } from '@/components/ui/sonner';
 import { Toaster } from '@/components/ui/toaster';
 import i18n from '@/locales/config';
 import { QueryClient, QueryClientProvider } from '@tanstack/react-query';
-import { ReactQueryDevtools } from '@tanstack/react-query-devtools';
 import { App, ConfigProvider, ConfigProviderProps, theme } from 'antd';
 import pt_BR from 'antd/lib/locale/pt_BR';
 import deDE from 'antd/locale/de_DE';
@ -85,7 +84,7 @@ function Root({ children }: React.PropsWithChildren) {
        <Sonner position={'top-right'} expand richColors closeButton></Sonner>
        <Toaster />
      </ConfigProvider>
-      <ReactQueryDevtools buttonPosition={'top-left'} initialIsOpen={false} />
+      {/* <ReactQueryDevtools buttonPosition={'top-left'} initialIsOpen={false} /> */}
    </>
  );
 }
--- a/web/src/components/file-uploader.tsx
+++ b/web/src/components/file-uploader.tsx
@ -158,6 +158,8 @@ interface FileUploaderProps extends React.HTMLAttributes<HTMLDivElement> {
   * @example disabled
   */
  disabled?: boolean;
+
+  description?: string;
 }

 export function FileUploader(props: FileUploaderProps) {
@ -174,6 +176,7 @@ export function FileUploader(props: FileUploaderProps) {
    multiple = false,
    disabled = false,
    className,
+    description,
    ...dropzoneProps
  } = props;
  const { t } = useTranslation();
@ -302,7 +305,7 @@ export function FileUploader(props: FileUploaderProps) {
                    {t('knowledgeDetails.uploadTitle')}
                  </p>
                  <p className="text-sm text-muted-foreground/70">
-                    {t('knowledgeDetails.uploadDescription')}
+                    {description || t('knowledgeDetails.uploadDescription')}
                    {/* You can upload
                    {maxFileCount > 1
                      ? ` ${maxFileCount === Infinity ? 'multiple' : maxFileCount}
--- a/web/src/components/large-model-form-field.tsx
+++ b/web/src/components/large-model-form-field.tsx
@ -12,6 +12,7 @@ import {
  FormMessage,
 } from '@/components/ui/form';
 import { LlmModelType } from '@/constants/knowledge';
+import { t } from 'i18next';
 import { Funnel } from 'lucide-react';
 import { useFormContext, useWatch } from 'react-hook-form';
 import { useTranslation } from 'react-i18next';
@ -21,15 +22,15 @@ import { Button } from './ui/button';

 const ModelTypes = [
  {
-    title: 'All Models',
+    title: t('flow.allModels'),
    value: 'all',
  },
  {
-    title: 'Text-only Models',
+    title: t('flow.textOnlyModels'),
    value: LlmModelType.Chat,
  },
  {
-    title: 'Multimodal Models',
+    title: t('flow.multimodalModels'),
    value: LlmModelType.Image2text,
  },
 ];
--- a/web/src/components/layout-recognize-form-field.tsx
+++ b/web/src/components/layout-recognize-form-field.tsx
@ -68,7 +68,7 @@ export function LayoutRecognizeFormField() {
            <div className="flex items-center">
              <FormLabel
                tooltip={t('layoutRecognizeTip')}
-                className="text-sm text-muted-foreground whitespace-nowrap w-1/4"
+                className="text-sm text-muted-foreground whitespace-wrap w-1/4"
              >
                {t('layoutRecognize')}
              </FormLabel>
--- a/web/src/components/llm-setting-items/slider.tsx
+++ b/web/src/components/llm-setting-items/slider.tsx
@ -19,6 +19,7 @@ type SliderInputSwitchFormFieldProps = {
  name: string;
  label: string;
  defaultValue?: number;
+  onChange?: (value: number) => void;
  className?: string;
  checkName: string;
 };
@ -30,6 +31,7 @@ export function SliderInputSwitchFormField({
  label,
  name,
  defaultValue,
+  onChange,
  className,
  checkName,
 }: SliderInputSwitchFormFieldProps) {
@ -66,6 +68,10 @@ export function SliderInputSwitchFormField({
            <FormControl>
              <SingleFormSlider
                {...field}
+                onChange={(value: number) => {
+                  onChange?.(value);
+                  field.onChange(value);
+                }}
                max={max}
                min={min}
                step={step}
@ -80,6 +86,10 @@ export function SliderInputSwitchFormField({
                min={min}
                step={step}
                {...field}
+                onChange={(value: number) => {
+                  onChange?.(value);
+                  field.onChange(value);
+                }}
              ></NumberInput>
            </FormControl>
          </div>
--- a/web/src/components/message-input/next.tsx
+++ b/web/src/components/message-input/next.tsx
@ -34,6 +34,7 @@ interface IProps {
  createConversationBeforeUploadDocument?(message: string): Promise<any>;
  stopOutputMessage?(): void;
  onUpload?: NonNullable<FileUploadProps['onUpload']>;
+  removeFile?(file: File): void;
 }

 export function NextMessageInput({
@ -47,6 +48,7 @@ export function NextMessageInput({
  onInputChange,
  stopOutputMessage,
  onPressEnter,
+  removeFile,
 }: IProps) {
  const [files, setFiles] = React.useState<File[]>([]);

@ -77,6 +79,13 @@ export function NextMessageInput({
    [submit],
  );

+  const handleRemoveFile = React.useCallback(
+    (file: File) => () => {
+      removeFile?.(file);
+    },
+    [removeFile],
+  );
+
  return (
    <FileUpload
      value={files}
@ -121,6 +130,7 @@ export function NextMessageInput({
                  variant="secondary"
                  size="icon"
                  className="-top-1 -right-1 absolute size-4 shrink-0 cursor-pointer rounded-full"
+                  onClick={handleRemoveFile(file)}
                >
                  <X className="size-2.5" />
                </Button>
--- a/web/src/components/originui/select-with-search.tsx
+++ b/web/src/components/originui/select-with-search.tsx
@ -28,6 +28,7 @@ import {
  PopoverTrigger,
 } from '@/components/ui/popover';
 import { cn } from '@/lib/utils';
+import { t } from 'i18next';
 import { RAGFlowSelectOptionType } from '../ui/select';
 import { Separator } from '../ui/separator';

@ -114,7 +115,9 @@ export const SelectWithSearch = forwardRef<
                <span className="leading-none truncate">{selectLabel}</span>
              </span>
            ) : (
-              <span className="text-muted-foreground">Select value</span>
+              <span className="text-muted-foreground">
+                {t('common.selectPlaceholder')}
+              </span>
            )}
            <div className="flex items-center justify-between">
              {value && allowClear && (
@ -142,9 +145,9 @@ export const SelectWithSearch = forwardRef<
          align="start"
        >
          <Command>
-            <CommandInput placeholder="Search ..." />
+            <CommandInput placeholder={t('common.search') + '...'} />
            <CommandList>
-              <CommandEmpty>No data found.</CommandEmpty>
+              <CommandEmpty>{t('common.noDataFound')}</CommandEmpty>
              {options.map((group, idx) => {
                if (group.options) {
                  return (
--- a/web/src/components/parse-configuration/raptor-form-fields.tsx
+++ b/web/src/components/parse-configuration/raptor-form-fields.tsx
@ -3,7 +3,7 @@ import { DocumentParserType } from '@/constants/knowledge';
 import { useTranslate } from '@/hooks/common-hooks';
 import random from 'lodash/random';
 import { Plus } from 'lucide-react';
-import { useCallback, useEffect } from 'react';
+import { useCallback } from 'react';
 import { useFormContext, useWatch } from 'react-hook-form';
 import { SliderInputFormField } from '../slider-input-form-field';
 import { Button } from '../ui/button';
@ -57,15 +57,19 @@ const RaptorFormFields = () => {
  const form = useFormContext();
  const { t } = useTranslate('knowledgeConfiguration');
  const useRaptor = useWatch({ name: UseRaptorField });
-  useEffect(() => {
-    if (useRaptor) {
-      form.setValue(MaxTokenField, 256);
-      form.setValue(ThresholdField, 0.1);
-      form.setValue(MaxCluster, 64);
-      form.setValue(RandomSeedField, 0);
-      form.setValue(Prompt, t('promptText'));
-    }
-  }, [form, useRaptor, t]);
+
+  const changeRaptor = useCallback(
+    (isUseRaptor: boolean) => {
+      if (isUseRaptor) {
+        form.setValue(MaxTokenField, 256);
+        form.setValue(ThresholdField, 0.1);
+        form.setValue(MaxCluster, 64);
+        form.setValue(RandomSeedField, 0);
+        form.setValue(Prompt, t('promptText'));
+      }
+    },
+    [form],
+  );

  const handleGenerate = useCallback(() => {
    form.setValue(RandomSeedField, random(10000));
@ -97,7 +101,10 @@ const RaptorFormFields = () => {
                  <FormControl>
                    <Switch
                      checked={field.value}
-                      onCheckedChange={field.onChange}
+                      onCheckedChange={(e) => {
+                        changeRaptor(e);
+                        field.onChange(e);
+                      }}
                    ></Switch>
                  </FormControl>
                </div>
@ -127,7 +134,13 @@ const RaptorFormFields = () => {
                    </FormLabel>
                    <div className="w-3/4">
                      <FormControl>
-                        <Textarea {...field} rows={8} />
+                        <Textarea
+                          {...field}
+                          rows={8}
+                          onChange={(e) => {
+                            field.onChange(e?.target?.value);
+                          }}
+                        />
                      </FormControl>
                    </div>
                  </div>
--- a/web/src/components/table-skeleton.tsx
+++ b/web/src/components/table-skeleton.tsx
@ -1,3 +1,4 @@
+import { t } from 'i18next';
 import { Loader2 } from 'lucide-react';
 import { PropsWithChildren } from 'react';
 import { TableCell, TableRow } from './ui/table';
@ -28,5 +29,5 @@ export function TableSkeleton({
 }

 export function TableEmpty({ columnsLength }: { columnsLength: number }) {
-  return <Row columnsLength={columnsLength}>No results.</Row>;
+  return <Row columnsLength={columnsLength}>{t('common.noResults')}</Row>;
 }
--- a/web/src/components/ui/multi-select.tsx
+++ b/web/src/components/ui/multi-select.tsx
@ -209,8 +209,16 @@ export const MultiSelect = React.forwardRef<
    const [isAnimating, setIsAnimating] = React.useState(false);

    React.useEffect(() => {
-      setSelectedValues(defaultValue);
-    }, [defaultValue]);
+      if (!selectedValues?.length && props.value) {
+        setSelectedValues(props.value as string[]);
+      }
+    }, [props.value, selectedValues]);
+
+    React.useEffect(() => {
+      if (!selectedValues?.length && !props.value && defaultValue) {
+        setSelectedValues(defaultValue);
+      }
+    }, [defaultValue, props.value, selectedValues]);

    const flatOptions = React.useMemo(() => {
      return options.flatMap((option) =>
@ -291,15 +299,18 @@ export const MultiSelect = React.forwardRef<
                        variant="secondary"
                        className={cn(
                          isAnimating ? 'animate-bounce' : '',
+                          'px-1',
                          multiSelectVariants({ variant }),
                        )}
                        style={{ animationDuration: `${animation}s` }}
                      >
-                        <div className="flex items-center gap-1">
+                        <div className="flex justify-between items-center gap-1">
                          {IconComponent && (
                            <IconComponent className="h-4 w-4" />
                          )}
-                          <div>{option?.label}</div>
+                          <div className="max-w-28 text-ellipsis overflow-hidden">
+                            {option?.label}
+                          </div>
                          <XCircle
                            className="h-4 w-4 cursor-pointer"
                            onClick={(event) => {
--- a/web/src/components/ui/table.tsx
+++ b/web/src/components/ui/table.tsx
@ -8,7 +8,7 @@ const Table = React.forwardRef<
 >(({ className, rootClassName, ...props }, ref) => (
  <div
    className={cn(
-      'relative w-full overflow-auto rounded-2xl bg-bg-card',
+      'relative w-full overflow-auto rounded-2xl bg-bg-card scrollbar-none',
      rootClassName,
    )}
  >
@ -27,7 +27,7 @@ const TableHeader = React.forwardRef<
 >(({ className, ...props }, ref) => (
  <thead
    ref={ref}
-    className={cn('[&_tr]:border-b top-0 sticky', className)}
+    className={cn('[&_tr]:border-b top-0 sticky bg-bg-title z-10', className)}
    {...props}
  />
 ));
@ -67,7 +67,7 @@ const TableRow = React.forwardRef<
  <tr
    ref={ref}
    className={cn(
-      'border-b transition-colors hover:bg-muted/50 data-[state=selected]:bg-muted',
+      'border-b border-border-button transition-colors hover:bg-bg-card data-[state=selected]:bg-bg-card',
      className,
    )}
    {...props}
@ -82,7 +82,7 @@ const TableHead = React.forwardRef<
  <th
    ref={ref}
    className={cn(
-      'h-12 px-4 text-left align-middle font-normal text-text-secondary [&:has([role=checkbox])]:pr-0',
+      'h-12 px-4 text-left align-middle font-normal text-text-secondary [&:has([role=checkbox])]:pr-0 ',
      className,
    )}
    {...props}
--- a/web/src/components/ui/tooltip.tsx
+++ b/web/src/components/ui/tooltip.tsx
@ -33,7 +33,7 @@ export { Tooltip, TooltipContent, TooltipProvider, TooltipTrigger };
 export const FormTooltip = ({ tooltip }: { tooltip: React.ReactNode }) => {
  return (
    <Tooltip>
-      <TooltipTrigger>
+      <TooltipTrigger tabIndex={-1}>
        <Info className="size-3 ml-2" />
      </TooltipTrigger>
      <TooltipContent>
--- a/web/src/hooks/auth-hooks.ts
+++ b/web/src/hooks/auth-hooks.ts
@ -1,5 +1,5 @@
+import message from '@/components/ui/message';
 import authorizationUtil from '@/utils/authorization-util';
-import { message } from 'antd';
 import { useEffect, useMemo, useState } from 'react';
 import { useNavigate, useSearchParams } from 'umi';

@ -28,7 +28,7 @@ export const useOAuthCallback = () => {
      authorizationUtil.setAuthorization(auth);
      newQueryParameters.delete('auth');
      setSearchParams(newQueryParameters);
-      navigate('/knowledge');
+      navigate('/');
    }
  }, [
    error,
--- a/web/src/hooks/use-agent-request.ts
+++ b/web/src/hooks/use-agent-request.ts
@ -390,7 +390,7 @@ export const useUploadCanvasFileWithProgress = (
        files.forEach((file) => {
          onError(file, error as Error);
        });
-        message.error('error', error?.message);
+        message.error(error?.message);
      }
    },
  });
--- a/web/src/hooks/use-chat-request.ts
+++ b/web/src/hooks/use-chat-request.ts
@ -1,3 +1,4 @@
+import { FileUploadProps } from '@/components/file-upload';
 import message from '@/components/ui/message';
 import { ChatSearchParams } from '@/constants/chat';
 import {
@ -14,7 +15,7 @@ import { buildMessageListWithUuid, getConversationId } from '@/utils/chat';
 import { useMutation, useQuery, useQueryClient } from '@tanstack/react-query';
 import { useDebounce } from 'ahooks';
 import { has } from 'lodash';
-import { useCallback, useMemo } from 'react';
+import { useCallback, useMemo, useRef } from 'react';
 import { useTranslation } from 'react-i18next';
 import { useParams, useSearchParams } from 'umi';
 import {
@ -395,9 +396,14 @@ export const useDeleteMessage = () => {
  return { data, loading, deleteMessage: mutateAsync };
 };

+type UploadParameters = Parameters<NonNullable<FileUploadProps['onUpload']>>;
+
+type X = { file: UploadParameters[0][0]; options: UploadParameters[1] };
+
 export function useUploadAndParseFile() {
  const { conversationId } = useGetChatSearchParams();
  const { t } = useTranslation();
+  const controller = useRef(new AbortController());

  const {
    data,
@ -405,22 +411,48 @@ export function useUploadAndParseFile() {
    mutateAsync,
  } = useMutation({
    mutationKey: [ChatApiAction.UploadAndParse],
-    mutationFn: async (file: File) => {
-      const formData = new FormData();
-      formData.append('file', file);
-      formData.append('conversation_id', conversationId);
+    mutationFn: async ({
+      file,
+      options: { onProgress, onSuccess, onError },
+    }: X) => {
+      try {
+        const formData = new FormData();
+        formData.append('file', file);
+        formData.append('conversation_id', conversationId);

-      const { data } = await chatService.uploadAndParse(formData);
+        const { data } = await chatService.uploadAndParse(
+          {
+            signal: controller.current.signal,
+            data: formData,
+            onUploadProgress: ({ progress }) => {
+              onProgress(file, (progress || 0) * 100 - 1);
+            },
+          },
+          true,
+        );

-      if (data.code === 0) {
-        message.success(t(`message.uploaded`));
+        onProgress(file, 100);
+
+        if (data.code === 0) {
+          onSuccess(file);
+          message.success(t(`message.uploaded`));
+        } else {
+          onError(file, new Error(data.message));
+        }
+
+        return data;
+      } catch (error) {
+        onError(file, error as Error);
      }
-
-      return data;
    },
  });

-  return { data, loading, uploadAndParseFile: mutateAsync };
+  const cancel = useCallback(() => {
+    controller.current.abort();
+    controller.current = new AbortController();
+  }, [controller]);
+
+  return { data, loading, uploadAndParseFile: mutateAsync, cancel };
 }

 export const useFetchExternalChatInfo = () => {
--- a/web/src/layouts/bell-button.tsx
+++ b/web/src/layouts/bell-button.tsx
@ -0,0 +1,28 @@
+import { Button } from '@/components/ui/button';
+import { useNavigateWithFromState } from '@/hooks/route-hook';
+import { useListTenant } from '@/hooks/use-user-setting-request';
+import { TenantRole } from '@/pages/user-setting/constants';
+import { BellRing } from 'lucide-react';
+import { useCallback, useMemo } from 'react';
+
+export function BellButton() {
+  const { data } = useListTenant();
+  const navigate = useNavigateWithFromState();
+
+  const showBell = useMemo(() => {
+    return data.some((x) => x.role === TenantRole.Invite);
+  }, [data]);
+
+  const handleBellClick = useCallback(() => {
+    navigate('/user-setting/team');
+  }, [navigate]);
+
+  return showBell ? (
+    <Button variant={'ghost'} onClick={handleBellClick}>
+      <div className="relative">
+        <BellRing className="size-4 " />
+        <span className="absolute size-1 rounded -right-1 -top-1 bg-red-600"></span>
+      </div>
+    </Button>
+  ) : null;
+}
--- a/web/src/layouts/next-header.tsx
+++ b/web/src/layouts/next-header.tsx
@ -12,13 +12,10 @@ import { LanguageList, LanguageMap, ThemeEnum } from '@/constants/common';
 import { useChangeLanguage } from '@/hooks/logic-hooks';
 import { useNavigatePage } from '@/hooks/logic-hooks/navigate-hooks';
 import { useNavigateWithFromState } from '@/hooks/route-hook';
-import { useListTenant } from '@/hooks/use-user-setting-request';
 import { useFetchUserInfo } from '@/hooks/user-setting-hooks';
-import { TenantRole } from '@/pages/user-setting/constants';
 import { Routes } from '@/routes';
 import { camelCase } from 'lodash';
 import {
-  BellRing,
  ChevronDown,
  CircleHelp,
  Cpu,
@ -34,6 +31,7 @@ import {
 import React, { useCallback, useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
 import { useLocation } from 'umi';
+import { BellButton } from './bell-button';

 const handleDocHelpCLick = () => {
  window.open('https://ragflow.io/docs/dev/category/guides', 'target');
@ -56,12 +54,6 @@ export function Header() {
    changeLanguage(key);
  };

-  const { data } = useListTenant();
-
-  const showBell = useMemo(() => {
-    return data.some((x) => x.role === TenantRole.Invite);
-  }, [data]);
-
  const items = LanguageList.map((x) => ({
    key: x,
    label: <span>{LanguageMap[x as keyof typeof LanguageMap]}</span>,
@ -71,10 +63,6 @@ export function Header() {
    setTheme(theme === ThemeEnum.Dark ? ThemeEnum.Light : ThemeEnum.Dark);
  }, [setTheme, theme]);

