67 lines
1.8 KiB
Python
67 lines
1.8 KiB
Python
"""
|
||
RAG 检索与生成模块
|
||
|
||
提供在线检索与生成功能，包括：
|
||
- 基础向量检索（稠密向量 / 混合检索）
|
||
- 重排序（Cross-Encoder）
|
||
- 多路查询改写（Multi-Query）
|
||
- RRF 融合（Reciprocal Rank Fusion）
|
||
- 完整的 RAG 流水线
|
||
- Agent 工具封装
|
||
|
||
固定流水线：
|
||
用户查询 → 多路改写 → 并行检索 → RRF 融合 → 重排序 → 返回父文档
|
||
|
||
示例用法：
|
||
>>> from app.rag.rag import RAGPipeline, create_rag_tool
|
||
>>> from rag_indexer.builder import IndexBuilder, IndexBuilderConfig
|
||
>>> from langchain_openai import ChatOpenAI
|
||
>>>
|
||
>>> # 获取基础检索器（如父子块检索器）
|
||
>>> config = IndexBuilderConfig(collection_name="my_docs")
|
||
>>> builder = IndexBuilder(config)
|
||
>>> retriever = builder.retriever
|
||
>>>
|
||
>>> # 创建 LLM 和流水线
|
||
>>> llm = ChatOpenAI(model="gpt-3.5-turbo")
|
||
>>> pipeline = RAGPipeline(retriever=retriever, llm=llm)
|
||
>>>
|
||
>>> # 检索
|
||
>>> docs = await pipeline.aretrieve("什么是 RAG？")
|
||
>>> context = pipeline.format_context(docs)
|
||
>>>
|
||
>>> # 创建 Agent 工具
|
||
>>> rag_tool = create_rag_tool(retriever=retriever, llm=llm)
|
||
"""
|
||
|
||
from .retriever import (
|
||
create_base_retriever,
|
||
create_hybrid_retriever,
|
||
)
|
||
from .reranker import LLaMaCPPReranker
|
||
from .query_transform import MultiQueryGenerator
|
||
from .fusion import reciprocal_rank_fusion
|
||
from .pipeline import RAGPipeline
|
||
from .tools import create_rag_tool_sync
|
||
|
||
|
||
__all__ = [
|
||
# 检索器工厂函数
|
||
"create_base_retriever",
|
||
"create_hybrid_retriever",
|
||
|
||
# 重排序器
|
||
"LLaMaCPPReranker",
|
||
|
||
# 查询改写生成器
|
||
"MultiQueryGenerator",
|
||
|
||
# 融合算法
|
||
"reciprocal_rank_fusion",
|
||
|
||
# 主流水线
|
||
"RAGPipeline",
|
||
|
||
# 工具创建（供 Agent 使用）
|
||
"create_rag_tool_sync",
|
||
] |