Refa: code format. (#9342)

### What problem does this PR solve?


### Type of change

- [x] Refactoring

.gitignore

@@ -193,3 +193,5 @@ dist
 # SvelteKit build / generate output
 .svelte-kit
 
+# Default backup dir
+backup

.trivyignore

@@ -0,0 +1,15 @@
+**/*.md
+**/*.min.js
+**/*.min.css
+**/*.svg
+**/*.png
+**/*.jpg
+**/*.jpeg
+**/*.gif
+**/*.woff
+**/*.woff2
+**/*.map
+**/*.webp
+**/*.ico
+**/*.ttf
+**/*.eot

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:v0.20.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -87,7 +87,9 @@ Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Latest Updates
 
-- 2025-08-01 Supports agentic workflow.
+- 2025-08-08 Supports OpenAI's latest GPT-5 series models.
+- 2025-08-04 Supports new models, including Kimi K2 and Grok 4.
+- 2025-08-01 Supports agentic workflow and MCP.
 - 2025-05-23 Adds a Python/JavaScript code executor component to Agent.
 - 2025-05-05 Supports cross-language query.
 - 2025-03-19 Supports using a multi-modal model to make sense of images within PDF or DOCX files.
@@ -188,7 +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 `v0.20.0-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0` for the full edition `v0.20.0`.
+   > The command below downloads the `v0.20.1-slim` edition of the RAGFlow Docker image. See the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.1-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` for the full edition `v0.20.1`.
 
    ```bash
    $ cd ragflow/docker
@@ -201,8 +203,8 @@ releases! 🌟
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    |-------------------|-----------------|-----------------------|--------------------------|
-   | v0.20.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.0-slim      | &approx;2       | ❌                   | Stable release            |
+   | v0.20.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.1-slim      | &approx;2       | ❌                   | Stable release            |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                   | _Unstable_ nightly build  |
 

README_id.md

@@ -22,7 +22,7 @@
         <img alt="Lencana Daring" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Rilis%20Terbaru" alt="Rilis Terbaru">
@@ -80,7 +80,9 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Pembaruan Terbaru
 
