Skip to content

ModelInvocationInput

Structure Class

ModelInvocationInput dataclass

Bases: _SerdeShape

The input for the pre-processing step.

  • The type matches the agent step.

  • The text contains the prompt.

  • The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

Attributes

foundation_model class-attribute instance-attribute
foundation_model: str | None = ...

The identifier of a foundation model.

inference_configuration class-attribute instance-attribute
inference_configuration: InferenceConfiguration | None = ...

Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.

override_lambda class-attribute instance-attribute
override_lambda: str | None = ...

The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.

parser_mode class-attribute instance-attribute
parser_mode: str | None = ...

Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType.

prompt_creation_mode class-attribute instance-attribute
prompt_creation_mode: str | None = ...

Specifies whether the default prompt template was OVERRIDDEN. If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.

text class-attribute instance-attribute
text: str | None = ...

The text that prompted the agent at this step.

trace_id class-attribute instance-attribute
trace_id: str | None = ...

The unique identifier of the trace.

type class-attribute instance-attribute
type: str | None = ...

The step in the agent sequence.