MinerU/zhch/mineru_fast_api_daemon.sh

#!/bin/bash

# MinerU FastAPI 服务守护进程脚本

LOGDIR="/home/ubuntu/zhch/logs"
mkdir -p $LOGDIR
PIDFILE="$LOGDIR/mineru_fastapi.pid"
LOGFILE="$LOGDIR/mineru_fastapi.log"

# 配置参数
CONDA_ENV="mineru2"
API_PORT="8120"
API_HOST="0.0.0.0"

# vLLM 后端配置（当使用 vlm-vllm-engine 后端时）
VLLM_PORT="8121"
VLLM_HOST="127.0.0.1"
MODEL_PATH="/home/ubuntu/models/modelscope_cache/models/OpenDataLab/MinerU2___5-2509-1___2B"
MODEL_NAME="MinerU2.5"

# GPU 配置
GPU_MEMORY_UTILIZATION="0.3"
CUDA_VISIBLE_DEVICES="4"
MAX_MODEL_LEN="16384"
MAX_NUM_BATCHED_TOKENS="8192"
MAX_NUM_SEQS="8"

# MinerU 配置
export MINERU_TOOLS_CONFIG_JSON="/home/ubuntu/zhch/MinerU/mineru.json"
export MODELSCOPE_CACHE="/home/ubuntu/models/modelscope_cache"
export USE_MODELSCOPE_HUB=1

# 正确初始化和激活conda环境
if [ -f "/home/ubuntu/anaconda3/etc/profile.d/conda.sh" ]; then
    source /home/ubuntu/anaconda3/etc/profile.d/conda.sh
    conda activate $CONDA_ENV
elif [ -f "/opt/conda/etc/profile.d/conda.sh" ]; then
    source /opt/conda/etc/profile.d/conda.sh
    conda activate $CONDA_ENV
else
    echo "Warning: Using direct conda path activation"
    export PATH="/home/ubuntu/anaconda3/envs/$CONDA_ENV/bin:$PATH"
fi

start() {
    if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
        echo "MinerU FastAPI is already running"
        return 1
    fi
    
    echo "Starting MinerU FastAPI daemon..."
    echo "API Host: $API_HOST, Port: $API_PORT"
    echo "Backend vLLM Host: $VLLM_HOST, Port: $VLLM_PORT"
    echo "Model path: $MODEL_PATH"
    echo "GPU memory utilization: $GPU_MEMORY_UTILIZATION"
    echo "CUDA devices: $CUDA_VISIBLE_DEVICES"
    
    # 检查模型文件是否存在（如果使用本地模型）
    if [ ! -d "$MODEL_PATH" ]; then
        echo "⚠️ Model path not found: $MODEL_PATH"
        echo "Will try to download model automatically or use HTTP client mode"
    fi
    
    # 检查conda环境
    if ! command -v python >/dev/null 2>&1; then
        echo "❌ Python not found. Check conda environment activation."
        return 1
    fi
    
    echo "🔧 Using Python: $(which python)"
    
    # 显示GPU状态
    echo "📊 GPU 状态检查:"
    if command -v nvidia-smi >/dev/null 2>&1; then
        nvidia-smi --query-gpu=index,name,memory.used,memory.total --format=csv,noheader,nounits | \
        awk -F',' '{printf "  GPU %s: %s - 内存: %sMB/%sMB\n", $1, $2, $3, $4}'
    else
        echo "⚠️ nvidia-smi not available"
    fi
    
    # 启动MinerU FastAPI服务
    # 设置GPU环境变量并启动
    nohup $CUDA_VISIBLE_DEVICES; python -m mineru.cli.fast_api \
            --host $API_HOST \
            --port $API_PORT \
            --gpu-memory-utilization $GPU_MEMORY_UTILIZATION \
            --max-model-len $MAX_MODEL_LEN \
            --max-num-batched-tokens $MAX_NUM_BATCHED_TOKENS \
            --max-num-seqs $MAX_NUM_SEQS \
            --served-model-name $MODEL_NAME \
            --server-url http://$VLLM_HOST:$VLLM_PORT \
            --source modelscope \
    > $LOGFILE 2>&1 &
    