-- 2025-08-01 Mendukung Alur Kerja agen.
+- 2025-08-08 Mendukung model seri GPT-5 terbaru dari OpenAI.
+- 2025-08-04 Mendukung model baru, termasuk Kimi K2 dan Grok 4.
+- 2025-08-01 Mendukung alur kerja agen dan MCP.
 - 2025-05-23 Menambahkan komponen pelaksana kode Python/JS ke Agen.
 - 2025-05-05 Mendukung kueri lintas bahasa.
 - 2025-03-19 Mendukung penggunaan model multi-modal untuk memahami gambar di dalam file PDF atau DOCX.
@@ -179,7 +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 v0.20.0-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.0-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0 untuk edisi lengkap v0.20.0.
+> Perintah di bawah ini mengunduh edisi v0.20.1-slim dari gambar Docker RAGFlow. Silakan merujuk ke tabel berikut untuk deskripsi berbagai edisi RAGFlow. Untuk mengunduh edisi RAGFlow yang berbeda dari v0.20.1-slim, perbarui variabel RAGFLOW_IMAGE di docker/.env sebelum menggunakan docker compose untuk memulai server. Misalnya, atur RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1 untuk edisi lengkap v0.20.1.
 
 ```bash
 $ cd ragflow/docker
@@ -192,8 +194,8 @@ $ docker compose -f docker-compose.yml up -d
 
 | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
 | ----------------- | --------------- | --------------------- | ------------------------ |
-| v0.20.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-| v0.20.0-slim      | &approx;2       | ❌                    | Stable release           |
+| v0.20.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+| v0.20.1-slim      | &approx;2       | ❌                    | Stable release           |
 | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
 | nightly-slim      | &approx;2       | ❌                    | _Unstable_ nightly build |
 

README_ja.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -60,7 +60,9 @@
 
 ## 🔥 最新情報
 
-- 2025-08-01 エージェントワークフローをサポートします。
+- 2025-08-08 OpenAI の最新 GPT-5 シリーズモデルをサポートします。
+- 2025-08-04 新モデル、キミK2およびGrok 4をサポート。
+- 2025-08-01 エージェントワークフローとMCPをサポート。
 - 2025-05-23 エージェントに Python/JS コードエグゼキュータコンポーネントを追加しました。
 - 2025-05-05 言語間クエリをサポートしました。
 - 2025-03-19 PDFまたはDOCXファイル内の画像を理解するために、多モーダルモデルを使用することをサポートします。
@@ -158,7 +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 v0.20.0-slim エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.20.0-slim とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。例えば、完全版 v0.20.0 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0 と設定します。
+   > 以下のコマンドは、RAGFlow Docker イメージの v0.20.1-slim エディションをダウンロードします。異なる RAGFlow エディションの説明については、以下の表を参照してください。v0.20.1-slim とは異なるエディションをダウンロードするには、docker/.env ファイルの RAGFLOW_IMAGE 変数を適宜更新し、docker compose を使用してサーバーを起動してください。例えば、完全版 v0.20.1 をダウンロードするには、RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1 と設定します。
 
    ```bash
    $ cd ragflow/docker
@@ -171,8 +173,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

README_ko.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -60,7 +60,9 @@
 
 ## 🔥 업데이트
 
-- 2025-08-01 에이전트 워크플로를 지원합니다.
+- 2025-08-08 OpenAI의 최신 GPT-5 시리즈 모델을 지원합니다.
+- 2025-08-04 새로운 모델인 Kimi K2와 Grok 4를 포함하여 지원합니다.
+- 2025-08-01 에이전트 워크플로우와 MCP를 지원합니다.
 - 2025-05-23 Agent에 Python/JS 코드 실행기 구성 요소를 추가합니다.
 - 2025-05-05 언어 간 쿼리를 지원합니다.
 - 2025-03-19 PDF 또는 DOCX 파일 내의 이미지를 이해하기 위해 다중 모드 모델을 사용하는 것을 지원합니다.
@@ -158,7 +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 v0.20.0-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.20.0-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.20.0을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0로 설정합니다.
+   > 아래 명령어는 RAGFlow Docker 이미지의 v0.20.1-slim 버전을 다운로드합니다. 다양한 RAGFlow 버전에 대한 설명은 다음 표를 참조하십시오. v0.20.1-slim과 다른 RAGFlow 버전을 다운로드하려면, docker/.env 파일에서 RAGFLOW_IMAGE 변수를 적절히 업데이트한 후 docker compose를 사용하여 서버를 시작하십시오. 예를 들어, 전체 버전인 v0.20.1을 다운로드하려면 RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1로 설정합니다.
 
    ```bash
    $ cd ragflow/docker
@@ -171,8 +173,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

README_pt_br.md

@@ -22,7 +22,7 @@
         <img alt="Badge Estático" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Última%20Relese" alt="Última Versão">
@@ -80,7 +80,9 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
 
 ## 🔥 Últimas Atualizações
 
-- 01-08-2025 Suporta o fluxo de trabalho agêntico.
+- 08-08-2025 Suporta a mais recente série GPT-5 da OpenAI.
+- 04-08-2025 Suporta novos modelos, incluindo Kimi K2 e Grok 4.
+- 01-08-2025 Suporta fluxo de trabalho agente e MCP.
 - 23-05-2025 Adicione o componente executor de código Python/JS ao Agente.
 - 05-05-2025 Suporte a consultas entre idiomas.
 - 19-03-2025 Suporta o uso de um modelo multi-modal para entender imagens dentro de arquivos PDF ou DOCX.
@@ -178,7 +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 `v0.20.0-slim` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.20.0-slim`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor. Por exemplo: defina `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0` para a edição completa `v0.20.0`.
+    > O comando abaixo baixa a edição `v0.20.1-slim` da imagem Docker do RAGFlow. Consulte a tabela a seguir para descrições de diferentes edições do RAGFlow. Para baixar uma edição do RAGFlow diferente da `v0.20.1-slim`, atualize a variável `RAGFLOW_IMAGE` conforme necessário no **docker/.env** antes de usar `docker compose` para iniciar o servidor. Por exemplo: defina `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` para a edição completa `v0.20.1`.
 
     ```bash
     $ cd ragflow/docker
@@ -191,8 +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?                 |
     | --------------------- | ---------------------- | ------------------------------- | ------------------------ |
-    | v0.20.0               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
-    | v0.20.0-slim          | ~2                     | ❌                              | Lançamento estável       |
+    | v0.20.1               | ~9                     | :heavy_check_mark:              | Lançamento estável       |
+    | v0.20.1-slim          | ~2                     | ❌                              | Lançamento estável       |
     | nightly               | ~9                     | :heavy_check_mark:              | _Instável_ build noturno |
     | nightly-slim          | ~2                     | ❌                               | _Instável_ build noturno |
 

README_tzh.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -83,7 +83,9 @@
 
 ## 🔥 近期更新
 
-- 2025-08-01 支援 agentic workflow
+- 2025-08-08 支援 OpenAI 最新的 GPT-5 系列模型。
+- 2025-08-04 支援 Kimi K2 和 Grok 4 等模型.
+- 2025-08-01 支援 agentic workflow 和 MCP
 - 2025-05-23 為 Agent 新增 Python/JS 程式碼執行器元件。
 - 2025-05-05 支援跨語言查詢。
 - 2025-03-19 PDF和DOCX中的圖支持用多模態大模型去解析得到描述.
@@ -181,7 +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 `v0.20.0-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.20.0-slim` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。例如，你可以透過設定 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0` 來下載 RAGFlow 鏡像的 `v0.20.0` 完整發行版。
+   > 執行以下指令會自動下載 RAGFlow slim Docker 映像 `v0.20.1-slim`。請參考下表查看不同 Docker 發行版的說明。如需下載不同於 `v0.20.1-slim` 的 Docker 映像，請在執行 `docker compose` 啟動服務之前先更新 **docker/.env** 檔案內的 `RAGFLOW_IMAGE` 變數。例如，你可以透過設定 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` 來下載 RAGFlow 鏡像的 `v0.20.1` 完整發行版。
 
    ```bash
    $ cd ragflow/docker
@@ -194,8 +196,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

README_zh.md

@@ -22,7 +22,7 @@
         <img alt="Static Badge" src="https://img.shields.io/badge/Online-Demo-4e6b99">
     </a>
     <a href="https://hub.docker.com/r/infiniflow/ragflow" target="_blank">
-        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.0">
+        <img src="https://img.shields.io/docker/pulls/infiniflow/ragflow?label=Docker%20Pulls&color=0db7ed&logo=docker&logoColor=white&style=flat-square" alt="docker pull infiniflow/ragflow:v0.20.1">
     </a>
     <a href="https://github.com/infiniflow/ragflow/releases/latest">
         <img src="https://img.shields.io/github/v/release/infiniflow/ragflow?color=blue&label=Latest%20Release" alt="Latest Release">
@@ -83,7 +83,9 @@
 
 ## 🔥 近期更新
 
-- 2025-08-01 支持 agentic workflow。
+- 2025-08-08 支持 OpenAI 最新的 GPT-5 系列模型.
+- 2025-08-04 新增对 Kimi K2 和 Grok 4 等模型的支持.
+- 2025-08-01 支持 agentic workflow 和 MCP。
 - 2025-05-23 Agent 新增 Python/JS 代码执行器组件。
 - 2025-05-05 支持跨语言查询。
 - 2025-03-19 PDF 和 DOCX 中的图支持用多模态大模型去解析得到描述.
@@ -181,7 +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 `v0.20.0-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.20.0-slim` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。比如，你可以通过设置 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0` 来下载 RAGFlow 镜像的 `v0.20.0` 完整发行版。
+   > 运行以下命令会自动下载 RAGFlow slim Docker 镜像 `v0.20.1-slim`。请参考下表查看不同 Docker 发行版的描述。如需下载不同于 `v0.20.1-slim` 的 Docker 镜像，请在运行 `docker compose` 启动服务之前先更新 **docker/.env** 文件内的 `RAGFLOW_IMAGE` 变量。比如，你可以通过设置 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` 来下载 RAGFlow 镜像的 `v0.20.1` 完整发行版。
 
    ```bash
    $ cd ragflow/docker
@@ -194,8 +196,8 @@
 
    | RAGFlow image tag | Image size (GB) | Has embedding models? | Stable?                  |
    | ----------------- | --------------- | --------------------- | ------------------------ |
-   | v0.20.0           | &approx;9       | :heavy_check_mark:    | Stable release           |
-   | v0.20.0-slim      | &approx;2       | ❌                    | Stable release           |
+   | v0.20.1           | &approx;9       | :heavy_check_mark:    | Stable release           |
+   | v0.20.1-slim      | &approx;2       | ❌                    | Stable release           |
    | nightly           | &approx;9       | :heavy_check_mark:    | _Unstable_ nightly build |
    | nightly-slim      | &approx;2       | ❌                     | _Unstable_ nightly build |
 

agent/templates/customer_support.json

@@ -89,11 +89,11 @@
                             "presence_penalty": 0.4,
                             "prompts": [
                                 {
-                                    "content": "{sys.query}",
+                                    "content": "The user query is {sys.query}\n\nThe relevant document are {Retrieval:ShyPumasJoke@formalized_content}",
                                     "role": "user"
                                 }
                             ],
-                            "sys_prompt": "You are a highly professional product information advisor.  \n\nYour only mission is to provide accurate, factual, and structured answers to all product-related queries.\n\nAbsolutely no assumptions, guesses, or fabricated content are allowed. \n\n**Key Principles:**\n\n1. **Strict Database Reliance:**  \n\n   - Every answer must be based solely on the verified product information stored in the database accessed through the Retrieval tool.  \n\n   - You are NOT allowed to invent, speculate, or infer details beyond what is retrieved.  \n\n   - If you cannot find relevant data, respond with: *\"I cannot find this information in our official product database. Please check back later or provide more details for further search.\"*\n\n2. **Information Accuracy and Structure:**  \n\n   - Provide information in a clear, concise, and professional way.  \n\n   - Use bullet points or numbered lists if there are multiple key points (e.g., features, price, warranty, technical specifications).  \n\n   - Always specify the version or model number when applicable to avoid confusion.\n\n3. **Tone and Style:**  \n\n   - Maintain a polite, professional, and helpful tone at all times.  \n\n   - Avoid marketing exaggeration or promotional language; stay strictly factual.  \n\n   - Do not express personal opinions; only cite official product data.\n\n4.  **User Guidance:**  \n\n   - If the user\u2019s query is unclear or too broad, politely request clarification or guide them to provide more specific product details (e.g., product name, model, version).  \n\n   - Example: *\"Could you please specify the product model or category so I can retrieve the most relevant information for you?\"*\n\n5. **Response Length and Formatting:**  \n\n   - Keep each answer within 100\u2013150 words for general queries.  \n\n   - For complex or multi-step explanations, you may extend to 200\u2013250 words, but always remain clear and well-structured.\n\n6. **Critical Reminder:**  \n\nYour authority and reliability depend entirely on database-driven responses. Any fabricated, speculative, or unverified content will be considered a critical failure of your role.\n\nAlways begin processing a query by accessing the Retrieval tool, confirming the data source, and then structuring your response according to the above principles.\n\n",
+                            "sys_prompt": "You are a highly professional product information advisor.  \n\nYour only mission is to provide accurate, factual, and structured answers to all product-related queries.\n\nAbsolutely no assumptions, guesses, or fabricated content are allowed. \n\n**Key Principles:**\n\n1. **Strict Database Reliance:**  \n\n   - Every answer must be based solely on the verified product information stored in the relevant documen.\n\n   - You are NOT allowed to invent, speculate, or infer details beyond what is retrieved.  \n\n   - If you cannot find relevant data, respond with: *\"I cannot find this information in our official product database. Please check back later or provide more details for further search.\"*\n\n2. **Information Accuracy and Structure:**  \n\n   - Provide information in a clear, concise, and professional way.  \n\n   - Use bullet points or numbered lists if there are multiple key points (e.g., features, price, warranty, technical specifications).  \n\n   - Always specify the version or model number when applicable to avoid confusion.\n\n3. **Tone and Style:**  \n\n   - Maintain a polite, professional, and helpful tone at all times.  \n\n   - Avoid marketing exaggeration or promotional language; stay strictly factual.  \n\n   - Do not express personal opinions; only cite official product data.\n\n4.  **User Guidance:**  \n\n   - If the user\u2019s query is unclear or too broad, politely request clarification or guide them to provide more specific product details (e.g., product name, model, version).  \n\n   - Example: *\"Could you please specify the product model or category so I can retrieve the most relevant information for you?\"*\n\n5. **Response Length and Formatting:**  \n\n   - Keep each answer within 100\u2013150 words for general queries.  \n\n   - For complex or multi-step explanations, you may extend to 200\u2013250 words, but always remain clear and well-structured.\n\n6. **Critical Reminder:**  \n\nYour authority and reliability depend entirely on the relevant document responses. Any fabricated, speculative, or unverified content will be considered a critical failure of your role.\n\n\n",
                             "temperature": 0.1,
                             "temperatureEnabled": true,
                             "tools": [],
@@ -699,7 +699,7 @@
                             "width": 200
                         },
                         "position": {
-                            "x": 644.5771854408022,
+                            "x": 645.6873721057459,
                             "y": 516.6923702571407
                         },
                         "selected": false,
@@ -735,11 +735,11 @@
                                 "presence_penalty": 0.4,
                                 "prompts": [
                                     {
-                                        "content": "{sys.query}",
+                                        "content": "The user query is {sys.query}\n\nThe relevant document are {Retrieval:ShyPumasJoke@formalized_content}",
                                         "role": "user"
                                     }
                                 ],
-                                "sys_prompt": "You are a highly professional product information advisor.  \n\nYour only mission is to provide accurate, factual, and structured answers to all product-related queries.\n\nAbsolutely no assumptions, guesses, or fabricated content are allowed. \n\n**Key Principles:**\n\n1. **Strict Database Reliance:**  \n\n   - Every answer must be based solely on the verified product information stored in the database accessed through the Retrieval tool.  \n\n   - You are NOT allowed to invent, speculate, or infer details beyond what is retrieved.  \n\n   - If you cannot find relevant data, respond with: *\"I cannot find this information in our official product database. Please check back later or provide more details for further search.\"*\n\n2. **Information Accuracy and Structure:**  \n\n   - Provide information in a clear, concise, and professional way.  \n\n   - Use bullet points or numbered lists if there are multiple key points (e.g., features, price, warranty, technical specifications).  \n\n   - Always specify the version or model number when applicable to avoid confusion.\n\n3. **Tone and Style:**  \n\n   - Maintain a polite, professional, and helpful tone at all times.  \n\n   - Avoid marketing exaggeration or promotional language; stay strictly factual.  \n\n   - Do not express personal opinions; only cite official product data.\n\n4.  **User Guidance:**  \n\n   - If the user\u2019s query is unclear or too broad, politely request clarification or guide them to provide more specific product details (e.g., product name, model, version).  \n\n   - Example: *\"Could you please specify the product model or category so I can retrieve the most relevant information for you?\"*\n\n5. **Response Length and Formatting:**  \n\n   - Keep each answer within 100\u2013150 words for general queries.  \n\n   - For complex or multi-step explanations, you may extend to 200\u2013250 words, but always remain clear and well-structured.\n\n6. **Critical Reminder:**  \n\nYour authority and reliability depend entirely on database-driven responses. Any fabricated, speculative, or unverified content will be considered a critical failure of your role.\n\nAlways begin processing a query by accessing the Retrieval tool, confirming the data source, and then structuring your response according to the above principles.\n\n",
+                                "sys_prompt": "You are a highly professional product information advisor.  \n\nYour only mission is to provide accurate, factual, and structured answers to all product-related queries.\n\nAbsolutely no assumptions, guesses, or fabricated content are allowed. \n\n**Key Principles:**\n\n1. **Strict Database Reliance:**  \n\n   - Every answer must be based solely on the verified product information stored in the relevant documen.\n\n   - You are NOT allowed to invent, speculate, or infer details beyond what is retrieved.  \n\n   - If you cannot find relevant data, respond with: *\"I cannot find this information in our official product database. Please check back later or provide more details for further search.\"*\n\n2. **Information Accuracy and Structure:**  \n\n   - Provide information in a clear, concise, and professional way.  \n\n   - Use bullet points or numbered lists if there are multiple key points (e.g., features, price, warranty, technical specifications).  \n\n   - Always specify the version or model number when applicable to avoid confusion.\n\n3. **Tone and Style:**  \n\n   - Maintain a polite, professional, and helpful tone at all times.  \n\n   - Avoid marketing exaggeration or promotional language; stay strictly factual.  \n\n   - Do not express personal opinions; only cite official product data.\n\n4.  **User Guidance:**  \n\n   - If the user\u2019s query is unclear or too broad, politely request clarification or guide them to provide more specific product details (e.g., product name, model, version).  \n\n   - Example: *\"Could you please specify the product model or category so I can retrieve the most relevant information for you?\"*\n\n5. **Response Length and Formatting:**  \n\n   - Keep each answer within 100\u2013150 words for general queries.  \n\n   - For complex or multi-step explanations, you may extend to 200\u2013250 words, but always remain clear and well-structured.\n\n6. **Critical Reminder:**  \n\nYour authority and reliability depend entirely on the relevant document responses. Any fabricated, speculative, or unverified content will be considered a critical failure of your role.\n\n\n",
                                 "temperature": 0.1,
                                 "temperatureEnabled": true,
                                 "tools": [],

agent/templates/cv_evaluation.json

@@ -170,7 +170,7 @@
                             "presence_penalty": 0.5,
                             "prompts": [
                                 {
-                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}",
+                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
                                     "role": "user"
                                 }
                             ],
@@ -250,7 +250,7 @@
                             "presence_penalty": 0.5,
                             "prompts": [
                                 {
-                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
+                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
                                     "role": "user"
                                 }
                             ],
@@ -602,7 +602,7 @@
                                 "presence_penalty": 0.5,
                                 "prompts": [
                                     {
-                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}",
+                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
                                         "role": "user"
                                     }
                                 ],
@@ -715,7 +715,7 @@
                                 "presence_penalty": 0.5,
                                 "prompts": [
                                     {
-                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
+                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
                                         "role": "user"
                                     }
                                 ],

agent/templates/market_generate_seo_blog.json

@@ -169,7 +169,7 @@
                             "presence_penalty": 0.5,
                             "prompts": [
                                 {
-                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}",
+                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
                                     "role": "user"
                                 }
                             ],
@@ -249,7 +249,7 @@
                             "presence_penalty": 0.5,
                             "prompts": [
                                 {
-                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
+                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
                                     "role": "user"
                                 }
                             ],
@@ -601,7 +601,7 @@
                                 "presence_penalty": 0.5,
                                 "prompts": [
                                     {
-                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}",
+                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
                                         "role": "user"
                                     }
                                 ],
@@ -714,7 +714,7 @@
                                 "presence_penalty": 0.5,
                                 "prompts": [
                                     {
-                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
+                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
                                         "role": "user"
                                     }
                                 ],
@@ -912,4 +912,4 @@
             "retrieval": []
         },
     "avatar": "data:image/jpeg;base64,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"
-}
+}

agent/templates/seo_blog.json

@@ -169,7 +169,7 @@
                             "presence_penalty": 0.5,
                             "prompts": [
                                 {
-                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}",
+                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
                                     "role": "user"
                                 }
                             ],
@@ -249,7 +249,7 @@
                             "presence_penalty": 0.5,
                             "prompts": [
                                 {
-                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
+                                    "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
                                     "role": "user"
                                 }
                             ],
@@ -601,7 +601,7 @@
                                 "presence_penalty": 0.5,
                                 "prompts": [
                                     {
-                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}",
+                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
                                         "role": "user"
                                     }
                                 ],
@@ -714,7 +714,7 @@
                                 "presence_penalty": 0.5,
                                 "prompts": [
                                     {
-                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Ouline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
+                                        "content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
                                         "role": "user"
                                     }
                                 ],
@@ -912,4 +912,4 @@
             "retrieval": []
         },
     "avatar": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/4gHYSUNDX1BST0ZJTEUAAQEAAAHIAAAAAAQwAABtbnRyUkdCIFhZWiAH4AABAAEAAAAAAABhY3NwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAA9tYAAQAAAADTLQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlkZXNjAAAA8AAAACRyWFlaAAABFAAAABRnWFlaAAABKAAAABRiWFlaAAABPAAAABR3dHB0AAABUAAAABRyVFJDAAABZAAAAChnVFJDAAABZAAAAChiVFJDAAABZAAAAChjcHJ0AAABjAAAADxtbHVjAAAAAAAAAAEAAAAMZW5VUwAAAAgAAAAcAHMAUgBHAEJYWVogAAAAAAAAb6IAADj1AAADkFhZWiAAAAAAAABimQAAt4UAABjaWFlaIAAAAAAAACSgAAAPhAAAts9YWVogAAAAAAAA9tYAAQAAAADTLXBhcmEAAAAAAAQAAAACZmYAAPKnAAANWQAAE9AAAApbAAAAAAAAAABtbHVjAAAAAAAAAAEAAAAMZW5VUwAAACAAAAAcAEcAbwBvAGcAbABlACAASQBuAGMALgAgADIAMAAxADb/2wBDAAEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/2wBDAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/wAARCAAwADADASIAAhEBAxEB/8QAGQAAAwEBAQAAAAAAAAAAAAAABgkKBwUI/8QAMBAAAAYCAQIEBQQCAwAAAAAAAQIDBAUGBxEhCAkAEjFBFFFhcaETFiKRFyOx8PH/xAAaAQACAwEBAAAAAAAAAAAAAAACAwABBgQF/8QALBEAAgIBAgUCBAcAAAAAAAAAAQIDBBEFEgATITFRIkEGIzJhFBUWgaGx8P/aAAwDAQACEQMRAD8AfF2hez9089t7pvxgQMa1Gb6qZ6oQE9m/NEvCIStyPfJSOF/M1epzMugo/qtMqbiRc1mJjoJKCLMNIxKcsLJedfO1Ct9cI63x9fx6CA/19t+oh4LFA5HfuAgP/A8eOIsnsTBrkBHXA7+v53+Q+ficTgJft9gIgA+/P9/1r342O/YA8A8k3/if+IbAN7+2/f8AAiI6H19PGoPyESTMZQPKUAHkQEN+3r9dh78/YPGUTk2wb/qAZZIugH1OHH5DjkdfbnWw2DsOxPj+xjrnx2H39unBopJGBn9s+PHv1HXjPJtH+J+B40O9a16h/wB/92j/ALrPa/wR104UyAobHlXhuo2HrEtK4qy3CwjKOuJLRHJLSkXWrFKs/gVrJVrE8TUiH8bPrP20UEu8m4hNpMJJuTOfnbUw/kUqyZgMHGjAO9+mtDsQ53sdcB6eMhnpEjhNQxRKICAgHy5+/roOdjr7c+J6O4x07dx484/n7nzw1gexBGfIPkZ/3t39uGpqc6+fP5/Ht8vGFZCzJjWpWuBxvO2yPjrtclUUK7BqmUI4fuASeyhG5FzFI0Bw4aQ0iZNoDgzvRW4qtyFkI4XmwyEk2YNnDp0sVBu3IUyy5iqH8gqKERSIRNIii67hddRJs1at01Xbx2sgzZoLu10UFJR+4V1A5cxF3FqNcLvjwcno43uuLrOxZYjujaClcb4QQfxEizpFiQyM9olcueRnjC2ZMt9iY06zL0qytrMSqSOVGsfHMaGhZ3l4lSRI2MqE74zJvRTveNFWWIh3RWw+XCAM5icKQLrCH57T17FhErSlRXnWvyZXKQwWJ3eraD14p5YuZCFgacskK2oGkVuKO5GYTHzf7DaD12cBD3DgPOIDrWw9PnrXPgDkpVsUDGMG+DD6E9gHXIjrYjwUPQTCXYgHPhIV974+F6E1hpC14Yzmzj56YaQEeZhXsayD1zLPW7pygxaMf81Nzu1iJsnIuDIKnaJAkPldqrHaoORZ73tMVEbFdSXT9nVgRQgnBq6j8e/HCIEATpAnH5KlmRVkFRFJwks/bqImSXJ5VFyA3N6Ikh3bCW3YHp5cowOmCfTgA+xJCnrjtwHKcLvJj2ZGcTRFj19kEhckdzgEjKnABGSSzdc1Fe5byXXGNjKdvRcw5NxvLidNZFFCxUa62KrzMaChw8hhYScFJtROAgmuLByq1MsgkZYPaVVuDe0wraRaqAdJwgRQo+YR8xTlAQNx6b49w41vXiJpCalLh1jZhyrTqRM4+jstdRmYryNkydLQRWg1LNGcWd5jIFFvCythlIySa0mNu74sKRQtaWsTmupqPItw0lE52ufpyYzrSkx6cw5bLmBEpkTsz+dt8P5QFuCRtAIkBH9MuwKHICIaDQhnojMs9mKaeGcrMxXlQtAYkdVljimRrE5MqI4zL8oSqQ6wxjodBqK05qdK3Vo3aCSVkBW7bjuC1NFJJBPaqyx6fp6pWkliYLXK2XrukkRu2CCVoSWMgsdMyySKwoLFcIGWSTUMg4IBgTcICoBhRcplMcpFkhIqQp1ClMBTmA0Zfe1zpjvHfXff65bZlzXpB3jjGTgiirmPjAfs16PHqHeQ75Wbj3xxZpOEkV3LRJJSPdomUBZISJLncV2k+8D07dxXp7xsYuTapA9UkJUYWIzNhadnWEZeCXGLQQiJi1ViHfhHL2unWh+mlORsrW0JFpEFnGVfm1mU4kq0FY3eD6corJncv6dr5NLSMNXVaTUksjTiMnaq8uFfSVuDyiJ1iZpy0LOJtpa3YfkcQ5fdozyxI2m5qqcrHN61YYmHsh6v3o9ParYmYJEtlhIx6+gUbjgD23M6oqg92YL0JyF6Bps+qDValVA9h9Lj5SZI3SHXdEQlj1wiQtLLIe6pGzjO3BlBkK1hxpblLVH5wdW0BcFKf/JwRtjsot2z8omaSdxbzzk1iEjsE0AM9rrRZNRIrVyo7dGO6E+oh8axLlJ5H5VaJKx7ePRGFbW6vUeFfHQIWPTI9Tm7HHfuhqY7E6C7JFqUzM6iZXIoncNxX7+bIVdJnTT48x3OQU1krIDW3UeixVhyISzYz6cadY5Xph6TseRNTRsTElzzBn9Vlly0TAERsdgnMYyLROjyFbg5R4ZlsGaMT4yNi2Zlq1GwjZB3jq0PsaJfA3t0jL0W0Y9xf1V41lpWckXMLaZiwxuKYPqc6LlHdkeRF+Qxswx5ASDqBVrsL+2A/N6SiCbYymV2BywJiMZj3GRRMTnL+lVyHCll3R7Szv0vqXMtQ74T+HijljIScLaEpkKCB3rqMBIi0jPs5JeOKTZMZEi5VVnouzy0k3jXjWSMlY6UcVGDxlKMVDqx91SILWSi3D2KdgYy3kP8E9X/AE1SnRXBNdNRMlefT6g7aY6giK+cPLGNg0bY68rcnpsNh9PqIBve/EcPQ3WIq2dR93xpSgk5SAZ9R6MLAOZFUkpLSUDXp6/KPpGUkmTdswlnKnwbl5ITMdGwcXJi7LKsqzUmT5tWYmkXuF9wjBvb76b7dHheazJ9RElUJOCxViuMlUJC0Gtz6PKyjLBY4qMWUe12r1xZ6lOyT6XPEBKN2CkTDOlZd02TBdTMt7Upx2knrkdCv1UKjDKn1A7XBYH6SCOOrWn5Oi/DtRiu+GleRthDL8rXdVjZlcfWrSIxVlGGGCOnH//Z"
-}
+}

agent/templates/sql_assistant.json

@@ -0,0 +1,724 @@
+{
+    "id": 17,
+    "title": "SQL Assistant",
+    "description": "SQL Assistant is an AI-powered tool that lets business users turn plain-English questions into fully formed SQL queries. Simply type your question (e.g., “Show me last quarter’s top 10 products by revenue”) and SQL Assistant generates the exact SQL, runs it against your database, and returns the results in seconds. ",
+    "canvas_type": "Marketing",
+    "dsl": {
+            "components": {
+                "Agent:WickedGoatsDivide": {
+                    "downstream": [
+                        "ExeSQL:TiredShirtsPull"
+                    ],
+                    "obj": {
+                        "component_name": "Agent",
+                        "params": {
+                            "delay_after_error": 1,
+                            "description": "",
+                            "exception_default_value": "",
+                            "exception_goto": [],
+                            "exception_method": "",
+                            "frequencyPenaltyEnabled": false,
+                            "frequency_penalty": 0.7,
+                            "llm_id": "qwen-max@Tongyi-Qianwen",
+                            "maxTokensEnabled": false,
+                            "max_retries": 3,
+                            "max_rounds": 5,
+                            "max_tokens": 256,
+                            "mcp": [],
+                            "message_history_window_size": 12,
+                            "outputs": {
+                                "content": {
+                                    "type": "string",
+                                    "value": ""
+                                }
+                            },
+                            "presencePenaltyEnabled": false,
+                            "presence_penalty": 0.4,
+                            "prompts": [
+                                {
+                                    "content": "User's query: {sys.query}\n\nSchema: {Retrieval:HappyTiesFilm@formalized_content}\n\nSamples about question to SQL: {Retrieval:SmartNewsHammer@formalized_content}\n\nDescription about meanings of tables and files: {Retrieval:SweetDancersAppear@formalized_content}",
+                                    "role": "user"
+                                }
+                            ],
+                            "sys_prompt": "### ROLE\nYou are a Text-to-SQL assistant.  \nGiven a relational database schema and a natural-language request, you must produce a **single, syntactically-correct MySQL query** that answers the request.  \nReturn **nothing except the SQL statement itself**\u2014no code fences, no commentary, no explanations, no comments, no trailing semicolon if not required.\n\n\n###  EXAMPLES  \n-- Example 1  \nUser: List every product name and its unit price.  \nSQL:\nSELECT name, unit_price FROM Products;\n\n-- Example 2  \nUser: Show the names and emails of customers who placed orders in January 2025.  \nSQL:\nSELECT DISTINCT c.name, c.email\nFROM Customers c\nJOIN Orders o ON o.customer_id = c.id\nWHERE o.order_date BETWEEN '2025-01-01' AND '2025-01-31';\n\n-- Example 3  \nUser: How many orders have a status of \"Completed\" for each month in 2024?  \nSQL:\nSELECT DATE_FORMAT(order_date, '%Y-%m') AS month,\n       COUNT(*) AS completed_orders\nFROM Orders\nWHERE status = 'Completed'\n  AND YEAR(order_date) = 2024\nGROUP BY month\nORDER BY month;\n\n-- Example 4  \nUser: Which products generated at least \\$10 000 in total revenue?  \nSQL:\nSELECT p.id, p.name, SUM(oi.quantity * oi.unit_price) AS revenue\nFROM Products p\nJOIN OrderItems oi ON oi.product_id = p.id\nGROUP BY p.id, p.name\nHAVING revenue >= 10000\nORDER BY revenue DESC;\n\n\n### OUTPUT GUIDELINES\n1. Think through the schema and the request.  \n2. Write **only** the final MySQL query.  \n3. Do **not** wrap the query in back-ticks or markdown fences.  \n4. Do **not** add explanations, comments, or additional text\u2014just the SQL.",
+                            "temperature": 0.1,
+                            "temperatureEnabled": false,
+                            "tools": [],
+                            "topPEnabled": false,
+                            "top_p": 0.3,
+                            "user_prompt": "",
+                            "visual_files_var": ""
+                        }
+                    },
+                    "upstream": [
+                        "Retrieval:HappyTiesFilm",
+                        "Retrieval:SmartNewsHammer",
+                        "Retrieval:SweetDancersAppear"
+                    ]
+                },
+                "ExeSQL:TiredShirtsPull": {
+                    "downstream": [
+                        "Message:ShaggyMasksAttend"
+                    ],
+                    "obj": {
+                        "component_name": "ExeSQL",
+                        "params": {
+                            "database": "",
+                            "db_type": "mysql",
+                            "host": "",
+                            "max_records": 1024,
+                            "outputs": {
+                                "formalized_content": {
+                                    "type": "string",
+                                    "value": ""
+                                },
+                                "json": {
+                                    "type": "Array<Object>",
+                                    "value": []
+                                }
+                            },
+                            "password": "20010812Yy!",
+                            "port": 3306,
+                            "sql": "Agent:WickedGoatsDivide@content",
+                            "username": "13637682833@163.com"
+                        }
+                    },
+                    "upstream": [
+                        "Agent:WickedGoatsDivide"
+                    ]
+                },
+                "Message:ShaggyMasksAttend": {
+                    "downstream": [],
+                    "obj": {
+                        "component_name": "Message",
+                        "params": {
+                            "content": [
+                                "{ExeSQL:TiredShirtsPull@formalized_content}"
+                            ]
+                        }
+                    },
+                    "upstream": [
+                        "ExeSQL:TiredShirtsPull"
+                    ]
+                },
+                "Retrieval:HappyTiesFilm": {
+                    "downstream": [
+                        "Agent:WickedGoatsDivide"
+                    ],
+                    "obj": {
+                        "component_name": "Retrieval",
+                        "params": {
+                            "cross_languages": [],
+                            "empty_response": "",
+                            "kb_ids": [
+                                "ed31364c727211f0bdb2bafe6e7908e6"
+                            ],
+                            "keywords_similarity_weight": 0.7,
+                            "outputs": {
+                                "formalized_content": {
+                                    "type": "string",
+                                    "value": ""
+                                }
+                            },
+                            "query": "sys.query",
+                            "rerank_id": "",
+                            "similarity_threshold": 0.2,
+                            "top_k": 1024,
+                            "top_n": 8,
+                            "use_kg": false
+                        }
+                    },
+                    "upstream": [
+                        "begin"
+                    ]
+                },
+                "Retrieval:SmartNewsHammer": {
+                    "downstream": [
+                        "Agent:WickedGoatsDivide"
+                    ],
+                    "obj": {
+                        "component_name": "Retrieval",
+                        "params": {
+                            "cross_languages": [],
+                            "empty_response": "",
+                            "kb_ids": [
+                                "0f968106727311f08357bafe6e7908e6"
+                            ],
+                            "keywords_similarity_weight": 0.7,
+                            "outputs": {
+                                "formalized_content": {
+                                    "type": "string",
+                                    "value": ""
+                                }
+                            },
+                            "query": "sys.query",
+                            "rerank_id": "",
+                            "similarity_threshold": 0.2,
+                            "top_k": 1024,
+                            "top_n": 8,
+                            "use_kg": false
+                        }
+                    },
+                    "upstream": [
+                        "begin"
+                    ]
+                },
+                "Retrieval:SweetDancersAppear": {
+                    "downstream": [
+                        "Agent:WickedGoatsDivide"
+                    ],
+                    "obj": {
+                        "component_name": "Retrieval",
+                        "params": {
+                            "cross_languages": [],
+                            "empty_response": "",
+                            "kb_ids": [
+                                "4ad1f9d0727311f0827dbafe6e7908e6"
+                            ],
+                            "keywords_similarity_weight": 0.7,
+                            "outputs": {
+                                "formalized_content": {
+                                    "type": "string",
+                                    "value": ""
+                                }
+                            },
+                            "query": "sys.query",
+                            "rerank_id": "",
+                            "similarity_threshold": 0.2,
+                            "top_k": 1024,
+                            "top_n": 8,
+                            "use_kg": false
+                        }
+                    },
+                    "upstream": [
+                        "begin"
+                    ]
+                },
+                "begin": {
+                    "downstream": [
+                        "Retrieval:HappyTiesFilm",
+                        "Retrieval:SmartNewsHammer",
+                        "Retrieval:SweetDancersAppear"
+                    ],
+                    "obj": {
+                        "component_name": "Begin",
+                        "params": {
+                            "enablePrologue": true,
+                            "inputs": {},
+                            "mode": "conversational",
+                            "prologue": "Hi! I'm your SQL assistant, what can I do for you?"
+                        }
+                    },
+                    "upstream": []
+                }
+            },
+            "globals": {
+                "sys.conversation_turns": 0,
+                "sys.files": [],
+                "sys.query": "",
+                "sys.user_id": ""
+            },
+            "graph": {
+                "edges": [
+                    {
+                        "data": {
+                            "isHovered": false
+                        },
+                        "id": "xy-edge__beginstart-Retrieval:HappyTiesFilmend",
+                        "source": "begin",
+                        "sourceHandle": "start",
+                        "target": "Retrieval:HappyTiesFilm",
