chore: update mineru & remove outdated version

builds/mineru/.env.example

@@ -0,0 +1,7 @@
+# MinerU Docker image
+MINERU_DOCKER_IMAGE=alexsuntop/mineru:2.6.5
+
+# Port configurations
+MINERU_PORT_OVERRIDE_VLLM=30000
+MINERU_PORT_OVERRIDE_API=8000
+MINERU_PORT_OVERRIDE_GRADIO=7860

builds/mineru/Dockerfile

@@ -0,0 +1,27 @@
+# Use the official vllm image for gpu with Ampere architecture and above (Compute Capability>=8.0)
+# Compute Capability version query (https://developer.nvidia.com/cuda-gpus)
+FROM vllm/vllm-openai:v0.10.1.1
+
+# Use the official vllm image for gpu with Turing architecture and below (Compute Capability<8.0)
+# FROM vllm/vllm-openai:v0.10.2
+
+# Install libgl for opencv support & Noto fonts for Chinese characters
+RUN apt-get update && \
+    apt-get install -y \
+        fonts-noto-core \
+        fonts-noto-cjk \
+        fontconfig \
+        libgl1 && \
+    fc-cache -fv && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install mineru latest
+RUN python3 -m pip install -U 'mineru[core]' --break-system-packages && \
+    python3 -m pip cache purge
+
+# Download models and update the configuration file
+RUN /bin/bash -c "mineru-models-download -s huggingface -m all"
+
+# Set the entry point to activate the virtual environment and run the command line tool
+ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"]

builds/mineru/README.md

@@ -0,0 +1,45 @@
+# MinerU v2
+
+[English](./README.md) | [中文](./README.zh.md)
+
+This service runs MinerU v2. See the [Reference Documentation](https://opendatalab.github.io/MinerU/zh/usage/quick_usage/).
+
+## Start Services
+
+- **VLM backend server**:
+
+  ```bash
+  docker compose --profile vllm-server up -d
+  ```
+
+- **Document parse API**:
+
+  ```bash
+  docker compose --profile api up -d
+  ```
+
+- **Gradio WebUI**:
+
+  ```bash
+  docker compose --profile gradio up -d
+  ```
+
+## Test vLLM backend
+
+```bash
+pip install mineru
+mineru -p demo.pdf -o ./output -b vlm-http-client -u http://localhost:30000
+```
+
+## Services
+
+- `mineru-vllm-server`: The VLM backend server.
+- `mineru-api`: The document parsing API.
+- `mineru-gradio`: The Gradio WebUI.
+
+## Configuration
+
+- `MINERU_VERSION`: The version for MinerU, default is `2.6.5`.
+- `MINERU_PORT_OVERRIDE_VLLM`: The host port for the VLLM server, default is `30000`.
+- `MINERU_PORT_OVERRIDE_API`: The host port for the API service, default is `8000`.
+- `MINERU_PORT_OVERRIDE_GRADIO`: The host port for the Gradio WebUI, default is `7860`.

builds/mineru/README.zh.md

@@ -0,0 +1,45 @@
+# MinerU v2
+
+[English](./README.md) | [中文](./README.zh.md)
+
+此服务运行 MinerU v2。请参阅[参考文档](https://opendatalab.github.io/MinerU/zh/usage/quick_usage/)。
+
+## 启动服务
+
+- **VLM 后端服务器**:
+
+  ```bash
+  docker compose --profile vllm-server up -d
+  ```
+
+- **文档解析 API**:
+
+  ```bash
+  docker compose --profile api up -d
+  ```
+
+- **Gradio WebUI**:
+
+  ```bash
+  docker compose --profile gradio up -d
+  ```
+
+## 测试 vLLM 后端
+
+```bash
+pip install mineru
+mineru -p demo.pdf -o ./output -b vlm-http-client -u http://localhost:30000
+```
+
+## 服务
+
+- `mineru-vllm-server`: VLM 后端服务器。
+- `mineru-api`: 文档解析 API。
+- `mineru-gradio`: Gradio WebUI。
+
+## 配置
+
+- `MINERU_VERSION`: MinerU 的 Docker 镜像版本，默认为 `2.6.5`。
+- `MINERU_PORT_OVERRIDE_VLLM`: VLLM 服务器的主机端口，默认为 `30000`。
+- `MINERU_PORT_OVERRIDE_API`: API 服务的主机端口，默认为 `8000`。
+- `MINERU_PORT_OVERRIDE_GRADIO`: Gradio WebUI 的主机端口，默认为 `7860`。

