OrchestrationConfiguration¶
Structure Class¶
dataclass
¶
Settings for how the model processes the prompt prior to retrieval and generation.
Attributes¶
class-attribute
instance-attribute
¶
additional_model_request_fields: dict[str, Document] | None = None
Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.
class-attribute
instance-attribute
¶
inference_config: InferenceConfig | None = None
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
class-attribute
instance-attribute
¶
performance_config: PerformanceConfiguration | None = None
The latency configuration for the model.
class-attribute
instance-attribute
¶
prompt_template: PromptTemplate | None = None
Contains the template for the prompt that's sent to the model.
Orchestration prompts must include the $conversation_history$ and
$output_format_instructions$ variables. For more information, see Use
placeholder
variables
in the user guide.
class-attribute
instance-attribute
¶
query_transformation_configuration: QueryTransformationConfiguration | None = None
To split up the prompt and retrieve multiple sources, set the
transformation type to QUERY_DECOMPOSITION.