Output transformer

Defines a base class for output transformers used in Gen AI applications.

Authors

Henry Wicaksono (henry.wicaksono@gdplabs.id)

References

NONE

BaseOutputTransformer(event_emitter=None)

Bases: ABC

A base class for output transformers used in Gen AI applications.

The BaseOutputTransformer class defines the interface for transforming the output of language models. Subclasses must implement the following methods: 1. _transform_output_item: Transforms an output item of a language model. 2. _transform_event: Transforms a stream event of a language model before it is emitted.

Attributes:

Name	Type	Description
event_emitter	EventEmitter | None	The event emitter to use for streaming events.

Initializes a new instance of the BaseOutputTransformer class.

Parameters:

Name	Type	Description	Default
event_emitter	EventEmitter | None	The event emitter to use for streaming events. Defaults to None.	None

emit(event) async

Transforms a stream event and emits it using the event emitter.

This method transforms a stream event and emits it using the event emitter.

Parameters:

Name	Type	Description	Default
event	Event	The event to transform and emit.	required

Raises:

Type	Description
ValueError	If the event emitter is not set.

transform(output)

Transforms the output of a language model.

This method transforms each output item of the language model output sequentially.

Parameters:

Name	Type	Description	Default
output	LMOutput	The output of a language model.	required

Returns:

Name	Type	Description
LMOutput	LMOutput	The transformed output of a language model.