forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
52 lines
1.6 KiB
Python
52 lines
1.6 KiB
Python
"""Retriever that wraps a base retriever and filters the results."""
|
|
from typing import List
|
|
|
|
from pydantic import BaseModel, Extra
|
|
|
|
from langchain.retrievers.document_compressors.base import (
|
|
BaseDocumentCompressor,
|
|
)
|
|
from langchain.schema import BaseRetriever, Document
|
|
|
|
|
|
class ContextualCompressionRetriever(BaseRetriever, BaseModel):
|
|
"""Retriever that wraps a base retriever and compresses the results."""
|
|
|
|
base_compressor: BaseDocumentCompressor
|
|
"""Compressor for compressing retrieved documents."""
|
|
|
|
base_retriever: BaseRetriever
|
|
"""Base Retriever to use for getting relevant documents."""
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
arbitrary_types_allowed = True
|
|
|
|
def get_relevant_documents(self, query: str) -> List[Document]:
|
|
"""Get documents relevant for a query.
|
|
|
|
Args:
|
|
query: string to find relevant documents for
|
|
|
|
Returns:
|
|
Sequence of relevant documents
|
|
"""
|
|
docs = self.base_retriever.get_relevant_documents(query)
|
|
compressed_docs = self.base_compressor.compress_documents(docs, query)
|
|
return list(compressed_docs)
|
|
|
|
async def aget_relevant_documents(self, query: str) -> List[Document]:
|
|
"""Get documents relevant for a query.
|
|
|
|
Args:
|
|
query: string to find relevant documents for
|
|
|
|
Returns:
|
|
List of relevant documents
|
|
"""
|
|
docs = await self.base_retriever.aget_relevant_documents(query)
|
|
compressed_docs = await self.base_compressor.acompress_documents(docs, query)
|
|
return list(compressed_docs)
|