Skip to main content

​
LocalIndex Objects

class LocalIndex(BaseIndex)

​
add

def add(embeddings: List[List[float]],
        routes: List[str],
        utterances: List[str],
        function_schemas: Optional[List[Dict[str, Any]]] = None,
        metadata_list: List[Dict[str, Any]] = [],
        **kwargs)
Add embeddings to the index. 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.
  • function_schemas (Optional[List[Dict[str, Any]]]): List of function schemas to add to the index.
  • metadata_list (List[Dict[str, Any]]): List of metadata to add to the index.

​
get_utterances

def get_utterances(include_metadata: bool = False) -> List[Utterance]
Gets a list of route and utterance objects currently stored in the index. Arguments:
  • include_metadata: Whether to include function schemas and metadata in the returned Utterance objects - LocalIndex now includes metadata if present.
Returns: List[Utterance]: A list of Utterance objects.

​
describe

def describe() -> IndexConfig
Describe the index. Returns: IndexConfig: An IndexConfig object.

​
is_ready

def is_ready() -> bool
Checks if the index is ready to be used. Returns: bool: True if the index is ready, False otherwise.

​
ais_ready

async def ais_ready() -> bool
Checks if the index is ready to be used asynchronously. Returns: bool: True if the index is ready, False otherwise.

​
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 vector to search for.
  • top_k (int): The number of results to return.
  • route_filter (Optional[List[str]]): The routes to filter the search by.
  • sparse_vector (dict[int, float] | SparseEmbedding | None): The sparse vector to search for.
Returns: Tuple[np.ndarray, List[str]]: A tuple containing the query vector and a list of route names.

​
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. Arguments:
  • vector (np.ndarray): The vector to search for.
  • top_k (int): The number of results to return.
  • route_filter (Optional[List[str]]): The routes to filter the search by.
  • sparse_vector (dict[int, float] | SparseEmbedding | None): The sparse vector to search for.
Returns: Tuple[np.ndarray, List[str]]: A tuple containing the query vector and a list of route names.

​
aget_routes

def aget_routes()
Get all routes from the index. Returns: List[str]: A list of routes.

​
delete

def delete(route_name: str)
Delete all records of a specific route from the index. Arguments:
  • route_name (str): The name of the route to delete.

​
adelete

async def adelete(route_name: str)
Delete all records of a specific route from the index. Note that this just points to the sync delete method as async makes no difference for the local computations of the LocalIndex. Arguments:
  • route_name (str): The name of the route to delete.

​
delete_index

def delete_index()
Deletes the index, effectively clearing it and setting it to None. Returns: None: None

​
adelete_index

async def adelete_index()
Deletes the index, effectively clearing it and setting it to None. Note that this just points to the sync delete_index method as async makes no difference for the local computations of the LocalIndex. Returns: None: None