semantic_router.index.hybrid_local

HybridLocalIndex Objects

class HybridLocalIndex(LocalIndex)

add

def add(embeddings: List[List[float]],
        routes: List[str],
        utterances: List[Any],
        metadata_list: Optional[List[Dict[str, Any]]] = None,
        sparse_embeddings: Optional[List[SparseEmbedding]] = None,
        **kwargs)

Upsert records into the index, one per (route, utterance) pair. A pair

that is already stored has its embeddings and metadata replaced.

Arguments:

• embeddings (List[List[float]]): List of embeddings to add to the index.
• routes (List[str]): List of routes to add to the index.
• utterances (List[str]): List of utterances to add to the index.
• metadata_list (Optional[List[Dict[str, Any]]]): List of metadata to add to the index.
• sparse_embeddings (Optional[List[SparseEmbedding]]): List of sparse embeddings to add to the index.

query

def query(
    vector: np.ndarray,
    top_k: int = 5,
    route_filter: Optional[List[str]] = None,
    sparse_vector: dict[int, float] | SparseEmbedding | None = None
) -> Tuple[np.ndarray, List[str]]

Search the index for the query and return top_k results.

Arguments:

• vector (np.ndarray): The query vector to search for.
• top_k (int, optional): The number of top results to return, defaults to 5.
• route_filter (Optional[List[str]], optional): A list of route names to filter the search results, defaults to None.
• sparse_vector (dict[int, float]): The sparse vector to search for, must be provided.

aquery

async def aquery(
    vector: np.ndarray,
    top_k: int = 5,
    route_filter: Optional[List[str]] = None,
    sparse_vector: dict[int, float] | SparseEmbedding | None = None
) -> Tuple[np.ndarray, List[str]]

Search the index for the query and return top_k results. This method calls the

sync query method as everything uses numpy computations which is CPU-bound and so no benefit can be gained from making this async.

Arguments:

• vector (np.ndarray): The query vector to search for.
• top_k (int, optional): The number of top results to return, defaults to 5.
• route_filter (Optional[List[str]], optional): A list of route names to filter the search results, defaults to None.
• sparse_vector (dict[int, float]): The sparse vector to search for, must be provided.

delete_index

def delete_index()

Deletes the index, effectively clearing it and setting it to None.

Returns:

None: None