feat(新增PaddleOCR-VL本地服务脚本): 新增paddle_local_daemon_1.6.sh脚本，支持在macOS上启动PaddleOCR-VL本地llama-server服务，配置模型路径、参数及日志管理，提升本地OCR服务的可用性与易用性。

ocr_tools/daemons/paddle_local_daemon_1.6.sh

@@ -0,0 +1,395 @@
+#!/bin/bash
+# filepath: ocr_platform/ocr_tools/daemons/paddleocr_local_daemon.sh
+# 对应: PaddleOCR-VL 本地 llama-server 服务（macOS），使用 GGUF 格式模型
+# 适用于 Mac M4 Pro 48G，使用 Metal GPU 加速
+# 模型下载地址: https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5-GGUF
+
+# unset https_proxy http_proxy HF_ENDPOINT
+# llama-server -hf PaddlePaddle/PaddleOCR-VL-1.5-GGUF
+# mv ~/Library/Caches/llama.cpp/PaddlePaddle_PaddleOCR-VL-1.5-GGUF_PaddleOCR-VL-1.5.gguf  ~/models/paddleocr_vl
+# mv ~/Library/Caches/llama.cpp/PaddlePaddle_PaddleOCR-VL-1.5-GGUF_PaddleOCR-VL-1.5-mmproj.gguf  ~/models/paddleocr_vl
+
+# curl -X POST http://localhost:8102/v1/chat/completions -d @payload.json
+
+LOGDIR="$HOME/workspace/logs"
+mkdir -p $LOGDIR
+PIDFILE="$LOGDIR/paddleocr_llamaserver.pid"
+LOGFILE="$LOGDIR/paddleocr_llamaserver.log"
+
+# 配置参数
+CONDA_ENV="mineru"
+PORT="8102"
+HOST="0.0.0.0"
+
+# 本地 GGUF 模型路径（llama-server -hf 下载后的实际路径）
+HF_CACHE="$HOME/models/PaddleOCR-VL-1.6-GGUF"
+MODEL_PATH="$HF_CACHE/PaddleOCR-VL-1.6-F16.gguf"
+MMPROJ_PATH="$HF_CACHE/PaddleOCR-VL-1.6-F16-mmproj.gguf"
+
+# 模型别名（对外暴露的模型 ID，对应 yaml 中的 model_name）
+MODEL_NAME="PaddleOCR-VL-1.6"
+
+# llama-server 执行文件
+LLAMA_SERVER_EXECUTABLE="/Users/zhch158/workspace/repository.git/llama.cpp/build/bin/llama-server"
+
+# llama-server 参数
+CONTEXT_SIZE="16384"         # 上下文长度（需 >= max_tokens，推荐 8192-16384）
+GPU_LAYERS="99"              # Metal GPU 层数（99 表示全部）
+THREADS="8"                  # CPU 线程数（M4 Pro 建议值）
+BATCH_SIZE="512"             # 批处理大小
+UBATCH_SIZE="128"            # 微批处理大小
+
+# conda 环境激活
+if [ -f "$HOME/anaconda3/etc/profile.d/conda.sh" ]; then
+    source "$HOME/anaconda3/etc/profile.d/conda.sh"
+    conda activate $CONDA_ENV
+elif [ -f "$HOME/miniconda3/etc/profile.d/conda.sh" ]; then
+    source "$HOME/miniconda3/etc/profile.d/conda.sh"
+    conda activate $CONDA_ENV
+elif [ -f "/opt/miniconda3/etc/profile.d/conda.sh" ]; then
+    source /opt/miniconda3/etc/profile.d/conda.sh
+    conda activate $CONDA_ENV
+else
+    echo "Warning: conda initialization file not found, trying direct path"
+    export PATH="/opt/miniconda3/envs/$CONDA_ENV/bin:$PATH"
+fi
+
+start() {
+    if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
+        echo "PaddleOCR-VL llama-server 已在运行"
+        return 1
+    fi
+
+    echo "启动 PaddleOCR-VL llama-server 守护进程..."