    echo $! > $PIDFILE
    echo "✅ MinerU FastAPI started with PID: $(cat $PIDFILE)"
    echo "📋 Log file: $LOGFILE"
    echo "🌐 FastAPI Service URL: http://$API_HOST:$API_PORT"
    echo "📖 API Documentation: http://localhost:$API_PORT/docs"
    echo "📖 ReDoc Documentation: http://localhost:$API_PORT/redoc"
    echo ""
    echo "Waiting for service to start..."
    sleep 5
    status
}

stop() {
    if [ ! -f $PIDFILE ]; then
        echo "MinerU FastAPI is not running"
        return 1
    fi
    
    PID=$(cat $PIDFILE)
    echo "Stopping MinerU FastAPI (PID: $PID)..."
    
    # 优雅停止
    kill $PID
    
    # 等待进程结束
    for i in {1..10}; do
        if ! kill -0 $PID 2>/dev/null; then
            break
        fi
        echo "Waiting for process to stop... ($i/10)"
        sleep 1
    done
    
    # 如果进程仍在运行，强制结束
    if kill -0 $PID 2>/dev/null; then
        echo "Force killing process..."
        kill -9 $PID
    fi
    
    rm -f $PIDFILE
    echo "✅ MinerU FastAPI stopped"
}

status() {
    if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
        PID=$(cat $PIDFILE)
        echo "✅ MinerU FastAPI is running (PID: $PID)"
        echo "🌐 FastAPI Service URL: http://$API_HOST:$API_PORT"
        echo "📋 Log file: $LOGFILE"
        
        # 检查端口是否被监听
        if command -v ss >/dev/null 2>&1; then
            if ss -tuln | grep -q ":$API_PORT "; then
                echo "🔗 Port $API_PORT is being listened"
            else
                echo "⚠️ Port $API_PORT is not being listened (service may be starting up)"
            fi
        elif command -v netstat >/dev/null 2>&1; then
            if netstat -tuln | grep -q ":$API_PORT "; then
                echo "🔗 Port $API_PORT is being listened"
            else
                echo "⚠️ Port $API_PORT is not being listened (service may be starting up)"
            fi
        fi
        
        # 检查API响应
        if command -v curl >/dev/null 2>&1; then
            if curl -s --connect-timeout 2 "http://127.0.0.1:$API_PORT/docs" > /dev/null 2>&1; then
                echo "🎯 FastAPI 响应正常"
            else
                echo "⚠️ FastAPI 无响应 (service may be starting up)"
            fi
        fi
        
        # 显示GPU使用情况
        if command -v nvidia-smi >/dev/null 2>&1; then
            echo "📊 GPU 使用情况:"
            nvidia-smi --query-gpu=index,utilization.gpu,utilization.memory,memory.used,memory.total --format=csv,noheader,nounits | \
            awk -F',' '{printf "  GPU %s: GPU利用率 %s%%, 内存利用率 %s%%, 显存 %sMB/%sMB\n", $1, $2, $3, $4, $5}'
        fi
        
        # 显示最新日志
        if [ -f $LOGFILE ]; then
            echo "📄 Latest logs (last 3 lines):"
            tail -3 $LOGFILE | sed 's/^/  /'
        fi
    else
        echo "❌ MinerU FastAPI is not running"
        if [ -f $PIDFILE ]; then
            echo "Removing stale PID file..."
            rm -f $PIDFILE
        fi
    fi
}

logs() {
    if [ -f $LOGFILE ]; then
        echo "📄 MinerU FastAPI logs:"
        echo "======================"
        tail -f $LOGFILE
    else
        echo "❌ Log file not found: $LOGFILE"
    fi
}

config() {
    echo "📋 Current configuration:"
    echo "  Conda Environment: $CONDA_ENV"
    echo "  FastAPI Host: $API_HOST"
    echo "  FastAPI Port: $API_PORT"
    echo "  vLLM Backend Host: $VLLM_HOST"
    echo "  vLLM Backend Port: $VLLM_PORT"
    echo "  Model Path: $MODEL_PATH"
    echo "  Model Name: $MODEL_NAME"
    echo "  GPU Memory Utilization: $GPU_MEMORY_UTILIZATION"
    echo "  CUDA Visible Devices: $CUDA_VISIBLE_DEVICES"
    echo "  Max Model Length: $MAX_MODEL_LEN"
    echo "  Max Num Seqs: $MAX_NUM_SEQS"
    echo "  PID File: $PIDFILE"
    echo "  Log File: $LOGFILE"
    echo ""
    echo "  MinerU Config: $MINERU_TOOLS_CONFIG_JSON"
    echo "  ModelScope Cache: $MODELSCOPE_CACHE"
    
    if [ -d "$MODEL_PATH" ]; then
        echo "✅ Model path exists"
        echo "  Model files:"
        ls -la "$MODEL_PATH" | head -5 | sed 's/^/    /'
        if [ $(ls -1 "$MODEL_PATH" | wc -l) -gt 5 ]; then
            echo "    ... and more files"
        fi
    else
        echo "⚠️ Model path not found (will use HTTP client mode or auto-download)"
    fi
    
    # 检查MinerU配置文件
    if [ -f "$MINERU_TOOLS_CONFIG_JSON" ]; then
        echo "✅ MinerU config file exists"
    else
        echo "❌ MinerU config file not found: $MINERU_TOOLS_CONFIG_JSON"
    fi
    
    # 显示环境信息
    echo ""
    echo "🔧 Environment:"
    echo "  Python: $(which python 2>/dev/null || echo 'Not found')"
    echo "  FastAPI module: $(python -c 'import fastapi; print(fastapi.__version__)' 2>/dev/null || echo 'Not found')"
    echo "  MinerU module: $(python -c 'import mineru; print(mineru.__version__)' 2>/dev/null || echo 'Not found')"
    echo "  Conda: $(which conda 2>/dev/null || echo 'Not found')"
    echo "  CUDA: $(which nvcc 2>/dev/null || echo 'Not found')"
    
    # 显示GPU信息
    if command -v nvidia-smi >/dev/null 2>&1; then
        echo ""
        echo "🔥 GPU Information:"
        nvidia-smi --query-gpu=index,name,driver_version,memory.total --format=csv,noheader,nounits | \
        awk -F',' '{printf "  GPU %s: %s (Driver: %s, Memory: %sMB)\n", $1, $2, $3, $4}'
    fi
}

test_api() {
    echo "🧪 Testing MinerU FastAPI..."
    
    if [ ! -f $PIDFILE ] || ! kill -0 $(cat $PIDFILE) 2>/dev/null; then
        echo "❌ MinerU FastAPI service is not running"
        return 1
    fi
    
    if ! command -v curl >/dev/null 2>&1; then
        echo "❌ curl command not found"
        return 1
    fi
    
    echo "📡 Testing FastAPI health..."
    response=$(curl -s --connect-timeout 5 "http://127.0.0.1:$API_PORT/docs")
    if [ $? -eq 0 ]; then
        echo "✅ FastAPI docs endpoint accessible"
    else
        echo "❌ FastAPI docs endpoint not accessible"
    fi
    
    # 测试文件上传API（需要测试文件）
    TEST_FILE="/home/ubuntu/zhch/MinerU/demo/pdfs/small_ocr.pdf"
    if [ -f "$TEST_FILE" ]; then
        echo ""
        echo "📡 Testing /file_parse endpoint..."
        response=$(curl -s -X POST "http://127.0.0.1:$API_PORT/file_parse" \
            -F "files=@$TEST_FILE" \
            -F "backend=vlm-http-client" \
			-F "server_url=http://$VLLM_HOST:$VLLM_PORT" \
            -F "return_md=true" \
			-F "response_format_zip=false" \
            --connect-timeout 300)
        
        if [[ "$response" == *"results"* ]]; then
            echo "✅ File parse endpoint working"
            echo "Response preview: $(echo "$response" | head -c 200)..."
        else
            echo "⚠️ File parse endpoint response unexpected"
            echo "Response: $response"
        fi
    else
        echo "⚠️ Test file not found: $TEST_FILE"
        echo "Please provide a test file to test the upload functionality"
    fi
}

test_client() {
    echo "🧪 Testing MinerU client with FastAPI..."
    