-  const handleBellClick = useCallback(() => {
-    navigate('/user-setting/team');
-  }, [navigate]);
-
  const tagsData = useMemo(
    () => [
      { path: Routes.Root, name: t('header.Root'), icon: House },
@ -163,14 +151,7 @@ export function Header() {
        <Button variant={'ghost'} onClick={onThemeClick}>
          {theme === 'light' ? <Sun /> : <Moon />}
        </Button>
-        {showBell && (
-          <Button variant={'ghost'} onClick={handleBellClick}>
-            <div className="relative">
-              <BellRing className="size-4 " />
-              <span className="absolute size-1 rounded -right-1 -top-1 bg-red-600"></span>
-            </div>
-          </Button>
-        )}
+        <BellButton></BellButton>
        <div className="relative">
          <RAGFlowAvatar
            name={nickname}
--- a/web/src/locales/en.ts
+++ b/web/src/locales/en.ts
@ -1,6 +1,8 @@
 export default {
  translation: {
    common: {
+      noResults: 'No results.',
+      selectPlaceholder: 'select value',
      delete: 'Delete',
      deleteModalTitle: 'Are you sure to delete this item?',
      ok: 'Yes',
@ -39,6 +41,9 @@ export default {
      previousPage: 'Previous',
      nextPage: 'Next',
      add: 'Add',
+      remove: 'Remove',
+      search: 'Search',
+      noDataFound: 'No data found.',
      promptPlaceholder: `Please input or use / to quickly insert variables.`,
      mcp: {
        namePlaceholder: 'My MCP Server',
@ -94,6 +99,16 @@ export default {
      noMoreData: `That's all. Nothing more.`,
    },
    knowledgeDetails: {
+      created: 'Created',
+      learnMore: 'Learn More',
+      general: 'General',
+      chunkMethodTab: 'Chunk Method',
+      testResults: 'Test Results',
+      testSetting: 'Test Setting',
+      retrievalTesting: 'Retrieval Testing',
+      retrievalTestingDescription:
+        'Conduct a retrieval test to check if RAGFlow can recover the intended content for the LLM.',
+      Parse: 'Parse',
      dataset: 'Dataset',
      testing: 'Retrieval testing',
      files: 'files',
@ -181,7 +196,7 @@ export default {
      delimiterTip:
        'A delimiter or separator can consist of one or multiple special characters. If it is multiple characters, ensure they are enclosed in backticks( ``). For example, if you configure your delimiters like this: \\n`##`;, then your texts will be separated at line breaks, double hash symbols (##), and semicolons.',
      html4excel: 'Excel to HTML',
-      html4excelTip: `Use with the General chunking method. When disabled, spreadsheets (XLSX or XLS(Excel 97-2003)) in the knowledge base will be parsed into key-value pairs. When enabled, they will be parsed into HTML tables, splitting every 12 rows if the original table has more than 12 rows.`,
+      html4excelTip: `Use with the General chunking method. When disabled, spreadsheets (XLSX or XLS(Excel 97-2003)) in the knowledge base will be parsed into key-value pairs. When enabled, they will be parsed into HTML tables, splitting every 12 rows if the original table has more than 12 rows. See https://ragflow.io/docs/dev/enable_excel2html for details.`,
      autoKeywords: 'Auto-keyword',
      autoKeywordsTip: `Automatically extract N keywords for each chunk to increase their ranking for queries containing those keywords. Be aware that extra tokens will be consumed by the chat model specified in 'System model settings'. You can check or update the added keywords for a chunk from the chunk list. For details, see https://ragflow.io/docs/dev/autokeyword_autoquestion.`,
      autoQuestions: 'Auto-question',
@ -479,6 +494,7 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
      improvise: 'Improvise',
      precise: 'Precise',
      balance: 'Balance',
+      custom: 'Custom',
      freedomTip: `A shortcut to 'Temperature', 'Top P', 'Presence penalty', and 'Frequency penalty' settings, indicating the freedom level of the model. This parameter has three options: Select 'Improvise' to produce more creative responses; select 'Precise' (default) to produce more conservative responses; 'Balance' is a middle ground between 'Improvise' and 'Precise'.`,
      temperature: 'Temperature',
      temperatureMessage: 'Temperature is required',
@ -825,7 +841,7 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
    fileManager: {
      name: 'Name',
      uploadDate: 'Upload Date',
-      knowledgeBase: 'Knowledge Base',
+      knowledgeBase: 'Dataset',
      size: 'Size',
      action: 'Action',
      addToKnowledge: 'Link to Knowledge Base',
@ -848,11 +864,87 @@ This auto-tagging feature enhances retrieval by adding another layer of domain-s
      pleaseUploadAtLeastOneFile: 'Please upload at least one file',
    },
    flow: {
+      days: 'Days',
+      beginInput: 'Begin Input',
+      ref: 'Variable',
+      stockCode: 'Stock Code',
+      apiKeyPlaceholder:
+        'YOUR_API_KEY (obtained from https://serpapi.com/manage-api-key)',
+      flowStart: 'Start',
+      flowNum: 'Num',
+      test: 'Test',
+      extractDepth: 'Extract Depth',
+      format: 'Format',
+      basic: 'basic',
+      advanced: 'advanced',
+      general: 'general',
+      searchDepth: 'Search Depth',
+      tavilyTopic: 'Tavily Topic',
+      maxResults: 'Max Results',
+      includeAnswer: 'Include Answer',
+      includeRawContent: 'Include Raw Content',
+      includeImages: 'Include Images',
+      includeImageDescriptions: 'Include Image Descriptions',
+      includeDomains: 'Include Domains',
+      ExcludeDomains: 'Exclude Domains',
+      Days: 'Days',
+      comma: 'Comma',
+      semicolon: 'Semicolon',
+      period: 'Period',
+      lineBreak: 'Line Break',
+      tab: 'Tab',
+      space: 'Space',
+      delimiters: 'Delimiters',
+      merge: 'Merge',
+      split: 'Split',
+      script: 'Script',
+      iterationItemDescription:
+        'It represents the current element in the iteration, which can be referenced and manipulated in subsequent steps.',
+      guidingQuestion: 'Guidance Question',
+      onFailure: 'On Failure',
+      userPromptDefaultValue:
+        'This is the order you need to send to the agent.',
+      search: 'Search',
+      communication: 'Communication',
+      developer: 'Developer',
+      typeCommandOrsearch: 'Type a command or search...',
+      builtIn: 'Built-in',
+      ExceptionDefaultValue: 'Exception default value',
+      exceptionMethod: 'Exception method',
+      maxRounds: 'Max rounds',
+      delayEfterError: 'Delay after error',
+      maxRetries: 'Max retries',
+      advancedSettings: 'Advanced Settings',
+      addTools: 'Add Tools',
+      sysPromptDefultValue: `
+      <role>
+        You are {{agent_name}}, an AI assistant specialized in {{domain_or_task}}.
+      </role>
+      <instructions>
+        1. Understand the user’s request.  
+        2. Decompose it into logical subtasks.  
+        3. Execute each subtask step by step, reasoning transparently.  
+        4. Validate accuracy and consistency.  
+        5. Summarize the final result clearly.
+      </instructions>`,
+      singleLineText: 'Single-line text',
+      multimodalModels: 'Multimodal Models',
+      textOnlyModels: 'Text-only Models',
+      allModels: 'All Models',
+      codeExecDescription: 'Write your custom Python or Javascript logic.',
+      stringTransformDescription:
+        'Modifies text content. Currently supports: Splitting or concatenating text.',
+      foundation: 'Foundation',
+      tools: 'Tools',
+      dataManipulation: 'Data Manipulation',
+      flow: 'Flow',
+      dialog: 'Dialogue',
      cite: 'Cite',
      citeTip: 'citeTip',
      name: 'Name',
      nameMessage: 'Please input name',
      description: 'Description',
+      descriptionMessage: 'This is an agent for a specific task.',
      examples: 'Examples',
      to: 'To',
      msg: 'Messages',
@ -1277,6 +1369,7 @@ This delimiter is used to split the input text into several text pieces echo of
      variableSettings: 'Variable settings',
      globalVariables: 'Global variables',
      systemPrompt: 'System prompt',
+      userPrompt: 'User prompt',
      addCategory: 'Add category',
      categoryName: 'Category name',
      nextStep: 'Next step',
@ -1340,10 +1433,15 @@ This delimiter is used to split the input text into several text pieces echo of
      openingSwitchTip:
        'Your users will see this welcome message at the beginning.',
      modeTip: 'The mode defines how the workflow is initiated.',
+      mode: 'Mode',
+      conversational: 'conversational',
+      task: 'task',
      beginInputTip:
        'By defining input parameters, this content can be accessed by other components in subsequent processes.',
      query: 'Query variables',
+      queryTip: 'Select the variable you want to use',
      agent: 'Agent',
+      addAgent: 'Add Agent',
      agentDescription:
        'Builds agent components equipped with reasoning, tool usage, and multi-agent collaboration. ',
      maxRecords: 'Max records',
--- a/web/src/locales/zh-traditional.ts
+++ b/web/src/locales/zh-traditional.ts
@ -69,7 +69,7 @@ export default {
      setting: '用戶設置',
      logout: '登出',
      fileManager: '文件管理',
-      flow: 'Agent',
+      flow: '智能體',
      search: '搜尋',
      welcome: '歡迎來到',
    },
@ -454,6 +454,7 @@ export default {
      improvise: '即興創作',
      precise: '精確',
      balance: '平衡',
+      custom: '自定義',
      freedomTip: `“精確”意味著法學碩士會保守並謹慎地回答你的問題。“即興發揮”意味著你希望法學碩士能夠自由地暢所欲言。“平衡”是謹慎與自由之間的平衡。`,
      temperature: '溫度',
      temperatureMessage: '溫度是必填項',
@ -763,6 +764,23 @@ export default {
      destinationFolder: '目標資料夾',
    },
    flow: {
+      line: '單行文本',
+      paragraph: '段落文字',
+      options: '選項',
+      file: '文件',
+      integer: '數字',
+      boolean: '布爾值',
+      multimodalModels: '多模態模型',
+      textOnlyModels: '進文本模型',
+      allModels: '所有模型',
+      codeExecDescription: '用 Python 或者 Javascript 編寫自定義邏輯',
+      stringTransformDescription:
+        '修改文本内容，目前支持文本分割、文本拼接操作',
+      foundation: '基礎',
+      tools: '工具',
+      dataManipulation: '數據操控',
+      flow: '流程',
+      dialog: '對話',
      cite: '引用',
      citeTip: 'citeTip',
      name: '名稱',
@ -804,7 +822,7 @@ export default {
      promptText: `請總結以下段落。注意數字，不要胡編亂造。段落如下：
 {input}
 以上就是你需要總結的內容。`,
-      createGraph: '建立 Agent',
+      createGraph: '創建智能體',
      createFromTemplates: '從模板創建',
      retrieval: '知識檢索',
      generate: '生成回答',
--- a/web/src/locales/zh.ts
+++ b/web/src/locales/zh.ts
@ -1,6 +1,8 @@
 export default {
  translation: {
    common: {
+      noResults: '无结果。',
+      selectPlaceholder: '请选择',
      delete: '删除',
      deleteModalTitle: '确定删除吗?',
      ok: '是',
@ -38,6 +40,9 @@ export default {
      previousPage: '上一页',
      nextPage: '下一页',
      add: '添加',
+      remove: '移除',
+      search: '搜索',
+      noDataFound: '没有找到数据。',
      promptPlaceholder: '请输入或使用 / 快速插入变量。',
    },
    login: {
@ -70,7 +75,7 @@ export default {
      setting: '用户设置',
      logout: '登出',
      fileManager: '文件管理',
-      flow: 'Agent',
+      flow: '智能体',
      search: '搜索',
      welcome: '欢迎来到',
      dataset: '数据集',
@ -86,6 +91,16 @@ export default {
      noMoreData: '没有更多数据了',
    },
    knowledgeDetails: {
+      created: '创建于',
+      learnMore: '了解更多',
+      general: '通用',
+      chunkMethodTab: '切片方法',
+      testResults: '测试结果',
+      testSetting: '测试设置',
+      retrievalTesting: '知识检索测试',
+      retrievalTestingDescription:
+        '进行检索测试，检查 RAGFlow 是否能够为大语言模型（LLM）恢复预期的内容。',
+      Parse: '解析',
      dataset: '数据集',
      testing: '检索测试',
      configuration: '配置',
@ -477,6 +492,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
      improvise: '即兴创作',
      precise: '精确',
      balance: '平衡',
+      custom: '自定义',
      freedomTip: `“精确”意味着大语言模型会保守并谨慎地回答你的问题。 “即兴发挥”意味着你希望大语言模型能够自由地畅所欲言。 “平衡”是谨慎与自由之间的平衡。`,
      temperature: '温度',
      temperatureMessage: '温度是必填项',
@ -802,6 +818,90 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
      pleaseUploadAtLeastOneFile: '请上传至少一个文件',
    },
    flow: {
+      beginInput: '开始输入',
+      seconds: '秒',
+      ref: '引用变量',
+      stockCode: '股票代码',
+      apiKeyPlaceholder: '您的API密钥(从https://serpapi.com获取)',
+      flowStart: '开始',
+      flowNum: '编号',
+      test: '测试',
+      extractDepth: '深度提取',
+      format: '格式',
+      basic: '基本',
+      advanced: '高级',
+      general: '通用',
+      searchDepth: '深度搜索',
+      tavilyTopic: 'Tavily话题',
+      maxResults: '最大结果数',
+      includeAnswer: '包含答案',
+      includeRawContent: '包含原始内容',
+      includeImages: '包含图片',
+      includeImageDescriptions: '包含图片描述',
+      includeDomains: '包含域名',
+      ExcludeDomains: '排除域名',
+      days: '天数',
+      comma: '逗号',
+      semicolon: '分号',
+      period: '句点',
+      linebreak: '换行符',
+      tab: '制表符',
+      space: '空格',
+      delimiters: '分隔符',
+      merge: '合并',
+      split: '拆分',
+      script: '脚本',
+      iterationItemDescription:
+        '它是迭代过程中的当前元素，可以被后续流程引用和操作。',
+      guidingQuestion: '引导问题',
+      onFailure: '异常时',
+      userPromptDefaultValue:
+        'This is the order you need to send to the agent.',
+      descriptionMessage: '这是一个用于特定任务的代理。',
+      search: '搜索',
+      communication: '通信',
+      developer: '开发者',
+      typeCommandOrsearch: '输入命令或或搜索...',
+      builtIn: '内置',
+      goto: '异常分支',
+      comment: '默认值',
+      ExceptionDefaultValue: '异常处理默认值',
+      exceptionMethod: '异常处理方法',
+      maxRounds: '最大轮数',
+      delayEfterError: '错误后延迟',
+      maxRetries: '最大重试次数',
+      advancedSettings: '高级设置',
+      addTools: '添加工具',
+      sysPromptDefultValue: `
+<role>
+        你是{{agent_name}}，一位专注于{{领域_or_任务}}的AI助手。
+</role>
+<instructions>
+        1. 理解用户请求。
+        2. 将其分解为逻辑子任务。
+        3. 逐步执行每个子任务，并清晰地进行推理。
+        4. 验证准确性和一致性。
+        5. 清晰地总结最终结果。
+</instructions>`,
+      line: '单行文本',
+      paragraph: '段落文字',
+      options: '选项',
+      file: '文件',
+      integer: '数字',
+      boolean: '布尔值',
+      name: '名称',
+      singleLineText: '单行文本',
+      variableSettings: '变量设置',
+      multimodalModels: '多模态模型',
+      textOnlyModels: '仅文本模型',
+      allModels: '所有模型',
+      codeExecDescription: '用 Python 或者 Javascript 编写自定义逻辑',
+      stringTransformDescription:
+        '修改文本内容，目前支持文本分割、文本拼接操作',
+      foundation: '基础',
+      tools: '工具',
+      dataManipulation: '数据操控',
+      dialog: '对话',
      flow: '工作流',
      noMoreData: '没有更多数据了',
      historyversion: '历史版本',
@ -811,7 +911,6 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
      },
      cite: '引用',
      citeTip: '引用',
-      name: '名称',
      nameMessage: '请输入名称',
      description: '描述',
      examples: '示例',
@ -827,7 +926,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
        'loop为当前组件循环次数上限，当循环次数超过loop的值时，说明组件不能完成当前任务，请重新优化agent',
      yes: '是',
      no: '否',
-      key: 'key',
+      key: '键',
      componentId: '组件ID',
      add: '新增',
      operation: '操作',
@ -849,7 +948,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
      promptText: `请总结以下段落。注意数字，不要胡编乱造。段落如下：
 {input}
 以上就是你需要总结的内容。`,
-      createGraph: '创建 Agent',
+      createGraph: '创建智能体',
      createFromTemplates: '从模板创建',
      retrieval: '知识检索',
      generate: '生成回答',
@ -899,7 +998,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
      bing: 'Bing',
      bingDescription:
        '此组件用于从 https://www.bing.com/ 获取搜索结果。通常，它作为知识库的补充。Top N 和 Bing Subscription-Key 指定您需要调整的搜索结果数量。',
-      apiKey: 'API KEY',
+      apiKey: 'API密钥',
      country: '国家和地区',
      language: '语言',
      googleScholar: '谷歌学术',
@ -1031,7 +1130,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
        '30d': '30天',
      },
      publish: 'API',
-      exeSQL: 'ExeSQL',
+      exeSQL: '执行 SQL',
      exeSQLDescription:
        '该组件通过SQL语句从相应的关系数据库中查询结果。支持MySQL，PostgreSQL，MariaDB。',
      dbType: '数据库类型',
@ -1243,6 +1342,7 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
        team: '团队',
      },
      systemPrompt: '系统提示词',
+      userPrompt: '用户提示词',
      prompt: '提示词',
      promptMessage: '提示词是必填项',
      promptTip:
@ -1258,21 +1358,26 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
      openingCopy: '开场白文案',
      openingSwitchTip: '您的用户将在开始时看到此欢迎消息。',
      modeTip: '模式定义了工作流的启动方式。',
+      mode: '模式',
+      conversational: '对话式',
+      task: '任务',
      beginInputTip: '通过定义输入参数，此内容可以被后续流程中的其他组件访问。',
      query: '查询变量',
+      queryTip: '选择您想要使用的变量',
      agent: '智能体',
+      addAgent: '添加智能体',
      agentDescription: '构建具备推理、工具调用和多智能体协同的智能体组件。',
      maxRecords: '最大记录数',
-      createAgent: 'Create Agent',
+      createAgent: '创建智能体',
      stringTransform: '文本处理',
      userFillUp: '等待输入',
      userFillUpDescription: `此组件会暂停当前的流程并等待用户发送消息，接收到消息之后再进行之后的流程。`,