+    echo "Host: $HOST, Port: $PORT"
+    echo "主模型: $MODEL_PATH"
+    echo "多模态投影器: $MMPROJ_PATH"
+    echo "上下文长度: $CONTEXT_SIZE"
+    echo "GPU 层数: $GPU_LAYERS (Metal)"
+    echo "线程数: $THREADS"
+
+    # 检查模型文件是否存在
+    if [ ! -f "$MODEL_PATH" ]; then
+        echo "❌ 主模型文件不存在: $MODEL_PATH"
+        echo "请确认模型已下载到 llama.cpp 缓存目录"
+        return 1
+    fi
+
+    if [ ! -f "$MMPROJ_PATH" ]; then
+        echo "❌ 多模态投影器文件不存在: $MMPROJ_PATH"
+        echo "请确认 mmproj 文件已下载"
+        return 1
+    fi
+
+    # 检查 llama-server 执行文件（本机编译版本）
+    if [ ! -x "$LLAMA_SERVER_EXECUTABLE" ]; then
+        echo "❌ llama-server 执行文件不存在或不可执行: $LLAMA_SERVER_EXECUTABLE"
+        echo "请确认已在本机编译 llama.cpp（cmake --build build）"
+        return 1
+    fi
+
+    echo "🔧 使用 llama-server: $LLAMA_SERVER_EXECUTABLE"
+    echo "🔧 llama.cpp 版本: $("$LLAMA_SERVER_EXECUTABLE" --version 2>&1 | head -1 || echo 'Unknown')"
+
+    echo "💻 系统信息:"
+    echo "  架构: $(uname -m)"
+    echo "  系统: $(uname -s)"
+    echo "  内存: $(sysctl -n hw.memsize | awk '{printf "%.1f GB", $1/1024/1024/1024}')"
+
+    # 启动 llama-server
+    nohup "$LLAMA_SERVER_EXECUTABLE" \
+        -m "$MODEL_PATH" \
+        --mmproj "$MMPROJ_PATH" \
+        --alias $MODEL_NAME \
+        --host $HOST \
+        --port $PORT \
+        --media-path $HOME/workspace \
+        -c $CONTEXT_SIZE \
+        -ngl $GPU_LAYERS \
+        -t $THREADS \
+        -b $BATCH_SIZE \
+        -ub $UBATCH_SIZE \
+        --temp 0 \
+        > $LOGFILE 2>&1 &
+
+    echo $! > $PIDFILE
+    echo "✅ PaddleOCR-VL llama-server 已启动，PID: $(cat $PIDFILE)"
+    echo "📋 日志文件: $LOGFILE"
+    echo "🌐 服务 URL: http://$HOST:$PORT"
+    echo "📖 OpenAI 兼容 API: http://localhost:$PORT/v1 (chat/completions, models)"
+    echo ""
+    echo "等待服务启动..."
+    sleep 5
+    status
+}
+
+stop() {
+    if [ ! -f $PIDFILE ]; then
+        echo "PaddleOCR-VL llama-server 未在运行"
+        return 1
+    fi
+
+    PID=$(cat $PIDFILE)
+    echo "停止 PaddleOCR-VL llama-server (PID: $PID)..."
+
+    kill $PID
+
+    for i in {1..30}; do
+        if ! kill -0 $PID 2>/dev/null; then
+            break
+        fi
+        echo "等待进程停止... ($i/30)"
+        sleep 1
+    done
+
+    if kill -0 $PID 2>/dev/null; then
+        echo "强制终止进程..."
+        kill -9 $PID
+    fi
+
+    rm -f $PIDFILE
+    echo "✅ PaddleOCR-VL llama-server 已停止"
+}
+
+status() {
+    if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
+        PID=$(cat $PIDFILE)
+        echo "✅ PaddleOCR-VL llama-server 正在运行 (PID: $PID)"
+        echo "🌐 服务 URL: http://$HOST:$PORT"
+        echo "📋 日志文件: $LOGFILE"
+
+        # 检查端口监听状态
+        if lsof -nP -iTCP:$PORT -sTCP:LISTEN >/dev/null 2>&1; then
+            echo "🔗 端口 $PORT 正在监听"
+        else
+            echo "⚠️  端口 $PORT 未在监听（服务可能正在启动）"
+        fi
+
+        # 检查 API 响应
+        if command -v curl >/dev/null 2>&1; then
+            if curl -s --connect-timeout 2 http://127.0.0.1:$PORT/v1/models > /dev/null 2>&1; then
+                echo "🎯 API 响应正常"
+            else
+                echo "⚠️  API 无响应（服务可能正在启动）"
+            fi
+        fi
+
+        # 显示进程内存使用
+        if command -v ps >/dev/null 2>&1; then
+            MEM=$(ps -o rss= -p $PID 2>/dev/null | awk '{printf "%.2f GB", $1/1024/1024}')
+            if [ -n "$MEM" ]; then
+                echo "💾 内存使用: $MEM"
+            fi
+        fi
+
+        if [ -f $LOGFILE ]; then
+            echo "📄 最近日志（最后 3 行）:"
+            tail -3 $LOGFILE | sed 's/^/  /'
+        fi
+    else
+        echo "❌ PaddleOCR-VL llama-server 未在运行"
+        if [ -f $PIDFILE ]; then
+            echo "删除过期的 PID 文件..."
