Skip to main content

model

superduper.ext.jina.model

Source code

JinaEmbedding​

JinaEmbedding(self,
identifier: str,
db: dataclasses.InitVar[typing.Optional[ForwardRef('Datalayer')]] = None,
uuid: str = None,
*,
artifacts: 'dc.InitVar[t.Optional[t.Dict]]' = None,
signature: str = 'singleton',
datatype: 'EncoderArg' = None,
output_schema: 't.Optional[Schema]' = None,
flatten: 'bool' = False,
model_update_kwargs: 't.Dict' = None,
predict_kwargs: 't.Dict' = None,
compute_kwargs: 't.Dict' = None,
validation: 't.Optional[Validation]' = None,
metric_values: 't.Dict' = None,
model: 't.Optional[str]' = None,
max_batch_size: 'int' = 8,
api_key: Optional[str] = None,
batch_size: int = 100,
shape: Optional[Sequence[int]] = None) -> None
ParameterDescription
identifierIdentifier of the leaf.
dbDatalayer instance.
uuidUUID of the leaf.
artifactsA dictionary of artifacts paths and DataType objects
signatureModel signature.
datatypeDataType instance.
output_schemaOutput schema (mapping of encoders).
flattenFlatten the model outputs.
model_update_kwargsThe kwargs to use for model update.
predict_kwargsAdditional arguments to use at prediction time.
compute_kwargsKwargs used for compute backend job submit. Example (Ray backend): compute_kwargs = dict(resources=...).
validationThe validation Dataset instances to use.
metric_valuesThe metrics to evaluate on.
modelThe Model to use, e.g. 'text-embedding-ada-002'
max_batch_sizeMaximum batch size.
api_keyThe API key to use for the predicto
batch_sizeThe batch size to use for the predictor.
shapeThe shape of the embedding as tuple. If not provided, it will be obtained by sending a simple query to the API

Jina embedding predictor.

Jina​

Jina(self,
identifier: str,
db: dataclasses.InitVar[typing.Optional[ForwardRef('Datalayer')]] = None,
uuid: str = None,
*,
artifacts: 'dc.InitVar[t.Optional[t.Dict]]' = None,
signature: 'Signature' = '*args,
**kwargs',
datatype: 'EncoderArg' = None,
output_schema: 't.Optional[Schema]' = None,
flatten: 'bool' = False,
model_update_kwargs: 't.Dict' = None,
predict_kwargs: 't.Dict' = None,
compute_kwargs: 't.Dict' = None,
validation: 't.Optional[Validation]' = None,
metric_values: 't.Dict' = None,
model: 't.Optional[str]' = None,
max_batch_size: 'int' = 8,
api_key: Optional[str] = None) -> None
ParameterDescription
identifierIdentifier of the leaf.
dbDatalayer instance.
uuidUUID of the leaf.
artifactsA dictionary of artifacts paths and DataType objects
signatureModel signature.
datatypeDataType instance.
output_schemaOutput schema (mapping of encoders).
flattenFlatten the model outputs.
model_update_kwargsThe kwargs to use for model update.
predict_kwargsAdditional arguments to use at prediction time.
compute_kwargsKwargs used for compute backend job submit. Example (Ray backend): compute_kwargs = dict(resources=...).
validationThe validation Dataset instances to use.
metric_valuesThe metrics to evaluate on.
modelThe Model to use, e.g. 'text-embedding-ada-002'
max_batch_sizeMaximum batch size.
api_keyThe API key to use for the predicto

Cohere predictor.