Types

Type definitions for the pipeline.

Author

Kadek Denaya (kadek.d.r.diana@gdplabs.id)

References

NONE

PipelineInvocation

Bases: BaseModel

A model representing the invocation parameters for a pipeline.

This model is used to validate the structure of data returned by pre_invoke_transform functions. It ensures the data has the correct format for pipeline invocation.

Examples:

invocation = PipelineInvocation(
    input={"user_query": "What is AI?"},
    config={"session_id": "abc123"}
)

# With no config
invocation = PipelineInvocation(input={"query": "test"})

Attributes:

Name	Type	Description
input	dict[str, Any]	The input data to pass to the pipeline. This is a required field and must be a dictionary.
config	dict[str, Any] | None	Optional configuration for the pipeline execution. Must be a dictionary if provided.

Val(value) dataclass

A value wrapper that represents a fixed/literal input.

Attributes:

Name	Type	Description
value	object	The literal value of the input.