Ask a question to get started
Enter to sendā¢Shift+Enter new line
similarity_search_by_vector_with_relevance_scores( self, embedding: list[float], k: int = DEFAULT_K
embedding
List[float]
Embedding to look up documents similar to.
k
int
DEFAULT_K
Number of Documents to return.
filter
dict[str, str] | None
None
where_document
kwargs
Any
{}
Return docs most similar to embedding vector and similarity score.
Filter by metadata.
dict used to filter by the documents. E.g. {"$contains": "hello"}.
Additional keyword arguments to pass to Chroma collection query.
