community: add len() implementation to Chroma (#19419)

Thank you for contributing to LangChain!

- [x] **Add len() implementation to Chroma**: "package: community"


- [x] **PR message**: 
- **Description:** add an implementation of the __len__() method for the
Chroma vectostore, for convenience.
- **Issue:** no exposed method to know the size of a Chroma vectorstore
    - **Dependencies:** None
    - **Twitter handle:** lowrank_adrian


- [x] **Add tests and docs**

- [x] **Lint and test**

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
This commit is contained in:
Adrian Valente 2024-03-26 17:53:10 +01:00 committed by GitHub
parent e0a1278d2b
commit 2763d8cbe5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 0 deletions

View File

@ -795,3 +795,7 @@ class Chroma(VectorStore):
ids: List of ids to delete.
"""
self._collection.delete(ids=ids)
def __len__(self) -> int:
"""Count the number of documents in the collection."""
return self._collection.count()

View File

@ -21,6 +21,7 @@ def test_chroma() -> None:
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
assert len(docsearch) == 3
async def test_chroma_async() -> None: