Em invoker

Defines a base class for embedding model invokers used in Gen AI applications.

Authors

Henry Wicaksono (henry.wicaksono@gdplabs.id)

References

NONE

BaseEMInvoker(model_id, default_hyperparameters=None, supported_attachments=None, retry_config=None, truncation_config=None)

Bases: ABC

A base class for embedding model invokers used in Gen AI applications.

The BaseEMInvoker class provides a framework for invoking embedding models.

Attributes:

Name	Type	Description
model_id	str	The model ID of the embedding model.
model_provider	str	The provider of the embedding model.
model_name	str	The name of the embedding model.
default_hyperparameters	dict[str, Any]	Default hyperparameters for invoking the embedding model. Defaults to None, in which case an empty dictionary is used.
retry_config	RetryConfig	The retry configuration for the embedding model. Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.
truncation_config	TruncationConfig | None	The truncation configuration for the embedding model. Defaults to None, in which case no truncation is applied.

Initializes a new instance of the BaseEMInvoker class.

Parameters:

Name	Type	Description	Default
model_id	ModelId	The model ID of the embedding model.	required
default_hyperparameters	dict[str, Any] | None	Default hyperparameters for invoking the embedding model. Defaults to None, in which case an empty dictionary is used.	None
supported_attachments	set[str] | None	A set of supported attachment types. Defaults to None, in which case an empty set is used (indicating that no attachments are supported).	None
retry_config	RetryConfig | None	The retry configuration for the embedding model. Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.	None
truncation_config	TruncationConfig | None	Configuration for text truncation behavior. Defaults to None, in which case no truncation is applied.	None

model_id: str property

The model ID of the embedding model.

Returns:

Name	Type	Description
str	str	The model ID of the embedding model.

model_name: str property

The name of the embedding model.

Returns:

Name	Type	Description
str	str	The name of the embedding model.

model_provider: str property

The provider of the embedding model.

Returns:

Name	Type	Description
str	str	The provider of the embedding model.

invoke(content, hyperparameters=None) async

Invokes the embedding model with the provided content or list of contents.

This method invokes the embedding model with the provided content or list of contents. It includes retry logic with exponential backoff for transient failures.

Parameters:

Name	Type	Description	Default
content	EMContent | list[EMContent]	The input or list of inputs to be embedded using the embedding model.	required
hyperparameters	dict[str, Any] | None	A dictionary of hyperparameters for the embedding model. Defaults to None, in which case the default hyperparameters are used.	None

Returns:

Type	Description
Vector | list[Vector]	Vector | list[Vector]: The vector representations of the input contents: 1. If the input is an EMContent, the output is a Vector. 2. If the input is a list[EMContent], the output is a list[Vector].

Raises:

Type	Description
CancelledError	If the invocation is cancelled.
ModelNotFoundError	If the model is not found.
ProviderAuthError	If the model authentication fails.
ProviderInternalError	If the model internal error occurs.
ProviderInvalidArgsError	If the model parameters are invalid.
ProviderOverloadedError	If the model is overloaded.
ProviderRateLimitError	If the model rate limit is exceeded.
TimeoutError	If the invocation times out.
ValueError	If the input content is invalid.