builds/mineru/docker-compose.yaml

@@ -0,0 +1,139 @@
+x-defaults: &defaults
+  restart: unless-stopped
+  logging:
+    driver: json-file
+    options:
+      max-size: 100m
+      max-file: "3"
+
+x-mineru-vllm: &mineru-vllm
+  <<: *defaults
+  image: ${GLOBAL_REGISTRY:-}alexsuntop/mineru:${MINERU_VERSION:-2.6.5}
+  build:
+    context: .
+    dockerfile: Dockerfile
+  environment:
+    TZ: ${TZ:-UTC}
+    MINERU_MODEL_SOURCE: local
+  ulimits:
+    memlock: -1
+    stack: 67108864
+  ipc: host
+  deploy:
+    resources:
+      limits:
+        cpus: '16.0'
+        memory: 32G
+      reservations:
+        cpus: '8.0'
+        memory: 16G
+        devices:
+          - driver: nvidia
+            device_ids: [ '0' ]
+            capabilities: [ gpu ]
+
+services:
+  mineru-openai-server:
+    <<: *mineru-vllm
+    profiles: ["openai-server"]
+    ports:
+      - ${MINERU_PORT_OVERRIDE_VLLM:-30000}:30000
+    entrypoint: mineru-openai-server
+    command:
+      # ==================== Engine Selection ====================
+      # WARNING: Only ONE engine can be enabled at a time!
+      # Choose 'vllm' OR 'lmdeploy' (uncomment one line below)
+      - --engine vllm
+      # --engine lmdeploy
+
+      # ==================== vLLM Engine Parameters ====================
+      # Uncomment if using --engine vllm
+      - --host 0.0.0.0
+      - --port 30000
+      # Multi-GPU configuration (increase throughput)
+      # --data-parallel-size 2
+      # Single GPU memory optimization (reduce if VRAM insufficient)
+      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if issues persist
+
+      # ==================== LMDeploy Engine Parameters ====================
+      # Uncomment if using --engine lmdeploy
+      # --server-name 0.0.0.0
+      # --server-port 30000
+      # Multi-GPU configuration (increase throughput)
+      # --dp 2
+      # Single GPU memory optimization (reduce if VRAM insufficient)
+      # --cache-max-entry-count 0.5  # Try 0.4 or lower if issues persist
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+
+
+  mineru-api:
+    <<: *mineru-vllm
+    profiles: ["api"]
+    ports:
+      - ${MINERU_PORT_OVERRIDE_API:-8000}:8000
+    entrypoint: mineru-api
+    command:
+      # ==================== Server Configuration ====================
+      - --host 0.0.0.0
+      - --port 8000
+
+      # ==================== vLLM Engine Parameters ====================
+      # Multi-GPU configuration
+      # --data-parallel-size 2
+      # Single GPU memory optimization
+      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient
+
+      # ==================== LMDeploy Engine Parameters ====================
+      # Multi-GPU configuration
+      # --dp 2
+      # Single GPU memory optimization
+      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+
+  mineru-gradio:
+    <<: *mineru-vllm
+    profiles: ["gradio"]
+    ports:
+      - ${MINERU_PORT_OVERRIDE_GRADIO:-7860}:7860
+    entrypoint: mineru-gradio
+    command:
+      # ==================== Gradio Server Configuration ====================
+      - --server-name 0.0.0.0
+      - --server-port 7860
+
+      # ==================== Gradio Feature Settings ====================
+      # --enable-api false  # Disable API endpoint
+      # --max-convert-pages 20  # Limit conversion page count
+
+      # ==================== Engine Selection ====================
+      # WARNING: Only ONE engine can be enabled at a time!
+
+      # Option 1: vLLM Engine (recommended for most users)
+      - --enable-vllm-engine true
+      # Multi-GPU configuration
+      # --data-parallel-size 2
+      # Single GPU memory optimization
+      # --gpu-memory-utilization 0.5  # Try 0.4 or lower if VRAM insufficient
+
+      # Option 2: LMDeploy Engine
+      # --enable-lmdeploy-engine true
+      # Multi-GPU configuration
+      # --dp 2
+      # Single GPU memory optimization
+      # --cache-max-entry-count 0.5  # Try 0.4 or lower if VRAM insufficient
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:7860/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s