      codeExec: '代码',
-      tavilySearch: 'Tavily Search',
+      tavilySearch: 'Tavily 搜索',
      tavilySearchDescription: '通过 Tavily 服务搜索结果',
-      tavilyExtract: 'Tavily Extract',
-      tavilyExtractDescription: 'Tavily Extract',
+      tavilyExtract: 'Tavily 提取',
+      tavilyExtractDescription: 'Tavily 提取',
      log: '日志',
      management: '管理',
      import: '导入',
--- a/web/src/pages/agent/canvas/node/agent-node.tsx
+++ b/web/src/pages/agent/canvas/node/agent-node.tsx
@ -89,7 +89,7 @@ function InnerAgentNode({
          {(isGotoMethod ||
            exceptionMethod === AgentExceptionMethod.Comment) && (
            <div className="bg-bg-card rounded-sm p-1 flex justify-between gap-2">
-              <span className="text-text-secondary">On Failure</span>
+              <span className="text-text-secondary">{t('flow.onFailure')}</span>
              <span className="truncate flex-1 text-right">
                {t(`flow.${exceptionMethod}`)}
              </span>
--- a/web/src/pages/agent/canvas/node/dropdown/next-step-dropdown.tsx
+++ b/web/src/pages/agent/canvas/node/dropdown/next-step-dropdown.tsx
@ -21,6 +21,7 @@ import { Operator } from '@/pages/agent/constant';
 import { AgentInstanceContext, HandleContext } from '@/pages/agent/context';
 import OperatorIcon from '@/pages/agent/operator-icon';
 import { Position } from '@xyflow/react';
+import { t } from 'i18next';
 import { lowerFirst } from 'lodash';
 import {
  PropsWithChildren,
@ -128,7 +129,9 @@ function AccordionOperators({
      defaultValue={['item-1', 'item-2', 'item-3', 'item-4', 'item-5']}
    >
      <AccordionItem value="item-1">
-        <AccordionTrigger className="text-xl">Foundation</AccordionTrigger>
+        <AccordionTrigger className="text-xl">
+          {t('flow.foundation')}
+        </AccordionTrigger>
        <AccordionContent className="flex flex-col gap-4 text-balance">
          <OperatorItemList
            operators={[Operator.Agent, Operator.Retrieval]}
@ -138,7 +141,9 @@ function AccordionOperators({
        </AccordionContent>
      </AccordionItem>
      <AccordionItem value="item-2">
-        <AccordionTrigger className="text-xl">Dialogue </AccordionTrigger>
+        <AccordionTrigger className="text-xl">
+          {t('flow.dialog')}
+        </AccordionTrigger>
        <AccordionContent className="flex flex-col gap-4 text-balance">
          <OperatorItemList
            operators={[Operator.Message, Operator.UserFillUp]}
@ -148,7 +153,9 @@ function AccordionOperators({
        </AccordionContent>
      </AccordionItem>
      <AccordionItem value="item-3">
-        <AccordionTrigger className="text-xl">Flow</AccordionTrigger>
+        <AccordionTrigger className="text-xl">
+          {t('flow.flow')}
+        </AccordionTrigger>
        <AccordionContent className="flex flex-col gap-4 text-balance">
          <OperatorItemList
            operators={[
@ -163,7 +170,7 @@ function AccordionOperators({
      </AccordionItem>
      <AccordionItem value="item-4">
        <AccordionTrigger className="text-xl">
-          Data Manipulation
+          {t('flow.dataManipulation')}
        </AccordionTrigger>
        <AccordionContent className="flex flex-col gap-4 text-balance">
          <OperatorItemList
@ -174,7 +181,9 @@ function AccordionOperators({
        </AccordionContent>
      </AccordionItem>
      <AccordionItem value="item-5">
-        <AccordionTrigger className="text-xl">Tools</AccordionTrigger>
+        <AccordionTrigger className="text-xl">
+          {t('flow.tools')}
+        </AccordionTrigger>
        <AccordionContent className="flex flex-col gap-4 text-balance">
          <OperatorItemList
            operators={[
@ -244,7 +253,7 @@ export function InnerNextStepDropdown({
      >
        <div className="w-[300px] font-semibold bg-bg-base border border-border rounded-md shadow-lg">
          <div className="px-3 py-2 border-b border-border">
-            <div className="text-sm font-medium">Next Step</div>
+            <div className="text-sm font-medium">{t('flow.nextStep')}</div>
          </div>
          <HideModalContext.Provider value={hideModal}>
            <OnNodeCreatedContext.Provider value={onNodeCreated}>
@ -273,7 +282,7 @@ export function InnerNextStepDropdown({
        onClick={(e) => e.stopPropagation()}
        className="w-[300px] font-semibold"
      >
-        <DropdownMenuLabel>Next Step</DropdownMenuLabel>
+        <DropdownMenuLabel>{t('flow.nextStep')}</DropdownMenuLabel>
        <HideModalContext.Provider value={hideModal}>
          <AccordionOperators></AccordionOperators>
        </HideModalContext.Provider>
--- a/web/src/pages/agent/chat/use-send-agent-message.ts
+++ b/web/src/pages/agent/chat/use-send-agent-message.ts
@ -188,11 +188,7 @@ export const useSendAgentMessage = (
    return answerList[0]?.message_id;
  }, [answerList]);

