​
HybridRouter Objects

class HybridRouter(BaseRouter)

A hybrid layer that uses both dense and sparse embeddings to classify routes.

​
__init__

def __init__(encoder: DenseEncoder,
             sparse_encoder: Optional[SparseEncoder] = None,
             llm: Optional[BaseLLM] = None,
             routes: Optional[List[Route]] = None,
             index: Optional[HybridLocalIndex] = None,
             top_k: int = 5,
             aggregation: str = "mean",
             auto_sync: Optional[str] = None,
             alpha: float = 0.3)

Initialize the HybridRouter.

Arguments:

  • encoder (DenseEncoder): The dense encoder to use.
  • sparse_encoder (Optional[SparseEncoder]): The sparse encoder to use.

​
add

def add(routes: List[Route] | Route)

Add a route to the local HybridRouter and index.

Arguments:

  • route (Route): The route to add.

​
__call__

def __call__(
    text: Optional[str] = None,
    vector: Optional[List[float] | np.ndarray] = None,
    simulate_static: bool = False,
    route_filter: Optional[List[str]] = None,
    sparse_vector: dict[int, float] | SparseEmbedding | None = None
) -> RouteChoice

Call the HybridRouter.

Arguments:

  • text (Optional[str]): The text to encode.
  • vector (Optional[List[float] | np.ndarray]): The vector to encode.
  • simulate_static (bool): Whether to simulate a static route.
  • route_filter (Optional[List[str]]): The route filter to use.
  • sparse_vector (dict[int, float] | SparseEmbedding | None): The sparse vector to use.

​
fit

def fit(X: List[str],
        y: List[str],
        batch_size: int = 500,
        max_iter: int = 500,
        local_execution: bool = False)

Fit the HybridRouter.

Arguments:

  • X (List[str]): The input data.
  • y (List[str]): The output data.
  • batch_size (int): The batch size to use for fitting.
  • max_iter (int): The maximum number of iterations to use for fitting.
  • local_execution (bool): Whether to execute the fitting locally.

​
evaluate

def evaluate(X: List[str], y: List[str], batch_size: int = 500) -> float

Evaluate the accuracy of the route selection.

Arguments:

  • X (List[str]): The input data.
  • y (List[str]): The output data.
  • batch_size (int): The batch size to use for evaluation.

Returns:

float: The accuracy of the route selection.

basesemantic