semantic_router.layer.LayerConfig#

class semantic_router.layer.LayerConfig(routes: List[Route] = [], encoder_type: str = 'openai', encoder_name: str | None = None)#

Bases: object

Generates a LayerConfig object that can be used for initializing a RouteLayer.

__init__(routes: List[Route] = [], encoder_type: str = 'openai', encoder_name: str | None = None)#

Methods

__init__([routes, encoder_type, encoder_name])

add(route)

from_file(path)

from_index(index[, encoder_type, encoder_name])

Initialize a LayerConfig from a BaseIndex object.

from_tuples(route_tuples[, encoder_type, ...])

Initialize a LayerConfig from a list of tuples of routes and utterances.

get(name)

get_hash()

remove(name)

to_dict()

to_file(path)

Save the routes to a file in JSON or YAML format

to_utterances()

Convert the routes to a list of Utterance objects.

Attributes

routes

classmethod from_index(index: BaseIndex, encoder_type: str = 'openai', encoder_name: str | None = None)#

Initialize a LayerConfig from a BaseIndex object.

Parameters:
  • index (BaseIndex) – The index to initialize the LayerConfig from.

  • encoder_type (str, optional) – The type of encoder to use, defaults to “openai”.

  • encoder_name (Optional[str], optional) – The name of the encoder to use, defaults to None.

classmethod from_tuples(route_tuples: List[Tuple[str, str, List[Dict[str, Any]] | None, Dict[str, Any]]], encoder_type: str = 'openai', encoder_name: str | None = None)#

Initialize a LayerConfig from a list of tuples of routes and utterances.

Parameters:
  • route_tuples (List[Tuple[str, str]]) – A list of tuples, each containing a route name and an associated utterance.

  • encoder_type (str, optional) – The type of encoder to use, defaults to “openai”.

  • encoder_name (Optional[str], optional) – The name of the encoder to use, defaults to None.

to_file(path: str)#

Save the routes to a file in JSON or YAML format

to_utterances() List[Utterance]#

Convert the routes to a list of Utterance objects.

Returns:

A list of Utterance objects.

Return type:

List[Utterance]