-  useEffect(() => {
-    if (answerList[0]?.session_id) {
-      setSessionId(answerList[0]?.session_id);
-    }
-  }, [answerList]);
+  // const { refetch } = useFetchAgent();

  const { findReferenceByMessageId } = useFindMessageReference(answerList);
  const prologue = useGetBeginNodePrologue();
@ -258,26 +254,27 @@ export const useSendAgentMessage = (
    },
    [
      agentId,
-      sessionId,
-      send,
-      clearUploadResponseList,
      inputs,
      beginParams,
      uploadResponseList,
+      sessionId,
+      send,
+      clearUploadResponseList,
      setValue,
      removeLatestMessage,
    ],
  );

  const sendFormMessage = useCallback(
-    (body: { id?: string; inputs: Record<string, BeginQuery> }) => {
-      send({ ...body, session_id: sessionId });
+    async (body: { id?: string; inputs: Record<string, BeginQuery> }) => {
      addNewestOneQuestion({
        content: Object.entries(body.inputs)
          .map(([key, val]) => `${key}: ${val.value}`)
          .join('<br/>'),
        role: MessageType.User,
      });
+      await send({ ...body, session_id: sessionId });
+      // refetch();
    },
    [addNewestOneQuestion, send, sessionId],
  );
@ -346,6 +343,12 @@ export const useSendAgentMessage = (
    }
  }, [addEventList, answerList, addEventListFun, messageId]);

+  useEffect(() => {
+    if (answerList[0]?.session_id) {
+      setSessionId(answerList[0]?.session_id);
+    }
+  }, [answerList]);
+
  return {
    value,
    sendLoading: !done,
--- a/web/src/pages/agent/constant.tsx
+++ b/web/src/pages/agent/constant.tsx
@ -20,6 +20,7 @@ import {
 import { ModelVariableType } from '@/constants/knowledge';
 import i18n from '@/locales/config';
 import { setInitialChatVariableEnabledFieldValue } from '@/utils/chat';
+import { t } from 'i18next';

 // DuckDuckGo's channel options
 export enum Channel {
@ -630,16 +631,7 @@ export const initialAgentValues = {
  ...initialLlmBaseValues,
  description: '',
  user_prompt: '',
-  sys_prompt: `<role>
-  You are {{agent_name}}, an AI assistant specialized in {{domain_or_task}}.
-</role>
-<instructions>
-  1. Understand the user’s request.  
-  2. Decompose it into logical subtasks.  
-  3. Execute each subtask step by step, reasoning transparently.  
-  4. Validate accuracy and consistency.  
-  5. Summarize the final result clearly.
-</instructions>`,
+  sys_prompt: t('flow.sysPromptDefultValue'),
  prompts: [{ role: PromptRole.User, content: `{${AgentGlobals.SysQuery}}` }],
  message_history_window_size: 12,
  max_retries: 3,
--- a/web/src/pages/agent/form/agent-form/agent-tools.tsx
+++ b/web/src/pages/agent/form/agent-form/agent-tools.tsx
@ -6,6 +6,7 @@ import {
 } from '@/components/ui/tooltip';
 import { cn } from '@/lib/utils';
 import { Position } from '@xyflow/react';
+import { t } from 'i18next';
 import { PencilLine, X } from 'lucide-react';
 import {
  MouseEventHandler,
@ -106,7 +107,7 @@ export function AgentTools() {

  return (
    <section className="space-y-2.5">
-      <span className="text-text-secondary">Tools</span>
+      <span className="text-text-secondary">{t('flow.tools')}</span>
      <ul className="space-y-2">
        {toolNames.map((x) => (
          <ToolCard key={x}>
@ -133,7 +134,7 @@ export function AgentTools() {
        ))}
      </ul>
      <ToolPopover>
-        <BlockButton>Add Tool</BlockButton>
+        <BlockButton>{t('flow.addTools')}</BlockButton>
      </ToolPopover>
    </section>
  );
@ -160,7 +161,7 @@ export function Agents({ node }: INextOperatorForm) {

  return (
    <section className="space-y-2.5">
-      <span className="text-text-secondary">Agents</span>
+      <span className="text-text-secondary">{t('flow.agent')}</span>
      <ul className="space-y-2">
        {subBottomAgentNodeIds.map((id) => {
          const currentNode = getNode(id);
@ -183,7 +184,7 @@ export function Agents({ node }: INextOperatorForm) {
          position: Position.Bottom,
        })}
      >
-        Add Agent
+        {t('flow.addAgent')}
      </BlockButton>
    </section>
  );
--- a/web/src/pages/agent/form/agent-form/index.tsx
+++ b/web/src/pages/agent/form/agent-form/index.tsx
@ -144,7 +144,7 @@ function AgentForm({ node }: INextOperatorForm) {
            name={`sys_prompt`}
            render={({ field }) => (
              <FormItem className="flex-1">
-                <FormLabel>System Prompt</FormLabel>
+                <FormLabel>{t('flow.systemPrompt')}</FormLabel>
                <FormControl>
                  <PromptEditor
                    {...field}
@ -164,7 +164,7 @@ function AgentForm({ node }: INextOperatorForm) {
              name={`prompts`}
              render={({ field }) => (
                <FormItem className="flex-1">
-                  <FormLabel>User Prompt</FormLabel>
+                  <FormLabel>{t('flow.userPrompt')}</FormLabel>
                  <FormControl>
                    <section>
                      <PromptEditor
@ -183,7 +183,7 @@ function AgentForm({ node }: INextOperatorForm) {
          <AgentTools></AgentTools>
          <Agents node={node}></Agents>
        </FormContainer>
-        <Collapse title={<div>Advanced Settings</div>}>
+        <Collapse title={<div>{t('flow.advancedSettings')}</div>}>
          <FormContainer>
            <MessageHistoryWindowSizeFormField></MessageHistoryWindowSizeFormField>
            <FormField
@ -208,7 +208,7 @@ function AgentForm({ node }: INextOperatorForm) {
              name={`max_retries`}
              render={({ field }) => (
                <FormItem className="flex-1">
-                  <FormLabel>Max retries</FormLabel>
+                  <FormLabel>{t('flow.maxRetries')}</FormLabel>
                  <FormControl>
                    <NumberInput {...field} max={8}></NumberInput>
                  </FormControl>
@ -220,7 +220,7 @@ function AgentForm({ node }: INextOperatorForm) {
              name={`delay_after_error`}
              render={({ field }) => (
                <FormItem className="flex-1">
-                  <FormLabel>Delay after error</FormLabel>
+                  <FormLabel>{t('flow.delayEfterError')}</FormLabel>
                  <FormControl>
                    <NumberInput {...field} max={5} step={0.1}></NumberInput>
                  </FormControl>
@ -232,7 +232,7 @@ function AgentForm({ node }: INextOperatorForm) {
              name={`max_rounds`}
              render={({ field }) => (
                <FormItem className="flex-1">
-                  <FormLabel>Max rounds</FormLabel>
+                  <FormLabel>{t('flow.maxRounds')}</FormLabel>
                  <FormControl>
                    <NumberInput {...field}></NumberInput>
                  </FormControl>
@ -244,7 +244,7 @@ function AgentForm({ node }: INextOperatorForm) {
              name={`exception_method`}
              render={({ field }) => (
                <FormItem className="flex-1">
-                  <FormLabel>Exception method</FormLabel>
+                  <FormLabel>{t('flow.exceptionMethod')}</FormLabel>
                  <FormControl>
                    <SelectWithSearch
                      {...field}
@ -261,7 +261,7 @@ function AgentForm({ node }: INextOperatorForm) {
                name={`exception_default_value`}
                render={({ field }) => (
                  <FormItem className="flex-1">
-                    <FormLabel>Exception default value</FormLabel>
+                    <FormLabel>{t('flow.ExceptionDefaultValue')}</FormLabel>
                    <FormControl>
                      <Input {...field} />
                    </FormControl>
--- a/web/src/pages/agent/form/agent-form/tool-popover/index.tsx
+++ b/web/src/pages/agent/form/agent-form/tool-popover/index.tsx
@ -8,6 +8,7 @@ import { Operator } from '@/pages/agent/constant';
 import { AgentFormContext, AgentInstanceContext } from '@/pages/agent/context';
 import useGraphStore from '@/pages/agent/store';
 import { Position } from '@xyflow/react';
+import { t } from 'i18next';
 import { PropsWithChildren, useCallback, useContext, useEffect } from 'react';
 import { useGetAgentMCPIds, useGetAgentToolNames } from '../use-get-tools';
 import { MCPCommand, ToolCommand } from './tool-command';
@ -65,8 +66,12 @@ export function ToolPopover({ children }: PropsWithChildren) {
      <PopoverContent className="w-80 p-4">
        <Tabs defaultValue={ToolType.Common}>
          <TabsList>
-            <TabsTrigger value={ToolType.Common}>Built-in</TabsTrigger>
-            <TabsTrigger value={ToolType.MCP}>MCP</TabsTrigger>
+            <TabsTrigger value={ToolType.Common} className="bg-bg-card">
+              {t('flow.builtIn')}
+            </TabsTrigger>
+            <TabsTrigger value={ToolType.MCP} className="bg-bg-card">
+              MCP
+            </TabsTrigger>
          </TabsList>
          <TabsContent value={ToolType.Common}>
            <ToolCommand
--- a/web/src/pages/agent/form/agent-form/tool-popover/tool-command.tsx
+++ b/web/src/pages/agent/form/agent-form/tool-popover/tool-command.tsx
@ -12,13 +12,14 @@ import { useListMcpServer } from '@/hooks/use-mcp-request';
 import { cn } from '@/lib/utils';
 import { Operator } from '@/pages/agent/constant';
 import OperatorIcon from '@/pages/agent/operator-icon';
+import { t } from 'i18next';
 import { lowerFirst } from 'lodash';
 import { PropsWithChildren, useCallback, useEffect, useState } from 'react';
 import { useTranslation } from 'react-i18next';

