feat(doc): 更新 MinerU 解析器参数，修改 Docker 配置，优化文档说明

backend/package/yuxi/plugins/parser/mineru.py

@@ -98,13 +98,14 @@ class MinerUParser(BaseDocumentProcessor):
             file_path: 文件路径
             params: 处理参数
                 - lang_list: 语言列表 (默认: ["ch"])
-                - backend: 后端类型 (默认: "pipeline", 支持 "vlm-*" 系列)
+                - backend: 后端类型 (默认: "hybrid-auto-engine")
                 - parse_method: 解析方法 (默认: "auto")
                 - start_page_id: 起始页码 (默认: 0)
                 - end_page_id: 结束页码 (默认: 99999)
                 - formula_enable: 启用公式解析 (默认: True)
                 - table_enable: 启用表格解析 (默认: True)
-                - server_url: VLM 服务器地址 (vlm-http-client 时需要)
+                - image_analysis: 启用图像/图表解析 (默认: True)
+                - server_url: OpenAI 兼容服务地址 (*-http-client 后端时可选)
 
         Returns:
             str: 提取的 Markdown 文本
@@ -121,23 +122,23 @@ class MinerUParser(BaseDocumentProcessor):
         # 解析参数
         params = params or {}
 
-        # 构建请求数据 - 只保留核心参数
         data = {
             "lang_list": params.get("lang_list", ["ch"]),
-            "backend": params.get("backend", "vlm-http-client"),
+            "backend": params.get("backend", "hybrid-auto-engine"),
             "parse_method": params.get("parse_method", "auto"),
-            # 固定返回 markdown 格式
+            "formula_enable": params.get("formula_enable", True),
+            "table_enable": params.get("table_enable", True),
+            "image_analysis": params.get("image_analysis", True),
+            "start_page_id": params.get("start_page_id", 0),
+            "end_page_id": params.get("end_page_id", 99999),
             "return_md": True,
-            # 添加图片解析支持
             "response_format_zip": True,
             "return_images": True,
         }
 
-        # vlm-http-client 后端需要 server_url
+        server_url = params.get("server_url")
-        if data["backend"] == "vlm-http-client":
+        if server_url:
-            mineru_vl_server = os.environ.get("MINERU_VL_SERVER")
+            data["server_url"] = server_url
-            assert mineru_vl_server, "MINERU_VL_SERVER 环境变量未配置"
-            data["server_url"] = mineru_vl_server
 
         try:
             start_time = time.time()
@@ -155,7 +156,7 @@ class MinerUParser(BaseDocumentProcessor):
                     self.parse_endpoint,
                     files=files,
                     data=data,
-                    timeout=os.environ.get("MINERU_TIMEOUT", 1800),  # 30分钟超时
+                    timeout=int(os.environ.get("MINERU_TIMEOUT", 1800)),  # 30分钟超时
                 )
 
             # 检查响应状态

docker-compose.prod.yml

@@ -3,7 +3,7 @@ x-api-worker-env: &api-worker-env
   LITE_MODE: ${LITE_MODE:-}
   RUNNING_IN_DOCKER: "true"
   YUXI_ENV: production
-  MODEL_DIR_IN_DOCKER: /models
+  MODEL_DIR_IN_DOCKER: /app/models
   PYTHONPATH: /app/package
   POSTGRES_URL: ${POSTGRES_URL:-postgresql+asyncpg://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@postgres:5432/${POSTGRES_DB:-yuxi_know}}
   REDIS_URL: ${REDIS_URL:-redis://redis:6379/0}
@@ -15,7 +15,6 @@ x-api-worker-env: &api-worker-env
   MILVUS_URI: ${MILVUS_URI:-http://milvus:19530}
   MILVUS_DB_NAME: ${MILVUS_DB_NAME:-default}
   MILVUS_TOKEN: ${MILVUS_TOKEN:-}
-  MINERU_VL_SERVER: ${MINERU_VL_SERVER:-http://mineru-vllm-server:30000}
   MINERU_API_URI: ${MINERU_API_URI:-http://mineru-api:30001}
   PADDLEX_URI: ${PADDLEX_URI:-http://paddlex:8080}
   MINIO_URI: ${MINIO_URI:-http://minio:9000}
@@ -283,39 +282,6 @@ services:
       - app-network
     restart: unless-stopped
 
