Merge branch 'main' into main

.github/workflows/tests.yml

@@ -42,19 +42,23 @@ jobs:
       - name: Ensure workspace ownership
         run: echo "chown -R $USER $GITHUB_WORKSPACE" && sudo chown -R $USER $GITHUB_WORKSPACE
 
+      # https://github.com/actions/checkout/issues/1781
       - name: Check out code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
 
       - name: Build ragflow:dev-slim
         run: |
           RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
           cp -r ${RUNNER_WORKSPACE_PREFIX}/huggingface.co ${RUNNER_WORKSPACE_PREFIX}/nltk_data ${RUNNER_WORKSPACE_PREFIX}/libssl*.deb  ${RUNNER_WORKSPACE_PREFIX}/tika-server*.jar* ${RUNNER_WORKSPACE_PREFIX}/chrome* ${RUNNER_WORKSPACE_PREFIX}/cl100k_base.tiktoken .
           sudo docker pull ubuntu:22.04
-          sudo docker build -f Dockerfile.slim -t infiniflow/ragflow:dev-slim .
+          sudo docker build --progress=plain -f Dockerfile.slim -t infiniflow/ragflow:dev-slim .
 
       - name: Build ragflow:dev
         run: |
-          sudo docker build -f Dockerfile -t infiniflow/ragflow:dev .
+          sudo docker build --progress=plain -f Dockerfile -t infiniflow/ragflow:dev .
 
       - name: Start ragflow:dev-slim
         run: |

Dockerfile

@@ -75,6 +75,7 @@ RUN current_commit=$(git rev-parse --short HEAD); \
     else \
         version_info="$version_info full"; \
     fi; \
+    echo "RAGFlow version: $version_info"; \
     echo $version_info > /ragflow/VERSION
 
 COPY web web
@@ -145,7 +146,7 @@ COPY cl100k_base.tiktoken /ragflow/9b5ad71b2ce5302211f9c61530b329a4922fc6a4
 # Add dependencies of selenium
 RUN --mount=type=bind,source=chrome-linux64-121-0-6167-85,target=/chrome-linux64.zip \
     unzip /chrome-linux64.zip && \
-    mv chrome-linux64 /opt/chrome/ && \
+    mv chrome-linux64 /opt/chrome && \
     ln -s /opt/chrome/chrome /usr/local/bin/
 RUN --mount=type=bind,source=chromedriver-linux64-121-0-6167-85,target=/chromedriver-linux64.zip \
     unzip -j /chromedriver-linux64.zip chromedriver-linux64/chromedriver && \

Dockerfile.slim

@@ -75,6 +75,7 @@ RUN current_commit=$(git rev-parse --short HEAD); \
     else \
         version_info="$version_info full"; \
     fi; \
+    echo "RAGFlow version: $version_info"; \
     echo $version_info > /ragflow/VERSION
 
 COPY web web
@@ -138,7 +139,7 @@ COPY cl100k_base.tiktoken /ragflow/9b5ad71b2ce5302211f9c61530b329a4922fc6a4
 # Add dependencies of selenium
 RUN --mount=type=bind,source=chrome-linux64-121-0-6167-85,target=/chrome-linux64.zip \
     unzip /chrome-linux64.zip && \
-    mv chrome-linux64 /opt/chrome/ && \
+    mv chrome-linux64 /opt/chrome && \
     ln -s /opt/chrome/chrome /usr/local/bin/
 RUN --mount=type=bind,source=chromedriver-linux64-121-0-6167-85,target=/chromedriver-linux64.zip \
     unzip -j /chromedriver-linux64.zip chromedriver-linux64/chromedriver && \

README.md

@@ -20,7 +20,7 @@
         <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/badge/docker_pull-ragflow:v0.13.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.13.0">
+        <img src="https://img.shields.io/badge/docker_pull-ragflow:v0.14.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.14.0">
     </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">
@@ -176,14 +176,14 @@ releases! 🌟
    ```
 
    > - To download a RAGFlow slim Docker image of a specific version, update the `RAGFLOW_IMAGE` variable in *
-       *docker/.env** to your desired version. For example, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0-slim`. After
+       *docker/.env** to your desired version. For example, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0-slim`. After
        making this change, rerun the command above to initiate the download.
    > - To download the dev version of RAGFlow Docker image *including* embedding models and Python libraries, update the
        `RAGFLOW_IMAGE` variable in **docker/.env** to `RAGFLOW_IMAGE=infiniflow/ragflow:dev`. After making this change,
        rerun the command above to initiate the download.
    > - To download a specific version of RAGFlow Docker image *including* embedding models and Python libraries, update
        the `RAGFLOW_IMAGE` variable in **docker/.env** to your desired version. For example,
-       `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0`. After making this change, rerun the command above to initiate the
+       `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0`. After making this change, rerun the command above to initiate the
        download.
 