 const Menus = [
  {
-    label: 'Search',
+    label: t('flow.search'),
    list: [
      Operator.TavilySearch,
      Operator.TavilyExtract,
@ -34,7 +35,7 @@ const Menus = [
    ],
  },
  {
-    label: 'Communication',
+    label: t('flow.communication'),
    list: [Operator.Email],
  },
  // {
@ -42,7 +43,7 @@ const Menus = [
  //   list: [],
  // },
  {
-    label: 'Developer',
+    label: t('flow.developer'),
    list: [Operator.GitHub, Operator.ExeSQL, Operator.Code, Operator.Retrieval],
  },
 ];
@ -116,7 +117,7 @@ export function ToolCommand({ value, onChange }: ToolCommandProps) {

  return (
    <Command>
-      <CommandInput placeholder="Type a command or search..." />
+      <CommandInput placeholder={t('flow.typeCommandOrsearch')} />
      <CommandList>
        <CommandEmpty>No results found.</CommandEmpty>
        {Menus.map((x) => (
--- a/web/src/pages/agent/form/begin-form/index.tsx
+++ b/web/src/pages/agent/form/begin-form/index.tsx
@ -12,8 +12,8 @@ import { RAGFlowSelect } from '@/components/ui/select';
 import { Switch } from '@/components/ui/switch';
 import { Textarea } from '@/components/ui/textarea';
 import { FormTooltip } from '@/components/ui/tooltip';
-import { buildSelectOptions } from '@/utils/component-util';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { t } from 'i18next';
 import { Plus } from 'lucide-react';
 import { memo, useEffect, useRef } from 'react';
 import { useForm, useWatch } from 'react-hook-form';
@ -27,10 +27,10 @@ import { useEditQueryRecord } from './use-edit-query';
 import { useValues } from './use-values';
 import { useWatchFormChange } from './use-watch-change';

-const ModeOptions = buildSelectOptions([
-  AgentDialogueMode.Conversational,
-  AgentDialogueMode.Task,
-]);
+const ModeOptions = [
+  { value: AgentDialogueMode.Conversational, label: t('flow.conversational') },
+  { value: AgentDialogueMode.Task, label: t('flow.task') },
+];

 function BeginForm({ node }: INextOperatorForm) {
  const { t } = useTranslation();
@ -103,7 +103,9 @@ function BeginForm({ node }: INextOperatorForm) {
          name={'mode'}
          render={({ field }) => (
            <FormItem>
-              <FormLabel tooltip={t('flow.modeTip')}>Mode</FormLabel>
+              <FormLabel tooltip={t('flow.modeTip')}>
+                {t('flow.mode')}
+              </FormLabel>
              <FormControl>
                <RAGFlowSelect
                  placeholder={t('common.pleaseSelect')}
--- a/web/src/pages/agent/form/begin-form/parameter-dialog.tsx
+++ b/web/src/pages/agent/form/begin-form/parameter-dialog.tsx
@ -138,7 +138,7 @@ function ParameterForm({
          control={form.control}
          render={({ field }) => (
            <FormItem>
-              <FormLabel>Type</FormLabel>
+              <FormLabel>{t('type')}</FormLabel>
              <FormControl>
                <RAGFlowSelect {...field} options={options} />
              </FormControl>
@ -151,7 +151,7 @@ function ParameterForm({
          control={form.control}
          render={({ field }) => (
            <FormItem>
-              <FormLabel>Key</FormLabel>
+              <FormLabel>{t('key')}</FormLabel>
              <FormControl>
                <Input {...field} autoComplete="off" onBlur={handleKeyChange} />
              </FormControl>
@ -164,7 +164,7 @@ function ParameterForm({
          control={form.control}
          render={({ field }) => (
            <FormItem>
-              <FormLabel>Name</FormLabel>
+              <FormLabel>{t('name')}</FormLabel>
              <FormControl>
                <Input {...field} />
              </FormControl>
@ -177,7 +177,7 @@ function ParameterForm({
          control={form.control}
          render={({ field }) => (
            <FormItem>
-              <FormLabel>Optional</FormLabel>
+              <FormLabel>{t('optional')}</FormLabel>
              <FormControl>
                <Switch
                  checked={field.value}
@ -217,7 +217,7 @@ export function ParameterDialog({
        ></ParameterForm>
        <DialogFooter>
          <Button type="submit" form={FormId}>
-            Confirm
+            {t('modal.okText')}
          </Button>
        </DialogFooter>
      </DialogContent>
--- a/web/src/pages/agent/form/begin-form/query-table.tsx
+++ b/web/src/pages/agent/form/begin-form/query-table.tsx
@ -53,7 +53,7 @@ export function QueryTable({ data = [], deleteRecord, showModal }: IProps) {
  const columns: ColumnDef<BeginQuery>[] = [
    {
      accessorKey: 'key',
-      header: 'Key',
+      header: t('flow.key'),
      meta: { cellClassName: 'max-w-30' },
      cell: ({ row }) => {
        const key: string = row.getValue('key');
--- a/web/src/pages/agent/form/components/api-key-field.tsx
+++ b/web/src/pages/agent/form/components/api-key-field.tsx
@ -6,6 +6,7 @@ import {
  FormMessage,
 } from '@/components/ui/form';
 import { Input } from '@/components/ui/input';
+import { t } from 'i18next';
 import { useFormContext } from 'react-hook-form';

 interface IApiKeyFieldProps {
@ -19,7 +20,7 @@ export function ApiKeyField({ placeholder }: IApiKeyFieldProps) {
      name="api_key"
      render={({ field }) => (
        <FormItem>
-          <FormLabel>Api Key</FormLabel>
+          <FormLabel>{t('flow.apiKey')}</FormLabel>
          <FormControl>
            <Input type="password" {...field} placeholder={placeholder}></Input>
          </FormControl>
--- a/web/src/pages/agent/form/components/description-field.tsx
+++ b/web/src/pages/agent/form/components/description-field.tsx
@ -5,6 +5,7 @@ import {
  FormLabel,
 } from '@/components/ui/form';
 import { Textarea } from '@/components/ui/textarea';
+import { t } from 'i18next';
 import { useFormContext } from 'react-hook-form';

 export function DescriptionField() {
@ -15,7 +16,7 @@ export function DescriptionField() {
      name={`description`}
      render={({ field }) => (
        <FormItem className="flex-1">
-          <FormLabel>Description</FormLabel>
+          <FormLabel>{t('flow.description')}</FormLabel>
          <FormControl>
            <Textarea {...field}></Textarea>
          </FormControl>
--- a/web/src/pages/agent/form/components/output.tsx
+++ b/web/src/pages/agent/form/components/output.tsx
@ -1,3 +1,5 @@
+import { t } from 'i18next';
+
 export type OutputType = {
  title: string;
  type?: string;
@ -17,7 +19,7 @@ export function transferOutputs(outputs: Record<string, any>) {
 export function Output({ list }: OutputProps) {
  return (
    <section className="space-y-2">
-      <div>Output</div>
+      <div>{t('flow.output')}</div>
      <ul>
        {list.map((x, idx) => (
          <li
--- a/web/src/pages/agent/form/components/query-variable.tsx
+++ b/web/src/pages/agent/form/components/query-variable.tsx
@ -47,7 +47,7 @@ export function QueryVariable({
      render={({ field }) => (
        <FormItem>
          {label || (
-            <FormLabel tooltip={t('chat.modelTip')}>
+            <FormLabel tooltip={t('flow.queryTip')}>
              {t('flow.query')}
            </FormLabel>
          )}
--- a/web/src/pages/agent/form/exesql-form/index.tsx
+++ b/web/src/pages/agent/form/exesql-form/index.tsx
@ -132,7 +132,7 @@ export function ExeSQLFormWidgets({ loading }: { loading: boolean }) {

