github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-16 09:48:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Keep also original query - multi_query.py (#12696)

Browse Source 
When you use a MultiQuery it might be useful to use the original query
as well as the newly generated ones to maximise the changes to retriever
the correct document. I haven't created an issue, it seems a very small
and easy thing.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
This commit is contained in:
Manuel Rech 2023-11-03 12:15:02 +11:00 committed by GitHub
parent 4fe9bf70b6
commit 2e2b9c76d9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
libs/langchain/langchain/retrievers/multi_query.py
View File

@ -61,6 +61,8 @@ class MultiQueryRetriever(BaseRetriever):
llm_chain: LLMChain
verbose: bool = True
parser_key: str = "lines"
include_original: bool = False
"""Whether to include the original query in the list of generated queries."""
@classmethod
def from_llm(
@ -69,12 +71,15 @@ class MultiQueryRetriever(BaseRetriever):
llm: BaseLLM,
prompt: PromptTemplate = DEFAULT_QUERY_PROMPT,
parser_key: str = "lines",
include_original: bool = False,
) -> "MultiQueryRetriever":
"""Initialize from llm using default template.
Args:
retriever: retriever to query documents from
llm: llm for query generation using DEFAULT_QUERY_PROMPT
include_original: Whether to include the original query in the list of
generated queries.
Returns:
MultiQueryRetriever
@ -85,6 +90,7 @@ class MultiQueryRetriever(BaseRetriever):
retriever=retriever,
llm_chain=llm_chain,
parser_key=parser_key,
include_original=include_original,
)
async def _aget_relevant_documents(
@ -102,6 +108,8 @@ class MultiQueryRetriever(BaseRetriever):
Unique union of relevant documents from all generated queries
"""
queries = await self.agenerate_queries(query, run_manager)
if self.include_original:
queries.append(query)
documents = await self.aretrieve_documents(queries, run_manager)
return self.unique_union(documents)
@ -160,6 +168,8 @@ class MultiQueryRetriever(BaseRetriever):
Unique union of relevant documents from all generated queries
"""
queries = self.generate_queries(query, run_manager)
if self.include_original:
queries.append(query)
documents = self.retrieve_documents(queries, run_manager)
return self.unique_union(documents)