    > **NOTE:** A RAGFlow Docker image that includes embedding models and Python libraries is approximately 9GB in size

README_id.md

@@ -20,7 +20,7 @@
         <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/badge/docker_pull-ragflow:v0.13.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.13.0">
+        <img src="https://img.shields.io/badge/docker_pull-ragflow:v0.14.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.14.0">
     </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">
@@ -169,14 +169,14 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
    ```
 
    > - Untuk mengunduh versi tertentu dari image Docker RAGFlow slim, perbarui variabel `RAGFlow_IMAGE` di *
-       *docker/.env** sesuai dengan versi yang diinginkan. Misalnya, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0-slim`.
+       *docker/.env** sesuai dengan versi yang diinginkan. Misalnya, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0-slim`.
        Setelah mengubah ini, jalankan ulang perintah di atas untuk memulai unduhan.
    > - Untuk mengunduh versi dev dari image Docker RAGFlow *termasuk* model embedding dan library Python, perbarui
        variabel `RAGFlow_IMAGE` di **docker/.env** menjadi `RAGFLOW_IMAGE=infiniflow/ragflow:dev`. Setelah mengubah ini,
        jalankan ulang perintah di atas untuk memulai unduhan.
    > - Untuk mengunduh versi tertentu dari image Docker RAGFlow *termasuk* model embedding dan library Python, perbarui
        variabel `RAGFlow_IMAGE` di **docker/.env** sesuai dengan versi yang diinginkan. Misalnya,
-       `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0`. Setelah mengubah ini, jalankan ulang perintah di atas untuk memulai unduhan.
+       `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0`. Setelah mengubah ini, jalankan ulang perintah di atas untuk memulai unduhan.
 
    > **CATATAN:** Image Docker RAGFlow yang mencakup model embedding dan library Python berukuran sekitar 9GB
    dan mungkin memerlukan waktu lebih lama untuk dimuat.
@@ -286,7 +286,7 @@ docker build -f Dockerfile -t infiniflow/ragflow:dev .
 
    Tambahkan baris berikut ke `/etc/hosts` untuk memetakan semua host yang ditentukan di **docker/service_conf.yaml** ke `127.0.0.1`:
    ```
-   127.0.0.1       es01 mysql minio redis
+   127.0.0.1       es01 infinity mysql minio redis
    ```  
    Di **docker/service_conf.yaml**, perbarui port mysql ke `5455` dan es ke `1200`, sesuai dengan yang ditentukan di **docker/.env**.
 

README_ja.md

@@ -20,7 +20,7 @@
         <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/badge/docker_pull-ragflow:v0.13.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.13.0">
+        <img src="https://img.shields.io/badge/docker_pull-ragflow:v0.14.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.14.0">
     </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">
@@ -148,9 +148,9 @@
    $ docker compose -f docker-compose.yml up -d
    ```
 
-   > - 特定のバージョンのRAGFlow slim Dockerイメージをダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を希望のバージョンに更新します。例えば、`RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0`とします。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。
+   > - 特定のバージョンのRAGFlow slim Dockerイメージをダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を希望のバージョンに更新します。例えば、`RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0`とします。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。
    > - RAGFlowの埋め込みモデルとPythonライブラリを含む開発版Dockerイメージをダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を`RAGFLOW_IMAGE=infiniflow/ragflow:dev`に更新します。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。
-   > - 特定のバージョンのRAGFlow Dockerイメージ（埋め込みモデルとPythonライブラリを含む）をダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を希望のバージョンに更新します。例えば、`RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0`とします。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。  
+   > - 特定のバージョンのRAGFlow Dockerイメージ（埋め込みモデルとPythonライブラリを含む）をダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を希望のバージョンに更新します。例えば、`RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0`とします。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。  
    
    > **NOTE:** 埋め込みモデルとPythonライブラリを含むRAGFlow Dockerイメージのサイズは約9GBであり、読み込みにかなりの時間がかかる場合があります。
 

README_ko.md

@@ -20,7 +20,7 @@
         <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/badge/docker_pull-ragflow:v0.13.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.13.0">
+        <img src="https://img.shields.io/badge/docker_pull-ragflow:v0.14.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.14.0">
     </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">
@@ -152,9 +152,9 @@
    $ docker compose -f docker-compose.yml up -d
    ```
 
-   > - 특정 버전의 RAGFlow slim Docker 이미지를 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 원하는 버전으로 업데이트하세요. 예를 들어, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0-slim`으로 설정합니다. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.
+   > - 특정 버전의 RAGFlow slim Docker 이미지를 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 원하는 버전으로 업데이트하세요. 예를 들어, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0-slim`으로 설정합니다. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.
    > - RAGFlow의 임베딩 모델과 Python 라이브러리를 포함한 개발 버전 Docker 이미지를 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 `RAGFLOW_IMAGE=infiniflow/ragflow:dev`로 업데이트하세요. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.
-   > - 특정 버전의 RAGFlow Docker 이미지를 임베딩 모델과 Python 라이브러리를 포함하여 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 원하는 버전으로 업데이트하세요. 예를 들어, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0` 로 설정합니다. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.  
+   > - 특정 버전의 RAGFlow Docker 이미지를 임베딩 모델과 Python 라이브러리를 포함하여 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 원하는 버전으로 업데이트하세요. 예를 들어, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0` 로 설정합니다. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.  
    