+                        "targetHandle": "end"
+                    },
+                    {
+                        "id": "xy-edge__beginstart-Retrieval:SmartNewsHammerend",
+                        "source": "begin",
+                        "sourceHandle": "start",
+                        "target": "Retrieval:SmartNewsHammer",
+                        "targetHandle": "end"
+                    },
+                    {
+                        "data": {
+                            "isHovered": false
+                        },
+                        "id": "xy-edge__beginstart-Retrieval:SweetDancersAppearend",
+                        "source": "begin",
+                        "sourceHandle": "start",
+                        "target": "Retrieval:SweetDancersAppear",
+                        "targetHandle": "end"
+                    },
+                    {
+                        "data": {
+                            "isHovered": false
+                        },
+                        "id": "xy-edge__Retrieval:HappyTiesFilmstart-Agent:WickedGoatsDivideend",
+                        "source": "Retrieval:HappyTiesFilm",
+                        "sourceHandle": "start",
+                        "target": "Agent:WickedGoatsDivide",
+                        "targetHandle": "end"
+                    },
+                    {
+                        "data": {
+                            "isHovered": false
+                        },
+                        "id": "xy-edge__Retrieval:SmartNewsHammerstart-Agent:WickedGoatsDivideend",
+                        "markerEnd": "logo",
+                        "source": "Retrieval:SmartNewsHammer",
+                        "sourceHandle": "start",
+                        "style": {
+                            "stroke": "rgba(91, 93, 106, 1)",
+                            "strokeWidth": 1
+                        },
+                        "target": "Agent:WickedGoatsDivide",
+                        "targetHandle": "end",
+                        "type": "buttonEdge",
+                        "zIndex": 1001
+                    },
+                    {
+                        "data": {
+                            "isHovered": false
+                        },
+                        "id": "xy-edge__Retrieval:SweetDancersAppearstart-Agent:WickedGoatsDivideend",
+                        "markerEnd": "logo",
+                        "source": "Retrieval:SweetDancersAppear",
+                        "sourceHandle": "start",
+                        "style": {
+                            "stroke": "rgba(91, 93, 106, 1)",
+                            "strokeWidth": 1
+                        },
+                        "target": "Agent:WickedGoatsDivide",
+                        "targetHandle": "end",
+                        "type": "buttonEdge",
+                        "zIndex": 1001
+                    },
+                    {
+                        "data": {
+                            "isHovered": false
+                        },
+                        "id": "xy-edge__Agent:WickedGoatsDividestart-ExeSQL:TiredShirtsPullend",
+                        "source": "Agent:WickedGoatsDivide",
+                        "sourceHandle": "start",
+                        "target": "ExeSQL:TiredShirtsPull",
+                        "targetHandle": "end"
+                    },
+                    {
+                        "data": {
+                            "isHovered": false
+                        },
+                        "id": "xy-edge__ExeSQL:TiredShirtsPullstart-Message:ShaggyMasksAttendend",
+                        "source": "ExeSQL:TiredShirtsPull",
+                        "sourceHandle": "start",
+                        "target": "Message:ShaggyMasksAttend",
+                        "targetHandle": "end"
+                    }
+                ],
+                "nodes": [
+                    {
+                        "data": {
+                            "form": {
+                                "enablePrologue": true,
+                                "inputs": {},
+                                "mode": "conversational",
+                                "prologue": "Hi! I'm your SQL assistant, what can I do for you?"
+                            },
+                            "label": "Begin",
+                            "name": "begin"
+                        },
+                        "id": "begin",
+                        "measured": {
+                            "height": 48,
+                            "width": 200
+                        },
+                        "position": {
+                            "x": 50,
+                            "y": 200
+                        },
+                        "selected": false,
+                        "sourcePosition": "left",
+                        "targetPosition": "right",
+                        "type": "beginNode"
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "cross_languages": [],
+                                "empty_response": "",
+                                "kb_ids": [
+                                    "ed31364c727211f0bdb2bafe6e7908e6"
+                                ],
+                                "keywords_similarity_weight": 0.7,
+                                "outputs": {
+                                    "formalized_content": {
+                                        "type": "string",
+                                        "value": ""
+                                    }
+                                },
+                                "query": "sys.query",
+                                "rerank_id": "",
+                                "similarity_threshold": 0.2,
+                                "top_k": 1024,
+                                "top_n": 8,
+                                "use_kg": false
+                            },
+                            "label": "Retrieval",
+                            "name": "Schema"
+                        },
+                        "dragging": false,
+                        "id": "Retrieval:HappyTiesFilm",
+                        "measured": {
+                            "height": 96,
+                            "width": 200
+                        },
+                        "position": {
+                            "x": 414,
+                            "y": 20.5
+                        },
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "retrievalNode"
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "cross_languages": [],
+                                "empty_response": "",
+                                "kb_ids": [
+                                    "0f968106727311f08357bafe6e7908e6"
+                                ],
+                                "keywords_similarity_weight": 0.7,
+                                "outputs": {
+                                    "formalized_content": {
+                                        "type": "string",
+                                        "value": ""
+                                    }
+                                },
+                                "query": "sys.query",
+                                "rerank_id": "",
+                                "similarity_threshold": 0.2,
+                                "top_k": 1024,
+                                "top_n": 8,
+                                "use_kg": false
+                            },
+                            "label": "Retrieval",
+                            "name": "Question to SQL"
+                        },
+                        "dragging": false,
+                        "id": "Retrieval:SmartNewsHammer",
+                        "measured": {
+                            "height": 96,
+                            "width": 200
+                        },
+                        "position": {
+                            "x": 406.5,
+                            "y": 175.5
+                        },
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "retrievalNode"
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "cross_languages": [],
+                                "empty_response": "",
+                                "kb_ids": [
+                                    "4ad1f9d0727311f0827dbafe6e7908e6"
+                                ],
+                                "keywords_similarity_weight": 0.7,
+                                "outputs": {
+                                    "formalized_content": {
+                                        "type": "string",
+                                        "value": ""
+                                    }
+                                },
+                                "query": "sys.query",
+                                "rerank_id": "",
+                                "similarity_threshold": 0.2,
+                                "top_k": 1024,
+                                "top_n": 8,
+                                "use_kg": false
+                            },
+                            "label": "Retrieval",
+                            "name": "Database Description"
+                        },
+                        "dragging": false,
+                        "id": "Retrieval:SweetDancersAppear",
+                        "measured": {
+                            "height": 96,
+                            "width": 200
+                        },
+                        "position": {
+                            "x": 403.5,
+                            "y": 328
+                        },
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "retrievalNode"
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "delay_after_error": 1,
+                                "description": "",
+                                "exception_default_value": "",
+                                "exception_goto": [],
+                                "exception_method": "",
+                                "frequencyPenaltyEnabled": false,
+                                "frequency_penalty": 0.7,
+                                "llm_id": "qwen-max@Tongyi-Qianwen",
+                                "maxTokensEnabled": false,
+                                "max_retries": 3,
+                                "max_rounds": 5,
+                                "max_tokens": 256,
+                                "mcp": [],
+                                "message_history_window_size": 12,
+                                "outputs": {
+                                    "content": {
+                                        "type": "string",
+                                        "value": ""
+                                    }
+                                },
+                                "presencePenaltyEnabled": false,
+                                "presence_penalty": 0.4,
+                                "prompts": [
+                                    {
+                                        "content": "User's query: {sys.query}\n\nSchema: {Retrieval:HappyTiesFilm@formalized_content}\n\nSamples about question to SQL: {Retrieval:SmartNewsHammer@formalized_content}\n\nDescription about meanings of tables and files: {Retrieval:SweetDancersAppear@formalized_content}",
+                                        "role": "user"
+                                    }
+                                ],
+                                "sys_prompt": "### ROLE\nYou are a Text-to-SQL assistant.  \nGiven a relational database schema and a natural-language request, you must produce a **single, syntactically-correct MySQL query** that answers the request.  \nReturn **nothing except the SQL statement itself**\u2014no code fences, no commentary, no explanations, no comments, no trailing semicolon if not required.\n\n\n###  EXAMPLES  \n-- Example 1  \nUser: List every product name and its unit price.  \nSQL:\nSELECT name, unit_price FROM Products;\n\n-- Example 2  \nUser: Show the names and emails of customers who placed orders in January 2025.  \nSQL:\nSELECT DISTINCT c.name, c.email\nFROM Customers c\nJOIN Orders o ON o.customer_id = c.id\nWHERE o.order_date BETWEEN '2025-01-01' AND '2025-01-31';\n\n-- Example 3  \nUser: How many orders have a status of \"Completed\" for each month in 2024?  \nSQL:\nSELECT DATE_FORMAT(order_date, '%Y-%m') AS month,\n       COUNT(*) AS completed_orders\nFROM Orders\nWHERE status = 'Completed'\n  AND YEAR(order_date) = 2024\nGROUP BY month\nORDER BY month;\n\n-- Example 4  \nUser: Which products generated at least \\$10 000 in total revenue?  \nSQL:\nSELECT p.id, p.name, SUM(oi.quantity * oi.unit_price) AS revenue\nFROM Products p\nJOIN OrderItems oi ON oi.product_id = p.id\nGROUP BY p.id, p.name\nHAVING revenue >= 10000\nORDER BY revenue DESC;\n\n\n### OUTPUT GUIDELINES\n1. Think through the schema and the request.  \n2. Write **only** the final MySQL query.  \n3. Do **not** wrap the query in back-ticks or markdown fences.  \n4. Do **not** add explanations, comments, or additional text\u2014just the SQL.",
+                                "temperature": 0.1,
+                                "temperatureEnabled": false,
+                                "tools": [],
+                                "topPEnabled": false,
+                                "top_p": 0.3,
+                                "user_prompt": "",
+                                "visual_files_var": ""
+                            },
+                            "label": "Agent",
+                            "name": "SQL Generator "
+                        },
+                        "dragging": false,
+                        "id": "Agent:WickedGoatsDivide",
+                        "measured": {
+                            "height": 84,
+                            "width": 200
+                        },
+                        "position": {
+                            "x": 981,
+                            "y": 174
+                        },
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "agentNode"
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "database": "",
+                                "db_type": "mysql",
+                                "host": "",
+                                "max_records": 1024,
+                                "outputs": {
+                                    "formalized_content": {
+                                        "type": "string",
+                                        "value": ""
+                                    },
+                                    "json": {
+                                        "type": "Array<Object>",
+                                        "value": []
+                                    }
+                                },
+                                "password": "20010812Yy!",
+                                "port": 3306,
+                                "sql": "Agent:WickedGoatsDivide@content",
+                                "username": "13637682833@163.com"
+                            },
+                            "label": "ExeSQL",
+                            "name": "ExeSQL"
+                        },
+                        "dragging": false,
+                        "id": "ExeSQL:TiredShirtsPull",
+                        "measured": {
+                            "height": 56,
+                            "width": 200
+                        },
+                        "position": {
+                            "x": 1211.5,
+                            "y": 212.5
+                        },
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "ragNode"
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "content": [
+                                    "{ExeSQL:TiredShirtsPull@formalized_content}"
+                                ]
+                            },
+                            "label": "Message",
+                            "name": "Message"
+                        },
+                        "dragging": false,
+                        "id": "Message:ShaggyMasksAttend",
+                        "measured": {
+                            "height": 56,
+                            "width": 200
+                        },
+                        "position": {
+                            "x": 1447.3125,
+                            "y": 181.5
+                        },
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "messageNode"
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "text": "Searches for relevant database creation statements.\n\nIt should label with a knowledgebase to which the schema is dumped in. You could use \" General \" as parsing method, \" 2 \" as chunk size and \" ; \"  as delimiter."
+                            },
+                            "label": "Note",
+                            "name": "Note Schema"
+                        },
+                        "dragHandle": ".note-drag-handle",
+                        "dragging": false,
+                        "height": 188,
+                        "id": "Note:ThickClubsFloat",
+                        "measured": {
+                            "height": 188,
+                            "width": 392
+                        },
+                        "position": {
+                            "x": 689,
+                            "y": -180.31251144409183
+                        },
+                        "resizing": false,
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "noteNode",
+                        "width": 392
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "text": "Searches for samples about question to SQL. \n\nYou could use \" Q&A \" as parsing method.\n\nPlease check this dataset:\nhttps://huggingface.co/datasets/InfiniFlow/text2sql"
+                            },
+                            "label": "Note",
+                            "name": "Note: Question to SQL"
+                        },
+                        "dragHandle": ".note-drag-handle",
+                        "dragging": false,
+                        "height": 154,
+                        "id": "Note:ElevenLionsJoke",
+                        "measured": {
+                            "height": 154,
+                            "width": 345
+                        },
+                        "position": {
+                            "x": 693.5,
+                            "y": 138
+                        },
+                        "resizing": false,
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "noteNode",
+                        "width": 345
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "text": "Searches for description about meanings of tables and fields.\n\nYou could use \" General \" as parsing method, \" 2 \" as chunk size and \" ### \"  as delimiter."
+                            },
+                            "label": "Note",
+                            "name": "Note: Database Description"
+                        },
+                        "dragHandle": ".note-drag-handle",
+                        "dragging": false,
+                        "height": 158,
+                        "id": "Note:ManyRosesTrade",
+                        "measured": {
+                            "height": 158,
+                            "width": 408
+                        },
+                        "position": {
+                            "x": 691.5,
+                            "y": 435.69736389555317
+                        },
+                        "resizing": false,
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "noteNode",
+                        "width": 408
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "text": "The Agent learns which tables may be available based on the responses from three knowledge bases and converts the user's input into SQL statements."
+                            },
+                            "label": "Note",
+                            "name": "Note: SQL Generator"
+                        },
+                        "dragHandle": ".note-drag-handle",
+                        "dragging": false,
+                        "height": 132,
+                        "id": "Note:RudeHousesInvite",
+                        "measured": {
+                            "height": 132,
+                            "width": 383
+                        },
+                        "position": {
+                            "x": 1106.9254833678003,
+                            "y": 290.5891036507015
+                        },
+                        "resizing": false,
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "noteNode",
+                        "width": 383
+                    },
+                    {
+                        "data": {
+                            "form": {
+                                "text": "Connect to your database to execute SQL statements."
+                            },
+                            "label": "Note",
+                            "name": "Note: SQL Executor"
+                        },
+                        "dragHandle": ".note-drag-handle",
+                        "dragging": false,
+                        "id": "Note:HungryBatsLay",
+                        "measured": {
+                            "height": 136,
+                            "width": 255
+                        },
+                        "position": {
+                            "x": 1185,
+                            "y": -30
+                        },
+                        "selected": false,
+                        "sourcePosition": "right",
+                        "targetPosition": "left",
+                        "type": "noteNode"
+                    }
+                ]
+            },
+            "history": [],
+            "messages": [],
+            "path": [],
+            "retrieval": []
+        },
+    "avatar": "data:image/jpeg;base64,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"
+}

agent/tools/retrieval.py

@@ -86,7 +86,7 @@ class Retrieval(ToolBase, ABC):
                 kb_ids.append(id)
                 continue
             kb_nm = self._canvas.get_variable_value(id)
-            e, kb = KnowledgebaseService.get_by_name(kb_nm)
+            e, kb = KnowledgebaseService.get_by_name(kb_nm, self._canvas._tenant_id)
             if not e:
                 raise Exception(f"Dataset({kb_nm}) does not exist.")
             kb_ids.append(kb.id)

agentic_reasoning/prompts.py

@@ -20,94 +20,128 @@ BEGIN_SEARCH_RESULT = "<|begin_search_result|>"
 END_SEARCH_RESULT = "<|end_search_result|>"
 MAX_SEARCH_LIMIT = 6
 
-REASON_PROMPT = (
-        "You are a reasoning assistant with the ability to perform dataset searches to help "
-        "you answer the user's question accurately. You have special tools:\n\n"
-        f"- To perform a search: write {BEGIN_SEARCH_QUERY} your query here {END_SEARCH_QUERY}.\n"
-        f"Then, the system will search and analyze relevant content, then provide you with helpful information in the format {BEGIN_SEARCH_RESULT} ...search results... {END_SEARCH_RESULT}.\n\n"
-        f"You can repeat the search process multiple times if necessary. The maximum number of search attempts is limited to {MAX_SEARCH_LIMIT}.\n\n"
-        "Once you have all the information you need, continue your reasoning.\n\n"
-        "-- Example 1 --\n" ########################################
-        "Question: \"Are both the directors of Jaws and Casino Royale from the same country?\"\n"
-        "Assistant:\n"
-        f"    {BEGIN_SEARCH_QUERY}Who is the director of Jaws?{END_SEARCH_QUERY}\n\n"
-        "User:\n"
-        f"    {BEGIN_SEARCH_RESULT}\nThe director of Jaws is Steven Spielberg...\n{END_SEARCH_RESULT}\n\n"
-        "Continues reasoning with the new information.\n"
-        "Assistant:\n"
-        f"    {BEGIN_SEARCH_QUERY}Where is Steven Spielberg from?{END_SEARCH_QUERY}\n\n"
-        "User:\n"
-        f"    {BEGIN_SEARCH_RESULT}\nSteven Allan Spielberg is an American filmmaker...\n{END_SEARCH_RESULT}\n\n"
-        "Continues reasoning with the new information...\n\n"
-        "Assistant:\n"
-        f"    {BEGIN_SEARCH_QUERY}Who is the director of Casino Royale?{END_SEARCH_QUERY}\n\n"
-        "User:\n"
-        f"    {BEGIN_SEARCH_RESULT}\nCasino Royale is a 2006 spy film directed by Martin Campbell...\n{END_SEARCH_RESULT}\n\n"
-        "Continues reasoning with the new information...\n\n"
-        "Assistant:\n"
-        f"    {BEGIN_SEARCH_QUERY}Where is Martin Campbell from?{END_SEARCH_QUERY}\n\n"
-        "User:\n"
-        f"    {BEGIN_SEARCH_RESULT}\nMartin Campbell (born 24 October 1943) is a New Zealand film and television director...\n{END_SEARCH_RESULT}\n\n"
-        "Continues reasoning with the new information...\n\n"
-        "Assistant:\nIt's enough to answer the question\n"
+REASON_PROMPT = f"""You are an advanced reasoning agent. Your goal is to answer the user's question by breaking it down into a series of verifiable steps.
 
-        "-- Example 2 --\n" #########################################
-        "Question: \"When was the founder of craigslist born?\"\n"
-        "Assistant:\n"
-        f"    {BEGIN_SEARCH_QUERY}Who was the founder of craigslist?{END_SEARCH_QUERY}\n\n"
-        "User:\n"
-        f"    {BEGIN_SEARCH_RESULT}\nCraigslist was founded by Craig Newmark...\n{END_SEARCH_RESULT}\n\n"
-        "Continues reasoning with the new information.\n"
-        "Assistant:\n"
-        f"    {BEGIN_SEARCH_QUERY} When was Craig Newmark born?{END_SEARCH_QUERY}\n\n"
-        "User:\n"
-        f"    {BEGIN_SEARCH_RESULT}\nCraig Newmark was born on December 6, 1952...\n{END_SEARCH_RESULT}\n\n"
-        "Continues reasoning with the new information...\n\n"
-        "Assistant:\nIt's enough to answer the question\n"
-        "**Remember**:\n"
-        f"- You have a dataset to search, so you just provide a proper search query.\n"
-        f"- Use {BEGIN_SEARCH_QUERY} to request a dataset search and end with {END_SEARCH_QUERY}.\n"
-        "- The language of query MUST be as the same as 'Question' or 'search result'.\n"
-        "- If no helpful information can be found, rewrite the search query to be less and precise keywords.\n"
-        "- When done searching, continue your reasoning.\n\n"
-        'Please answer the following question. You should think step by step to solve it.\n\n'
-    )
+You have access to a powerful search tool to find information.
 
-RELEVANT_EXTRACTION_PROMPT = """**Task Instruction:**
+**Your Task:**
+1.  Analyze the user's question.
+2.  If you need information, issue a search query to find a specific fact.
+3.  Review the search results.
+4.  Repeat the search process until you have all the facts needed to answer the question.
+5.  Once you have gathered sufficient information, synthesize the facts and provide the final answer directly.
 
-    You are tasked with reading and analyzing web pages based on the following inputs: **Previous Reasoning Steps**, **Current Search Query**, and **Searched Web Pages**. Your objective is to extract relevant and helpful information for **Current Search Query** from the **Searched Web Pages** and seamlessly integrate this information into the **Previous Reasoning Steps** to continue reasoning for the original question.
+**Tool Usage:**
+- To search, you MUST write your query between the special tokens: {BEGIN_SEARCH_QUERY}your query{END_SEARCH_QUERY}.
+- The system will provide results between {BEGIN_SEARCH_RESULT}search results{END_SEARCH_RESULT}.
+- You have a maximum of {MAX_SEARCH_LIMIT} search attempts.
 
-    **Guidelines:**
+---
+**Example 1: Multi-hop Question**
 
-    1. **Analyze the Searched Web Pages:**
-    - Carefully review the content of each searched web page.
-    - Identify factual information that is relevant to the **Current Search Query** and can aid in the reasoning process for the original question.
+**Question:** "Are both the directors of Jaws and Casino Royale from the same country?"
 
-    2. **Extract Relevant Information:**
-    - Select the information from the Searched Web Pages that directly contributes to advancing the **Previous Reasoning Steps**.
-    - Ensure that the extracted information is accurate and relevant.
+**Your Thought Process & Actions:**
+First, I need to identify the director of Jaws.
+{BEGIN_SEARCH_QUERY}who is the director of Jaws?{END_SEARCH_QUERY}
+[System returns search results]
+{BEGIN_SEARCH_RESULT}
+Jaws is a 1975 American thriller film directed by Steven Spielberg.
+{END_SEARCH_RESULT}
+Okay, the director of Jaws is Steven Spielberg. Now I need to find out his nationality.
+{BEGIN_SEARCH_QUERY}where is Steven Spielberg from?{END_SEARCH_QUERY}
+[System returns search results]
+{BEGIN_SEARCH_RESULT}
+Steven Allan Spielberg is an American filmmaker. Born in Cincinnati, Ohio...
+{END_SEARCH_RESULT}
+So, Steven Spielberg is from the USA. Next, I need to find the director of Casino Royale.
+{BEGIN_SEARCH_QUERY}who is the director of Casino Royale 2006?{END_SEARCH_QUERY}
+[System returns search results]
+{BEGIN_SEARCH_RESULT}
+Casino Royale is a 2006 spy film directed by Martin Campbell.
+{END_SEARCH_RESULT}
+The director of Casino Royale is Martin Campbell. Now I need his nationality.
+{BEGIN_SEARCH_QUERY}where is Martin Campbell from?{END_SEARCH_QUERY}
+[System returns search results]
+{BEGIN_SEARCH_RESULT}
+Martin Campbell (born 24 October 1943) is a New Zealand film and television director.
+{END_SEARCH_RESULT}
+I have all the information. Steven Spielberg is from the USA, and Martin Campbell is from New Zealand. They are not from the same country.
 
-    3. **Output Format:**
-    - **If the web pages provide helpful information for current search query:** Present the information beginning with `**Final Information**` as shown below.
-    - The language of query **MUST BE** as the same as 'Search Query' or 'Web Pages'.\n"
-    **Final Information**
+Final Answer: No, the directors of Jaws and Casino Royale are not from the same country. Steven Spielberg is from the USA, and Martin Campbell is from New Zealand.
 
-    [Helpful information]
+---
+**Example 2: Simple Fact Retrieval**
 
-    - **If the web pages do not provide any helpful information for current search query:** Output the following text.
+**Question:** "When was the founder of craigslist born?"
 
-    **Final Information**
+**Your Thought Process & Actions:**
+First, I need to know who founded craigslist.
+{BEGIN_SEARCH_QUERY}who founded craigslist?{END_SEARCH_QUERY}
+[System returns search results]
+{BEGIN_SEARCH_RESULT}
+Craigslist was founded in 1995 by Craig Newmark.
+{END_SEARCH_RESULT}
+The founder is Craig Newmark. Now I need his birth date.
+{BEGIN_SEARCH_QUERY}when was Craig Newmark born?{END_SEARCH_QUERY}
+[System returns search results]
+{BEGIN_SEARCH_RESULT}
+Craig Newmark was born on December 6, 1952.
+{END_SEARCH_RESULT}
+I have found the answer.
 
-    No helpful information found.
+Final Answer: The founder of craigslist, Craig Newmark, was born on December 6, 1952.
 
-    **Inputs:**
-    - **Previous Reasoning Steps:**  
-    {prev_reasoning}
+---
+**Important Rules:**
+- **One Fact at a Time:** Decompose the problem and issue one search query at a time to find a single, specific piece of information.
+- **Be Precise:** Formulate clear and precise search queries. If a search fails, rephrase it.
+- **Synthesize at the End:** Do not provide the final answer until you have completed all necessary searches.
+- **Language Consistency:** Your search queries should be in the same language as the user's question.
 
-    - **Current Search Query:**  
-    {search_query}
+Now, begin your work. Please answer the following question by thinking step-by-step.
+"""
 
-    - **Searched Web Pages:**  
-    {document}
+RELEVANT_EXTRACTION_PROMPT = """You are a highly efficient information extraction module. Your sole purpose is to extract the single most relevant piece of information from the provided `Searched Web Pages` that directly answers the `Current Search Query`.
 
-    """
+**Your Task:**
+1.  Read the `Current Search Query` to understand what specific information is needed.
+2.  Scan the `Searched Web Pages` to find the answer to that query.
+3.  Extract only the essential, factual information that answers the query. Be concise.
+
+**Context (For Your Information Only):**
+The `Previous Reasoning Steps` are provided to give you context on the overall goal, but your primary focus MUST be on answering the `Current Search Query`. Do not use information from the previous steps in your output.
+
+**Output Format:**
+Your response must follow one of two formats precisely.
+
+1.  **If a direct and relevant answer is found:**
+    - Start your response immediately with `Final Information`.
+    - Provide only the extracted fact(s). Do not add any extra conversational text.
+
+    *Example:*
+    `Current Search Query`: Where is Martin Campbell from?
+    `Searched Web Pages`: [Long article snippet about Martin Campbell's career, which includes the sentence "Martin Campbell (born 24 October 1943) is a New Zealand film and television director..."]
+    
+    *Your Output:*
+    Final Information
+    Martin Campbell is a New Zealand film and television director.
+
+2.  **If no relevant answer that directly addresses the query is found in the web pages:**
+    - Start your response immediately with `Final Information`.
+    - Write the exact phrase: `No helpful information found.`
+
+---
+**BEGIN TASK**
+
+**Inputs:**
+
+- **Previous Reasoning Steps:**
+{prev_reasoning}
+
+- **Current Search Query:**
+{search_query}
+
+- **Searched Web Pages:**
+{document}
+"""

api/apps/canvas_app.py

@@ -32,8 +32,7 @@ from api.db.services.user_service import TenantService
 from api.db.services.user_canvas_version import UserCanvasVersionService
 from api.settings import RetCode
 from api.utils import get_uuid
-from api.utils.api_utils import get_json_result, server_error_response, validate_request, get_data_error_result, \
-    get_error_data_result
+from api.utils.api_utils import get_json_result, server_error_response, validate_request, get_data_error_result
 from agent.canvas import Canvas
 from peewee import MySQLDatabase, PostgresqlDatabase
 from api.db.db_models import APIToken
@@ -62,7 +61,7 @@ def canvas_list():
 @login_required
 def rm():
     for i in request.json["canvas_ids"]:
-        if not UserCanvasService.query(user_id=current_user.id,id=i):
+        if not UserCanvasService.accessible(i, current_user.id):
             return get_json_result(
                 data=False, message='Only owner of canvas authorized for this operation.',
                 code=RetCode.OPERATING_ERROR)
@@ -86,7 +85,7 @@ def save():
         if not UserCanvasService.save(**req):
             return get_data_error_result(message="Fail to save canvas.")
     else:
-        if not UserCanvasService.query(user_id=current_user.id, id=req["id"]):
+        if not UserCanvasService.accessible(req["id"], current_user.id):
             return get_json_result(
                 data=False, message='Only owner of canvas authorized for this operation.',
                 code=RetCode.OPERATING_ERROR)
@@ -100,9 +99,9 @@ def save():
 @manager.route('/get/<canvas_id>', methods=['GET'])  # noqa: F821
 @login_required
 def get(canvas_id):
-    e, c = UserCanvasService.get_by_tenant_id(canvas_id)
-    if not e or c["user_id"] != current_user.id:
+    if not UserCanvasService.accessible(canvas_id, current_user.id):
         return get_data_error_result(message="canvas not found.")
+    e, c = UserCanvasService.get_by_tenant_id(canvas_id)
     return get_json_result(data=c)
 
 
@@ -131,14 +130,15 @@ def run():
     files = req.get("files", [])
     inputs = req.get("inputs", {})
     user_id = req.get("user_id", current_user.id)
-    e, cvs = UserCanvasService.get_by_id(req["id"])
-    if not e:
-        return get_data_error_result(message="canvas not found.")
-    if not UserCanvasService.query(user_id=current_user.id, id=req["id"]):
+    if not UserCanvasService.accessible(req["id"], current_user.id):
         return get_json_result(
             data=False, message='Only owner of canvas authorized for this operation.',
             code=RetCode.OPERATING_ERROR)
 
+    e, cvs = UserCanvasService.get_by_id(req["id"])
+    if not e:
+        return get_data_error_result(message="canvas not found.")
+
     if not isinstance(cvs.dsl, str):
         cvs.dsl = json.dumps(cvs.dsl, ensure_ascii=False)
 
@@ -172,14 +172,14 @@ def run():
 @login_required
 def reset():
     req = request.json
+    if not UserCanvasService.accessible(req["id"], current_user.id):
+        return get_json_result(
+            data=False, message='Only owner of canvas authorized for this operation.',
+            code=RetCode.OPERATING_ERROR)
     try:
         e, user_canvas = UserCanvasService.get_by_id(req["id"])
         if not e:
             return get_data_error_result(message="canvas not found.")
-        if not UserCanvasService.query(user_id=current_user.id, id=req["id"]):
-            return get_json_result(
-                data=False, message='Only owner of canvas authorized for this operation.',
-                code=RetCode.OPERATING_ERROR)
 
         canvas = Canvas(json.dumps(user_canvas.dsl), current_user.id)
         canvas.reset()
@@ -290,15 +290,12 @@ def input_form():
 @login_required
 def debug():
     req = request.json
+    if not UserCanvasService.accessible(req["id"], current_user.id):
+        return get_json_result(
+            data=False, message='Only owner of canvas authorized for this operation.',
+            code=RetCode.OPERATING_ERROR)
     try:
         e, user_canvas = UserCanvasService.get_by_id(req["id"])
-        if not e:
-            return get_data_error_result(message="canvas not found.")
-        if not UserCanvasService.query(user_id=current_user.id, id=req["id"]):
-            return get_json_result(
-                data=False, message='Only owner of canvas authorized for this operation.',
-                code=RetCode.OPERATING_ERROR)
-
         canvas = Canvas(json.dumps(user_canvas.dsl), current_user.id)
         canvas.reset()
         canvas.message_id = get_uuid()
@@ -404,6 +401,12 @@ def list_kbs():
 def setting():
     req = request.json
     req["user_id"] = current_user.id
+
+    if not UserCanvasService.accessible(req["id"], current_user.id):
+        return get_json_result(
+            data=False, message='Only owner of canvas authorized for this operation.',
+            code=RetCode.OPERATING_ERROR)
+
     e,flow = UserCanvasService.get_by_id(req["id"])
     if not e:
         return get_data_error_result(message="canvas not found.")
@@ -415,10 +418,7 @@ def setting():
         flow["permission"] = req["permission"]
     if req["avatar"]:
         flow["avatar"] = req["avatar"]
-    if not UserCanvasService.query(user_id=current_user.id, id=req["id"]):
-        return get_json_result(
-            data=False, message='Only owner of canvas authorized for this operation.',
-            code=RetCode.OPERATING_ERROR)
+
     num= UserCanvasService.update_by_id(req["id"], flow)
     return get_json_result(data=num)
 
@@ -441,8 +441,10 @@ def trace():
 @login_required
 def sessions(canvas_id):
     tenant_id = current_user.id
-    if not UserCanvasService.query(user_id=tenant_id, id=canvas_id):
-        return get_error_data_result(message=f"You don't own the agent {canvas_id}.")
+    if not UserCanvasService.accessible(canvas_id, tenant_id):
+        return get_json_result(
+            data=False, message='Only owner of canvas authorized for this operation.',
+            code=RetCode.OPERATING_ERROR)
 
     user_id = request.args.get("user_id")
     page_number = int(request.args.get("page", 1))

api/apps/conversation_app.py

@@ -66,7 +66,8 @@ def set_conversation():
         e, dia = DialogService.get_by_id(req["dialog_id"])
         if not e:
             return get_data_error_result(message="Dialog not found")
-        conv = {"id": conv_id, "dialog_id": req["dialog_id"], "name": name, "message": [{"role": "assistant", "content": dia.prompt_config["prologue"]}],"user_id": current_user.id}
+        conv = {"id": conv_id, "dialog_id": req["dialog_id"], "name": name, "message": [{"role": "assistant", "content": dia.prompt_config["prologue"]}],"user_id": current_user.id,
+                "reference":[{}],}
         ConversationService.save(**conv)
         return get_json_result(data=conv)
     except Exception as e:

api/apps/dialog_app.py

@@ -32,7 +32,8 @@ from api.utils.api_utils import get_json_result
 @login_required
 def set_dialog():
     req = request.json
-    dialog_id = req.get("dialog_id")
+    dialog_id = req.get("dialog_id", "")
+    is_create = not dialog_id
     name = req.get("name", "New Dialog")
     if not isinstance(name, str):
         return get_data_error_result(message="Dialog name must be string.")
@@ -52,15 +53,16 @@ def set_dialog():
     llm_setting = req.get("llm_setting", {})
     prompt_config = req["prompt_config"]
 
-    if not req.get("kb_ids", []) and not prompt_config.get("tavily_api_key") and "{knowledge}" in prompt_config['system']:
-        return get_data_error_result(message="Please remove `{knowledge}` in system prompt since no knowledge base/Tavily used here.")
+    if not is_create:
+        if not req.get("kb_ids", []) and not prompt_config.get("tavily_api_key") and "{knowledge}" in prompt_config['system']:
+            return get_data_error_result(message="Please remove `{knowledge}` in system prompt since no knowledge base/Tavily used here.")
 
