github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-11 07:50:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: BM25Retriever preservation of document id (#27019)

Browse Source 
Currently this retriever discards document ids

---------

Co-authored-by: asi-cider <88270351+asi-cider@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
Asi Greenholts
2024-12-04 02:36:00 +02:00
committed by GitHub
parent a009249369
commit d34bf78f3b
2 changed files with 54 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
libs/community/tests/unit_tests/retrievers/test_bm25.py
View File

@@ -43,3 +43,42 @@ def test_repr() -> None:
]
bm25_retriever = BM25Retriever.from_documents(documents=input_docs)
assert "I have a pen" not in repr(bm25_retriever)
@pytest.mark.requires("rank_bm25")
def test_doc_id() -> None:
docs_with_ids = [
Document(page_content="I have a pen.", id="1"),
Document(page_content="Do you have a pen?", id="2"),
Document(page_content="I have a bag.", id="3"),
]
docs_without_ids = [
Document(page_content="I have a pen."),
Document(page_content="Do you have a pen?"),
Document(page_content="I have a bag."),
]
docs_with_some_ids = [
Document(page_content="I have a pen.", id="1"),
Document(page_content="Do you have a pen?"),
Document(page_content="I have a bag.", id="3"),
]
bm25_retriever_with_ids = BM25Retriever.from_documents(documents=docs_with_ids)
bm25_retriever_without_ids = BM25Retriever.from_documents(
documents=docs_without_ids
)
bm25_retriever_with_some_ids = BM25Retriever.from_documents(
documents=docs_with_some_ids
)
for doc in bm25_retriever_with_ids.docs:
assert doc.id is not None
for doc in bm25_retriever_without_ids.docs:
assert doc.id is None
for doc in bm25_retriever_with_some_ids.docs:
if doc.page_content == "I have a pen.":
assert doc.id == "1"
elif doc.page_content == "Do you have a pen?":
assert doc.id is None
elif doc.page_content == "I have a bag.":
assert doc.id == "3"
else:
raise ValueError("Unexpected document")