chore: init monorepo snapshot

services/mineru/src/docker/china/Dockerfile

@@ -0,0 +1,33 @@
+# Use DaoCloud mirrored vllm image for China region for gpu with Ampere architecture and above (Compute Capability>=8.0)
+# Compute Capability version query (https://developer.nvidia.com/cuda-gpus)
+FROM docker.m.daocloud.io/vllm/vllm-openai:v0.10.1.1
+
+# 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 && \
+    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]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages && \
+    python3 -m pip cache purge
+
+# Download models and update the configuration file
+RUN /bin/bash -c "mineru-models-download -s modelscope -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 \"$@\"", "--"]

services/mineru/src/docker/compose.yaml

@@ -0,0 +1,88 @@
+services:
+  mineru-vllm-server:
+    image: mineru-vllm:latest
+    container_name: mineru-vllm-server
+    restart: always
+    profiles: ["vllm-server"]
+    ports:
+      - 30000:30000
+    environment:
+      MINERU_MODEL_SOURCE: local
+    entrypoint: mineru-vllm-server
+    command:
+      --host 0.0.0.0
+      --port 30000
+      # --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]
+
+  mineru-api:
+    image: mineru-vllm:latest
+    container_name: mineru-api
+    restart: always
+    profiles: ["api"]
+    ports:
+      - 8000:8000
+    environment:
+      MINERU_MODEL_SOURCE: local
+    entrypoint: mineru-api
+    command:
+      --host 0.0.0.0
+      --port 8000
+      # 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
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: [ "0" ]
+              capabilities: [ gpu ]
+
+  mineru-gradio:
+    image: mineru-vllm:latest
+    container_name: mineru-gradio
+    restart: always
+    profiles: ["gradio"]
+    ports:
+      - 7860:7860
+    environment:
+      MINERU_MODEL_SOURCE: local
+    entrypoint: mineru-gradio
+    command:
+      --server-name 0.0.0.0
+      --server-port 7860
+      --enable-vllm-engine true  # Enable the vllm engine for Gradio
+      # --enable-api false  # If you want to disable the API, set this to false
+      # --max-convert-pages 20  # If you want to limit the number of pages for conversion, set this to a specific number
+      # 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
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: [ "0" ]
+              capabilities: [ gpu ]

services/mineru/src/docker/global/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 \"$@\"", "--"]