Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: Allow search in ChromaDocumentStore without metadata #863

Merged
merged 10 commits into from
Jul 8, 2024
Merged

fix: Allow search in ChromaDocumentStore without metadata #863

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
570cc74
Fix a bug for checking metadata values
Jul 1, 2024
18d7296
Added a unit test
Jul 1, 2024
88e2e26
Fix linting
Jul 1, 2024
282f214
Fixing bug
Jul 1, 2024
32d1cb9
Fixing Lint
Jul 1, 2024
5202670
Fix bugs in test
Jul 2, 2024
8cd47d0
Included review comments and added a test
Jul 8, 2024
489044f
Fixed linting
Jul 8, 2024
21fa63e
Fixed Errors
Jul 8, 2024
0ab48ff
Update integrations/chroma/tests/test_document_store.py
Amnah199 Jul 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions integrations/chroma/src/haystack_integrations/document_stores/chroma/document_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -428,8 +428,9 @@ def _query_result_to_documents(result: QueryResult) -> List[List[Document]]:
}

# prepare metadata
if metadatas := result.get("metadatas"):
document_dict["meta"] = dict(metadatas[i][j])
metadatas = result.get("metadatas")
if metadatas and metadatas[i][j] is not None:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can it ever happen that metadatas size is shorter than i? And metadatas[i] is shorter than j? 🤔

Cause if it can happen this could fail.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added an exception here as discussed.

document_dict["meta"] = metadatas[i][j]

if embeddings := result.get("embeddings"):
document_dict["embedding"] = np.array(embeddings[i][j])
Expand Down
9 changes: 9 additions & 0 deletions integrations/chroma/tests/test_document_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,15 @@ def test_delete_not_empty_nonexisting(self, document_store: ChromaDocumentStore)

assert document_store.filter_documents(filters={"id": doc.id}) == [doc]

def test_document_store_search_without_metadata(self):
document_store = ChromaDocumentStore()
document_store.write_documents([Document(content=e) for e in ["First document", "Second document"]])
result = document_store.search(["First document"], top_k=1)

# Assertions to verify correctness
assert len(result) == 1
assert result[0][0].content == "First document"

@pytest.mark.integration
def test_to_json(self, request):
ds = ChromaDocumentStore(
Expand Down
Loading