+            rm -f $PIDFILE
+        fi
+    fi
+}
+
+logs() {
+    if [ -f $LOGFILE ]; then
+        echo "📄 PaddleOCR-VL llama-server 日志:"
+        echo "====================="
+        tail -f $LOGFILE
+    else
+        echo "❌ 日志文件不存在: $LOGFILE"
+    fi
+}
+
+config() {
+    echo "📋 当前配置:"
+    echo "  Conda 环境: $CONDA_ENV"
+    echo "  Host: $HOST"
+    echo "  Port: $PORT"
+    echo "  模型别名: $MODEL_NAME"
+    echo "  主模型路径: $MODEL_PATH"
+    echo "  多模态投影器: $MMPROJ_PATH"
+    echo "  上下文长度: $CONTEXT_SIZE"
+    echo "  GPU 层数: $GPU_LAYERS"
+    echo "  线程数: $THREADS"
+    echo "  批处理大小: $BATCH_SIZE"
+    echo "  微批处理大小: $UBATCH_SIZE"
+    echo "  PID 文件: $PIDFILE"
+    echo "  日志文件: $LOGFILE"
+
+    echo ""
+    echo "📦 模型文件检查:"
+    if [ -f "$MODEL_PATH" ]; then
+        SIZE=$(du -h "$MODEL_PATH" | cut -f1)
+        echo "  ✅ 主模型存在 ($SIZE)"
+    else
+        echo "  ❌ 主模型不存在"
+    fi
+
+    if [ -f "$MMPROJ_PATH" ]; then
+        SIZE=$(du -h "$MMPROJ_PATH" | cut -f1)
+        echo "  ✅ 多模态投影器存在 ($SIZE)"
+    else
+        echo "  ❌ 多模态投影器不存在"
+    fi
+
+    echo ""
+    echo "🔧 环境检查:"
+    echo "  llama-server: $LLAMA_SERVER_EXECUTABLE"
+    if [ -x "$LLAMA_SERVER_EXECUTABLE" ]; then
+        LLAMA_VERSION=$("$LLAMA_SERVER_EXECUTABLE" --version 2>&1 | head -1 || echo 'Unknown')
+        echo "  版本: $LLAMA_VERSION"
+    else
+        echo "  ⚠️  执行文件不存在或不可执行"
+    fi
+    echo "  Conda: $(which conda 2>/dev/null || echo '未找到')"
+    echo "  当前 Python: $(which python 2>/dev/null || echo '未找到')"
+
+    echo ""
+    echo "💻 系统信息:"
+    echo "  架构: $(uname -m)"
+    echo "  系统版本: $(sw_vers -productVersion 2>/dev/null || echo 'Unknown')"
+    echo "  总内存: $(sysctl -n hw.memsize 2>/dev/null | awk '{printf "%.1f GB", $1/1024/1024/1024}' || echo 'Unknown')"
+    echo "  CPU 核心: $(sysctl -n hw.ncpu 2>/dev/null || echo 'Unknown')"
+}
+
+test_api() {
+    echo "🧪 测试 PaddleOCR-VL llama-server API..."
+
+    if [ ! -f $PIDFILE ] || ! kill -0 $(cat $PIDFILE) 2>/dev/null; then
+        echo "❌ PaddleOCR-VL llama-server 服务未在运行"
+        return 1
+    fi
+
+    if ! command -v curl >/dev/null 2>&1; then
+        echo "❌ curl 命令未找到"
+        return 1
+    fi
+
+    echo "📡 测试 /v1/models 端点..."