-    for p in prompt_config["parameters"]:
-        if p["optional"]:
-            continue
-        if prompt_config["system"].find("{%s}" % p["key"]) < 0:
-            return get_data_error_result(
-                message="Parameter '{}' is not used".format(p["key"]))
+        for p in prompt_config["parameters"]:
+            if p["optional"]:
+                continue
+            if prompt_config["system"].find("{%s}" % p["key"]) < 0:
+                return get_data_error_result(
+                    message="Parameter '{}' is not used".format(p["key"]))
 
     try:
         e, tenant = TenantService.get_by_id(current_user.id)
@@ -153,6 +155,43 @@ def list_dialogs():
         return server_error_response(e)
 
 
+@manager.route('/next', methods=['POST'])  # noqa: F821
+@login_required
+def list_dialogs_next():
+    keywords = request.args.get("keywords", "")
+    page_number = int(request.args.get("page", 0))
+    items_per_page = int(request.args.get("page_size", 0))
+    parser_id = request.args.get("parser_id")
+    orderby = request.args.get("orderby", "create_time")
+    if request.args.get("desc", "true").lower() == "false":
+        desc = False
+    else:
+        desc = True
+
+    req = request.get_json()
+    owner_ids = req.get("owner_ids", [])
+    try:
+        if not owner_ids:
+            # tenants = TenantService.get_joined_tenants_by_user_id(current_user.id)
+            # tenants = [tenant["tenant_id"] for tenant in tenants]
+            tenants = [] # keep it here
+            dialogs, total = DialogService.get_by_tenant_ids(
+                tenants, current_user.id, page_number,
+                items_per_page, orderby, desc, keywords, parser_id)
+        else:
+            tenants = owner_ids
+            dialogs, total = DialogService.get_by_tenant_ids(
+                tenants, current_user.id, 0,
+                0, orderby, desc, keywords, parser_id)
+            dialogs = [dialog for dialog in dialogs if dialog["tenant_id"] in tenants]
+            total = len(dialogs)
+            if page_number and items_per_page:
+                dialogs = dialogs[(page_number-1)*items_per_page:page_number*items_per_page]
+        return get_json_result(data={"dialogs": dialogs, "total": total})
+    except Exception as e:
+        return server_error_response(e)
+
+
 @manager.route('/rm', methods=['POST'])  # noqa: F821
 @login_required
 @validate_request("dialog_ids")

api/apps/document_app.py

@@ -166,6 +166,17 @@ def create():
         if DocumentService.query(name=req["name"], kb_id=kb_id):
             return get_data_error_result(message="Duplicated document name in the same knowledgebase.")
 
+        kb_root_folder = FileService.get_kb_folder(kb.tenant_id)
+        if not kb_root_folder:
+            return get_data_error_result(message="Cannot find the root folder.")
+        kb_folder = FileService.new_a_file_from_kb(
+            kb.tenant_id,
+            kb.name,
+            kb_root_folder["id"],
+        )
+        if not kb_folder:
+            return get_data_error_result(message="Cannot find the kb folder for this file.")
+
         doc = DocumentService.insert(
             {
                 "id": get_uuid(),
@@ -180,6 +191,9 @@ def create():
                 "size": 0,
             }
         )
+
+        FileService.add_file_from_kb(doc.to_dict(), kb_folder["id"], kb.tenant_id)
+
         return get_json_result(data=doc.to_json())
     except Exception as e:
         return server_error_response(e)
@@ -206,6 +220,8 @@ def list_docs():
         desc = False
     else:
         desc = True
+    create_time_from = int(request.args.get("create_time_from", 0))
+    create_time_to = int(request.args.get("create_time_to", 0))
 
     req = request.get_json()
 
@@ -226,6 +242,14 @@ def list_docs():
     try:
         docs, tol = DocumentService.get_by_kb_id(kb_id, page_number, items_per_page, orderby, desc, keywords, run_status, types, suffix)
 
+        if create_time_from or create_time_to:
+            filtered_docs = []
+            for doc in docs:
+                doc_create_time = doc.get("create_time", 0)
+                if (create_time_from == 0 or doc_create_time >= create_time_from) and (create_time_to == 0 or doc_create_time <= create_time_to):
+                    filtered_docs.append(doc)
+            docs = filtered_docs
+
         for doc_item in docs:
             if doc_item["thumbnail"] and not doc_item["thumbnail"].startswith(IMG_BASE64_PREFIX):
                 doc_item["thumbnail"] = f"/v1/document/image/{kb_id}-{doc_item['thumbnail']}"

api/apps/kb_app.py

@@ -247,7 +247,10 @@ def list_tags(kb_id):
             code=settings.RetCode.AUTHENTICATION_ERROR
         )
 
-    tags = settings.retrievaler.all_tags(current_user.id, [kb_id])
+    tenants = UserTenantService.get_tenants_by_user_id(current_user.id)
+    tags = []
+    for tenant in tenants:
+        tags += settings.retrievaler.all_tags(tenant["tenant_id"], [kb_id])
     return get_json_result(data=tags)
 
 
@@ -263,7 +266,10 @@ def list_tags_from_kbs():
                 code=settings.RetCode.AUTHENTICATION_ERROR
             )
 
-    tags = settings.retrievaler.all_tags(current_user.id, kb_ids)
+    tenants = UserTenantService.get_tenants_by_user_id(current_user.id)
+    tags = []
+    for tenant in tenants:
+        tags += settings.retrievaler.all_tags(tenant["tenant_id"], kb_ids)
     return get_json_result(data=tags)
 
 

api/apps/llm_app.py

@@ -15,7 +15,6 @@
 #
 import logging
 import json
-import base64
 from flask import request
 from flask_login import login_required, current_user
 from api.db.services.llm_service import LLMFactoriesService, TenantLLMService, LLMService
@@ -24,7 +23,7 @@ from api.utils.api_utils import server_error_response, get_data_error_result, va
 from api.db import StatusEnum, LLMType
 from api.db.db_models import TenantLLM
 from api.utils.api_utils import get_json_result
-from api.utils.base64_image import test_image_base64
+from api.utils.base64_image import test_image
 from rag.llm import EmbeddingModel, ChatModel, RerankModel, CvModel, TTSModel
 
 
@@ -82,7 +81,7 @@ def set_api_key():
                     raise Exception(m)
                 chat_passed = True
             except Exception as e:
-                msg += f"\nFail to access model({llm.llm_name}) using this api key." + str(
+                msg += f"\nFail to access model({llm.fid}/{llm.llm_name}) using this api key." + str(
                     e)
         elif not rerank_passed and llm.model_type == LLMType.RERANK:
             assert factory in RerankModel, f"Re-rank model from {factory} is not supported yet."
@@ -95,7 +94,7 @@ def set_api_key():
                 rerank_passed = True
                 logging.debug(f'passed model rerank {llm.llm_name}')
             except Exception as e:
-                msg += f"\nFail to access model({llm.llm_name}) using this api key." + str(
+                msg += f"\nFail to access model({llm.fid}/{llm.llm_name}) using this api key." + str(
                     e)
         if any([embd_passed, chat_passed, rerank_passed]):
             msg = ''
@@ -230,7 +229,7 @@ def add_llm():
             if not tc and m.find("**ERROR**:") >= 0:
                 raise Exception(m)
         except Exception as e:
-            msg += f"\nFail to access model({mdl_nm})." + str(
+            msg += f"\nFail to access model({factory}/{mdl_nm})." + str(
                 e)
     elif llm["model_type"] == LLMType.RERANK:
         assert factory in RerankModel, f"RE-rank model from {factory} is not supported yet."
@@ -244,9 +243,9 @@ def add_llm():
             if len(arr) == 0:
                 raise Exception("Not known.")
         except KeyError:
-            msg += f"{factory} dose not support this model({mdl_nm})"
+            msg += f"{factory} dose not support this model({factory}/{mdl_nm})"
         except Exception as e:
-            msg += f"\nFail to access model({mdl_nm})." + str(
+            msg += f"\nFail to access model({factory}/{mdl_nm})." + str(
                 e)
     elif llm["model_type"] == LLMType.IMAGE2TEXT.value:
         assert factory in CvModel, f"Image to text model from {factory} is not supported yet."
@@ -256,12 +255,12 @@ def add_llm():
             base_url=llm["api_base"]
         )
         try:
-            image_data = base64.b64decode(test_image_base64)
+            image_data = test_image
             m, tc = mdl.describe(image_data)
             if not m and not tc:
                 raise Exception(m)
         except Exception as e:
-            msg += f"\nFail to access model({mdl_nm})." + str(e)
+            msg += f"\nFail to access model({factory}/{mdl_nm})." + str(e)
     elif llm["model_type"] == LLMType.TTS:
         assert factory in TTSModel, f"TTS model from {factory} is not supported yet."
         mdl = TTSModel[factory](
@@ -271,7 +270,7 @@ def add_llm():
             for resp in mdl.tts("Hello~ Ragflower!"):
                 pass
         except RuntimeError as e:
-            msg += f"\nFail to access model({mdl_nm})." + str(e)
+            msg += f"\nFail to access model({factory}/{mdl_nm})." + str(e)
     else:
         # TODO: check other type of models
         pass
@@ -359,8 +358,6 @@ def my_llms():
         return server_error_response(e)
 
 
-
-
 @manager.route('/list', methods=['GET'])  # noqa: F821
 @login_required
 def list_app():

api/apps/sdk/dify_retrieval.py

@@ -1,4 +1,4 @@
-#
+    #
 #  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
 #
 #  Licensed under the Apache License, Version 2.0 (the "License");
@@ -13,6 +13,8 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
+
 from flask import request, jsonify
 
 from api.db import LLMType
@@ -73,11 +75,13 @@ def retrieval(tenant_id):
         for c in ranks["chunks"]:
             e, doc = DocumentService.get_by_id( c["doc_id"])
             c.pop("vector", None)
+            meta = getattr(doc, 'meta_fields', {})
+            meta["doc_id"] = c["doc_id"]
             records.append({
                 "content": c["content_with_weight"],
                 "score": c["similarity"],
                 "title": c["docnm_kwd"],
-                "metadata": doc.meta_fields
+                "metadata": meta
             })
 
         return jsonify({"records": records})
@@ -87,4 +91,5 @@ def retrieval(tenant_id):
                 message='No chunk found! Check the chunk status please!',
                 code=settings.RetCode.NOT_FOUND
             )
+        logging.exception(e)
         return build_error_result(message=str(e), code=settings.RetCode.SERVER_ERROR)

api/apps/sdk/doc.py

@@ -38,7 +38,7 @@ from api.utils.api_utils import check_duplicate_ids, construct_json_result, get_
 from rag.app.qa import beAdoc, rmPrefix
 from rag.app.tag import label_question
 from rag.nlp import rag_tokenizer, search
-from rag.prompts import keyword_extraction, cross_languages
+from rag.prompts import cross_languages, keyword_extraction
 from rag.utils import rmSpace
 from rag.utils.storage_factory import STORAGE_IMPL
 
@@ -456,6 +456,18 @@ def list_docs(dataset_id, tenant_id):
         required: false
         default: true
         description: Order in descending.
+    - in: query
+        name: create_time_from
+        type: integer
+        required: false
+        default: 0
+        description: Unix timestamp for filtering documents created after this time. 0 means no filter.
+      - in: query
+        name: create_time_to
+        type: integer
+        required: false
+        default: 0
+        description: Unix timestamp for filtering documents created before this time. 0 means no filter.
       - in: header
         name: Authorization
         type: string
@@ -517,6 +529,17 @@ def list_docs(dataset_id, tenant_id):
         desc = True
     docs, tol = DocumentService.get_list(dataset_id, page, page_size, orderby, desc, keywords, id, name)
 
+    create_time_from = int(request.args.get("create_time_from", 0))
+    create_time_to = int(request.args.get("create_time_to", 0))
+
+    if create_time_from or create_time_to:
+        filtered_docs = []
+        for doc in docs:
+            doc_create_time = doc.get("create_time", 0)
+            if (create_time_from == 0 or doc_create_time >= create_time_from) and (create_time_to == 0 or doc_create_time <= create_time_to):
+                filtered_docs.append(doc)
+        docs = filtered_docs
+
     # rename key's name
     renamed_doc_list = []
     key_mapping = {

api/apps/sdk/session.py

@@ -51,6 +51,7 @@ def create(tenant_id, chat_id):
         "name": req.get("name", "New session"),
         "message": [{"role": "assistant", "content": dia[0].prompt_config.get("prologue")}],
         "user_id": req.get("user_id", ""),
+        "reference": [{}],
     }
     if not conv.get("name"):
         return get_error_data_result(message="`name` can not be empty.")
@@ -435,14 +436,38 @@ def agents_completion_openai_compatibility(tenant_id, agent_id):
             )
         )
 
-    # Get the last user message as the question
     question = next((m["content"] for m in reversed(messages) if m["role"] == "user"), "")
 
-    if req.get("stream", True):
-        return Response(completionOpenAI(tenant_id, agent_id, question, session_id=req.get("id", req.get("metadata", {}).get("id", "")), stream=True), mimetype="text/event-stream")
+    stream = req.pop("stream", False)
+    if stream:
+        resp = Response(
+            completionOpenAI(
+                tenant_id,
+                agent_id,
+                question,
+                session_id=req.get("id", req.get("metadata", {}).get("id", "")),
+                stream=True,
+                **req,
+            ),
+            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
     else:
         # For non-streaming, just return the response directly
-        response = next(completionOpenAI(tenant_id, agent_id, question, session_id=req.get("id", req.get("metadata", {}).get("id", "")), stream=False))
+        response = next(
+            completionOpenAI(
+                tenant_id,
+                agent_id,
+                question,
+                session_id=req.get("id", req.get("metadata", {}).get("id", "")),
+                stream=False,
+                **req,
+            )
+        )
         return jsonify(response)
 
 
@@ -450,41 +475,38 @@ def agents_completion_openai_compatibility(tenant_id, agent_id):
 @token_required
 def agent_completions(tenant_id, agent_id):
     req = request.json
-    cvs = UserCanvasService.query(user_id=tenant_id, id=agent_id)
-    if not cvs:
-        return get_error_data_result(f"You don't own the agent {agent_id}")
-    if req.get("session_id"):
-        dsl = cvs[0].dsl
-        if not isinstance(dsl, str):
-            dsl = json.dumps(dsl)
 
-        conv = API4ConversationService.query(id=req["session_id"], dialog_id=agent_id)
-        if not conv:
-            return get_error_data_result(f"You don't own the session {req['session_id']}")
-        # If an update to UserCanvas is detected, update the API4Conversation.dsl
-        sync_dsl = req.get("sync_dsl", False)
-        if sync_dsl is True and cvs[0].update_time > conv[0].update_time:
-            current_dsl = conv[0].dsl
-            new_dsl = json.loads(dsl)
-            state_fields = ["history", "messages", "path", "reference"]
-            states = {field: current_dsl.get(field, []) for field in state_fields}
-            current_dsl.update(new_dsl)
-            current_dsl.update(states)
-            API4ConversationService.update_by_id(req["session_id"], {"dsl": current_dsl})
-    else:
-        req["question"] = ""
+    ans = {}
     if req.get("stream", True):
-        resp = Response(agent_completion(tenant_id, agent_id, **req), mimetype="text/event-stream")
+
+        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":
+                    continue
+
+                yield answer
+
+            yield "data:[DONE]\n\n"
+
+        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
-    try:
-        for answer in agent_completion(tenant_id, agent_id, **req):
-            return get_result(data=answer)
-    except Exception as e:
-        return get_error_data_result(str(e))
+
+    for answer in agent_completion(tenant_id=tenant_id, agent_id=agent_id, **req):
+        try:
+            ans = json.loads(answer[5:])  # remove "data:"
+        except Exception as e:
+            return get_result(data=f"**ERROR**: {str(e)}")
+    return get_result(data=ans)
 
 
 @manager.route("/chats/<chat_id>/sessions", methods=["GET"])  # noqa: F821
@@ -512,16 +534,16 @@ def list_session(tenant_id, chat_id):
             if "prompt" in info:
                 info.pop("prompt")
         conv["chat_id"] = conv.pop("dialog_id")
-        if conv["reference"]:
+        ref_messages = conv["reference"]
+        if ref_messages:
             messages = conv["messages"]
             message_num = 0
-            while message_num < len(messages) and message_num < len(conv["reference"]):
-                if message_num != 0 and messages[message_num]["role"] != "user":
-                    if message_num >= len(conv["reference"]):
-                        break
+            ref_num = 0
+            while message_num < len(messages) and ref_num < len(ref_messages):
+                if messages[message_num]["role"] != "user":
                     chunk_list = []
-                    if "chunks" in conv["reference"][message_num]:
-                        chunks = conv["reference"][message_num]["chunks"]
+                    if "chunks" in ref_messages[ref_num]:
+                        chunks = ref_messages[ref_num]["chunks"]
                         for chunk in chunks:
                             new_chunk = {
                                 "id": chunk.get("chunk_id", chunk.get("id")),
@@ -535,6 +557,7 @@ def list_session(tenant_id, chat_id):
 
                             chunk_list.append(new_chunk)
                     messages[message_num]["reference"] = chunk_list
+                    ref_num += 1
                 message_num += 1
         del conv["reference"]
     return get_result(data=convs)
@@ -848,10 +871,11 @@ 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")
-    })
-
-
+    return get_result(
+        data={
+            "title": cvs.title,
+            "avatar": cvs.avatar,
+            "inputs": canvas.get_component_input_form("begin"),
+            "prologue": canvas.get_prologue()
+        }
+    )

api/db/services/canvas_service.py

@@ -16,7 +16,6 @@
 import json
 import logging
 import time
-import traceback
 from uuid import uuid4
 from agent.canvas import Canvas
 from api.db import TenantPermission
@@ -54,12 +53,12 @@ class UserCanvasService(CommonService):
         agents = agents.paginate(page_number, items_per_page)
 
         return list(agents.dicts())
-   
+
     @classmethod
     @DB.connection_context()
     def get_by_tenant_id(cls, pid):
         try:
-            
+
             fields = [
                 cls.model.id,
                 cls.model.avatar,
@@ -83,7 +82,7 @@ class UserCanvasService(CommonService):
         except Exception as e:
             logging.exception(e)
             return False, None
-     
+
     @classmethod
     @DB.connection_context()
     def get_by_tenant_ids(cls, joined_tenant_ids, user_id,
@@ -103,14 +102,14 @@ class UserCanvasService(CommonService):
         ]
         if keywords:
             agents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
-                ((cls.model.user_id.in_(joined_tenant_ids) & (cls.model.permission == 
+                ((cls.model.user_id.in_(joined_tenant_ids) & (cls.model.permission ==
                                                                 TenantPermission.TEAM.value)) | (
                     cls.model.user_id == user_id)),
                 (fn.LOWER(cls.model.title).contains(keywords.lower()))
             )
         else:
             agents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
-                ((cls.model.user_id.in_(joined_tenant_ids) & (cls.model.permission == 
+                ((cls.model.user_id.in_(joined_tenant_ids) & (cls.model.permission ==
                                                                 TenantPermission.TEAM.value)) | (
                     cls.model.user_id == user_id))
             )
@@ -122,9 +121,21 @@ class UserCanvasService(CommonService):
         agents = agents.paginate(page_number, items_per_page)
         return list(agents.dicts()), count
 
+    @classmethod
+    @DB.connection_context()
+    def accessible(cls, canvas_id, tenant_id):
+        from api.db.services.user_service import UserTenantService
+        e, c = UserCanvasService.get_by_tenant_id(canvas_id)
+        if not e:
+            return False
+
+        tids = [t.tenant_id for t in UserTenantService.query(user_id=tenant_id)]
+        if c["user_id"] != canvas_id and c["user_id"]  not in tids:
+            return False
+        return True
 
 def completion(tenant_id, agent_id, session_id=None, **kwargs):
-    query = kwargs.get("query", "")
+    query = kwargs.get("query", "") or kwargs.get("question", "")
     files = kwargs.get("files", [])
     inputs = kwargs.get("inputs", {})
     user_id = kwargs.get("user_id", "")
@@ -173,223 +184,105 @@ def completion(tenant_id, agent_id, session_id=None, **kwargs):
     conv.message.append({"role": "assistant", "content": txt, "created_at": time.time(), "id": message_id})
     conv.reference = canvas.get_reference()
     conv.errors = canvas.error
-    API4ConversationService.append_message(conv.id, conv.to_dict())
+    conv.dsl = str(canvas)
+    conv = conv.to_dict()
+    API4ConversationService.append_message(conv["id"], conv)
 
 
 def completionOpenAI(tenant_id, agent_id, question, session_id=None, stream=True, **kwargs):
-    """Main function for OpenAI-compatible completions, structured similarly to the completion function."""
     tiktokenenc = tiktoken.get_encoding("cl100k_base")
-    e, cvs = UserCanvasService.get_by_id(agent_id)
-    
-    if not e:
-        yield get_data_openai(
-            id=session_id,
-            model=agent_id,
-            content="**ERROR**: Agent not found."
-        )
-        return
-    
-    if cvs.user_id != tenant_id:
-        yield get_data_openai(
-            id=session_id,
-            model=agent_id,
-            content="**ERROR**: You do not own the agent"
-        )
-        return
-    
-    if not isinstance(cvs.dsl, str):
-        cvs.dsl = json.dumps(cvs.dsl, ensure_ascii=False)
-    
-    canvas = Canvas(cvs.dsl, tenant_id)
-    canvas.reset()
-    message_id = str(uuid4())
-    
-    # Handle new session creation
-    if not session_id:
-        query = canvas.get_preset_param()
-        if query:
-            for ele in query:
-                if not ele["optional"]:
-                    if not kwargs.get(ele["key"]):
-                        yield get_data_openai(
-                            id=None,
-                            model=agent_id,
-                            content=f"`{ele['key']}` is required",
-                            completion_tokens=len(tiktokenenc.encode(f"`{ele['key']}` is required")),
-                            prompt_tokens=len(tiktokenenc.encode(question if question else ""))
-                        )
-                        return
-                    ele["value"] = kwargs[ele["key"]]
-                if ele["optional"]:
-                    if kwargs.get(ele["key"]):
-                        ele["value"] = kwargs[ele['key']]
-                    else:
-                        if "value" in ele:
-                            ele.pop("value")
-        
-        cvs.dsl = json.loads(str(canvas))
-        session_id = get_uuid()
-        conv = {
-            "id": session_id,
-            "dialog_id": cvs.id,
-            "user_id": kwargs.get("user_id", "") if isinstance(kwargs, dict) else "",
-            "message": [{"role": "assistant", "content": canvas.get_prologue(), "created_at": time.time()}],
-            "source": "agent",
-            "dsl": cvs.dsl
-        }
-        canvas.messages.append({"role": "user", "content": question, "id": message_id})
-        canvas.add_user_input(question)
-
-        API4ConversationService.save(**conv)
-        conv = API4Conversation(**conv)
-        if not conv.message:
-            conv.message = []
-        conv.message.append({
-            "role": "user",
-            "content": question,
-            "id": message_id
-        })
-        
-        if not conv.reference:
-            conv.reference = []
-        conv.reference.append({"chunks": [], "doc_aggs": []})
-            
-    # Handle existing session
-    else:
-        e, conv = API4ConversationService.get_by_id(session_id)
-        if not e:
-            yield get_data_openai(
-                id=session_id,
-                model=agent_id,
-                content="**ERROR**: Session not found!"
-            )
-            return
-        
-        canvas = Canvas(json.dumps(conv.dsl), tenant_id)
-        canvas.messages.append({"role": "user", "content": question, "id": message_id})
-        canvas.add_user_input(question)
-        
-        if not conv.message:
-            conv.message = []
-        conv.message.append({
-            "role": "user",
-            "content": question,
-            "id": message_id
-        })
-        
-        if not conv.reference:
-            conv.reference = []
-        conv.reference.append({"chunks": [], "doc_aggs": []})
-    
-    # Process request based on stream mode
-    final_ans = {"reference": [], "content": ""}
     prompt_tokens = len(tiktokenenc.encode(str(question)))
-    
+    user_id = kwargs.get("user_id", "")
+
     if stream:
+        completion_tokens = 0
         try:
-            completion_tokens = 0
-            for ans in canvas.run(stream=True, bypass_begin=True):
-                if ans.get("running_status"):
-                    completion_tokens += len(tiktokenenc.encode(ans.get("content", "")))
-                    yield "data: " + json.dumps(
-                        get_data_openai(
-                            id=session_id,
-                            model=agent_id,
-                            content=ans["content"],
-                            object="chat.completion.chunk",
-                            completion_tokens=completion_tokens,
-                            prompt_tokens=prompt_tokens
-                        ),
-                        ensure_ascii=False
-                    ) + "\n\n"
+            for ans in completion(
+                tenant_id=tenant_id,
+                agent_id=agent_id,
+                session_id=session_id,
+                query=question,
+                user_id=user_id,
+                **kwargs
+            ):
+                if isinstance(ans, str):
+                    try:
+                        ans = json.loads(ans[5:])  # remove "data:"
+                    except Exception as e:
+                        logging.exception(f"Agent OpenAI-Compatible completionOpenAI parse answer failed: {e}")
+                        continue
+
+                if ans.get("event") != "message":
                     continue
-                
-                for k in ans.keys():
-                    final_ans[k] = ans[k]
-                
-                completion_tokens += len(tiktokenenc.encode(final_ans.get("content", "")))
+
+                content_piece = ans["data"]["content"]
+                completion_tokens += len(tiktokenenc.encode(content_piece))
+
                 yield "data: " + json.dumps(
                     get_data_openai(
-                        id=session_id,
+                        id=session_id or str(uuid4()),
                         model=agent_id,
-                        content=final_ans["content"],
-                        object="chat.completion.chunk",
-                        finish_reason="stop",
+                        content=content_piece,
+                        prompt_tokens=prompt_tokens,
                         completion_tokens=completion_tokens,
-                        prompt_tokens=prompt_tokens
+                        stream=True
                     ),
                     ensure_ascii=False
                 ) + "\n\n"
-            
-            # Update conversation
-            canvas.messages.append({"role": "assistant", "content": final_ans["content"], "created_at": time.time(), "id": message_id})
-            canvas.history.append(("assistant", final_ans["content"]))
-            if final_ans.get("reference"):
-                canvas.reference.append(final_ans["reference"])
-            conv.dsl = json.loads(str(canvas))
-            API4ConversationService.append_message(conv.id, conv.to_dict())
-            
+
             yield "data: [DONE]\n\n"
-            
+
         except Exception as e:
-            traceback.print_exc()
-            conv.dsl = json.loads(str(canvas))
-            API4ConversationService.append_message(conv.id, conv.to_dict())
             yield "data: " + json.dumps(
                 get_data_openai(
-                    id=session_id,
+                    id=session_id or str(uuid4()),
                     model=agent_id,
-                    content="**ERROR**: " + str(e),
+                    content=f"**ERROR**: {str(e)}",
                     finish_reason="stop",
-                    completion_tokens=len(tiktokenenc.encode("**ERROR**: " + str(e))),
-                    prompt_tokens=prompt_tokens
+                    prompt_tokens=prompt_tokens,
+                    completion_tokens=len(tiktokenenc.encode(f"**ERROR**: {str(e)}")),
+                    stream=True
                 ),
                 ensure_ascii=False
             ) + "\n\n"
             yield "data: [DONE]\n\n"
-    
-    else:  # Non-streaming mode
+
+    else:
         try:
-            all_answer_content = ""
-            for answer in canvas.run(stream=False, bypass_begin=True):
-                if answer.get("running_status"):
+            all_content = ""
+            for ans in completion(
+                tenant_id=tenant_id,
+                agent_id=agent_id,
+                session_id=session_id,
+                query=question,
+                user_id=user_id,
+                **kwargs
+            ):
+                if isinstance(ans, str):
+                    ans = json.loads(ans[5:])
+                if ans.get("event") != "message":
                     continue
-                
-                final_ans["content"] = "\n".join(answer["content"]) if "content" in answer else ""
-                final_ans["reference"] = answer.get("reference", [])
-                all_answer_content += final_ans["content"]
-            
-            final_ans["content"] = all_answer_content
-            
-            # Update conversation
-            canvas.messages.append({"role": "assistant", "content": final_ans["content"], "created_at": time.time(), "id": message_id})
-            canvas.history.append(("assistant", final_ans["content"]))
-            if final_ans.get("reference"):
-                canvas.reference.append(final_ans["reference"])
-            conv.dsl = json.loads(str(canvas))
-            API4ConversationService.append_message(conv.id, conv.to_dict())
-            
-            # Return the response in OpenAI format
+                all_content += ans["data"]["content"]
+
+            completion_tokens = len(tiktokenenc.encode(all_content))
+
             yield get_data_openai(
-                id=session_id,
+                id=session_id or str(uuid4()),
                 model=agent_id,
-                content=final_ans["content"],
-                finish_reason="stop",
-                completion_tokens=len(tiktokenenc.encode(final_ans["content"])),
                 prompt_tokens=prompt_tokens,
-                param=canvas.get_preset_param()  # Added param info like in completion
-            )
-            
-        except Exception as e:
-            traceback.print_exc()
-            conv.dsl = json.loads(str(canvas))
-            API4ConversationService.append_message(conv.id, conv.to_dict())
-            yield get_data_openai(
-                id=session_id,
-                model=agent_id,
-                content="**ERROR**: " + str(e),
+                completion_tokens=completion_tokens,
+                content=all_content,
                 finish_reason="stop",
-                completion_tokens=len(tiktokenenc.encode("**ERROR**: " + str(e))),
-                prompt_tokens=prompt_tokens
+                param=None
             )
 
+        except Exception as e:
+            yield get_data_openai(
+                id=session_id or str(uuid4()),
+                model=agent_id,
+                prompt_tokens=prompt_tokens,
+                completion_tokens=len(tiktokenenc.encode(f"**ERROR**: {str(e)}")),
+                content=f"**ERROR**: {str(e)}",
+                finish_reason="stop",
+                param=None
+            )

api/db/services/dialog_service.py

@@ -23,6 +23,7 @@ from functools import partial
 from timeit import default_timer as timer
 
 from langfuse import Langfuse
+from peewee import fn
 
 from agentic_reasoning import DeepResearcher
 from api import settings
@@ -96,6 +97,66 @@ class DialogService(CommonService):
         return list(chats.dicts())
 
 
+    @classmethod
+    @DB.connection_context()
+    def get_by_tenant_ids(cls, joined_tenant_ids, user_id, page_number, items_per_page, orderby, desc, keywords, parser_id=None):
+        from api.db.db_models import User
+
+        fields = [
+            cls.model.id,
+            cls.model.tenant_id,
+            cls.model.name,
+            cls.model.description,
+            cls.model.language,
+            cls.model.llm_id,
+            cls.model.llm_setting,
+            cls.model.prompt_type,
+            cls.model.prompt_config,
+            cls.model.similarity_threshold,
+            cls.model.vector_similarity_weight,
+            cls.model.top_n,
+            cls.model.top_k,
+            cls.model.do_refer,
+            cls.model.rerank_id,
+            cls.model.kb_ids,
+            cls.model.status,
+            User.nickname,
+            User.avatar.alias("tenant_avatar"),
+            cls.model.update_time,
+            cls.model.create_time,
+        ]
+        if keywords:
+            dialogs = (
+                cls.model.select(*fields)
+                .join(User, on=(cls.model.tenant_id == User.id))
+                .where(
+                    (cls.model.tenant_id.in_(joined_tenant_ids) | (cls.model.tenant_id == user_id)) & (cls.model.status == StatusEnum.VALID.value),
+                    (fn.LOWER(cls.model.name).contains(keywords.lower())),
+                )
+            )
+        else:
+            dialogs = (
+                cls.model.select(*fields)
+                .join(User, on=(cls.model.tenant_id == User.id))
+                .where(
+                    (cls.model.tenant_id.in_(joined_tenant_ids) | (cls.model.tenant_id == user_id)) & (cls.model.status == StatusEnum.VALID.value),
+                )
+            )
+        if parser_id:
+            dialogs = dialogs.where(cls.model.parser_id == parser_id)
+        if desc:
+            dialogs = dialogs.order_by(cls.model.getter_by(orderby).desc())
+        else:
+            dialogs = dialogs.order_by(cls.model.getter_by(orderby).asc())
+
+        count = dialogs.count()
+
+        if page_number and items_per_page:
+            dialogs = dialogs.paginate(page_number, items_per_page)
+
+        return list(dialogs.dicts()), count
+
+
 def chat_solo(dialog, messages, stream=True):
     if TenantLLMService.llm_id2llm_type(dialog.llm_id) == "image2text":
         chat_mdl = LLMBundle(dialog.tenant_id, LLMType.IMAGE2TEXT, dialog.llm_id)
@@ -208,12 +269,14 @@ def chat(dialog, messages, stream=True, **kwargs):
     check_llm_ts = timer()
 
     langfuse_tracer = None
+    trace_context = {}
     langfuse_keys = TenantLangfuseService.filter_by_tenant(tenant_id=dialog.tenant_id)
     if langfuse_keys:
         langfuse = Langfuse(public_key=langfuse_keys.public_key, secret_key=langfuse_keys.secret_key, host=langfuse_keys.host)
         if langfuse.auth_check():
             langfuse_tracer = langfuse
-            langfuse.trace = langfuse_tracer.trace(name=f"{dialog.name}-{llm_model_config['llm_name']}")
+            trace_id = langfuse_tracer.create_trace_id()
+            trace_context = {"trace_id": trace_id}
 
     check_langfuse_tracer_ts = timer()
     kbs, embd_mdl, rerank_mdl, chat_mdl, tts_mdl = get_models(dialog)
@@ -400,17 +463,19 @@ def chat(dialog, messages, stream=True, **kwargs):
             f"  - Token speed: {int(tk_num / (generate_result_time_cost / 1000.0))}/s"
         )
 
-        langfuse_output = "\n" + re.sub(r"^.*?(### Query:.*)", r"\1", prompt, flags=re.DOTALL)
-        langfuse_output = {"time_elapsed:": re.sub(r"\n", "  \n", langfuse_output), "created_at": time.time()}
-
         # Add a condition check to call the end method only if langfuse_tracer exists
         if langfuse_tracer and "langfuse_generation" in locals():
-            langfuse_generation.end(output=langfuse_output)
+            langfuse_output = "\n" + re.sub(r"^.*?(### Query:.*)", r"\1", prompt, flags=re.DOTALL)
+            langfuse_output = {"time_elapsed:": re.sub(r"\n", "  \n", langfuse_output), "created_at": time.time()}
+            langfuse_generation.update(output=langfuse_output)
+            langfuse_generation.end()
 
         return {"answer": think + answer, "reference": refs, "prompt": re.sub(r"\n", "  \n", prompt), "created_at": time.time()}
 
     if langfuse_tracer:
-        langfuse_generation = langfuse_tracer.trace.generation(name="chat", model=llm_model_config["llm_name"], input={"prompt": prompt, "prompt4citation": prompt4citation, "messages": msg})
+        langfuse_generation = langfuse_tracer.start_generation(
+            trace_context=trace_context, name="chat", model=llm_model_config["llm_name"], input={"prompt": prompt, "prompt4citation": prompt4citation, "messages": msg}
+        )
 
     if stream:
         last_ans = ""

api/db/services/llm_service.py

@@ -217,7 +217,7 @@ class TenantLLMService(CommonService):
         return list(objs)
 
     @staticmethod
-    def llm_id2llm_type(llm_id: str) ->str|None:
+    def llm_id2llm_type(llm_id: str) -> str | None:
         llm_id, *_ = TenantLLMService.split_model_name_and_factory(llm_id)
         llm_factories = settings.FACTORY_LLM_INFOS
         for llm_factory in llm_factories:
@@ -225,6 +225,15 @@ class TenantLLMService(CommonService):
                 if llm_id == llm["llm_name"]:
                     return llm["model_type"].split(",")[-1]
 
+        for llm in LLMService.query(llm_name=llm_id):
+            return llm.model_type
+
+        llm = TenantLLMService.get_or_none(llm_name=llm_id)
+        if llm:
+            return llm.model_type
+        for llm in TenantLLMService.query(llm_name=llm_id):
+            return llm.model_type
+
 
 class LLMBundle:
     def __init__(self, tenant_id, llm_type, llm_name=None, lang="Chinese", **kwargs):
@@ -240,13 +249,13 @@ class LLMBundle:
         self.verbose_tool_use = kwargs.get("verbose_tool_use")
 
         langfuse_keys = TenantLangfuseService.filter_by_tenant(tenant_id=tenant_id)
+        self.langfuse = None
         if langfuse_keys:
             langfuse = Langfuse(public_key=langfuse_keys.public_key, secret_key=langfuse_keys.secret_key, host=langfuse_keys.host)
             if langfuse.auth_check():
                 self.langfuse = langfuse
-                self.trace = self.langfuse.trace(name=f"{self.llm_type}-{self.llm_name}")
-        else:
-            self.langfuse = None
+                trace_id = self.langfuse.create_trace_id()
+                self.trace_context = {"trace_id": trace_id}
 
     def bind_tools(self, toolcall_session, tools):
         if not self.is_tools:
@@ -256,7 +265,7 @@ class LLMBundle:
 
     def encode(self, texts: list):
         if self.langfuse:
-            generation = self.trace.generation(name="encode", model=self.llm_name, input={"texts": texts})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="encode", model=self.llm_name, input={"texts": texts})
 
         embeddings, used_tokens = self.mdl.encode(texts)
         llm_name = getattr(self, "llm_name", None)
@@ -264,13 +273,14 @@ class LLMBundle:
             logging.error("LLMBundle.encode can't update token usage for {}/EMBEDDING used_tokens: {}".format(self.tenant_id, used_tokens))
 
         if self.langfuse:
-            generation.end(usage_details={"total_tokens": used_tokens})
+            generation.update(usage_details={"total_tokens": used_tokens})
+            generation.end()
 
         return embeddings, used_tokens
 
     def encode_queries(self, query: str):
         if self.langfuse:
-            generation = self.trace.generation(name="encode_queries", model=self.llm_name, input={"query": query})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="encode_queries", model=self.llm_name, input={"query": query})
 
         emd, used_tokens = self.mdl.encode_queries(query)
         llm_name = getattr(self, "llm_name", None)
@@ -278,65 +288,70 @@ class LLMBundle:
             logging.error("LLMBundle.encode_queries can't update token usage for {}/EMBEDDING used_tokens: {}".format(self.tenant_id, used_tokens))
 
         if self.langfuse:
-            generation.end(usage_details={"total_tokens": used_tokens})
+            generation.update(usage_details={"total_tokens": used_tokens})
+            generation.end()
 
         return emd, used_tokens
 
     def similarity(self, query: str, texts: list):