      <div className="flex justify-end">
        <ButtonLoading loading={loading} type="submit">
-          Test
+          {t('test')}
        </ButtonLoading>
      </div>
    </>
--- a/web/src/pages/agent/form/google-form/index.tsx
+++ b/web/src/pages/agent/form/google-form/index.tsx
@ -99,13 +99,13 @@ const GoogleForm = ({ node }: INextOperatorForm) => {
          <QueryVariable name="q"></QueryVariable>
        </FormContainer>
        <FormContainer>
-          <ApiKeyField placeholder="YOUR_API_KEY (obtained from https://serpapi.com/manage-api-key)"></ApiKeyField>
+          <ApiKeyField placeholder={t('apiKeyPlaceholder')}></ApiKeyField>
          <FormField
            control={form.control}
            name={`start`}
            render={({ field }) => (
              <FormItem>
-                <FormLabel>{t('start')}</FormLabel>
+                <FormLabel>{t('flowStart')}</FormLabel>
                <FormControl>
                  <NumberInput {...field} className="w-full"></NumberInput>
                </FormControl>
@ -118,7 +118,7 @@ const GoogleForm = ({ node }: INextOperatorForm) => {
            name={`num`}
            render={({ field }) => (
              <FormItem>
-                <FormLabel>{t('num')}</FormLabel>
+                <FormLabel>{t('flowNum')}</FormLabel>
                <FormControl>
                  <NumberInput {...field} className="w-full"></NumberInput>
                </FormControl>
--- a/web/src/pages/agent/form/invoke-form/variable-dialog.tsx
+++ b/web/src/pages/agent/form/invoke-form/variable-dialog.tsx
@ -134,7 +134,7 @@ export function VariableDialog({
        ></VariableForm>
        <DialogFooter>
          <Button type="submit" form={FormId}>
-            Confirm
+            {t('modal.okText')}
          </Button>
        </DialogFooter>
      </DialogContent>
--- a/web/src/pages/agent/form/invoke-form/variable-table.tsx
+++ b/web/src/pages/agent/form/invoke-form/variable-table.tsx
@ -61,7 +61,7 @@ export function VariableTable({
  const columns: ColumnDef<VariableFormSchemaType>[] = [
    {
      accessorKey: 'key',
-      header: 'key',
+      header: t('flow.key'),
      meta: { cellClassName: 'max-w-30' },
      cell: ({ row }) => {
        const key: string = row.getValue('key');
--- a/web/src/pages/agent/form/iteration-form/dynamic-output.tsx
+++ b/web/src/pages/agent/form/iteration-form/dynamic-output.tsx
@ -12,6 +12,7 @@ import {
 import { Input } from '@/components/ui/input';
 import { Separator } from '@/components/ui/separator';
 import { RAGFlowNodeType } from '@/interfaces/database/flow';
+import { t } from 'i18next';
 import { X } from 'lucide-react';
 import { ReactNode, useCallback, useMemo } from 'react';
 import { useFieldArray, useFormContext } from 'react-hook-form';
@ -107,7 +108,7 @@ export function DynamicOutputForm({ node }: IProps) {
        );
      })}
      <BlockButton onClick={() => append({ name: '', ref: undefined })}>
-        Add
+        {t('common.add')}
      </BlockButton>
    </div>
  );
@ -120,7 +121,7 @@ export function VariableTitle({ title }: { title: ReactNode }) {
 export function DynamicOutput({ node }: IProps) {
  return (
    <FormContainer>
-      <VariableTitle title={'Output'}></VariableTitle>
+      <VariableTitle title={t('flow.output')}></VariableTitle>
      <DynamicOutputForm node={node}></DynamicOutputForm>
    </FormContainer>
  );
--- a/web/src/pages/agent/form/retrieval-form/next.tsx
+++ b/web/src/pages/agent/form/retrieval-form/next.tsx
@ -104,7 +104,7 @@ function RetrievalForm({ node }: INextOperatorForm) {
          </RAGFlowFormItem>
          <KnowledgeBaseFormField showVariable></KnowledgeBaseFormField>
        </FormContainer>
-        <Collapse title={<div>Advanced Settings</div>}>
+        <Collapse title={<div>{t('flow.advancedSettings')}</div>}>
          <FormContainer>
            <SimilaritySliderFormField
              vectorSimilarityWeightName="keywords_similarity_weight"
--- a/web/src/pages/agent/form/string-transform-form/index.tsx
+++ b/web/src/pages/agent/form/string-transform-form/index.tsx
@ -9,8 +9,9 @@ import {
 } from '@/components/ui/form';
 import { MultiSelect } from '@/components/ui/multi-select';
 import { RAGFlowSelect } from '@/components/ui/select';
-import { buildOptions } from '@/utils/form';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { t } from 'i18next';
+import { toLower } from 'lodash';
 import { memo, useCallback, useMemo } from 'react';
 import { useForm, useWatch } from 'react-hook-form';
 import { z } from 'zod';
@ -28,7 +29,7 @@ import { useValues } from './use-values';
 import { useWatchFormChange } from './use-watch-form-change';

 const DelimiterOptions = Object.entries(StringTransformDelimiter).map(
-  ([key, val]) => ({ label: key, value: val }),
+  ([key, val]) => ({ label: t('flow.' + toLower(key)), value: val }),
 );