+    response=$(curl -s --connect-timeout 10 http://127.0.0.1:$PORT/v1/models)
+    if [ $? -eq 0 ]; then
+        echo "✅ Models 端点可访问"
+        echo "$response" | python -m json.tool 2>/dev/null || echo "$response"
+    else
+        echo "❌ Models 端点不可访问"
+    fi
+
+    echo ""
+    echo "📡 测试 /health 端点..."
+    health=$(curl -s --connect-timeout 5 http://127.0.0.1:$PORT/health)
+    if [ $? -eq 0 ]; then
+        echo "✅ Health 端点: $health"
+    else
+        echo "⚠️  Health 端点不可访问"
+    fi
+}
+
+test_client() {
+    echo "🧪 测试 PaddleOCR-VL 与 llama-server 集成..."
+
+    if [ ! -f $PIDFILE ] || ! kill -0 $(cat $PIDFILE) 2>/dev/null; then
+        echo "❌ PaddleOCR-VL llama-server 服务未在运行，请先启动: $0 start"
+        return 1
+    fi
+
+    CONFIG_FILE="/Users/zhch158/workspace/repository.git/ocr_platform/ocr_tools/universal_doc_parser/config/bank_statement_paddleocr_local.yaml"
+    
+    echo "📄 配置文件: $CONFIG_FILE"
+    echo ""
+    echo "确保配置文件中 vl_recognition.api_url 指向: http://localhost:$PORT/v1/chat/completions"
+    echo ""
+    echo "测试命令示例:"
+    echo "  cd /Users/zhch158/workspace/repository.git/ocr_platform/ocr_tools/universal_doc_parser"
+    echo "  conda activate mineru"
+    echo "  python parse.py --input /path/to/test/image.png --config $CONFIG_FILE --debug"
+    echo ""
+    echo "或者使用 curl 直接测试 API:"
+    echo "  curl -X POST http://localhost:$PORT/v1/chat/completions \\"
+    echo "    -H 'Content-Type: application/json' \\"
+    echo "    -d '{"
+    echo "      \"model\": \"paddleocr-vl\","
+    echo "      \"messages\": ["
+    echo "        {"
+    echo "          \"role\": \"user\","
+    echo "          \"content\": ["
+    echo "            {\"type\": \"text\", \"text\": \"Table Recognition:\"},"
+    echo "            {\"type\": \"image_url\", \"image_url\": {\"url\": \"file:///path/to/image.png\"}}"
+    echo "          ]"
+    echo "        }"
+    echo "      ],"
+    echo "      \"max_tokens\": 4096"
+    echo "    }'"
+}
+
+usage() {
+    echo "PaddleOCR-VL llama-server 服务守护进程（macOS）"
+    echo "==========================================="
+    echo "用法: $0 {start|stop|restart|status|logs|config|test|test-client}"
+    echo ""
+    echo "命令:"
+    echo "  start       - 启动 PaddleOCR-VL llama-server 服务"
+    echo "  stop        - 停止 PaddleOCR-VL llama-server 服务"
+    echo "  restart     - 重启 PaddleOCR-VL llama-server 服务"
+    echo "  status      - 显示服务状态和资源使用"
+    echo "  logs        - 显示服务日志（跟踪模式）"
+    echo "  config      - 显示当前配置"
+    echo "  test        - 测试 /v1/models API 端点"
+    echo "  test-client - 显示如何测试与配置文件集成"
+    echo ""
+    echo "配置（编辑脚本修改）:"
+    echo "  Host: $HOST"
+    echo "  Port: $PORT"
+    echo "  主模型: $MODEL_PATH"
+    echo "  多模态投影器: $MMPROJ_PATH"
+    echo "  上下文长度: $CONTEXT_SIZE"
+    echo "  GPU 层数: $GPU_LAYERS (Metal)"
+    echo ""
+    echo "示例:"
+    echo "  ./paddleocr_local_daemon.sh start"
+    echo "  ./paddleocr_local_daemon.sh status"
+    echo "  ./paddleocr_local_daemon.sh logs"
+    echo "  ./paddleocr_local_daemon.sh test"
+    echo ""
+    echo "前置要求:"
+    echo "  1. 本机编译 llama.cpp，执行文件: $LLAMA_SERVER_EXECUTABLE"
+    echo "  2. 模型文件位于: $HF_CACHE"
+    echo "  3. conda 环境 mineru 已配置"
+}
+
+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