init: RAG 知识库服务初始提交
- 后端 API(Flask + Gunicorn) - RAG 引擎(混合检索 + 云端 Reranker + 引用溯源) - 文档解析(MinerU + 多格式支持) - Docker 生产部署配置 - 排除前端项目、敏感配置、模型文件
This commit is contained in:
48
requirements-prod.txt
Normal file
48
requirements-prod.txt
Normal file
@@ -0,0 +1,48 @@
|
||||
# RAG 服务生产环境依赖
|
||||
# ================================
|
||||
# 适用场景:CPU 服务器部署,无 GPU
|
||||
# 安装命令:
|
||||
# pip install torch --index-url https://download.pytorch.org/whl/cpu
|
||||
# pip install -r requirements-prod.txt -i https://mirrors.aliyun.com/pypi/simple/
|
||||
|
||||
# ==================== 核心框架 ====================
|
||||
flask>=2.0.0 # Web 框架
|
||||
flask-cors>=4.0.0 # CORS 支持
|
||||
werkzeug>=2.0.0 # WSGI 工具
|
||||
gunicorn>=21.0.0 # WSGI 服务器
|
||||
|
||||
# ==================== 向量检索 ====================
|
||||
chromadb>=0.4.0 # 向量数据库
|
||||
sentence-transformers>=2.2.0 # 向量嵌入模型
|
||||
rank-bm25>=0.2.2 # BM25 关键词检索
|
||||
jieba>=0.42.1 # 中文分词
|
||||
faiss-cpu>=1.7.0 # FAISS 向量索引(语义缓存)
|
||||
|
||||
# ==================== Rerank 加速 ====================
|
||||
optimum[onnxruntime]>=1.14.0 # ONNX Runtime(CPU 推理加速)
|
||||
|
||||
# ==================== LLM 调用 ====================
|
||||
openai>=1.0.0 # LLM API 客户端
|
||||
requests>=2.28.0 # HTTP 客户端
|
||||
|
||||
# ==================== 文档解析(必需) ====================
|
||||
# MinerU 核心依赖 - PDF/Word/PPT/图片解析
|
||||
mineru>=3.0.0 # 文档解析核心
|
||||
|
||||
# Excel 解析
|
||||
pandas>=2.0.0
|
||||
openpyxl>=3.1.0
|
||||
|
||||
# 备用解析器(可选,MinerU 失败时降级)
|
||||
pdfplumber>=0.10.0
|
||||
python-docx>=0.8.11
|
||||
|
||||
# ==================== 文本处理 ====================
|
||||
langchain-text-splitters>=0.3.0 # 语义分块器
|
||||
numpy>=1.24.0
|
||||
|
||||
# ==================== 文件监控 ====================
|
||||
watchdog>=3.0.0 # 文档变更监控
|
||||
|
||||
# ==================== 配置管理 ====================
|
||||
python-dotenv>=1.0.0 # 环境变量
|
||||
Reference in New Issue
Block a user