ModelInvocationInput¶
Structure Class¶
ModelInvocationInput
dataclass
¶
The input for the pre-processing step.
-
The
typematches the agent step. -
The
textcontains the prompt. -
The
inferenceConfiguration,parserMode, andoverrideLambdavalues 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 = None
The identifier of a foundation model.
inference_configuration
class-attribute
instance-attribute
¶
inference_configuration: InferenceConfiguration | None = 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 = 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: CreationMode | None = 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: CreationMode | None = 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 = field(repr=False, default=None)
The text that prompted the agent at this step.
trace_id
class-attribute
instance-attribute
¶
trace_id: str | None = None
The unique identifier of the trace.
type
class-attribute
instance-attribute
¶
type: PromptType | None = None
The step in the agent sequence.