semantic_router.index.qdrant.QdrantIndex#

class semantic_router.index.qdrant.QdrantIndex(*, index: Any | None = None, routes: ndarray | None = None, utterances: ndarray | None = None, dimensions: int | None = None, type: str = 'base', init_async_index: bool = False, sync: str | None = None, index_name: str = 'semantic-router-index', location: str | None = ':memory:', url: str | None = None, port: int | None = 6333, grpc_port: int = 6334, prefer_grpc: bool = None, https: bool | None = None, api_key: str | None = None, prefix: str | None = None, timeout: int | None = None, host: str | None = None, path: str | None = None, grpc_options: Dict[str, Any] | None = None, metric: Metric = Metric.COSINE, config: Dict[str, Any] | None = {}, client: Any = None, aclient: Any = None)#

Bases: BaseIndex

The name of the collection to use

__init__(**kwargs)#

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

Methods

__init__(**kwargs)

Create a new model by parsing and validating input data from keyword arguments.

add(embeddings, routes, utterances[, batch_size])

Add embeddings to the index.

aquery(vector[, top_k, route_filter])

Search the index for the query_vector and return top_k results.

construct([_fields_set])

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.

convert_metric(metric)

copy(*[, include, exclude, update, deep])

Duplicate a model, optionally choose which fields to include, exclude and change.

delete(route_name)

Deletes route by route name.

delete_index()

Deletes or resets the index.

describe()

Returns a dictionary with index details such as type, dimensions, and total vector count.

dict(*[, include, exclude, by_alias, ...])

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

from_orm(obj)

rtype:

Model

get_routes()

Gets a list of route and utterance objects currently stored in the index.

json(*[, include, exclude, by_alias, ...])

Generate a JSON representation of the model, include and exclude arguments as per dict().

parse_file(path, *[, content_type, ...])

rtype:

Model

parse_obj(obj)

rtype:

Model

parse_raw(b, *[, content_type, encoding, ...])

rtype:

Model

query(vector[, top_k, route_filter])

Search the index for the query_vector and return top_k results.

schema([by_alias, ref_template])

rtype:

DictStrAny

schema_json(*[, by_alias, ref_template])

rtype:

str

update_forward_refs(**localns)

Try to update ForwardRefs on fields based on this Model, globalns and localns.

validate(value)

rtype:

Model

Attributes

index_name

location

url

port

grpc_port

prefer_grpc

https

api_key

prefix

timeout

host

path

grpc_options

dimensions

metric

config

client

aclient

index

routes

utterances

type

init_async_index

sync

add(embeddings, routes, utterances, batch_size=100)#

Add embeddings to the index. This method should be implemented by subclasses.

async aquery(vector, top_k=5, route_filter=None)#

Search the index for the query_vector and return top_k results. This method should be implemented by subclasses.

Return type:

Tuple[ndarray, List[str]]

classmethod construct(_fields_set=None, **values)#

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values

Return type:

Model

copy(*, include=None, exclude=None, update=None, deep=False)#

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters:

  • include (Union[AbstractSetIntStr, MappingIntStrAny, None]) – fields to include in new model

  • exclude (Union[AbstractSetIntStr, MappingIntStrAny, None]) – fields to exclude from new model, as with values this takes precedence over include

  • update (Optional[DictStrAny]) – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

  • deep (bool) – set to True to make a deep copy of the model

Return type:

Model

Returns:

new model instance

delete(route_name)#

Deletes route by route name. This method should be implemented by subclasses.

delete_index()#

Deletes or resets the index. This method should be implemented by subclasses.

describe()#

Returns a dictionary with index details such as type, dimensions, and total vector count. This method should be implemented by subclasses.

Return type:

Dict

dict(*, include=None, exclude=None, by_alias=False, skip_defaults=None, exclude_unset=False, exclude_defaults=False, exclude_none=False)#

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Return type:

DictStrAny

get_routes()#

Gets a list of route and utterance objects currently stored in the index.

Return type:

List[Tuple]

Returns:

List[Tuple]: A list of (route_name, utterance) objects.

json(*, include=None, exclude=None, by_alias=False, skip_defaults=None, exclude_unset=False, exclude_defaults=False, exclude_none=False, encoder=None, models_as_dict=True, **dumps_kwargs)#

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

Return type:

str

query(vector, top_k=5, route_filter=None)#

Search the index for the query_vector and return top_k results. This method should be implemented by subclasses.

Return type:

Tuple[ndarray, List[str]]

classmethod update_forward_refs(**localns)#

Try to update ForwardRefs on fields based on this Model, globalns and localns.

Return type:

None