-  mineru-vllm-server:
-    build:
-      context: .
-      dockerfile: docker/mineru.Dockerfile
-    image: mineru-vllm:latest
-    container_name: mineru-vllm-server
-    profiles:
-      - all
-    env_file:
-      - .env.prod
-    environment:
-      MINERU_MODEL_SOURCE: local
-    entrypoint: mineru-vllm-server
-    command:
-      --host 0.0.0.0
-      --port 30000
-    ulimits:
-      memlock: -1
-      stack: 67108864
-    ipc: host
-    healthcheck:
-      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids: ["0"]
-              capabilities: [gpu]
-    networks:
-      - app-network
-    restart: unless-stopped
-
   mineru-api:
     build:
       context: .
@@ -334,13 +300,25 @@ services:
     command:
       --host 0.0.0.0
       --port 30001
+      # --allow-public-http-client  # Disabled by default; when binding to 0.0.0.0 or ::, this re-enables *-http-client backends and server_url. Enable only if you accept the SSRF risk.
+      # parameters for vllm-engine
+      # --gpu-memory-utilization 0.5  # If encountering VRAM shortage, reduce the KV cache size by this parameter; if VRAM issues persist, try lowering it further to `0.4` or below.
     ulimits:
       memlock: -1
       stack: 67108864
     ipc: host
-    restart: unless-stopped
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:30001/health || exit 1"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ["0"]  # Modify for multiple GPUs: ["0", "1"]
+              capabilities: [gpu]
     networks:
       - app-network
+    restart: unless-stopped
 
   paddlex:
     build:

docker-compose.yml

@@ -15,7 +15,6 @@ x-api-worker-env: &api-worker-env
   MILVUS_TOKEN: ${MILVUS_TOKEN:-}
   MINIO_URI: ${MINIO_URI:-http://minio:9000}
   # 文档解析
-  MINERU_VL_SERVER: ${MINERU_VL_SERVER:-http://mineru-vllm-server:30000}
   MINERU_API_URI: ${MINERU_API_URI:-http://mineru-api:30001}
   PADDLEX_URI: ${PADDLEX_URI:-http://paddlex:8080}
   # Sandbox related
@@ -340,44 +339,6 @@ services:
     restart: unless-stopped
 
   # lastest version: wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml
-  mineru-vllm-server:
-    build:
-      context: .
-      dockerfile: docker/mineru.Dockerfile
-    image: mineru-vllm:latest
-    container_name: mineru-vllm-server
-    profiles:
-      - all
-    env_file:
-      - .env
-    ports:
-      - 30000:30000
-    environment:
-      MINERU_MODEL_SOURCE: local
-    entrypoint: mineru-vllm-server
-    command:
-      --host 0.0.0.0
-      --port 30000
-      # parameters for vllm-engine
-      # --data-parallel-size 2  # If using multiple GPUs, increase throughput using vllm's multi-GPU parallel mode
-      # --gpu-memory-utilization 0.5  # If running on a single GPU and encountering VRAM shortage, reduce the KV cache size by this parameter, if VRAM issues persist, try lowering it further to `0.4` or below.
-    ulimits:
-      memlock: -1
-      stack: 67108864
-    ipc: host
-    healthcheck:
-      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              device_ids: ["0"]
-              capabilities: [gpu]
-    networks:
-      - app-network
-    restart: unless-stopped
-
   mineru-api:
     build:
       context: .
@@ -392,17 +353,30 @@ services:
       - 30001:30001
     environment:
       MINERU_MODEL_SOURCE: local
+      VLLM_USE_V1: "1"
     entrypoint: mineru-api
     command:
       --host 0.0.0.0
       --port 30001
+      # --allow-public-http-client  # Disabled by default; when binding to 0.0.0.0 or ::, this re-enables *-http-client backends and server_url. Enable only if you accept the SSRF risk.
+      # parameters for vllm-engine
+      # --gpu-memory-utilization 0.5  # If encountering VRAM shortage, reduce the KV cache size by this parameter; if VRAM issues persist, try lowering it further to `0.4` or below.
     ulimits:
       memlock: -1
       stack: 67108864
     ipc: host
-    restart: unless-stopped
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:30001/health || exit 1"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ["0"]  # Modify for multiple GPUs: ["0", "1"]
+              capabilities: [gpu]
     networks:
       - app-network
+    restart: unless-stopped
 
