Returns documents with relevance scores in the range [0, 1], with optional score filtering. 
_similarity_search_with_relevance_scores(
    query: str,
    k: int,
    **kwargs
) -> List[Tuple[Document, float]]

​
Parameters

ParameterTypeDescription
querystrQuery text to search for
kintNumber of documents to return
**kwargsAnyAdditional arguments including filter and score_threshold

​
Keyword Arguments

ParameterTypeDescription
filterDict[str, Any](Optional) Metadata filters to apply
score_thresholdfloat(Optional) Minimum score threshold for results

​
Returns

List[Tuple[Document, float]]: List of (Document, score) tuples with scores in [0, 1]

​
Example Usage

# Search with relevance scores and threshold
results = store._similarity_search_with_relevance_scores(
    "machine learning",
    k=10,
    score_threshold=0.5
)

print(f"Found {len(results)} documents above threshold")
for doc, score in results:
    print(f"Relevance: {score:.2%} - {doc.page_content[:50]}...")