 function StringTransformForm({ node }: INextOperatorForm) {
@ -84,11 +85,13 @@ function StringTransformForm({ node }: INextOperatorForm) {
            name="method"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>method</FormLabel>
+                <FormLabel>{t('flow.method')}</FormLabel>
                <FormControl>
                  <RAGFlowSelect
                    {...field}
-                    options={buildOptions(StringTransformMethod)}
+                    options={Object.values(StringTransformMethod).map(
+                      (val) => ({ label: t('flow.' + val), value: val }),
+                    )}
                    onChange={(value) => {
                      handleMethodChange(value);
                      field.onChange(value);
@ -111,7 +114,7 @@ function StringTransformForm({ node }: INextOperatorForm) {
              name="script"
              render={({ field }) => (
                <FormItem>
-                  <FormLabel>script</FormLabel>
+                  <FormLabel>{t('flow.script')}</FormLabel>
                  <FormControl>
                    <PromptEditor {...field} showToolbar={false}></PromptEditor>
                  </FormControl>
@ -125,7 +128,7 @@ function StringTransformForm({ node }: INextOperatorForm) {
            name="delimiters"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>delimiters</FormLabel>
+                <FormLabel>{t('flow.delimiters')}</FormLabel>
                <FormControl>
                  {isSplit ? (
                    <MultiSelect
--- a/web/src/pages/agent/form/switch-form/index.tsx
+++ b/web/src/pages/agent/form/switch-form/index.tsx
@ -15,6 +15,7 @@ import { Separator } from '@/components/ui/separator';
 import { Textarea } from '@/components/ui/textarea';
 import { cn } from '@/lib/utils';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { t } from 'i18next';
 import { toLower } from 'lodash';
 import { X } from 'lucide-react';
 import { memo, useCallback, useMemo } from 'react';
@ -197,7 +198,7 @@ function ConditionCards({
          className="mt-6"
          onClick={() => append({ operator: switchOperatorOptions[0].value })}
        >
-          Add
+          {t('common.add')}
        </BlockButton>
      </div>
    </section>
@ -268,7 +269,7 @@ function SwitchForm({ node }: IOperatorForm) {
                    className="-translate-y-1"
                    onClick={() => remove(index)}
                  >
-                    Remove <X />
+                    {t('common.remove')} <X />
                  </Button>
                )}
              </div>
@ -317,7 +318,7 @@ function SwitchForm({ node }: IOperatorForm) {
            })
          }
        >
-          Add
+          {t('common.add')}
        </BlockButton>
      </FormWrapper>
    </Form>
--- a/web/src/pages/agent/form/tavily-extract-form/index.tsx
+++ b/web/src/pages/agent/form/tavily-extract-form/index.tsx
@ -10,6 +10,7 @@ import {
 import { RAGFlowSelect } from '@/components/ui/select';
 import { buildOptions } from '@/utils/form';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { t } from 'i18next';
 import { memo } from 'react';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
@ -79,12 +80,12 @@ function TavilyExtractForm({ node }: INextOperatorForm) {
            name="extract_depth"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Extract Depth</FormLabel>
+                <FormLabel>{t('flow.extractDepth')}</FormLabel>
                <FormControl>
                  <RAGFlowSelect
                    placeholder="shadcn"
                    {...field}
-                    options={buildOptions(TavilyExtractDepth)}
+                    options={buildOptions(TavilyExtractDepth, t, 'flow')}
                  />
                </FormControl>
                <FormMessage />
@ -96,7 +97,7 @@ function TavilyExtractForm({ node }: INextOperatorForm) {
            name="format"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Format</FormLabel>
+                <FormLabel>{t('flow.format')}</FormLabel>
                <FormControl>
                  <RAGFlowSelect
                    placeholder="shadcn"
--- a/web/src/pages/agent/form/tavily-form/dynamic-domain.tsx
+++ b/web/src/pages/agent/form/tavily-form/dynamic-domain.tsx
@ -7,6 +7,7 @@ import {
  FormMessage,
 } from '@/components/ui/form';
 import { Input } from '@/components/ui/input';
+import { t } from 'i18next';
 import { X } from 'lucide-react';
 import { ReactNode } from 'react';
 import { useFieldArray, useFormContext } from 'react-hook-form';
@ -51,7 +52,9 @@ export const DynamicDomain = ({ name, label }: DynamicDomainProps) => {
        ))}
      </div>
      <FormMessage />
-      <BlockButton onClick={() => append({ value: '' })}>Add</BlockButton>
+      <BlockButton onClick={() => append({ value: '' })}>
+        {t('common.add')}
+      </BlockButton>
    </FormItem>
  );
 };
--- a/web/src/pages/agent/form/tavily-form/index.tsx
+++ b/web/src/pages/agent/form/tavily-form/index.tsx
@ -12,6 +12,7 @@ import { RAGFlowSelect } from '@/components/ui/select';
 import { Switch } from '@/components/ui/switch';
 import { buildOptions } from '@/utils/form';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { t } from 'i18next';
 import { memo } from 'react';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
@ -74,12 +75,12 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="search_depth"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Search Depth</FormLabel>
+                <FormLabel>{t('flow.searchDepth')}</FormLabel>
                <FormControl>
                  <RAGFlowSelect
                    placeholder="shadcn"
                    {...field}
-                    options={buildOptions(TavilySearchDepth)}
+                    options={buildOptions(TavilySearchDepth, t, 'flow')}
                  />
                </FormControl>
                <FormMessage />
@ -91,12 +92,12 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="topic"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>TavilyTopic</FormLabel>
+                <FormLabel>{t('flow.tavilyTopic')}</FormLabel>
                <FormControl>
                  <RAGFlowSelect
                    placeholder="shadcn"
                    {...field}
-                    options={buildOptions(TavilyTopic)}
+                    options={buildOptions(TavilyTopic, t, 'flow')}
                  />
                </FormControl>
                <FormMessage />
@ -108,7 +109,7 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="max_results"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Max Results</FormLabel>
+                <FormLabel>{t('flow.maxResults')}</FormLabel>
                <FormControl>
                  <Input type={'number'} {...field}></Input>
                </FormControl>
@ -121,7 +122,7 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="days"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Days</FormLabel>
+                <FormLabel>{t('flow.days')}</FormLabel>
                <FormControl>
                  <Input type={'number'} {...field}></Input>
                </FormControl>
@ -134,7 +135,7 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="include_answer"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Include Answer</FormLabel>
+                <FormLabel>{t('flow.includeAnswer')}</FormLabel>
                <FormControl>
                  <Switch
                    checked={field.value}
@ -150,7 +151,7 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="include_raw_content"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Include Raw Content</FormLabel>
+                <FormLabel>{t('flow.includeRawContent')}</FormLabel>
                <FormControl>
                  <Switch
                    checked={field.value}
@ -166,7 +167,7 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="include_images"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Include Images</FormLabel>
+                <FormLabel>{t('flow.includeImages')}</FormLabel>
                <FormControl>
                  <Switch
                    checked={field.value}
@ -182,7 +183,7 @@ function TavilyForm({ node }: INextOperatorForm) {
            name="include_image_descriptions"
            render={({ field }) => (
              <FormItem>
-                <FormLabel>Include Image Descriptions</FormLabel>
+                <FormLabel>{t('flow.includeImageDescriptions')}</FormLabel>
                <FormControl>
                  <Switch
                    checked={field.value}
@ -195,11 +196,11 @@ function TavilyForm({ node }: INextOperatorForm) {
          />
          <DynamicDomain
            name="include_domains"
-            label={'Include Domains'}
+            label={t('flow.includeDomains')}
          ></DynamicDomain>
          <DynamicDomain
            name="exclude_domains"
-            label={'Exclude Domains'}
+            label={t('flow.ExcludeDomains')}
          ></DynamicDomain>
        </FormContainer>
      </FormWrapper>
--- a/web/src/pages/agent/form/tool-form/retrieval-form/index.tsx
+++ b/web/src/pages/agent/form/tool-form/retrieval-form/index.tsx
@ -8,6 +8,7 @@ import { TopNFormField } from '@/components/top-n-item';
 import { Form } from '@/components/ui/form';
 import { UseKnowledgeGraphFormField } from '@/components/use-knowledge-graph-item';
 import { zodResolver } from '@hookform/resolvers/zod';
+import { t } from 'i18next';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
 import { DescriptionField } from '../../components/description-field';
@ -41,7 +42,7 @@ const RetrievalForm = () => {
          <DescriptionField></DescriptionField>
          <KnowledgeBaseFormField showVariable></KnowledgeBaseFormField>
        </FormContainer>
-        <Collapse title={<div>Advanced Settings</div>}>
+        <Collapse title={<div>{t('flow.advancedSettings')}</div>}>
          <FormContainer>
            <SimilaritySliderFormField
              vectorSimilarityWeightName="keywords_similarity_weight"
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Yongteng Lei	2d89863fdd	Fix: search list permission (#9767 ) ### What problem does this PR solve? Search list permission. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-27 18:50:02 +08:00
Yongteng Lei	6cb3e08381	Revert: broken agent completion by #9631 (#9760 ) ### What problem does this PR solve? Revert broken agent completion by #9631. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-27 17:16:55 +08:00
Liu An	986b9cbb1a	Docs: Update version references to v0.20.4 in READMEs and docs (#9758 ) ### What problem does this PR solve? - Update version tags in README files (including translations) from v0.20.3 to v0.20.4 - 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	2025-08-27 16:56:55 +08:00
writinwaters	9c456adffd	Added v0.20.4 release notes (#9757 ) ### What problem does this PR solve? ### Type of change - [x] Documentation Update	2025-08-27 15:29:09 +08:00
YyBoom	c15b138839	Create ecommerce_customer_service_workflow.json (#9755 ) ### What problem does this PR solve? Update workflow template. ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-08-27 15:15:24 +08:00
chanx	ff11348f7c	Fix: Optimize the MultiSelect component and system prompt templates #3221 (#9752 ) ### What problem does this PR solve? Fix: Optimize the MultiSelect component and system prompt templates #3221 - Modify the conditional statements in the MultiSelect component, using the ?. operator to improve code readability - Optimize the formatting of the system prompt template to make it more standardized and easier to read - Update the Chinese translation, changing "ExeSQL" to "Execute SQL" ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>	2025-08-27 15:12:12 +08:00
balibabu	cbdabbb58f	Fix: Fixed the issue that the agent embedded page needs to be logged in #9750 (#9751 ) ### What problem does this PR solve? Fix: Fixed the issue that the agent embedded page needs to be logged in #9750 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-27 14:18:00 +08:00
pingguoCooler	cf0011be67	Feat: Upgrade html parser (#9675 ) ### What problem does this PR solve? parse more html content. ### Type of change - [x] Other (please describe):	2025-08-27 12:43:55 +08:00
chanx	1f47001c82	Fix: Optimize tooltips and I118n #3221 (#9744 ) ### What problem does this PR solve? Fix: Optimize tooltips and I118n #3221 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>	2025-08-27 11:46:51 +08:00
Kevin Hu	a914535344	Fix: add `mode` for embeded agent. (#9741 ) ### What problem does this PR solve? ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-27 11:46:15 +08:00
writinwaters	ba1063c2b9	Docs: Miscellaneous updates (#9729 ) ### What problem does this PR solve? ### Type of change - [x] Documentation Update	2025-08-26 19:35:29 +08:00
chanx	2b4bca4447	Fix(i18n): Added new translations #3221 (#9727 ) ### What problem does this PR solve? Fix(i18n): Added new translations #3221 - Added and updated internationalization translations in multiple components ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>	2025-08-26 17:57:53 +08:00
balibabu	11cf6ae313	Fix: After deleting the knowledge graph, jump to the dataset page #9722 (#9723 ) ### What problem does this PR solve? Fix: After deleting the knowledge graph, jump to the dataset page #9722 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-26 17:57:41 +08:00
balibabu	88db5d90d1	Fix: Try to fix the issue of not being able to log in through Oauth2 #9601 (#9717 ) ### What problem does this PR solve? Fix: Try to fix the issue of not being able to log in through Oauth2 #9601 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-26 14:06:28 +08:00
Yongteng Lei	209ef09dc3	Feat: add Zhipu GLM-4.5 model series (#9715 ) ### What problem does this PR solve? Add Zhipu GLM-4.5 model series. #9708. ### Type of change - [x] New Feature (non-breaking change which adds functionality) Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>	2025-08-26 13:48:00 +08:00
ycz	370c8bc25b	Update llm_factories.json (#9714 ) ### What problem does this PR solve? add ZhipuAI GLM-4.5 model series ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-08-26 11:49:01 +08:00
chanx	e90a959b4d	Fix: Chunk error when re-parsing created file #9665 (#9711 ) ### What problem does this PR solve? Fix: Chunk error when re-parsing created file ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>	2025-08-26 10:50:30 +08:00
Stephen Hu	ca320a8c30	Refactor: for total_token_count method use if to check first. (#9707 ) ### What problem does this PR solve? for total_token_count method use if to check first, to improve the performance when we need to handle exception cases ### Type of change - [x] Refactoring	2025-08-26 10:47:20 +08:00
chanx	ae505e6165	Fix: Optimize table style #3221 (#9703 ) ### What problem does this PR solve? Fix: Optimize table style -Modify the style of the table scrollbar and remove unnecessary scrollbars -Adjust the header style of the table, add background color and hierarchy -Optimize the style of datasets and file tables -Add a new background color variable ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-26 10:46:54 +08:00
balibabu	63b5c2292d	Fix: Delete the uploaded file in the chat input box, the corresponding file ID is not deleted #9701 (#9702 ) ### What problem does this PR solve? Fix: Delete the uploaded file in the chat input box, the corresponding file ID is not deleted #9701 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-26 09:27:49 +08:00
Kevin Hu	8d8a5f73b6	Fix: meta data filter with AND logic operations. (#9687 ) ### What problem does this PR solve? Close #9648 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 18:29:24 +08:00
Liu An	d0fa66f4d5	Docs: update API endpoint paths (#9683 ) ### What problem does this PR solve? - Update API endpoint paths in docs from `/v1/` to `/api/v1/` for consistency ### Type of change - [x] Documentation Update	2025-08-25 17:57:24 +08:00
Mckennasora	9dd22e141b	fix: validate chunk type before processing to prevent AttributeError (#9698 ) ### What problem does this PR solve? This PR fixes a critical bug in the session listing endpoint where the application crashes with an `AttributeError` when processing chunk data that contains non-dictionary objects. Error before fix: ```json { "code": 100, "data": null, "message": "AttributeError(\"'str' object has no attribute 'get'\")" } ``` Root cause: The code assumes all items in the `chunks` array are dictionary objects and directly calls the `.get()` method on them. However, in some cases, the chunks array contains string objects or other non-dictionary types, causing the application to crash when attempting to call `.get()` on a string. Solution: Added type validation to ensure each chunk is a dictionary before processing. Non-dictionary chunks are safely skipped, preventing the crash while maintaining functionality for valid chunk data. This fix improves the robustness of the session listing endpoint and ensures users can retrieve their conversation sessions without encountering server errors due to data format inconsistencies. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 17:57:01 +08:00
Yongteng Lei	b6c1ca828e	Refa: replace Chat Ollama implementation with LiteLLM (#9693 ) ### What problem does this PR solve? replace Chat Ollama implementation with LiteLLM. ### Type of change - [x] Refactoring	2025-08-25 17:56:31 +08:00
chanx	d367c7e226	Fix: Optimize dataset page layout and internationalization and default values for multi selection #3221 (#9695 ) ### What problem does this PR solve? Fix: Optimize dataset page layout and internationalization and Fix setting default values for multi selection drop-down boxes #3221 -Adjust the style and layout of each component on the dataset page -Add and update multilingual translation content ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 17:29:15 +08:00
Yongteng Lei	a3aa3f0d36	Refa: improve lightrag (#9690 ) ### What problem does this PR solve? Improve lightrag. #9647 ### Type of change - [x] Refactoring	2025-08-25 17:08:44 +08:00
天海蒼灆	7b8752fe24	fix: Create conversation sessions will lost prologue (#9666 ) ### What problem does this PR solve? When create conversation,the prologue hasn't save in conversation. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 14:09:28 +08:00
天海蒼灆	5e2c33e5b0	Fix: grow reference list (#9674 ) ### What problem does this PR solve? Fix Multiple conversations cause the reference list to grow indefinitely due to Python's mutable default argument behavior. Explicitly initialize reference as empty list when creating new sessions ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 14:08:15 +08:00
balibabu	e40be8e541	Feat: Exclude operator_permission field from renaming chat fields #3221 (#9692 ) ### What problem does this PR solve? Feat: Exclude operator_permission field from renaming chat fields #3221 ### Type of change - [x] New Feature (non-breaking change which adds functionality)	2025-08-25 14:06:06 +08:00
uciadonis	23d0b564d3	Fix: Wrap VersionDialog in DropdownProvider for proper context (#9677 ) ### What problem does this PR solve? The VersionDialog component was not receiving the correct context for dropdown handling, causing improper behavior in its interactions. This PR wraps VersionDialog in DropdownProvider to ensure it gets the proper context and functions as expected. ### Type of change - [X] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 10:18:04 +08:00
Stephen Hu	ecaa9de843	Fix:[ERROR]'LLMBundle' object has no attribute 'language' (#9682 ) ### What problem does this PR solve? https://github.com/infiniflow/ragflow/issues/9672 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 10:17:10 +08:00
Kevin Hu	2f74727bb9	Fix: meta data error. (#9670 ) ### What problem does this PR solve? ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-25 09:41:52 +08:00
balibabu	adbb038a87	Fix: Place the invitation reminder icon in a separate file #9634 (#9662 ) ### What problem does this PR solve? Fix: Place the invitation reminder icon in a separate file #9634 Fix: After receiving the agent message, pull the agent data to highlight the edges passed #9538 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-22 20:08:55 +08:00
Yongteng Lei	3947da10ae	Fix: unexpected LLM parameters (#9661 ) ### What problem does this PR solve? Remove unexpected LLM parameters. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-22 19:33:09 +08:00
chanx	4862be28ad	Fix: Search app AI summary ERROR And The tag set cannot be selected #9649 #9652 (#9664 ) ### What problem does this PR solve? Fix: Search app AI summary ERROR And The tag set cannot be selected #9649 #9652 - Search app AI summary ERROR: 'dict' object has no attribute 'split' #9649 - fix The tag set cannot be selected in the knowledge base. #9652 - Added custom parameter options to the LlmSettingFieldItems component - Adjusted the document preview height to improve page layout adaptability ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-22 19:32:32 +08:00
Yongteng Lei	035e8ed0f7	Fix: code executor timeout (#9671 ) ### What problem does this PR solve? Code executor timeout. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)	2025-08-22 19:31:49 +08:00