    if [ ! -f $PIDFILE ] || ! kill -0 $(cat $PIDFILE) 2>/dev/null; then
        echo "❌ MinerU FastAPI service is not running. Start it first with: $0 start"
        return 1
    fi
    
    # 测试用例文件路径
    TEST_IMAGE="/home/ubuntu/zhch/MinerU/demo/pdfs/small_ocr.pdf"
    TEST_OUTPUT="/tmp/mineru_fastapi_test_output"
    
    if [ ! -f "$TEST_IMAGE" ]; then
        echo "⚠️ Test image not found: $TEST_IMAGE"
        echo "Please provide a test image or update the TEST_IMAGE path in the script"
        return 1
    fi
    
    echo "📄 Testing with image: $TEST_IMAGE"
    echo "📁 Output directory: $TEST_OUTPUT"
    
    # 使用 curl 直接测试 FastAPI
    echo "Testing via curl..."
    curl -X POST "http://127.0.0.1:$API_PORT/file_parse" \
        -F "files=@$TEST_IMAGE" \
        -F "backend=vlm-http-client" \
		-F "server_url=http://$VLLM_HOST:$VLLM_PORT" \
        -F "return_md=true" \
        -F "output_dir=$TEST_OUTPUT" \
        -o "$TEST_OUTPUT/fastapi_result.json"
    
    if [ $? -eq 0 ]; then
        echo "✅ FastAPI test completed successfully"
        echo "📁 Check output in: $TEST_OUTPUT"
        if [ -f "$TEST_OUTPUT/fastapi_result.json" ]; then
            echo "📄 Result file size: $(du -h "$TEST_OUTPUT/fastapi_result.json" | cut -f1)"
        fi
    else
        echo "❌ FastAPI test failed"
    fi
}

# 显示使用帮助
usage() {
    echo "MinerU FastAPI Service Daemon"
    echo "============================="
    echo "Usage: $0 {start|stop|restart|status|logs|config|test|test-client}"
    echo ""
    echo "Commands:"
    echo "  start       - Start the MinerU FastAPI service"
    echo "  stop        - Stop the MinerU FastAPI service"  
    echo "  restart     - Restart the MinerU FastAPI service"
    echo "  status      - Show service status and resource usage"
    echo "  logs        - Show service logs (follow mode)"
    echo "  config      - Show current configuration"
    echo "  test        - Test API endpoints"
    echo "  test-client - Test FastAPI with sample file"
    echo ""
    echo "Configuration (edit script to modify):"
    echo "  FastAPI Host: $API_HOST"
    echo "  FastAPI Port: $API_PORT"
    echo "  vLLM Backend: $VLLM_HOST:$VLLM_PORT"
    echo "  Model: $MODEL_PATH"
    echo "  GPU Memory: $GPU_MEMORY_UTILIZATION"
    echo "  CUDA Devices: $CUDA_VISIBLE_DEVICES"
    echo ""
    echo "API Endpoints:"
    echo "  Swagger UI: http://localhost:$API_PORT/docs"
    echo "  ReDoc: http://localhost:$API_PORT/redoc"
    echo "  File Parse: POST http://localhost:$API_PORT/file_parse"
    echo ""
    echo "Examples:"
    echo "  ./mineru_fast_api_daemon.sh start"
    echo "  ./mineru_fast_api_daemon.sh status"
    echo "  ./mineru_fast_api_daemon.sh logs"
    echo "  ./mineru_fast_api_daemon.sh test"
}

case "$1" in
    start)
        start
        ;;
    stop)
        stop
        ;;
    restart)
        stop
        sleep 3
        start
        ;;
    status)
        status
        ;;
    logs)
        logs
        ;;
    config)
        config
        ;;
    test)
        test_api
        ;;
    test-client)
        test_client
        ;;
    *)
        usage
        exit 1
        ;;
esac