         if self.langfuse:
-            generation = self.trace.generation(name="similarity", model=self.llm_name, input={"query": query, "texts": texts})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="similarity", model=self.llm_name, input={"query": query, "texts": texts})
 
         sim, used_tokens = self.mdl.similarity(query, texts)
         if not TenantLLMService.increase_usage(self.tenant_id, self.llm_type, used_tokens):
             logging.error("LLMBundle.similarity can't update token usage for {}/RERANK used_tokens: {}".format(self.tenant_id, used_tokens))
 
         if self.langfuse:
-            generation.end(usage_details={"total_tokens": used_tokens})
+            generation.update(usage_details={"total_tokens": used_tokens})
+            generation.end()
 
         return sim, used_tokens
 
     def describe(self, image, max_tokens=300):
         if self.langfuse:
-            generation = self.trace.generation(name="describe", metadata={"model": self.llm_name})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="describe", metadata={"model": self.llm_name})
 
         txt, used_tokens = self.mdl.describe(image)
         if not TenantLLMService.increase_usage(self.tenant_id, self.llm_type, used_tokens):
             logging.error("LLMBundle.describe can't update token usage for {}/IMAGE2TEXT used_tokens: {}".format(self.tenant_id, used_tokens))
 
         if self.langfuse:
-            generation.end(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.update(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.end()
 
         return txt
 
     def describe_with_prompt(self, image, prompt):
         if self.langfuse:
-            generation = self.trace.generation(name="describe_with_prompt", metadata={"model": self.llm_name, "prompt": prompt})
+            generation = self.language.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):
             logging.error("LLMBundle.describe can't update token usage for {}/IMAGE2TEXT used_tokens: {}".format(self.tenant_id, used_tokens))
 
         if self.langfuse:
-            generation.end(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.update(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.end()
 
         return txt
 
     def transcription(self, audio):
         if self.langfuse:
-            generation = self.trace.generation(name="transcription", metadata={"model": self.llm_name})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="transcription", metadata={"model": self.llm_name})
 
         txt, used_tokens = self.mdl.transcription(audio)
         if not TenantLLMService.increase_usage(self.tenant_id, self.llm_type, used_tokens):
             logging.error("LLMBundle.transcription can't update token usage for {}/SEQUENCE2TXT used_tokens: {}".format(self.tenant_id, used_tokens))
 
         if self.langfuse:
-            generation.end(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.update(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.end()
 
         return txt
 
     def tts(self, text: str) -> Generator[bytes, None, None]:
         if self.langfuse:
-            span = self.trace.span(name="tts", input={"text": text})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="tts", input={"text": text})
 
         for chunk in self.mdl.tts(text):
             if isinstance(chunk, int):
@@ -346,7 +361,7 @@ class LLMBundle:
             yield chunk
 
         if self.langfuse:
-            span.end()
+            generation.end()
 
     def _remove_reasoning_content(self, txt: str) -> str:
         first_think_start = txt.find("<think>")
@@ -362,9 +377,9 @@ class LLMBundle:
 
         return txt[last_think_end + len("</think>") :]
 
-    def chat(self, system: str, history: list, gen_conf: dict={}, **kwargs) -> str:
+    def chat(self, system: str, history: list, gen_conf: dict = {}, **kwargs) -> str:
         if self.langfuse:
-            generation = self.trace.generation(name="chat", model=self.llm_name, input={"system": system, "history": history})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="chat", model=self.llm_name, input={"system": system, "history": history})
 
         chat_partial = partial(self.mdl.chat, system, history, gen_conf)
         if self.is_tools and self.mdl.is_tools:
@@ -380,13 +395,14 @@ class LLMBundle:
             logging.error("LLMBundle.chat can't update token usage for {}/CHAT llm_name: {}, used_tokens: {}".format(self.tenant_id, self.llm_name, used_tokens))
 
         if self.langfuse:
-            generation.end(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.update(output={"output": txt}, usage_details={"total_tokens": used_tokens})
+            generation.end()
 
         return txt
 
-    def chat_streamly(self, system: str, history: list, gen_conf: dict={}, **kwargs):
+    def chat_streamly(self, system: str, history: list, gen_conf: dict = {}, **kwargs):
         if self.langfuse:
-            generation = self.trace.generation(name="chat_streamly", model=self.llm_name, input={"system": system, "history": history})
+            generation = self.langfuse.start_generation(trace_context=self.trace_context, name="chat_streamly", model=self.llm_name, input={"system": system, "history": history})
 
         ans = ""
         chat_partial = partial(self.mdl.chat_streamly, system, history, gen_conf)
@@ -398,7 +414,8 @@ class LLMBundle:
             if isinstance(txt, int):
                 total_tokens = txt
                 if self.langfuse:
-                    generation.end(output={"output": ans})
+                    generation.update(output={"output": ans})
+                    generation.end()
                 break
 
             if txt.endswith("</think>"):

api/settings.py

@@ -70,6 +70,7 @@ REGISTER_ENABLED = 1
 # sandbox-executor-manager
 SANDBOX_ENABLED = 0
 SANDBOX_HOST = None
+STRONG_TEST_COUNT = int(os.environ.get("STRONG_TEST_COUNT", "8"))
 
 BUILTIN_EMBEDDING_MODELS = ["BAAI/bge-large-zh-v1.5@BAAI", "maidalun1020/bce-embedding-base_v1@Youdao"]
 

api/utils/api_utils.py

@@ -402,8 +402,22 @@ def get_data_openai(
     finish_reason=None,
     object="chat.completion",
     param=None,
+    stream=False
 ):
     total_tokens = prompt_tokens + completion_tokens
+
+    if stream:
+        return {
+            "id": f"{id}",
+            "object": "chat.completion.chunk",
+            "model": model,
+            "choices": [{
+                "delta": {"content": content},
+                "finish_reason": finish_reason,
+                "index": 0,
+            }],
+        }
+
     return {
         "id": f"{id}",
         "object": object,
@@ -414,9 +428,21 @@ def get_data_openai(
             "prompt_tokens": prompt_tokens,
             "completion_tokens": completion_tokens,
             "total_tokens": total_tokens,
-            "completion_tokens_details": {"reasoning_tokens": 0, "accepted_prediction_tokens": 0, "rejected_prediction_tokens": 0},
+            "completion_tokens_details": {
+                "reasoning_tokens": 0,
+                "accepted_prediction_tokens": 0,
+                "rejected_prediction_tokens": 0,
+            },
         },
-        "choices": [{"message": {"role": "assistant", "content": content}, "logprobs": None, "finish_reason": finish_reason, "index": 0}],
+        "choices": [{
+            "message": {
+                "role": "assistant",
+                "content": content
+            },
+            "logprobs": None,
+            "finish_reason": finish_reason,
+            "index": 0,
+        }],
     }
 
 
@@ -687,7 +713,13 @@ def timeout(seconds: float | int = None, attempts: int = 2, *, exception: Option
 
 
 async def is_strong_enough(chat_model, embedding_model):
-    @timeout(30, 2)
+    count = settings.STRONG_TEST_COUNT
+    if not chat_model or not embedding_model:
+        return
+    if isinstance(count, int) and count <= 0:
+        return
+
+    @timeout(60, 2)
     async def _is_strong_enough():
         nonlocal chat_model, embedding_model
         if embedding_model:
@@ -701,5 +733,5 @@ async def is_strong_enough(chat_model, embedding_model):
 
     # Pressure test for GraphRAG task
     async with trio.open_nursery() as nursery:
-        for _ in range(32):
+        for _ in range(count):
             nursery.start_soon(_is_strong_enough)

api/utils/base64_image.py

@@ -1 +1,3 @@
+import base64
 test_image_base64 = "iVBORw0KGgoAAAANSUhEUgAAAGQAAABkCAIAAAD/gAIDAAAA6ElEQVR4nO3QwQ3AIBDAsIP9d25XIC+EZE8QZc18w5l9O+AlZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBT+IYAHHLHkdEgAAAABJRU5ErkJggg=="
+test_image = base64.b64decode(test_image_base64)

conf/llm_factories.json

@@ -6,6 +6,34 @@
             "tags": "LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION",
             "status": "1",
             "llm": [
+                {
+                    "llm_name": "gpt-5",
+                    "tags": "LLM,CHAT,400k,IMAGE2TEXT",
+                    "max_tokens": 400000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "gpt-5-mini",
+                    "tags": "LLM,CHAT,400k,IMAGE2TEXT",
+                    "max_tokens": 400000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "gpt-5-nano",
+                    "tags": "LLM,CHAT,400k,IMAGE2TEXT",
+                    "max_tokens": 400000,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "gpt-5-chat-latest",
+                    "tags": "LLM,CHAT,400k,IMAGE2TEXT",
+                    "max_tokens": 400000,
+                    "model_type": "chat",
+                    "is_tools": false
+                },
                 {
                     "llm_name": "gpt-4.1",
                     "tags": "LLM,CHAT,1M,IMAGE2TEXT",
@@ -2598,234 +2626,255 @@
             "tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK,IMAGE2TEXT",
             "status": "1",
             "llm": [
+                {
+                    "llm_name": "Qwen3-Embedding-8B",
+                    "tags": "TEXT EMBEDDING,TEXT RE-RANK,32k",
+                    "max_tokens": 32000,
+                    "model_type": "embedding",
+                    "is_tools": false
+                },
+                {
+                    "llm_name": "Qwen3-Embedding-4B",
+                    "tags": "TEXT EMBEDDING,TEXT RE-RANK,32k",
+                    "max_tokens": 32000,
+                    "model_type": "embedding",
+                    "is_tools": false
+                },
+                {
+                    "llm_name": "Qwen3-Embedding-0.6B",
+                    "tags": "TEXT EMBEDDING,TEXT RE-RANK,32k",
+                    "max_tokens": 32000,
+                    "model_type": "embedding",
+                    "is_tools": false
+                },
                 {
                     "llm_name": "Qwen/Qwen3-235B-A22B",
                     "tags": "LLM,CHAT,128k",
-                    "max_tokens": 8192,
+                    "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen3-30B-A3B",
                     "tags": "LLM,CHAT,128k",
-                    "max_tokens": 8192,
+                    "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen3-32B",
                     "tags": "LLM,CHAT,128k",
-                    "max_tokens": 8192,
+                    "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen3-14B",
                     "tags": "LLM,CHAT,128k",
-                    "max_tokens": 8192,
+                    "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen3-8B",
                     "tags": "LLM,CHAT,64k",
-                    "max_tokens": 8192,
+                    "max_tokens": 64000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/QVQ-72B-Preview",
                     "tags": "LLM,CHAT,IMAGE2TEXT,32k",
-                    "max_tokens": 16384,
+                    "max_tokens": 32000,
                     "model_type": "image2text",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Pro/deepseek-ai/DeepSeek-R1",
                     "tags": "LLM,CHAT,64k",
-                    "max_tokens": 16384,
+                    "max_tokens": 64000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "deepseek-ai/DeepSeek-R1",
                     "tags": "LLM,CHAT,64k",
-                    "max_tokens": 16384,
+                    "max_tokens": 64000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Pro/deepseek-ai/DeepSeek-V3",
                     "tags": "LLM,CHAT,64k",
-                    "max_tokens": 8192,
+                    "max_tokens": 64000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "deepseek-ai/DeepSeek-V3",
                     "tags": "LLM,CHAT,64k",
-                    "max_tokens": 8192,
+                    "max_tokens": 64000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Pro/deepseek-ai/DeepSeek-V3-1226",
                     "tags": "LLM,CHAT,64k",
-                    "max_tokens": 4096,
+                    "max_tokens": 64000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 16384,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 16384,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 16384,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 16384,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 16384,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 16384,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "deepseek-ai/DeepSeek-V2.5",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/QwQ-32B",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 32768,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen2.5-VL-72B-Instruct",
                     "tags": "LLM,CHAT,IMAGE2TEXT,128k",
-                    "max_tokens": 4096,
+                    "max_tokens": 128000,
                     "model_type": "image2text",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Pro/Qwen/Qwen2.5-VL-7B-Instruct",
                     "tags": "LLM,CHAT,IMAGE2TEXT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "image2text",
                     "is_tools": true
                 },
                 {
                     "llm_name": "THUDM/GLM-Z1-32B-0414",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "THUDM/GLM-4-32B-0414",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 8192,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "THUDM/GLM-Z1-9B-0414",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 8192,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "THUDM/GLM-4-9B-0414",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "THUDM/chatglm3-6b",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Pro/THUDM/glm-4-9b-chat",
                     "tags": "LLM,CHAT,128k",
-                    "max_tokens": 4096,
+                    "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": false
                 },
                 {
                     "llm_name": "THUDM/GLM-Z1-Rumination-32B-0414",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": false
                 },
                 {
                     "llm_name": "THUDM/glm-4-9b-chat",
                     "tags": "LLM,CHAT,128k",
-                    "max_tokens": 4096,
+                    "max_tokens": 128000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/QwQ-32B-Preview",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 8192,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Qwen/Qwen2.5-Coder-32B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Qwen/Qwen2-VL-72B-Instruct",
                     "tags": "LLM,IMAGE2TEXT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "image2text",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Qwen/Qwen2.5-72B-Instruct-128Kt",
                     "tags": "LLM,IMAGE2TEXT,128k",
-                    "max_tokens": 4096,
+                    "max_tokens": 128000,
                     "model_type": "image2text",
                     "is_tools": false
                 },
@@ -2839,98 +2888,98 @@
                 {
                     "llm_name": "Qwen/Qwen2.5-72B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen2.5-32B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen2.5-14B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen2.5-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen2.5-Coder-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "internlm/internlm2_5-20b-chat",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "internlm/internlm2_5-7b-chat",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen2-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Qwen/Qwen2-1.5B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Pro/Qwen/Qwen2.5-Coder-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Pro/Qwen/Qwen2-VL-7B-Instruct",
                     "tags": "LLM,CHAT,IMAGE2TEXT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "image2text",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Pro/Qwen/Qwen2.5-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "Pro/Qwen/Qwen2-7B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": false
                 },
                 {
                     "llm_name": "Pro/Qwen/Qwen2-1.5B-Instruct",
                     "tags": "LLM,CHAT,32k",
-                    "max_tokens": 4096,
+                    "max_tokens": 32000,
                     "model_type": "chat",
                     "is_tools": false
                 },
@@ -3267,45 +3316,52 @@
             "status": "1",
             "llm": [
                 {
-                    "llm_name": "claude-opus-4-20250514",
-                    "tags": "LLM,IMAGE2TEXT,200k",
-                    "max_tokens": 204800,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-sonnet-4-20250514",
-                    "tags": "LLM,IMAGE2TEXT,200k",
-                    "max_tokens": 204800,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-3-7-sonnet-20250219",
-                    "tags": "LLM,IMAGE2TEXT,200k",
-                    "max_tokens": 204800,
-                    "model_type": "image2text",
-                    "is_tools": true
-                },
-                {
-                    "llm_name": "claude-3-5-sonnet-20241022",
-                    "tags": "LLM,IMAGE2TEXT,200k",
+                    "llm_name": "claude-opus-4-1-20250805",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
                     "max_tokens": 204800,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
-                    "llm_name": "claude-3-opus-20240229",
-                    "tags": "LLM,IMAGE2TEXT,200k",
+                    "llm_name": "claude-opus-4-20250514",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
+                    "max_tokens": 204800,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "claude-sonnet-4-20250514",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
+                    "max_tokens": 204800,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "claude-3-7-sonnet-20250219",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
+                    "max_tokens": 204800,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "claude-3-5-sonnet-20241022",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
+                    "max_tokens": 204800,
+                    "model_type": "chat",
+                    "is_tools": true
+                },
+                {
+                    "llm_name": "claude-3-5-haiku-20241022",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
                     "max_tokens": 204800,
                     "model_type": "chat",
                     "is_tools": true
                 },
                 {
                     "llm_name": "claude-3-haiku-20240307",
-                    "tags": "LLM,IMAGE2TEXT,200k",
+                    "tags": "LLM,CHAT,IMAGE2TEXT,200k",
                     "max_tokens": 204800,
-                    "model_type": "image2text",
+                    "model_type": "chat",
                     "is_tools": true
                 }
             ]

deepdoc/parser/ppt_parser.py

@@ -87,7 +87,7 @@ class RAGFlowPptParser:
                 break
             texts = []
             for shape in sorted(
-                    slide.shapes, key=lambda x: ((x.top if x.top is not None else 0) // 10, x.left)):
+                    slide.shapes, key=lambda x: ((x.top if x.top is not None else 0) // 10, x.left if x.left is not None else 0)):
                 try:
                     txt = self.__extract(shape)
                     if txt:
@@ -96,4 +96,4 @@ class RAGFlowPptParser:
                     logging.exception(e)
             txts.append("\n".join(texts))
 
-        return txts
+        return txts

docker/.env

@@ -62,6 +62,8 @@ MYSQL_DBNAME=rag_flow
 # The port used to expose the MySQL service to the host machine,
 # allowing EXTERNAL access to the MySQL database running inside the Docker container.
 MYSQL_PORT=5455
+# The maximum size of communication packets sent to the MySQL server
+MYSQL_MAX_PACKET=1073741824
 
 # The hostname where the MinIO service is exposed
 MINIO_HOST=minio
@@ -91,13 +93,13 @@ REDIS_PASSWORD=infini_rag_flow
 SVR_HTTP_PORT=9380
 
 # The RAGFlow Docker image to download.
-# Defaults to the v0.20.0-slim edition, which is the RAGFlow Docker image without embedding models.
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0-slim
+# Defaults to the v0.20.1-slim edition, which is the RAGFlow Docker image without embedding models.
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1-slim
 #
 # To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
-# RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0
+# RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1
 #
-# The Docker image of the v0.20.0 edition includes built-in embedding models:
+# The Docker image of the v0.20.1 edition includes built-in embedding models:
 #   - BAAI/bge-large-zh-v1.5
 #   - maidalun1020/bce-embedding-base_v1
 #

docker/README.md

@@ -79,8 +79,8 @@ The [.env](./.env) file contains important environment variables for Docker.
 - `RAGFLOW-IMAGE`  
   The Docker image edition. Available editions:  
   
-  - `infiniflow/ragflow:v0.20.0-slim` (default): The RAGFlow Docker image without embedding models.  
-  - `infiniflow/ragflow:v0.20.0`: The RAGFlow Docker image with embedding models including:
+  - `infiniflow/ragflow:v0.20.1-slim` (default): The RAGFlow Docker image without embedding models.  
+  - `infiniflow/ragflow:v0.20.1`: The RAGFlow Docker image with embedding models including:
     - Built-in embedding models:
       - `BAAI/bge-large-zh-v1.5` 
       - `maidalun1020/bce-embedding-base_v1`

docker/migration.sh

@@ -0,0 +1,298 @@
+#!/bin/bash
+
+# RAGFlow Data Migration Script
+# Usage: ./migration.sh [backup|restore] [backup_folder]
+# 
+# This script helps you backup and restore RAGFlow Docker volumes
+# including MySQL, MinIO, Redis, and Elasticsearch data.
+
+set -e  # Exit on any error
+# Instead, we'll handle errors manually for better debugging experience
+
+# Default values
+DEFAULT_BACKUP_FOLDER="backup"
+VOLUMES=("docker_mysql_data" "docker_minio_data" "docker_redis_data" "docker_esdata01")
+BACKUP_FILES=("mysql_backup.tar.gz" "minio_backup.tar.gz" "redis_backup.tar.gz" "es_backup.tar.gz")
+
+# Function to display help information
+show_help() {
+    echo "RAGFlow Data Migration Tool"
+    echo ""
+    echo "USAGE:"
+    echo "  $0 <operation> [backup_folder]"
+    echo ""
+    echo "OPERATIONS:"
+    echo "  backup   - Create backup of all RAGFlow data volumes"
+    echo "  restore  - Restore RAGFlow data volumes from backup"
+    echo "  help     - Show this help message"
+    echo ""
+    echo "PARAMETERS:"
+    echo "  backup_folder  - Name of backup folder (default: '$DEFAULT_BACKUP_FOLDER')"
+    echo ""
+    echo "EXAMPLES:"
+    echo "  $0 backup                    # Backup to './backup' folder"
+    echo "  $0 backup my_backup          # Backup to './my_backup' folder"
+    echo "  $0 restore                   # Restore from './backup' folder"
+    echo "  $0 restore my_backup         # Restore from './my_backup' folder"
+    echo ""
+    echo "DOCKER VOLUMES:"
+    echo "  - docker_mysql_data     (MySQL database)"
+    echo "  - docker_minio_data     (MinIO object storage)"
+    echo "  - docker_redis_data     (Redis cache)"
+    echo "  - docker_esdata01       (Elasticsearch indices)"
+}
+
+# Function to check if Docker is running
+check_docker() {
+    if ! docker info >/dev/null 2>&1; then
+        echo "❌ Error: Docker is not running or not accessible"
+        echo "Please start Docker and try again"
+        exit 1
+    fi
+}
+
+# Function to check if volume exists
+volume_exists() {
+    local volume_name=$1
+    docker volume inspect "$volume_name" >/dev/null 2>&1
+}
+
+# Function to check if any containers are using the target volumes
+check_containers_using_volumes() {
+    echo "🔍 Checking for running containers that might be using target volumes..."
+    
+    # Get all running containers
+    local running_containers=$(docker ps --format "{{.Names}}")
+    
+    if [ -z "$running_containers" ]; then
+        echo "✅ No running containers found"
+        return 0
+    fi
+    
+    # Check each running container for volume usage
+    local containers_using_volumes=()
+    local volume_usage_details=()
+    
+    for container in $running_containers; do
+        # Get container's mount information
+        local mounts=$(docker inspect "$container" --format '{{range .Mounts}}{{.Source}}{{"|"}}{{end}}' 2>/dev/null || echo "")
+        
+        # Check if any of our target volumes are used by this container
+        for volume in "${VOLUMES[@]}"; do
+            if echo "$mounts" | grep -q "$volume"; then
+                containers_using_volumes+=("$container")
+                volume_usage_details+=("$container -> $volume")
+                break
+            fi
+        done
+    done
+    
+    # If any containers are using our volumes, show error and exit
+    if [ ${#containers_using_volumes[@]} -gt 0 ]; then
+        echo ""
+        echo "❌ ERROR: Found running containers using target volumes!"
+        echo ""
+        echo "📋 Running containers status:"
+        docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Image}}"
+        echo ""
+        echo "🔗 Volume usage details:"
+        for detail in "${volume_usage_details[@]}"; do
+            echo "  - $detail"
+        done
+        echo ""
+        echo "🛑 SOLUTION: Stop the containers before performing backup/restore operations:"
+        echo "   docker-compose -f docker/<your-docker-compose-file>.yml down"
+        echo ""
+        echo "💡 After backup/restore, you can restart with:"
+        echo "   docker-compose -f docker/<your-docker-compose-file>.yml up -d"
+        echo ""
+        exit 1
+    fi
+    
+    echo "✅ No containers are using target volumes, safe to proceed"
+    return 0
+}
+
+# Function to confirm user action
+confirm_action() {
+    local message=$1
+    echo -n "$message (y/N): "
+    read -r response
+    case "$response" in
+        [yY]|[yY][eE][sS]) return 0 ;;
+        *) return 1 ;;
+    esac
+}
+
+# Function to perform backup
+perform_backup() {
+    local backup_folder=$1
+    
+    echo "🚀 Starting RAGFlow data backup..."
+    echo "📁 Backup folder: $backup_folder"
+    echo ""
+    
+    # Check if any containers are using the volumes
+    check_containers_using_volumes
+    
+    # Create backup folder if it doesn't exist
+    mkdir -p "$backup_folder"
+    
+    # Backup each volume
+    for i in "${!VOLUMES[@]}"; do
+        local volume="${VOLUMES[$i]}"
+        local backup_file="${BACKUP_FILES[$i]}"
+        local step=$((i + 1))
+        
+        echo "📦 Step $step/4: Backing up $volume..."
+        
+        if volume_exists "$volume"; then
+            docker run --rm \
+                -v "$volume":/source \
+                -v "$(pwd)/$backup_folder":/backup \
+                alpine tar czf "/backup/$backup_file" -C /source .
+            echo "✅ Successfully backed up $volume to $backup_folder/$backup_file"
+        else
+            echo "⚠️  Warning: Volume $volume does not exist, skipping..."
+        fi
+        echo ""
+    done
+    
+    echo "🎉 Backup completed successfully!"
+    echo "📍 Backup location: $(pwd)/$backup_folder"
+    
+    # List backup files with sizes
+    echo ""
+    echo "📋 Backup files created:"
+    for backup_file in "${BACKUP_FILES[@]}"; do
+        if [ -f "$backup_folder/$backup_file" ]; then
+            local size=$(ls -lh "$backup_folder/$backup_file" | awk '{print $5}')
+            echo "  - $backup_file ($size)"
+        fi
+    done
+}
+
+# Function to perform restore
+perform_restore() {
+    local backup_folder=$1
+    
+    echo "🔄 Starting RAGFlow data restore..."
+    echo "📁 Backup folder: $backup_folder"
+    echo ""
+    
+    # Check if any containers are using the volumes
+    check_containers_using_volumes
+    
+    # Check if backup folder exists
+    if [ ! -d "$backup_folder" ]; then
+        echo "❌ Error: Backup folder '$backup_folder' does not exist"
+        exit 1
+    fi
+    
+    # Check if all backup files exist
+    local missing_files=()
+    for backup_file in "${BACKUP_FILES[@]}"; do
+        if [ ! -f "$backup_folder/$backup_file" ]; then
+            missing_files+=("$backup_file")
+        fi
+    done
+    
+    if [ ${#missing_files[@]} -gt 0 ]; then
+        echo "❌ Error: Missing backup files:"
+        for file in "${missing_files[@]}"; do
+            echo "  - $file"
+        done
+        echo "Please ensure all backup files are present in '$backup_folder'"
+        exit 1
+    fi
+    
+    # Check for existing volumes and warn user
+    local existing_volumes=()
+    for volume in "${VOLUMES[@]}"; do
+        if volume_exists "$volume"; then
+            existing_volumes+=("$volume")
+        fi
+    done
+    
+    if [ ${#existing_volumes[@]} -gt 0 ]; then
+        echo "⚠️  WARNING: The following Docker volumes already exist:"
+        for volume in "${existing_volumes[@]}"; do
+            echo "  - $volume"
+        done
+        echo ""
+        echo "🔴 IMPORTANT: Restoring will OVERWRITE existing data!"
+        echo "💡 Recommendation: Create a backup of your current data first:"
+        echo "   $0 backup current_backup_$(date +%Y%m%d_%H%M%S)"
+        echo ""
+        
+        if ! confirm_action "Do you want to continue with the restore operation?"; then
+            echo "❌ Restore operation cancelled by user"
+            exit 0
+        fi
+    fi
+    
+    # Create volumes and restore data
+    for i in "${!VOLUMES[@]}"; do
+        local volume="${VOLUMES[$i]}"
+        local backup_file="${BACKUP_FILES[$i]}"
+        local step=$((i + 1))
+        
+        echo "🔧 Step $step/4: Restoring $volume..."
+        
+        # Create volume if it doesn't exist
+        if ! volume_exists "$volume"; then
+            echo "  📋 Creating Docker volume: $volume"
+            docker volume create "$volume"
+        else
+            echo "  📋 Using existing Docker volume: $volume"
+        fi
+        
+        # Restore data
+        echo "  📥 Restoring data from $backup_file..."
+        docker run --rm \
+            -v "$volume":/target \
+            -v "$(pwd)/$backup_folder":/backup \
+            alpine tar xzf "/backup/$backup_file" -C /target
+        
+        echo "✅ Successfully restored $volume"
+        echo ""
+    done
+    
+    echo "🎉 Restore completed successfully!"
+    echo "💡 You can now start your RAGFlow services"
+}
+
+# Main script logic
+main() {
+    # Check if Docker is available
+    check_docker
+    
+    # Parse command line arguments
+    local operation=${1:-}
+    local backup_folder=${2:-$DEFAULT_BACKUP_FOLDER}
+    
+    # Handle help or no arguments
+    if [ -z "$operation" ] || [ "$operation" = "help" ] || [ "$operation" = "-h" ] || [ "$operation" = "--help" ]; then
+        show_help
+        exit 0
+    fi
+    
+    # Validate operation
+    case "$operation" in
+        backup)
+            perform_backup "$backup_folder"
+            ;;
+        restore)
+            perform_restore "$backup_folder"
+            ;;
+        *)
+            echo "❌ Error: Invalid operation '$operation'"
+            echo ""
+            show_help
+            exit 1
+            ;;
+    esac
+}
+
+# Run main function with all arguments
+main "$@"

docker/service_conf.yaml.template

@@ -9,6 +9,7 @@ mysql:
   port: 3306
   max_connections: 900
   stale_timeout: 300
+  max_allowed_packet: ${MYSQL_MAX_PACKET:-1073741824}
 minio:
   user: '${MINIO_USER:-rag_flow}'
   password: '${MINIO_PASSWORD:-infini_rag_flow}'

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:v0.20.0-slim` (default): The RAGFlow Docker image without embedding models.  
-  - `infiniflow/ragflow:v0.20.0`: The RAGFlow Docker image with embedding models including:
+  - `infiniflow/ragflow:v0.20.1-slim` (default): The RAGFlow Docker image without embedding models.  
+  - `infiniflow/ragflow:v0.20.1`: The RAGFlow Docker image with embedding models including:
     - Built-in embedding models:
       - `BAAI/bge-large-zh-v1.5` 
       - `maidalun1020/bce-embedding-base_v1`

docs/develop/build_docker_image.mdx

@@ -77,7 +77,7 @@ After building the infiniflow/ragflow:nightly-slim image, you are ready to launc
 
 1. Edit Docker Compose Configuration
 
-Open the `docker/.env` file. Find the `RAGFLOW_IMAGE` setting and change the image reference from `infiniflow/ragflow:v0.20.0-slim` to `infiniflow/ragflow:nightly-slim` to use the pre-built image.
+Open the `docker/.env` file. Find the `RAGFLOW_IMAGE` setting and change the image reference from `infiniflow/ragflow:v0.20.1-slim` to `infiniflow/ragflow:nightly-slim` to use the pre-built image.
 
 
 2. Launch the Service

docs/faq.mdx

@@ -30,17 +30,17 @@ The "garbage in garbage out" status quo remains unchanged despite the fact that
 
 Each RAGFlow release is available in two editions:
 
-- **Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.20.0-slim`
-- **Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.20.0`
+- **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`
 
 ---
 
 ### Which embedding models can be deployed locally?
 
-RAGFlow offers two Docker image editions, `v0.20.0-slim` and `v0.20.0`:  
+RAGFlow offers two Docker image editions, `v0.20.1-slim` and `v0.20.1`:  
   
-- `infiniflow/ragflow:v0.20.0-slim` (default): The RAGFlow Docker image without embedding models.  
-- `infiniflow/ragflow:v0.20.0`: The RAGFlow Docker image with embedding models including:
+- `infiniflow/ragflow:v0.20.1-slim` (default): The RAGFlow Docker image without embedding models.  
+- `infiniflow/ragflow:v0.20.1`: The RAGFlow Docker image with embedding models including:
   - Built-in embedding models:
     - `BAAI/bge-large-zh-v1.5`
     - `maidalun1020/bce-embedding-base_v1`

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 v0.20.0 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 v0.20.1 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.
@@ -82,7 +82,7 @@ An integer specifying the number of previous dialogue rounds to input into the L
 This feature is used for multi-turn dialogue *only*.
 :::
 
-### Max retrieves
+### Max retries
 
 Defines the maximum number of attempts the agent will make to retry a failed task or operation before stopping or reporting failure.
 
@@ -92,7 +92,11 @@ The waiting period in seconds that the agent observes before retrying a failed t
 
 ### Max rounds
 
-Defines the maximum number reflection rounds of the selected chat model. Defaults to 5 rounds.
+Defines the maximum number reflection rounds of the selected chat model. Defaults to 1 round.
+
+:::tip NOTE
+Increasing this value will significantly extend your agent's response time.
+:::
 
 ### Output
 

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 v0.20.0, 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 v0.20.1, a **Retrieval** component can operate either as a workflow component or as a tool of an **Agent**, enabling the Agent to control its invocation and search queries.
 
 ## Configurations
 

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 v0.20.0, if you add custom variables here, the only way you can pass in their values is to call:
+      - As of v0.20.1, if you add custom variables here, the only way you can pass in their values is to call:
          - HTTP method [Converse with chat assistant](../../references/http_api_reference.md#converse-with-chat-assistant), or
          - Python method [Converse with chat assistant](../../references/python_api_reference.md#converse-with-chat-assistant).
 

docs/guides/dataset/configure_knowledge_base.md

@@ -128,7 +128,7 @@ See [Run retrieval test](./run_retrieval_test.md) for details.
 
 ## Search for knowledge base
 
-As of RAGFlow v0.20.0, the search feature is still in a rudimentary form, supporting only knowledge base search by name.
+As of RAGFlow v0.20.1, 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)
 

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 v0.20.0, bulk download is not supported, nor can you download an entire folder. 
+> As of RAGFlow v0.20.1, bulk download is not supported, nor can you download an entire folder. 

docs/guides/migration/migrate_from_docker_compose.md

@@ -0,0 +1,108 @@
+# Data Migration Guide
+
+A common scenario is processing large datasets on a powerful instance (e.g., with a GPU) and then migrating the entire RAGFlow service to a different production environment (e.g., a CPU-only server). This guide explains how to safely back up and restore your data using our provided migration script.
+
+## Identifying Your Data
+
+By default, RAGFlow uses Docker volumes to store all persistent data, including your database, uploaded files, and search indexes. You can see these volumes by running:
+
+```bash
+docker volume ls
+```
+
+The output will look similar to this:
+
+```text
+DRIVER    VOLUME NAME
+local     docker_esdata01
+local     docker_minio_data
+local     docker_mysql_data
+local     docker_redis_data
+```
+
+These volumes contain all the data you need to migrate.
+
+## Step 1: Stop RAGFlow Services
+
+Before starting the migration, you must stop all running RAGFlow services on the **source machine**. Navigate to the project's root directory and run:
+
+```bash
+docker-compose -f docker/docker-compose.yml down
+```
+
+**Important:** Do **not** use the `-v` flag (e.g., `docker-compose down -v`), as this will delete all your data volumes. The migration script includes a check and will prevent you from running it if services are active.
+
+## Step 2: Back Up Your Data
+
+We provide a convenient script to package all your data volumes into a single backup folder.
+
+For a quick reference of the script's commands and options, you can run:
+```bash
+bash docker/migration.sh help
+```
+
+To create a backup, run the following command from the project's root directory:
+
+```bash
+bash docker/migration.sh backup
+```
+
+This will create a `backup/` folder in your project root containing compressed archives of your data volumes.
+
+You can also specify a custom name for your backup folder:
+
+```bash
+bash docker/migration.sh backup my_ragflow_backup
+```
+
+This will create a folder named `my_ragflow_backup/` instead.
+
+## Step 3: Transfer the Backup Folder
+
+Copy the entire backup folder (e.g., `backup/` or `my_ragflow_backup/`) from your source machine to the RAGFlow project directory on your **target machine**. You can use tools like `scp`, `rsync`, or a physical drive for the transfer.
+
+## Step 4: Restore Your Data
+
+On the **target machine**, ensure that RAGFlow services are not running. Then, use the migration script to restore your data from the backup folder.
+
+If your backup folder is named `backup/`, run:
+
+```bash
+bash docker/migration.sh restore
+```
+
+If you used a custom name, specify it in the command:
+
+```bash
+bash docker/migration.sh restore my_ragflow_backup
+```
+
+The script will automatically create the necessary Docker volumes and unpack the data.
+
+**Note:** If the script detects that Docker volumes with the same names already exist on the target machine, it will warn you that restoring will overwrite the existing data and ask for confirmation before proceeding.
+
+## Step 5: Start RAGFlow Services
+
+Once the restore process is complete, you can start the RAGFlow services on your new machine:
+
+```bash
+docker-compose -f docker/docker-compose.yml up -d
+```
+
+**Note:** If you already have build an service by docker-compose before, you may need to backup your data for target machine like this guide above and run like:
+
+```bash
+# Please backup by `sh docker/migration.sh backup backup_dir_name` before you do the following line.
+# !!! this line -v flag will delete the original docker volume
+docker-compose -f docker/docker-compose.yml down -v
+docker-compose -f docker/docker-compose.yml up -d
+```
+
+Your RAGFlow instance is now running with all the data from your original machine.
+
+
+
+
+
+
+

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 **≥ 0.20.0** (contains the Langfuse connector)  
+• RAGFlow **≥ 0.20.1** (contains the Langfuse connector)  
 • A Langfuse workspace (cloud or self-hosted) with a _Project Public Key_ and _Secret Key_
 :::
 

docs/guides/upgrade_ragflow.mdx

@@ -66,10 +66,10 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
    git clone https://github.com/infiniflow/ragflow.git
    ```
 
-2. Switch to the latest, officially published release, e.g., `v0.20.0`:
+2. Switch to the latest, officially published release, e.g., `v0.20.1`:
 
    ```bash
-   git checkout -f v0.20.0
+   git checkout -f v0.20.1
    ```
 
 3. Update **ragflow/docker/.env**:
@@ -83,14 +83,14 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
   <TabItem value="slim">
 
