feat: add extraction_service (PDF/Docx/Txt) and update .gitignore to exclude venv

extraction_service/start.bat

@@ -0,0 +1,37 @@
+@echo off
+chcp 65001 >nul
+echo ================================
+echo 启动文档提取微服务
+echo ================================
+echo.
+
+REM 检查虚拟环境
+if exist venv\Scripts\activate.bat (
+    echo [1/3] 激活虚拟环境...
+    call venv\Scripts\activate
+) else (
+    echo 警告: 未找到虚拟环境，使用全局Python
+)
+
+REM 检查依赖
+echo [2/3] 检查依赖...
+pip list | findstr "fastapi" >nul
+if errorlevel 1 (
+    echo 依赖未安装，正在安装...
+    pip install -r requirements.txt
+)
+
+REM 启动服务
+echo [3/3] 启动服务...
+echo.
+echo 服务地址: http://localhost:8000
+echo 健康检查: http://localhost:8000/api/health
+echo API文档: http://localhost:8000/docs
+echo.
+echo 按 Ctrl+C 停止服务
+echo.
+
+uvicorn main:app --host 0.0.0.0 --port 8000 --reload
+
+pause
+