feat: Added filtering option to FAISS vectorstore (#5966)

Inspired by the filtering capability available in ChromaDB, added the
same functionality to the FAISS vectorestore as well. Since FAISS does
not have an inbuilt method of filtering used the approach suggested in
this [thread](https://github.com/facebookresearch/faiss/issues/1079)
Langchain Issue inspiration:
https://github.com/hwchase17/langchain/issues/4572

- [x] Added filtering capability to semantic similarly and MMR
- [x] Added test cases for filtering in
`tests/integration_tests/vectorstores/test_faiss.py`

#### Who can review?

Tag maintainers/contributors who might be interested:

  VectorStores / Retrievers / Memory
  - @dev2049
  - @hwchase17
This commit is contained in:
Akhil Vempali
2023-06-12 01:50:03 +05:30
committed by GitHub
parent 6e90406e0f
commit d7d629911b
4 changed files with 282 additions and 59 deletions

View File

@@ -74,6 +74,28 @@ def test_faiss_with_metadatas() -> None:
assert output == [Document(page_content="foo", metadata={"page": 0})]
def test_faiss_with_metadatas_and_filter() -> None:
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = FAISS.from_texts(texts, FakeEmbeddings(), metadatas=metadatas)
expected_docstore = InMemoryDocstore(
{
docsearch.index_to_docstore_id[0]: Document(
page_content="foo", metadata={"page": 0}
),
docsearch.index_to_docstore_id[1]: Document(
page_content="bar", metadata={"page": 1}
),
docsearch.index_to_docstore_id[2]: Document(
page_content="baz", metadata={"page": 2}
),
}
)
assert docsearch.docstore.__dict__ == expected_docstore.__dict__
output = docsearch.similarity_search("foo", k=1, filter={"page": 1})
assert output == []
def test_faiss_search_not_found() -> None:
"""Test what happens when document is not found."""
texts = ["foo", "bar", "baz"]