    > **NOTE:** 임베딩 모델과 Python 라이브러리를 포함한 RAGFlow Docker 이미지의 크기는 약 9GB이며, 로드하는 데 상당히 오랜 시간이 걸릴 수 있습니다.
 

README_zh.md

@@ -20,7 +20,7 @@
         <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/badge/docker_pull-ragflow:v0.13.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.13.0">
+        <img src="https://img.shields.io/badge/docker_pull-ragflow:v0.14.0-brightgreen" alt="docker pull infiniflow/ragflow:v0.14.0">
     </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">
@@ -149,9 +149,9 @@
    $ docker compose -f docker-compose.yml up -d
    ```
 
-   > - 如果你想下载并运行特定版本的 RAGFlow slim Docker 镜像，请在 **docker/.env** 文件中找到 `RAGFLOW_IMAGE` 变量，将其改为对应版本。例如 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0-slim`，然后再运行上述命令。
+   > - 如果你想下载并运行特定版本的 RAGFlow slim Docker 镜像，请在 **docker/.env** 文件中找到 `RAGFLOW_IMAGE` 变量，将其改为对应版本。例如 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0-slim`，然后再运行上述命令。
    > - 如果您想安装内置 embedding 模型和 Python 库的 dev 版本的 Docker 镜像，需要将 **docker/.env** 文件中的 `RAGFLOW_IMAGE` 变量修改为： `RAGFLOW_IMAGE=infiniflow/ragflow:dev`。
-   > - 如果您想安装内置 embedding 模型和 Python 库的指定版本的 RAGFlow Docker 镜像，需要将 **docker/.env** 文件中的 `RAGFLOW_IMAGE` 变量修改为： `RAGFLOW_IMAGE=infiniflow/ragflow:v0.13.0`。修改后，再运行上面的命令。
+   > - 如果您想安装内置 embedding 模型和 Python 库的指定版本的 RAGFlow Docker 镜像，需要将 **docker/.env** 文件中的 `RAGFLOW_IMAGE` 变量修改为： `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.0`。修改后，再运行上面的命令。
    > **注意：** 安装内置 embedding 模型和 Python 库的指定版本的 RAGFlow Docker 镜像大小约 9 GB，可能需要更长时间下载，请耐心等待。
    
 4. 服务器启动成功后再次确认服务器状态：

agent/component/crawler.py

@@ -17,6 +17,7 @@
 import asyncio
 from crawl4ai import AsyncWebCrawler
 from agent.component.base import ComponentBase, ComponentParamBase
+from api.utils.web_utils import is_valid_url
 
 
 class CrawlerParam(ComponentParamBase):
@@ -39,7 +40,7 @@ class Crawler(ComponentBase, ABC):
     def _run(self, history, **kwargs):
         ans = self.get_input()
         ans = " - ".join(ans["content"]) if "content" in ans else ""
-        if not ans:
+        if not is_valid_url(ans):
             return Crawler.be_output("")
         try:
             result = asyncio.run(self.get_web(ans))

api/apps/kb_app.py

@@ -162,6 +162,7 @@ def rm():
                     message="Database error (Document removal)!")
             f2d = File2DocumentService.get_by_document_id(doc.id)
             FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.id == f2d[0].file_id])
+            FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kbs[0].name])
             File2DocumentService.delete_by_document_id(doc.id)
 
         if not KnowledgebaseService.delete_by_id(req["kb_id"]):

api/apps/sdk/chat.py

@@ -111,7 +111,7 @@ def create(tenant_id):
         req['prompt_config'] = {}
     for key in key_list_2:
         temp = req['prompt_config'].get(key)
-        if not temp:
+        if (not temp and key == 'system') or (key not in req["prompt_config"]):
             req['prompt_config'][key] = default_prompt[key]
     for p in req['prompt_config']["parameters"]:
         if p["optional"]:

api/apps/sdk/dataset.py

@@ -252,6 +252,8 @@ def delete(tenant_id):
                     File.id == f2d[0].file_id,
                 ]
             )
+            FileService.filter_delete(
+                [File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kbs[0].name])
             File2DocumentService.delete_by_document_id(doc.id)
         if not KnowledgebaseService.delete_by_id(id):
             return get_error_data_result(message="Delete dataset error.(Database error)")