 ```bash
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0-slim
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1-slim
 ```
 
   </TabItem>
   <TabItem value="full">
 
 ```bash
-RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0
+RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1
 ```
 
   </TabItem>
@@ -114,10 +114,10 @@ No, you do not need to. Upgrading RAGFlow in itself will *not* remove your uploa
 1. From an environment with Internet access, pull the required Docker image.
 2. Save the Docker image to a **.tar** file.
    ```bash
-   docker save -o ragflow.v0.20.0.tar infiniflow/ragflow:v0.20.0
+   docker save -o ragflow.v0.20.1.tar infiniflow/ragflow:v0.20.1
    ```
 3. Copy the **.tar** file to the target server.
 4. Load the **.tar** file into Docker:
    ```bash
-   docker load -i ragflow.v0.20.0.tar
+   docker load -i ragflow.v0.20.1.tar
    ```

docs/quickstart.mdx

@@ -44,7 +44,7 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
 
    `vm.max_map_count`. This value sets the maximum number of memory map areas a process may have. Its default value is 65530. While most applications require fewer than a thousand maps, reducing this value can result in abnormal behaviors, and the system will throw out-of-memory errors when a process reaches the limitation.
 
-   RAGFlow v0.20.0 uses Elasticsearch or [Infinity](https://github.com/infiniflow/infinity) for multiple recall. Setting the value of `vm.max_map_count` correctly is crucial to the proper functioning of the Elasticsearch component.
+   RAGFlow v0.20.1 uses Elasticsearch or [Infinity](https://github.com/infiniflow/infinity) for multiple recall. Setting the value of `vm.max_map_count` correctly is crucial to the proper functioning of the Elasticsearch component.
 
 <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 v0.20.0
+   $ git checkout -f v0.20.1
    ```
 
 3. Use the pre-built Docker images and start up the server:
 
    :::tip NOTE
-   The command below downloads the `v0.20.0-slim` edition of the RAGFlow Docker image. Refer to the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.0-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.0` for the full edition `v0.20.0`.
+   The command below downloads the `v0.20.1-slim` edition of the RAGFlow Docker image. Refer to the following table for descriptions of different RAGFlow editions. To download a RAGFlow edition different from `v0.20.1-slim`, update the `RAGFLOW_IMAGE` variable accordingly in **docker/.env** before using `docker compose` to start the server. For example: set `RAGFLOW_IMAGE=infiniflow/ragflow:v0.20.1` for the full edition `v0.20.1`.
    :::
 
    ```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?                  |
 | ------------------- | --------------- | ----------------------------------------- | ------------------------ |
-| `v0.20.0`           | &approx;9       | :heavy_check_mark:                        | Stable release           |
-| `v0.20.0-slim`      | &approx;2       | ❌                                        | Stable release           |
+| `v0.20.1`           | &approx;9       | :heavy_check_mark:                        | Stable release           |
+| `v0.20.1-slim`      | &approx;2       | ❌                                        | Stable release           |
 | `nightly`           | &approx;9       | :heavy_check_mark:                        | *Unstable* nightly build |
 | `nightly-slim`      | &approx;2       | ❌                                        | *Unstable* nightly build |
 
@@ -217,7 +217,7 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
 ```
 