   paddlex:
     build:

docker/mineru.Dockerfile

@@ -1,15 +1,8 @@
-# Use DaoCloud mirrored vllm image for China region for gpu with Ampere architecture and above (Compute Capability>=8.0)
+# https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/Dockerfile
+# Use DaoCloud mirrored vllm image for China region for gpu with Volta、Turing、Ampere、Ada Lovelace、Hopper、Blackwell architecture (7.0 <= Compute Capability <= 12.0)
 # Compute Capability version query (https://developer.nvidia.com/cuda-gpus)
-FROM docker.m.daocloud.io/vllm/vllm-openai:v0.10.1.1
+# support x86_64 architecture and ARM(AArch64) architecture
-
+FROM docker.m.daocloud.io/vllm/vllm-openai:v0.11.2
-# Use the official vllm image
-# FROM vllm/vllm-openai:v0.10.1.1
-
-# Use DaoCloud mirrored vllm image for China region for gpu with Turing architecture and below (Compute Capability<8.0)
-# FROM docker.m.daocloud.io/vllm/vllm-openai:v0.10.2
-
-# Use the official vllm image
-# FROM vllm/vllm-openai:v0.10.2
 
 # Install libgl for opencv support & Noto fonts for Chinese characters
 RUN apt-get update && \
@@ -23,7 +16,7 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/*
 
 # Install mineru latest
-RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages && \
+RUN python3 -m pip install -U 'mineru[core]>=3.0.0' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages && \
     python3 -m pip cache purge
 
 # Download models and update the configuration file

docs/advanced/document-processing.md

@@ -76,35 +76,39 @@ docker compose up -d api
 
 ### MinerU（高精度）
 
-```env
+首先从官网下载最新的 docker-compose 文件：
-# .env 配置
-MINERU_VL_SERVER=http://localhost:30000
-MINERU_API_URI=http://localhost:30001
 
-# 启动服务（需要 GPU）
+```bash
-docker compose up mineru-vllm-server mineru-api -d
+wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/compose.yaml -O docker/mineru.compose.yml
+```
+
+启动服务（需要 GPU）
+
+```bash
+docker compose -f docker/mineru.compose.yml --profile openai-server up -d
 ```
 
 ### MinerU Official（云服务）
 
+从 [MinerU 官网](https://mineru.net) 获取 API 密钥，在 .env 配置环境变量
+
 ```env
-# .env 配置
 MINERU_API_KEY=your-api-key-here
 ```
 
-从 [MinerU 官网](https://mineru.net) 获取 API 密钥。
-
 ### PP-Structure-V3（结构化）
 
+启动服务（需要 GPU）
+
 ```bash
-# 启动服务（需要 GPU）
 docker compose up paddlex -d
 ```
 
 ### DeepSeek OCR（简单云服务）
 
+在 .env 配置（使用已有的 SiliconFlow 密钥）
+
 ```env
-# .env 配置（使用已有的 SiliconFlow 密钥）
 SILICONFLOW_API_KEY=your-api-key-here
 ```
 
@@ -114,7 +118,7 @@ SILICONFLOW_API_KEY=your-api-key-here
 
 在 `.env` 中设置服务器 IP：
 
-```env
+```
 HOST_IP=your_server_ip
 ```
 

web/src/components/FileUploadModal.vue

@@ -66,7 +66,7 @@
           </div>
           <div class="col-item" v-if="uploadMode !== 'url'">
             <div class="setting-label">
-              OCR 引擎
+              OCR 引擎（仅应用于 PDF/图片文件）
               <a-tooltip title="检查服务状态">
                 <ReloadOutlined
                   class="action-icon refresh-icon"