OrchestrationConfiguration
Settings for how the model processes the prompt prior to retrieval and generation.
Contents
- additionalModelRequestFields
-
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.
Type: String to JSON value map
Key Length Constraints: Minimum length of 1. Maximum length of 100.
Required: No
- inferenceConfig
-
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
Type: InferenceConfig object
Required: No
- promptTemplate
-
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.Type: PromptTemplate object
Required: No
- queryTransformationConfiguration
-
To split up the prompt and retrieve multiple sources, set the transformation type to
QUERY_DECOMPOSITION.Type: QueryTransformationConfiguration object
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
