semantic_router.encoders.bedrock.BedrockEncoder#

class semantic_router.encoders.bedrock.BedrockEncoder(name: str = 'amazon.titan-embed-image-v1', input_type: str | None = 'search_query', score_threshold: float = 0.3, access_key_id: str | None = None, secret_access_key: str | None = None, session_token: str | None = None, region: str | None = None)#

Bases: BaseEncoder

__init__(name: str = 'amazon.titan-embed-image-v1', input_type: str | None = 'search_query', score_threshold: float = 0.3, access_key_id: str | None = None, secret_access_key: str | None = None, session_token: str | None = None, region: str | None = None)#

Initializes the BedrockEncoder.

Args:
name: The name of the pre-trained model to use for embedding.

If not provided, the default model specified in EncoderDefault will be used.

score_threshold: The threshold for similarity scores. access_key_id: The AWS access key id for an IAM principle.

If not provided, it will be retrieved from the access_key_id environment variable.

secret_access_key: The secret access key for an IAM principle.

If not provided, it will be retrieved from the AWS_SECRET_KEY environment variable.

session_token: The session token for an IAM principle.

If not provided, it will be retrieved from the AWS_SESSION_TOKEN environment variable.

region: The location of the Bedrock resources.

If not provided, it will be retrieved from the AWS_REGION environment variable, defaulting to “us-west-1”

Raises:

ValueError: If the Bedrock Platform client fails to initialize.

Methods

__init__([name, input_type, ...])

Initializes the BedrockEncoder.

acall(docs)

chunk_strings(strings[, MAX_WORDS])

Breaks up a list of strings into smaller chunks.

construct([_fields_set])

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

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

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

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

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

from_orm(obj)

get_env_variable(var_name, provided_value[, ...])

Retrieves environment variable or uses a provided value.

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

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

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

parse_obj(obj)

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

schema([by_alias, ref_template])

schema_json(*[, by_alias, ref_template])

set_score_threshold(v)

update_forward_refs(**localns)

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

validate(value)

Attributes

client

type

input_type

name

access_key_id

secret_access_key

session_token

region

score_threshold

chunk_strings(strings, MAX_WORDS=20)#

Breaks up a list of strings into smaller chunks.

Args:

strings (list): A list of strings to be chunked. max_chunk_size (int): The maximum size of each chunk. Default is 20.

Returns:

list: A list of lists, where each inner list contains a chunk of strings.

classmethod construct(_fields_set: SetStr | None = None, **values: Any) → Model#

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

copy(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, update: DictStrAny | None = None, deep: bool = False) → Model#

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

Parameters:

  • include – fields to include in new model

  • exclude – fields to exclude from new model, as with values this takes precedence over include

  • update – 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 – set to True to make a deep copy of the model

Returns:

new model instance

dict(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny#

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

static get_env_variable(var_name, provided_value, default=None)#

Retrieves environment variable or uses a provided value.

Args:

var_name (str): The name of the environment variable. provided_value (Optional[str]): The provided value to use if not None. default (Optional[str]): The default value if the environment variable is not set.

Returns:

str: The value of the environment variable or the provided/default value. None: Where AWS_SESSION_TOKEN is not set or provided

Raises:

ValueError: If no value is provided and the environment variable is not set.

json(*, include: AbstractSetIntStr | MappingIntStrAny | None = None, exclude: AbstractSetIntStr | MappingIntStrAny | None = None, by_alias: bool = False, skip_defaults: bool | None = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Callable[[Any], Any] | None = None, models_as_dict: bool = True, **dumps_kwargs: Any) → str#

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().

classmethod update_forward_refs(**localns: Any) → None#

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