 :::danger IMPORTANT
-The embedding models included in `v0.20.0` and `nightly` are:
+The embedding models included in `v0.20.1` and `nightly` are:
 
 - BAAI/bge-large-zh-v1.5
 - maidalun1020/bce-embedding-base_v1

docs/references/glossary.mdx

@@ -19,7 +19,7 @@ import TOCInline from '@theme/TOCInline';
 
 ### Cross-language search
 
-Cross-language search (also known as cross-lingual retrieval) is a feature introduced in version 0.20.0. It enables users to submit queries in one language (for example, English) and retrieve relevant documents written in other languages such as Chinese or Spanish. This feature is enabled by the system’s default chat model, which translates queries to ensure accurate matching of semantic meaning across languages.
+Cross-language search (also known as cross-lingual retrieval) is a feature introduced in version 0.20.1. It enables users to submit queries in one language (for example, English) and retrieve relevant documents written in other languages such as Chinese or Spanish. This feature is enabled by the system’s default chat model, which translates queries to ensure accurate matching of semantic meaning across languages.
 
 By enabling cross-language search, users can effortlessly access a broader range of information regardless of language barriers, significantly enhancing the system’s usability and inclusiveness.
 

docs/references/http_api_reference.md

@@ -1118,14 +1118,14 @@ Failure:
 
 ### List documents
 
-**GET** `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}`
+**GET** `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp}`
 
 Lists documents in a specified dataset.
 
 #### Request
 
 - Method: GET
-- URL: `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}`
+- URL: `/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp}`
 - Headers:
   - `'content-Type: application/json'`
   - `'Authorization: Bearer <YOUR_API_KEY>'`
@@ -1134,7 +1134,7 @@ Lists documents in a specified dataset.
 
 ```bash
 curl --request GET \
-     --url http://{address}/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name} \
+     --url http://{address}/api/v1/datasets/{dataset_id}/documents?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}&name={document_name}&create_time_from={timestamp}&create_time_to={timestamp} \
      --header 'Authorization: Bearer <YOUR_API_KEY>'
 ```
 
@@ -1156,6 +1156,10 @@ curl --request GET \
   Indicates whether the retrieved documents should be sorted in descending order. Defaults to `true`.
 - `id`: (*Filter parameter*), `string`  
   The ID of the document to retrieve.
+- `create_time_from`: (*Filter parameter*), `integer`
+  Unix timestamp for filtering documents created after this time. 0 means no filter. Defaults to `0`.
+- `create_time_to`: (*Filter parameter*), `integer`
+  Unix timestamp for filtering documents created before this time. 0 means no filter. Defaults to `0`.
 
 #### Response
 

docs/references/python_api_reference.md

@@ -507,7 +507,16 @@ print(doc)
 ### List documents
 
 ```python
-Dataset.list_documents(id:str =None, keywords: str=None, page: int=1, page_size:int = 30, order_by:str = "create_time", desc: bool = True) -> list[Document]
+Dataset.list_documents(
+    id: str = None,
+    keywords: str = None,
+    page: int = 1,
+    page_size: int = 30,
+    order_by: str = "create_time",
+    desc: bool = True,
+    create_time_from: int = 0,
+    create_time_to: int = 0
+) -> list[Document]
 ```
 
 Lists documents in the current dataset.
@@ -541,6 +550,12 @@ The field by which documents should be sorted. Available options:
 
 Indicates whether the retrieved documents should be sorted in descending order. Defaults to `True`.
 
+##### create_time_from: `int`
+Unix timestamp for filtering documents created after this time. 0 means no filter. Defaults to 0.
+
+##### create_time_to: `int`
+Unix timestamp for filtering documents created before this time. 0 means no filter. Defaults to 0.
+
 #### Returns
 
 - Success: A list of `Document` objects.

docs/release_notes.md

@@ -22,6 +22,65 @@ 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.
 :::
 
+## v0.20.1
+
+Released on August 8, 2025.
+
+### New Features
+
+- The **Retrieval** component now supports the dynamic specification of knowledge base names using variables.
+- The user interface now includes a French language option.
+
+### Added Models
+
+- ChatGPT 5
+- Claude 4.1
+
+### New agent Templates (both workflow and agentic)
+
+- SQL Assistant Workflow: Empowers non-technical teams (e.g., operations, product) to independently query business data.
+- Choose Your Knowledge Base Workflow: Lets users select a knowledge base to query during conversations. [#9325](https://github.com/infiniflow/ragflow/pull/9325)
+- Choose Your Knowledge Base Agent: Delivers higher-quality responses with extended reasoning time, suited for complex queries. [#9325](https://github.com/infiniflow/ragflow/pull/9325)
+
+### Fixed Issues
+
+- The **Agent** component was unable to invoke models installed via vLLM.
+- Agents could not be shared with the team.
+- Embedding an Agent into a webpage was not functioning properly.
+
+## v0.20.0
+
+Released on August 4, 2025.
+
+### Compatibility changes
+
+From v0.20.0 onwards, Agents are no longer compatible with earlier versions, and all existing Agents from previous versions must be rebuilt following the upgrade.
+
+### New features
+
+- Unified orchestration of both Agents and Workflows.
+- A comprehensive refactor of the Agent, greatly enhancing its capabilities and usability, with support for Multi-Agent configurations, planning and reflection, and visual functionalities.
+- Fully implemented MCP functionality, allowing for MCP Server import, Agents functioning as MCP Clients, and RAGFlow itself operating as an MCP Server.
+- Access to runtime logs for Agents.
+- Chat histories with Agents available through the management panel.
+- Integration of a new, more robust version of Infinity, enabling the auto-tagging functionality with Infinity as the underlying document engine.
+- An OpenAI-compatible API that supports file reference information.
+- Support for new models, including Kimi K2, Grok 4, and Voyage embedding.
+- RAGFlow’s codebase is now mirrored on Gitee.
+- Introduction of a new model provider, Gitee AI.
+
+### New agent templates introduced
+
+- Multi-Agent based Deep Research: Collaborative Agent teamwork led by a Lead Agent with multiple Subagents, distinct from traditional workflow orchestration.
+- An intelligent Q&A chatbot leveraging internal knowledge bases, designed for customer service and training scenarios.
+- A resume analysis template used by the RAGFlow team to screen, analyze, and record candidate information.
+- A blog generation workflow that transforms raw ideas into SEO-friendly blog content.
+- An intelligent customer service workflow.
+- A user feedback analysis template that directs user feedback to appropriate teams through semantic analysis.
+- Trip Planner: Uses web search and map MCP servers to assist with travel planning.
+- Image Lingo: Translates content from uploaded photos.
+- An information search assistant that retrieves answers from both internal knowledge bases and the web.
+
 ## v0.19.1
 
 Released on June 23, 2025.

graphrag/general/extractor.py

@@ -47,7 +47,7 @@ class Extractor:
         self._language = language
         self._entity_types = entity_types or DEFAULT_ENTITY_TYPES
 
-    @timeout(60*3)
+    @timeout(60*5)
     def _chat(self, system, history, gen_conf={}):
         hist = deepcopy(history)
         conf = deepcopy(gen_conf)

helm/values.yaml

@@ -33,13 +33,13 @@ env:
   REDIS_PASSWORD: infini_rag_flow_helm
 
   # The RAGFlow Docker image to download.
-  # Defaults to the v0.20.0-slim edition, which is the RAGFlow Docker image without embedding models.
-  RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.0-slim
+  # Defaults to the v0.20.1-slim edition, which is the RAGFlow Docker image without embedding models.
+  RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.1-slim
   #
   # To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
-  # RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.0
+  # RAGFLOW_IMAGE: infiniflow/ragflow:v0.20.1
   #
-  # The Docker image of the v0.20.0 edition includes:
+  # The Docker image of the v0.20.1 edition includes:
   # - Built-in embedding models:
   #   - BAAI/bge-large-zh-v1.5
   #   - BAAI/bge-reranker-v2-m3

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragflow"
-version = "0.20.0"
+version = "0.20.1"
 description = "[RAGFlow](https://ragflow.io/) is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data."
 authors = [{ name = "Zhichang Yu", email = "yuzhichang@gmail.com" }]
 license-files = ["LICENSE"]

rag/app/presentation.py

@@ -42,7 +42,7 @@ class Ppt(PptParser):
                 try:
                     with BytesIO() as buffered:
                         slide.get_thumbnail(
-                            0.5, 0.5).save(
+                            0.1, 0.1).save(
                             buffered, drawing.imaging.ImageFormat.jpeg)
                         buffered.seek(0)
                         imgs.append(Image.open(buffered).copy())
@@ -135,7 +135,8 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             sections = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback)
         elif layout_recognizer == "Plain Text":
             pdf_parser = PlainParser()
-            sections, _ = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback)
+            sections, _ = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page,
+                                      callback=callback)
         else:
             vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT, llm_name=layout_recognizer, lang=lang)
             pdf_parser = VisionParser(vision_model=vision_model, **kwargs)

rag/llm/chat_model.py

@@ -1075,6 +1075,9 @@ class GeminiChat(Base):
         for k in list(gen_conf.keys()):
             if k not in ["temperature", "top_p", "max_tokens"]:
                 del gen_conf[k]
+            # if max_tokens exists, rename it to max_output_tokens to match Gemini's API
+            if k == "max_tokens":
+                gen_conf["max_output_tokens"] = gen_conf.pop("max_tokens")
         return gen_conf
 
     def _chat(self, history, gen_conf={}, **kwargs):
@@ -1096,9 +1099,20 @@ class GeminiChat(Base):
 
         if system:
             self.model._system_instruction = content_types.to_content(system)
-        response = self.model.generate_content(hist, generation_config=gen_conf)
-        ans = response.text
-        return ans, response.usage_metadata.total_token_count
+        retry_count = 0
+        max_retries = 3
+        while retry_count < max_retries:
+            try:
+                response = self.model.generate_content(hist, generation_config=gen_conf)
+                ans = response.text
+                return ans, response.usage_metadata.total_token_count
+            except Exception as e:
+                retry_count += 1
+                if retry_count >= max_retries:
+                    raise e
+                else:
+                    import time
+                    time.sleep(50) 
 
     def chat_streamly(self, system, history, gen_conf={}, **kwargs):
         from google.generativeai.types import content_types
@@ -1213,11 +1227,11 @@ class LmStudioChat(Base):
 class OpenAI_APIChat(Base):
     _FACTORY_NAME = ["VLLM", "OpenAI-API-Compatible"]
 
-    def __init__(self, key, model_name, base_url):
+    def __init__(self, key, model_name, base_url, **kwargs):
         if not base_url:
             raise ValueError("url cannot be None")
         model_name = model_name.split("___")[0]
-        super().__init__(key, model_name, base_url)
+        super().__init__(key, model_name, base_url, **kwargs)
 
 
 class PPIOChat(Base):

rag/llm/cv_model.py

@@ -59,6 +59,10 @@ class Base(ABC):
     def _image_prompt(self, text, images):
         if not images:
             return text
+
+        if isinstance(images, str) or "bytes" in type(images).__name__:
+            images = [images]
+
         pmpt = [{"type": "text", "text": text}]
         for img in images:
             pmpt.append({
@@ -518,6 +522,7 @@ class GeminiCV(Base):
     def chat_streamly(self, system, history, gen_conf, images=[]):
         from transformers import GenerationConfig
         ans = ""
+        response = None
         try:
             response = self.model.generate_content(
                 self._form_history(system, history, images),
@@ -533,8 +538,11 @@ class GeminiCV(Base):
         except Exception as e:
             yield ans + "\n**ERROR**: " + str(e)
 
-        yield response._chunks[-1].usage_metadata.total_token_count
-
+        if response and hasattr(response, "usage_metadata") and hasattr(response.usage_metadata, "total_token_count"):
+            yield response.usage_metadata.total_token_count
+        else:
+            yield 0
+            
 
 class NvidiaCV(Base):
     _FACTORY_NAME = "NVIDIA"
@@ -616,15 +624,18 @@ class NvidiaCV(Base):
             return "**ERROR**: " + str(e), 0
 
     def chat_streamly(self, system, history, gen_conf, images=[], **kwargs):
+        total_tokens = 0
         try:
             response = self._request(self._form_history(system, history, images), gen_conf)
             cnt = response["choices"][0]["message"]["content"]
+            if "usage" in response and "total_tokens" in response["usage"]:
+                total_tokens += response["usage"]["total_tokens"]
             for resp in cnt:
                 yield resp
         except Exception as e:
             yield "\n**ERROR**: " + str(e)
 
-        yield response["usage"]["total_tokens"]
+        yield total_tokens
 
 
 class AnthropicCV(Base):
@@ -795,4 +806,4 @@ class GoogleCV(AnthropicCV, GeminiCV):
                 yield ans
         else:
             for ans in GeminiCV.chat_streamly(self, system, history, gen_conf, images):
-                yield ans
+                yield ans

rag/llm/embedding_model.py

@@ -37,7 +37,12 @@ from rag.utils import num_tokens_from_string, truncate
 
 
 class Base(ABC):
-    def __init__(self, key, model_name):
+    def __init__(self, key, model_name, **kwargs):
+        """
+        Constructor for abstract base class.
+        Parameters are accepted for interface consistency but are not stored.
+        Subclasses should implement their own initialization as needed.
+        """
         pass
 
     def encode(self, texts: list):
@@ -864,7 +869,7 @@ class VoyageEmbed(Base):
 class HuggingFaceEmbed(Base):
     _FACTORY_NAME = "HuggingFace"
 
-    def __init__(self, key, model_name, base_url=None):
+    def __init__(self, key, model_name, base_url=None, **kwargs):
         if not model_name:
             raise ValueError("Model name cannot be None")
         self.key = key
@@ -946,4 +951,4 @@ class Ai302Embed(Base):
     def __init__(self, key, model_name, base_url="https://api.302.ai/v1/embeddings"):
         if not base_url:
             base_url = "https://api.302.ai/v1/embeddings"
-        super().__init__(key, model_name, base_url)
+        super().__init__(key, model_name, base_url)

rag/llm/rerank_model.py

@@ -33,7 +33,11 @@ from api.utils.log_utils import log_exception
 from rag.utils import num_tokens_from_string, truncate
 
 class Base(ABC):
-    def __init__(self, key, model_name):
+    def __init__(self, key, model_name, **kwargs):
+        """
+        Abstract base class constructor.
+        Parameters are not stored; initialization is left to subclasses.
+        """
         pass
 
     def similarity(self, query: str, texts: list):
@@ -315,7 +319,7 @@ class NvidiaRerank(Base):
 class LmStudioRerank(Base):
     _FACTORY_NAME = "LM-Studio"
 
-    def __init__(self, key, model_name, base_url):
+    def __init__(self, key, model_name, base_url, **kwargs):
         pass
 
     def similarity(self, query: str, texts: list):
@@ -396,7 +400,7 @@ class CoHereRerank(Base):
 class TogetherAIRerank(Base):
     _FACTORY_NAME = "TogetherAI"
 
-    def __init__(self, key, model_name, base_url):
+    def __init__(self, key, model_name, base_url, **kwargs):
         pass
 
     def similarity(self, query: str, texts: list):

rag/llm/sequence2txt_model.py

@@ -28,7 +28,11 @@ from rag.utils import num_tokens_from_string
 
 
 class Base(ABC):
-    def __init__(self, key, model_name):
+    def __init__(self, key, model_name, **kwargs):
+        """
+        Abstract base class constructor.
+        Parameters are not stored; initialization is left to subclasses.
+        """
         pass
 
     def transcription(self, audio, **kwargs):

rag/llm/tts_model.py

@@ -63,7 +63,11 @@ class ServeTTSRequest(BaseModel):
 
 
 class Base(ABC):
-    def __init__(self, key, model_name, base_url):
+    def __init__(self, key, model_name, base_url, **kwargs):
+        """
+        Abstract base class constructor.
+        Parameters are not stored; subclasses should handle their own initialization.
+        """
         pass
 
     def tts(self, audio):

rag/nlp/__init__.py

@@ -611,6 +611,10 @@ def naive_merge_with_images(texts, images, chunk_token_num=128, delimiter="\n。
                 if re.match(f"^{dels}$", sub_sec):
                     continue
                 add_chunk(sub_sec, image)
+        
+        for img in images:
+            if isinstance(img, Image.Image):
+                img.close()
 
     return cks, result_images
 
@@ -634,6 +638,16 @@ def concat_img(img1, img2):
         return img2
     if not img1 and not img2:
         return None
+    
+    if img1 is img2:
+        return img1
+    
+    if isinstance(img1, Image.Image) and isinstance(img2, Image.Image):
+        pixel_data1 = img1.tobytes()
+        pixel_data2 = img2.tobytes()
+        if pixel_data1 == pixel_data2:
+            return img1
+
     width1, height1 = img1.size
     width2, height2 = img2.size
 
@@ -643,7 +657,6 @@ def concat_img(img1, img2):
 
     new_image.paste(img1, (0, 0))
     new_image.paste(img2, (0, height1))
-
     return new_image
 
 

rag/svr/task_executor.py

@@ -231,7 +231,7 @@ async def get_storage_binary(bucket, name):
     return await trio.to_thread.run_sync(lambda: STORAGE_IMPL.get(bucket, name))
 
 
-@timeout(60*40, 1)
+@timeout(60*80, 1)
 async def build_chunks(task, progress_callback):
     if task["size"] > DOC_MAXIMUM_SIZE:
         set_progress(task["id"], prog=-1, msg="File size exceeds( <= %dMb )" %
@@ -284,7 +284,7 @@ async def build_chunks(task, progress_callback):
         try:
             d = copy.deepcopy(document)
             d.update(chunk)
-            d["id"] = xxhash.xxh64((chunk["content_with_weight"] + str(d["doc_id"])).encode("utf-8")).hexdigest()
+            d["id"] = xxhash.xxh64((chunk["content_with_weight"] + str(d["doc_id"])).encode("utf-8", "surrogatepass")).hexdigest()
             d["create_time"] = str(datetime.now()).replace("T", " ")[:19]
             d["create_timestamp_flt"] = datetime.now().timestamp()
             if not d.get("image"):
@@ -420,7 +420,6 @@ def init_kb(row, vector_size: int):
     return settings.docStoreConn.createIdx(idxnm, row.get("kb_id", ""), vector_size)
 
 
-@timeout(60*20)
 async def embedding(docs, mdl, parser_config=None, callback=None):
     if parser_config is None:
         parser_config = {}
@@ -441,10 +440,15 @@ async def embedding(docs, mdl, parser_config=None, callback=None):
         tts = np.concatenate([vts for _ in range(len(tts))], axis=0)
         tk_count += c
 
+    @timeout(5)
+    def batch_encode(txts):
+        nonlocal mdl
+        return mdl.encode([truncate(c, mdl.max_length-10) for c in txts])
+
     cnts_ = np.array([])
     for i in range(0, len(cnts), EMBEDDING_BATCH_SIZE):
         async with embed_limiter:
-            vts, c = await trio.to_thread.run_sync(lambda: mdl.encode([truncate(c, mdl.max_length-10) for c in cnts[i: i + EMBEDDING_BATCH_SIZE]]))
+            vts, c = await trio.to_thread.run_sync(lambda: batch_encode(cnts[i: i + EMBEDDING_BATCH_SIZE]))
         if len(cnts_) == 0:
             cnts_ = vts
         else:

rag/utils/opendal_conn.py

@@ -23,7 +23,7 @@ SET GLOBAL max_allowed_packet={}
 def get_opendal_config():
     try:
         opendal_config = get_base_config('opendal', {})
-        if opendal_config.get("scheme") == 'mysql':
+        if opendal_config.get("scheme", "mysql") == 'mysql':
             mysql_config = get_base_config('mysql', {})
             max_packet = mysql_config.get("max_allowed_packet", 134217728)
             kwargs = {
@@ -33,7 +33,7 @@ def get_opendal_config():
                 "user": mysql_config.get("user", "root"),
                 "password": mysql_config.get("password", ""),
                 "database": mysql_config.get("name", "test_open_dal"),
-                "table": opendal_config.get("config").get("oss_table", "opendal_storage"),
+                "table": opendal_config.get("config", {}).get("oss_table", "opendal_storage"),
                 "max_allowed_packet": str(max_packet)
             }
             kwargs["connection_string"] = f"mysql://{kwargs['user']}:{quote_plus(kwargs['password'])}@{kwargs['host']}:{kwargs['port']}/{kwargs['database']}?max_allowed_packet={max_packet}"

rag/utils/redis_conn.py

@@ -227,9 +227,20 @@ class RedisDB:
         """https://redis.io/docs/latest/commands/xreadgroup/"""
         for _ in range(3):
             try:
-                group_info = self.REDIS.xinfo_groups(queue_name)
-                if not any(gi["name"] == group_name for gi in group_info):
-                    self.REDIS.xgroup_create(queue_name, group_name, id="0", mkstream=True)
+
+                try:
+                    group_info = self.REDIS.xinfo_groups(queue_name)
+                    if not any(gi["name"] == group_name for gi in group_info):
+                        self.REDIS.xgroup_create(queue_name, group_name, id="0", mkstream=True)
+                except redis.exceptions.ResponseError as e:
+                    if "no such key" in str(e).lower():
+                        self.REDIS.xgroup_create(queue_name, group_name, id="0", mkstream=True)
+                    elif "busygroup" in str(e).lower():
+                        logging.warning("Group already exists, continue.")
+                        pass
+                    else:
+                        raise
+
                 args = {
                     "groupname": group_name,
                     "consumername": consumer_name,
@@ -338,8 +349,8 @@ class RedisDB:
             logging.warning("RedisDB.delete " + str(key) + " got exception: " + str(e))
             self.__open__()
         return False
-    
-    
+
+
 REDIS_CONN = RedisDB()
 
 

rag/utils/s3_conn.py

@@ -30,7 +30,8 @@ class RAGFlowS3:
         self.s3_config = settings.S3
         self.access_key = self.s3_config.get('access_key', None)
         self.secret_key = self.s3_config.get('secret_key', None)
-        self.region = self.s3_config.get('region', None)
+        self.session_token = self.s3_config.get('session_token', None)
+        self.region_name = self.s3_config.get('region_name', None)
         self.endpoint_url = self.s3_config.get('endpoint_url', None)
         self.signature_version = self.s3_config.get('signature_version', None)
         self.addressing_style = self.s3_config.get('addressing_style', None)
@@ -73,31 +74,32 @@ class RAGFlowS3:
                 s3_params = {
                     'aws_access_key_id': self.access_key,
                     'aws_secret_access_key': self.secret_key,
+                    'aws_session_token': self.session_token,
                 }
-            if self.region in self.s3_config:
-                s3_params['region_name'] = self.region
-            if 'endpoint_url' in self.s3_config:
+            if self.region_name:
+                s3_params['region_name'] = self.region_name
+            if self.endpoint_url:
                 s3_params['endpoint_url'] = self.endpoint_url
-            if 'signature_version' in self.s3_config:
-                config_kwargs['signature_version'] = self.signature_version
-            if 'addressing_style' in self.s3_config:
-                config_kwargs['addressing_style'] = self.addressing_style
+            if self.signature_version:
+                s3_params['signature_version'] = self.signature_version
+            if self.addressing_style:
+                s3_params['addressing_style'] = self.addressing_style
             if config_kwargs:
                 s3_params['config'] = Config(**config_kwargs)
             
-            self.conn = boto3.client('s3', **s3_params)
+            self.conn = [boto3.client('s3', **s3_params)]
         except Exception:
-            logging.exception(f"Fail to connect at region {self.region} or endpoint {self.endpoint_url}")
+            logging.exception(f"Fail to connect at region {self.region_name} or endpoint {self.endpoint_url}")
 
     def __close__(self):
-        del self.conn
+        del self.conn[0]
         self.conn = None
 
     @use_default_bucket
-    def bucket_exists(self, bucket):
+    def bucket_exists(self, bucket, *args, **kwargs):
         try:
             logging.debug(f"head_bucket bucketname {bucket}")
-            self.conn.head_bucket(Bucket=bucket)
+            self.conn[0].head_bucket(Bucket=bucket)
             exists = True
         except ClientError:
             logging.exception(f"head_bucket error {bucket}")
@@ -109,10 +111,10 @@ class RAGFlowS3:
         fnm = "txtxtxtxt1"
         fnm, binary = f"{self.prefix_path}/{fnm}" if self.prefix_path else fnm, b"_t@@@1"
         if not self.bucket_exists(bucket):
-            self.conn.create_bucket(Bucket=bucket)
+            self.conn[0].create_bucket(Bucket=bucket)
             logging.debug(f"create bucket {bucket} ********")
 
-        r = self.conn.upload_fileobj(BytesIO(binary), bucket, fnm)
+        r = self.conn[0].upload_fileobj(BytesIO(binary), bucket, fnm)
         return r
 
     def get_properties(self, bucket, key):
@@ -123,14 +125,14 @@ class RAGFlowS3:
 
     @use_prefix_path
     @use_default_bucket
-    def put(self, bucket, fnm, binary):
+    def put(self, bucket, fnm, binary, *args, **kwargs):
         logging.debug(f"bucket name {bucket}; filename :{fnm}:")
         for _ in range(1):
             try:
                 if not self.bucket_exists(bucket):
-                    self.conn.create_bucket(Bucket=bucket)
+                    self.conn[0].create_bucket(Bucket=bucket)
                     logging.info(f"create bucket {bucket} ********")
-                r = self.conn.upload_fileobj(BytesIO(binary), bucket, fnm)
+                r = self.conn[0].upload_fileobj(BytesIO(binary), bucket, fnm)
 
                 return r
             except Exception:
@@ -140,18 +142,18 @@ class RAGFlowS3:
 
     @use_prefix_path
     @use_default_bucket
-    def rm(self, bucket, fnm):
+    def rm(self, bucket, fnm, *args, **kwargs):
         try:
-            self.conn.delete_object(Bucket=bucket, Key=fnm)
+            self.conn[0].delete_object(Bucket=bucket, Key=fnm)
         except Exception:
             logging.exception(f"Fail rm {bucket}/{fnm}")
 
     @use_prefix_path
     @use_default_bucket
-    def get(self, bucket, fnm):
+    def get(self, bucket, fnm, *args, **kwargs):
         for _ in range(1):
             try:
-                r = self.conn.get_object(Bucket=bucket, Key=fnm)
+                r = self.conn[0].get_object(Bucket=bucket, Key=fnm)
                 object_data = r['Body'].read()
                 return object_data
             except Exception:
@@ -162,9 +164,9 @@ class RAGFlowS3:
 
     @use_prefix_path
     @use_default_bucket
-    def obj_exist(self, bucket, fnm):
+    def obj_exist(self, bucket, fnm, *args, **kwargs):
         try:
-            if self.conn.head_object(Bucket=bucket, Key=fnm):
+            if self.conn[0].head_object(Bucket=bucket, Key=fnm):
                 return True
         except ClientError as e:
             if e.response['Error']['Code'] == '404':
@@ -174,10 +176,10 @@ class RAGFlowS3:
 
