langchain_community.cross_encoders.sagemaker_endpoint
.SagemakerEndpointCrossEncoderยถ
- class langchain_community.cross_encoders.sagemaker_endpoint.SagemakerEndpointCrossEncoder[source]ยถ
Bases:
BaseModel
,BaseCrossEncoder
SageMaker Inference CrossEncoder endpoint.
To use, you must supply the endpoint name from your deployed Sagemaker model & the region where it is deployed.
To authenticate, the AWS client uses the following methods to automatically load credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
If a specific credential profile should be used, you must pass the name of the profile from the ~/.aws/credentials file that is to be used.
Make sure the credentials / roles used have the required policies to access the Sagemaker endpoint. See: https://docs.aws.amazon.com/IAM/latest/UserGuide/access_policies.html
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.
- param content_handler: CrossEncoderContentHandler = <langchain_community.cross_encoders.sagemaker_endpoint.CrossEncoderContentHandler object>ยถ
- param credentials_profile_name: Optional[str] = Noneยถ
The name of the profile in the ~/.aws/credentials or ~/.aws/config files, which has either access keys or role information specified. If not specified, the default credential profile or, if on an EC2 instance, credentials from IMDS will be used. See: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
- param endpoint_kwargs: Optional[Dict] = Noneยถ
Optional attributes passed to the invoke_endpoint function. See `boto3`_. docs for more info. .. _boto3: <https://boto3.amazonaws.com/v1/documentation/api/latest/index.html>
- param endpoint_name: str = ''ยถ
The name of the endpoint from the deployed Sagemaker model. Must be unique within an AWS Region.
- param model_kwargs: Optional[Dict] = Noneยถ
Keyword arguments to pass to the model.
- param region_name: str = ''ยถ
The aws region where the Sagemaker model is deployed, eg. us-west-2.
- classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) Model ยถ
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 = โallowโ was set since it adds all passed values
- Parameters
_fields_set (Optional[SetStr]) โ
values (Any) โ
- Return type
Model
- copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) Model ยถ
Duplicate a model, optionally choose which fields to include, exclude and change.
- Parameters
include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ fields to include in new model
exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ fields to exclude from new model, as with values this takes precedence over include
update (Optional[DictStrAny]) โ 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) โ set to True to make a deep copy of the model
self (Model) โ
- Returns
new model instance
- Return type
Model
- dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) DictStrAny ยถ
Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
- Parameters
include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
by_alias (bool) โ
skip_defaults (Optional[bool]) โ
exclude_unset (bool) โ
exclude_defaults (bool) โ
exclude_none (bool) โ
- Return type
DictStrAny
- classmethod from_orm(obj: Any) Model ยถ
- Parameters
obj (Any) โ
- Return type
Model
- json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) unicode ยถ
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().
- Parameters
include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
by_alias (bool) โ
skip_defaults (Optional[bool]) โ
exclude_unset (bool) โ
exclude_defaults (bool) โ
exclude_none (bool) โ
encoder (Optional[Callable[[Any], Any]]) โ
models_as_dict (bool) โ
dumps_kwargs (Any) โ
- Return type
unicode
- classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model ยถ
- Parameters
path (Union[str, Path]) โ
content_type (unicode) โ
encoding (unicode) โ
proto (Protocol) โ
allow_pickle (bool) โ
- Return type
Model
- classmethod parse_obj(obj: Any) Model ยถ
- Parameters
obj (Any) โ
- Return type
Model
- classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model ยถ
- Parameters
b (Union[str, bytes]) โ
content_type (unicode) โ
encoding (unicode) โ
proto (Protocol) โ
allow_pickle (bool) โ
- Return type
Model
- classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') DictStrAny ยถ
- Parameters
by_alias (bool) โ
ref_template (unicode) โ
- Return type
DictStrAny
- classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) unicode ยถ
- Parameters
by_alias (bool) โ
ref_template (unicode) โ
dumps_kwargs (Any) โ
- Return type
unicode
- score(text_pairs: List[Tuple[str, str]]) List[float] [source]ยถ
Call out to SageMaker Inference CrossEncoder endpoint.
- Parameters
text_pairs (List[Tuple[str, str]]) โ
- Return type
List[float]
- classmethod update_forward_refs(**localns: Any) None ยถ
Try to update ForwardRefs on fields based on this Model, globalns and localns.
- Parameters
localns (Any) โ
- Return type
None
- classmethod validate(value: Any) Model ยถ
- Parameters
value (Any) โ
- Return type
Model