     @use_prefix_path
     @use_default_bucket
-    def get_presigned_url(self, bucket, fnm, expires):
+    def get_presigned_url(self, bucket, fnm, expires, *args, **kwargs):
         for _ in range(10):
             try:
-                r = self.conn.generate_presigned_url('get_object',
+                r = self.conn[0].generate_presigned_url('get_object',
                                                      Params={'Bucket': bucket,
                                                              'Key': fnm},
                                                      ExpiresIn=expires)

sdk/python/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragflow-sdk"
-version = "0.20.0"
+version = "0.20.1"
 description = "Python client sdk of [RAGFlow](https://github.com/infiniflow/ragflow). RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding."
 authors = [{ name = "Zhichang Yu", email = "yuzhichang@gmail.com" }]
 license = { text = "Apache License, Version 2.0" }

sdk/python/ragflow_sdk/modules/dataset.py

@@ -63,8 +63,30 @@ class DataSet(Base):
             return doc_list
         raise Exception(res.get("message"))
 
-    def list_documents(self, id: str | None = None, name: str | None = None, keywords: str | None = None, page: int = 1, page_size: int = 30, orderby: str = "create_time", desc: bool = True):
-        res = self.get(f"/datasets/{self.id}/documents", params={"id": id, "name": name, "keywords": keywords, "page": page, "page_size": page_size, "orderby": orderby, "desc": desc})
+    def list_documents(
+        self,
+        id: str | None = None,
+        name: str | None = None,
+        keywords: str | None = None,
+        page: int = 1,
+        page_size: int = 30,
+        orderby: str = "create_time",
+        desc: bool = True,
+        create_time_from: int = 0,
+        create_time_to: int = 0,
+    ):
+        params = {
+            "id": id,
+            "name": name,
+            "keywords": keywords,
+            "page": page,
+            "page_size": page_size,
+            "orderby": orderby,
+            "desc": desc,
+            "create_time_from": create_time_from,
+            "create_time_to": create_time_to,
+        }
+        res = self.get(f"/datasets/{self.id}/documents", params=params)
         res = res.json()
         documents = []
         if res.get("code") == 0:

sdk/python/uv.lock

@@ -342,7 +342,7 @@ wheels = [
 
 [[package]]
 name = "ragflow-sdk"
-version = "0.20.0"
+version = "0.20.1"
 source = { virtual = "." }
 dependencies = [
     { name = "beartype" },

uv.lock

@@ -5188,7 +5188,7 @@ wheels = [
 
 [[package]]
 name = "ragflow"
-version = "0.20.0"
+version = "0.20.1"
 source = { virtual = "." }
 dependencies = [
     { name = "akshare" },

web/src/assets/svg/llm/grok.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 48 48" width="48px" height="48px"><path d="M18.542 30.532l15.956-11.776c.783-.576 1.902-.354 2.274.545 1.962 4.728 1.084 10.411-2.819 14.315-3.903 3.901-9.333 4.756-14.299 2.808l-5.423 2.511c7.778 5.315 17.224 4 23.125-1.903 4.682-4.679 6.131-11.058 4.775-16.812l.011.011c-1.966-8.452.482-11.829 5.501-18.735C47.759 1.332 47.88 1.166 48 1l-6.602 6.599V7.577l-22.86 22.958M15.248 33.392c-5.582-5.329-4.619-13.579.142-18.339 3.521-3.522 9.294-4.958 14.331-2.847l5.412-2.497c-.974-.704-2.224-1.46-3.659-1.994-6.478-2.666-14.238-1.34-19.505 3.922C6.904 16.701 5.31 24.488 8.045 31.133c2.044 4.965-1.307 8.48-4.682 12.023C2.164 44.411.967 45.67 0 47l15.241-13.608"/></svg>

web/src/assets/svg/llm/xai.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 48 48" width="48px" height="48px" fill-rule="evenodd" clip-rule="evenodd" baseProfile="basic"><polygon fill="#212121" fill-rule="evenodd" points="24.032,28.919 40.145,5.989 33.145,5.989 20.518,23.958" clip-rule="evenodd"/><polygon fill="#212121" fill-rule="evenodd" points="14.591,32.393 7.145,42.989 14.145,42.989 18.105,37.354" clip-rule="evenodd"/><polygon fill="#212121" fill-rule="evenodd" points="14.547,18.989 7.547,18.989 24.547,42.989 31.547,42.989" clip-rule="evenodd"/><polygon fill="#212121" fill-rule="evenodd" points="35,16.789 35,43 41,43 41,8.251" clip-rule="evenodd"/></svg>

web/src/components/bulk-operate-bar.tsx

@@ -40,7 +40,7 @@ export function BulkOperateBar({
           {list.map((x) => (
             <li
               key={x.id}
-              className={cn({ ['text-text-delete-red']: isDeleteItem(x.id) })}
+              className={cn({ ['text-state-error']: isDeleteItem(x.id) })}
             >
               <ConfirmDeleteDialog
                 hidden={!isDeleteItem(x.id)}

web/src/components/chat-input.tsx

@@ -1,46 +0,0 @@
-import { useEventListener } from 'ahooks';
-import { Mic, Paperclip, Send } from 'lucide-react';
-import { useRef, useState } from 'react';
-import { Button } from './ui/button';
-import { Textarea } from './ui/textarea';
-
-export function ChatInput() {
-  const textareaRef = useRef<HTMLTextAreaElement>(null);
-  const [textareaHeight, setTextareaHeight] = useState<number>(40);
-
-  useEventListener(
-    'keydown',
-    (ev) => {
-      if (ev.shiftKey && ev.code === 'Enter') {
-        setTextareaHeight((h) => {
-          return h + 10;
-        });
-      }
-    },
-    {
-      target: textareaRef,
-    },
-  );
-
-  return (
-    <section className="flex items-end bg-colors-background-neutral-strong px-4 py-3 rounded-xl m-8">
-      <Button variant={'icon'} className="w-10 h-10">
-        <Mic />
-      </Button>
-      <Textarea
-        ref={textareaRef}
-        placeholder="Tell us a little bit about yourself "
-        className="resize-none focus-visible:ring-0 focus-visible:ring-offset-0 bg-transparent border-none min-h-0 max-h-20"
-        style={{ height: textareaHeight }}
-      />
-      <div className="flex gap-2">
-        <Button variant={'icon'} size={'icon'}>
-          <Paperclip />
-        </Button>
-        <Button variant={'tertiary'} size={'icon'}>
-          <Send />
-        </Button>
-      </div>
-    </section>
-  );
-}

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

@@ -52,7 +52,7 @@ export function ConfirmDeleteDialog({
             {t('common.cancel')}
           </AlertDialogCancel>
           <AlertDialogAction
-            className="bg-text-delete-red text-text-title"
+            className="bg-state-error text-text-primary"
             onClick={onOk}
           >
             {t('common.ok')}

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

@@ -58,7 +58,7 @@ const EditTag = ({ value = [], onChange }: EditTagsProps) => {
         <HoverCardTrigger>
           <div
             key={tag}
-            className="w-fit flex items-center justify-center gap-2 border-dashed border px-1 rounded-sm bg-background-card"
+            className="w-fit flex items-center justify-center gap-2 border-dashed border px-1 rounded-sm bg-bg-card"
           >
             <div className="flex gap-2 items-center">
               <div className="max-w-80 overflow-hidden text-ellipsis">
@@ -90,7 +90,7 @@ const EditTag = ({ value = [], onChange }: EditTagsProps) => {
         <Input
           ref={inputRef}
           type="text"
-          className="h-8 bg-background-card"
+          className="h-8 bg-bg-card"
           value={inputValue}
           onChange={handleInputChange}
           onBlur={handleInputConfirm}
@@ -103,7 +103,7 @@ const EditTag = ({ value = [], onChange }: EditTagsProps) => {
       ) : (
         <Button
           variant="dashed"
-          className="w-fit flex items-center justify-center gap-2 bg-background-card"
+          className="w-fit flex items-center justify-center gap-2 bg-bg-card"
           onClick={showInput}
           style={tagPlusStyle}
         >

web/src/components/knowledge-base-item.tsx

@@ -1,9 +1,13 @@
 import { DocumentParserType } from '@/constants/knowledge';
 import { useTranslate } from '@/hooks/common-hooks';
 import { useFetchKnowledgeList } from '@/hooks/knowledge-hooks';
+import { useBuildQueryVariableOptions } from '@/pages/agent/hooks/use-get-begin-query';
 import { UserOutlined } from '@ant-design/icons';
 import { Avatar as AntAvatar, Form, Select, Space } from 'antd';
+import { toLower } from 'lodash';
+import { useMemo } from 'react';
 import { useFormContext } from 'react-hook-form';
+import { useTranslation } from 'react-i18next';
 import { RAGFlowAvatar } from './ragflow-avatar';
 import { FormControl, FormField, FormItem, FormLabel } from './ui/form';
 import { MultiSelect } from './ui/multi-select';
@@ -66,9 +70,13 @@ const KnowledgeBaseItem = ({
 
 export default KnowledgeBaseItem;
 
-export function KnowledgeBaseFormField() {
+export function KnowledgeBaseFormField({
+  showVariable = false,
+}: {
+  showVariable?: boolean;
+}) {
   const form = useFormContext();
-  const { t } = useTranslate('chat');
+  const { t } = useTranslation();
 
   const { list: knowledgeList } = useFetchKnowledgeList(true);
 
@@ -76,6 +84,8 @@ export function KnowledgeBaseFormField() {
     (x) => x.parser_id !== DocumentParserType.Tag,
   );
 
+  const nextOptions = useBuildQueryVariableOptions();
+
   const knowledgeOptions = filteredKnowledgeList.map((x) => ({
     label: x.name,
     value: x.id,
@@ -84,18 +94,48 @@ export function KnowledgeBaseFormField() {
     ),
   }));
 
+  const options = useMemo(() => {
+    if (showVariable) {
+      return [
+        {
+          label: t('knowledgeDetails.dataset'),
+          options: knowledgeOptions,
+        },
+        ...nextOptions.map((x) => {
+          return {
+            ...x,
+            options: x.options
+              .filter((y) => toLower(y.type).includes('string'))
+              .map((x) => ({
+                ...x,
+                icon: () => (
+                  <RAGFlowAvatar
+                    className="size-4 mr-2"
+                    avatar={x.label}
+                    name={x.label}
+                  />
+                ),
+              })),
+          };
+        }),
+      ];
+    }
+
+    return knowledgeOptions;
+  }, [knowledgeOptions, nextOptions, showVariable, t]);
+
   return (
     <FormField
       control={form.control}
       name="kb_ids"
       render={({ field }) => (
         <FormItem>
-          <FormLabel>{t('knowledgeBases')}</FormLabel>
+          <FormLabel>{t('chat.knowledgeBases')}</FormLabel>
           <FormControl>
             <MultiSelect
-              options={knowledgeOptions}
+              options={options}
               onValueChange={field.onChange}
-              placeholder={t('knowledgeBasesMessage')}
+              placeholder={t('chat.knowledgeBasesMessage')}
               variant="inverted"
               maxCount={100}
               defaultValue={field.value}

web/src/components/list-filter-bar/filter-popover.tsx

@@ -95,7 +95,7 @@ function CheckboxFormMultiple({
                     name={x.field}
                     render={({ field }) => {
                       return (
-                        <div className="flex items-center justify-between text-text-title text-xs">
+                        <div className="flex items-center justify-between text-text-primary text-xs">
                           <FormItem
                             key={item.id}
                             className="flex flex-row  space-x-3 space-y-0 items-center "

web/src/components/list-filter-bar/index.tsx

@@ -27,7 +27,7 @@ export const FilterButton = React.forwardRef<
     <Button variant="secondary" {...props} ref={ref}>
       <span
         className={cn({
-          'text-text-title': count > 0,
+          'text-text-primary': count > 0,
           'text-text-sub-title-invert': count === 0,
         })}
       >

web/src/components/next-message-item/index.tsx

@@ -226,7 +226,7 @@ function MessageItem({
                   ? styles.messageTextDark
                   : styles.messageText]: isAssistant,
                 [styles.messageUserText]: !isAssistant,
-                'bg-background-card': !isAssistant,
+                'bg-bg-card': !isAssistant,
               })}
             >
               {item.data ? (

web/src/components/next-message-item/uploaded-message-files.tsx

@@ -25,7 +25,7 @@ export function InnerUploadedMessageFiles({ files = [] }: IProps) {
           )}
           <div className="text-xs max-w-20">
             <div className="truncate">{file.name}</div>
-            <p className="text-text-sub-title pt-1">{formatBytes(file.size)}</p>
+            <p className="text-text-secondary pt-1">{formatBytes(file.size)}</p>
           </div>
         </div>
       ))}

web/src/components/originui/number-input.tsx

@@ -63,7 +63,7 @@ const NumberInput: React.FC<NumberInputProps> = ({
     >
       <button
         type="button"
-        className="w-10 p-2 text-white focus:outline-none border-r-[1px]"
+        className="w-10 p-2 focus:outline-none border-r-[1px]"
         onClick={handleDecrement}
         style={style}
       >
@@ -74,12 +74,12 @@ const NumberInput: React.FC<NumberInputProps> = ({
         value={value}
         onInput={handleInput}
         onChange={handleChange}
-        className="w-full flex-1 text-center bg-transparent text-white focus:outline-none"
+        className="w-full flex-1 text-center bg-transparent focus:outline-none"
         style={style}
       />
       <button
         type="button"
-        className="w-10 p-2 text-white focus:outline-none border-l-[1px]"
+        className="w-10 p-2 focus:outline-none border-l-[1px]"
         onClick={handleIncrement}
         style={style}
       >

web/src/components/prompt-editor/index.tsx

@@ -142,7 +142,7 @@ export function PromptEditor({
           }
           placeholder={
             <div
-              className="absolute top-10 left-2 text-text-sub-title"
+              className="absolute top-10 left-2 text-text-secondary"
               data-xxx
             >
               {placeholder || t('common.pleaseInput')}

web/src/components/ragflow-form.tsx

@@ -0,0 +1,44 @@
+import {
+  FormControl,
+  FormField,
+  FormItem,
+  FormLabel,
+  FormMessage,
+} from '@/components/ui/form';
+import { ReactNode, cloneElement, isValidElement } from 'react';
+import { ControllerRenderProps, useFormContext } from 'react-hook-form';
+
+type RAGFlowFormItemProps = {
+  name: string;
+  label: ReactNode;
+  tooltip?: ReactNode;
+  children: ReactNode | ((field: ControllerRenderProps) => ReactNode);
+};
+
+export function RAGFlowFormItem({
+  name,
+  label,
+  tooltip,
+  children,
+}: RAGFlowFormItemProps) {
+  const form = useFormContext();
+  return (
+    <FormField
+      control={form.control}
+      name={name}
+      render={({ field }) => (
+        <FormItem>
+          <FormLabel tooltip={tooltip}>{label}</FormLabel>
+          <FormControl>
+            {typeof children === 'function'
+              ? children(field)
+              : isValidElement(children)
+                ? cloneElement(children, { ...field })
+                : children}
+          </FormControl>
+          <FormMessage />
+        </FormItem>
+      )}
+    />
+  );
+}

web/src/components/shared-badge.tsx

@@ -0,0 +1,16 @@
+import { useFetchUserInfo } from '@/hooks/user-setting-hooks';
+import { PropsWithChildren } from 'react';
+
+export function SharedBadge({ children }: PropsWithChildren) {
+  const { data: userInfo } = useFetchUserInfo();
+
+  if (typeof children === 'string' && userInfo.nickname === children) {
+    return null;
+  }
+
+  return (
+    <span className="bg-text-secondary rounded-sm px-1 text-bg-base text-xs">
+      {children}
+    </span>
+  );
+}

web/src/components/ui/accordion.tsx

@@ -28,8 +28,11 @@ function AccordionItem({
 function AccordionTrigger({
   className,
   children,
+  hideDownIcon = false,
   ...props
-}: React.ComponentProps<typeof AccordionPrimitive.Trigger>) {
+}: React.ComponentProps<typeof AccordionPrimitive.Trigger> & {
+  hideDownIcon?: boolean;
+}) {
   return (
     <AccordionPrimitive.Header className="flex">
       <AccordionPrimitive.Trigger
@@ -41,7 +44,9 @@ function AccordionTrigger({
         {...props}
       >
         {children}
-        <ChevronDownIcon className="text-muted-foreground pointer-events-none size-4 shrink-0 translate-y-0.5 transition-transform duration-200" />
+        {!hideDownIcon && (
+          <ChevronDownIcon className="text-muted-foreground pointer-events-none size-4 shrink-0 translate-y-0.5 transition-transform duration-200" />
+        )}
       </AccordionPrimitive.Trigger>
     </AccordionPrimitive.Header>
   );

web/src/components/ui/badge.tsx

@@ -11,12 +11,10 @@ const badgeVariants = cva(
         default:
           'border-transparent bg-primary text-primary-foreground hover:bg-primary/80',
         secondary:
-          'border-transparent bg-background-card text-text-sub-title-invert hover:bg-secondary/80 rounded-md',
+          'border-transparent bg-bg-card text-text-sub-title-invert hover:bg-secondary/80 rounded-md',
         destructive:
           'border-transparent bg-destructive text-destructive-foreground hover:bg-destructive/80',
         outline: 'text-foreground',
-        tertiary:
-          'border-transparent bg-colors-background-core-strong text-colors-text-persist-light hover:bg-colors-background-core-strong/80',
       },
     },
     defaultVariants: {

web/src/components/ui/breadcrumb.tsx

@@ -34,7 +34,7 @@ const BreadcrumbItem = React.forwardRef<
   <li
     ref={ref}
     className={cn(
-      'inline-flex items-center gap-1.5 text-text-sub-title',
+      'inline-flex items-center gap-1.5 text-text-secondary',
       className,
     )}
     {...props}

web/src/components/ui/button.tsx

@@ -6,21 +6,21 @@ import { cn } from '@/lib/utils';
 import { Loader2, Plus } from 'lucide-react';
 
 const buttonVariants = cva(
-  'inline-flex items-center justify-center gap-2 whitespace-nowrap rounded-md text-sm font-medium ring-offset-background transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:pointer-events-none disabled:opacity-50 [&_svg]:pointer-events-none [&_svg]:size-4 [&_svg]:shrink-0',
+  "inline-flex items-center justify-center gap-2 whitespace-nowrap rounded-md text-sm font-medium transition-all disabled:pointer-events-none disabled:opacity-50 [&_svg]:pointer-events-none [&_svg:not([class*='size-'])]:size-4 shrink-0 [&_svg]:shrink-0 outline-none focus-visible:border-ring focus-visible:ring-ring/50 focus-visible:ring-[3px] aria-invalid:ring-destructive/20 dark:aria-invalid:ring-destructive/40 aria-invalid:border-destructive",
   {
     variants: {
       variant: {
-        default: 'bg-primary text-primary-foreground hover:bg-primary/90',
+        default:
+          'bg-primary text-primary-foreground shadow-xs hover:bg-primary/90',
         destructive:
-          'bg-destructive text-destructive-foreground hover:bg-destructive/90',
+          'bg-destructive text-white shadow-xs hover:bg-destructive/90 focus-visible:ring-destructive/20 dark:focus-visible:ring-destructive/40 dark:bg-destructive/60',
         outline:
-          'border border-text-sub-title-invert bg-transparent hover:bg-accent hover:text-accent-foreground',
+          'border bg-background shadow-xs hover:bg-accent hover:text-accent-foreground dark:bg-input/30 dark:border-input dark:hover:bg-input/50',
         secondary:
-          'bg-background-card text-secondary-foreground hover:bg-secondary/80',
-        ghost: 'hover:bg-accent hover:text-accent-foreground',
+          'bg-secondary text-secondary-foreground shadow-xs hover:bg-secondary/80',
+        ghost:
+          'hover:bg-accent hover:text-accent-foreground dark:hover:bg-accent/50',
         link: 'text-primary underline-offset-4 hover:underline',
-        tertiary:
-          'bg-colors-background-sentiment-solid-primary text-colors-text-persist-light hover:bg-colors-background-sentiment-solid-primary/80',
         icon: 'bg-colors-background-inverse-standard text-foreground hover:bg-colors-background-inverse-standard/80',
         dashed: 'border border-dashed border-input hover:bg-accent',
         transparent: 'bg-transparent hover:bg-accent border',
@@ -52,7 +52,7 @@ const Button = React.forwardRef<HTMLButtonElement, ButtonProps>(
     return (
       <Comp
         className={cn(
-          'bg-background-card',
+          'bg-bg-card',
           buttonVariants({ variant, size, className }),
         )}
         ref={ref}

web/src/components/ui/card.tsx

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

web/src/components/ui/container.tsx

@@ -1,19 +0,0 @@
-import { cn } from '@/lib/utils';
-
-export function Container({
-  children,
-  className,
-  ...props
-}: React.PropsWithChildren<React.HTMLAttributes<HTMLDivElement>>) {
-  return (
-    <div
-      className={cn(
-        'px-2 py-1 bg-colors-background-inverse-standard  inline-flex items-center rounded-sm gap-2',
-        className,
-      )}
-      {...props}
-    >
-      {children}
-    </div>
-  );
-}

web/src/components/ui/dual-range-slider.tsx

@@ -29,11 +29,11 @@ const DualRangeSlider = React.forwardRef<
       {...props}
     >
       <SliderPrimitive.Track className="relative h-2 w-full grow overflow-hidden rounded-full bg-secondary">
-        <SliderPrimitive.Range className="absolute h-full bg-background-checked" />
+        <SliderPrimitive.Range className="absolute h-full bg-accent-primary" />
       </SliderPrimitive.Track>
       {initialValue.map((value, index) => (
         <React.Fragment key={index}>
-          <SliderPrimitive.Thumb className="relative block h-4 w-4 rounded-full border-2 border-background-checked bg-white ring-offset-background transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:pointer-events-none disabled:opacity-50 cursor-pointer">
+          <SliderPrimitive.Thumb className="relative block h-4 w-4 rounded-full border-2 border-accent-primary bg-white ring-offset-background transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:pointer-events-none disabled:opacity-50 cursor-pointer">
             {label && (
               <span
                 className={cn(

web/src/components/ui/input.tsx

@@ -14,7 +14,7 @@ const Input = React.forwardRef<HTMLInputElement, InputProps>(
       <input
         type={type}
         className={cn(
-          'flex h-8 w-full rounded-md border border-input bg-colors-background-inverse-weak px-2 py-2 text-sm ring-offset-background file:border-0 file:bg-transparent file:text-sm file:font-medium file:text-foreground placeholder:text-muted-foreground focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:cursor-not-allowed disabled:opacity-50',
+          'flex h-8 w-full rounded-md border border-input bg-bg-card px-2 py-2 text-sm ring-offset-background file:border-0 file:bg-transparent file:text-sm file:font-medium file:text-foreground placeholder:text-muted-foreground focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:cursor-not-allowed disabled:opacity-50',
           className,
         )}
         ref={ref}

web/src/components/ui/loading-button.tsx

@@ -20,8 +20,6 @@ const buttonVariants = cva(
           'bg-secondary text-secondary-foreground hover:bg-secondary/80',
         ghost: 'hover:bg-accent hover:text-accent-foreground',
         link: 'text-primary underline-offset-4 hover:underline',
-        tertiary:
-          'bg-colors-background-sentiment-solid-primary text-colors-text-persist-light hover:bg-colors-background-sentiment-solid-primary/80',
       },
       size: {
         default: 'h-10 px-4 py-2',

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

@@ -0,0 +1,102 @@
+import { ReactNode, useEffect, useState } from 'react';
+import { createPortal } from 'react-dom';
+import { createRoot } from 'react-dom/client';
+import { Modal, ModalProps } from './modal';
+
+type PortalModalProps = Omit<ModalProps, 'open' | 'onOpenChange'> & {
+  visible: boolean;
+  onVisibleChange: (visible: boolean) => void;
+  container?: HTMLElement;
+  children: ReactNode;
+  [key: string]: any;
+};
+
+const PortalModal = ({
+  visible,
+  onVisibleChange,
+  container,
+  children,
+  ...restProps
+}: PortalModalProps) => {
+  const [mounted, setMounted] = useState(false);
+
+  useEffect(() => {
+    setMounted(true);
+    return () => setMounted(false);
+  }, []);
+
+  if (!mounted || !visible) return null;
+  console.log('PortalModal:', visible);
+  return createPortal(
+    <Modal open={visible} onOpenChange={onVisibleChange} {...restProps}>
+      {children}
+    </Modal>,
+    container || document.body,
+  );
+};
+
+export const createPortalModal = () => {
+  let container = document.createElement('div');
+  document.body.appendChild(container);
+
+  let currentProps: any = {};
+  let isVisible = false;
+  let root: ReturnType<typeof createRoot> | null = null;
+
+  root = createRoot(container);
+  const destroy = () => {
+    if (root && container) {
+      root.unmount();
+      if (container.parentNode) {
+        container.parentNode.removeChild(container);
+      }
+      root = null;
+    }
+    isVisible = false;
+    currentProps = {};
+  };
+  const render = () => {
+    const { onVisibleChange, ...props } = currentProps;
+    const modalParam = {
+      visible: isVisible,
+
+      onVisibleChange: (visible: boolean) => {
+        isVisible = visible;
+        if (onVisibleChange) {
+          onVisibleChange(visible);
+        }
+
+        if (!visible) {
+          render();
+        }
+      },
+      ...props,
+    };
+    root?.render(isVisible ? <PortalModal {...modalParam} /> : null);
+  };
+
+  const show = (props: PortalModalProps) => {
+    if (!container) {
+      container = document.createElement('div');
+      document.body.appendChild(container);
+    }
+    if (!root) {
+      root = createRoot(container);
+    }
+    currentProps = { ...currentProps, ...props };
+    isVisible = true;
+    render();
+  };
+
+  const hide = () => {
+    isVisible = false;
+    render();
+  };
+
+  const update = (props = {}) => {
+    currentProps = { ...currentProps, ...props };
+    render();
+  };
+
+  return { show, hide, update, destroy };
+};