Skip to content

/AWS1/CL_BDZORCHESTRATIONCONF

Settings for how the model processes the prompt prior to retrieval and generation.

CONSTRUCTOR

IMPORTING

Optional arguments:

io_prompttemplate TYPE REF TO /AWS1/CL_BDZPROMPTTEMPLATE /AWS1/CL_BDZPROMPTTEMPLATE

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.

io_inferenceconfig TYPE REF TO /AWS1/CL_BDZINFERENCECONFIG /AWS1/CL_BDZINFERENCECONFIG

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

it_addlmodelrequestfields TYPE /AWS1/CL_RT_DOCUMENT=>TT_MAP TT_MAP

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.

io_querytransformationconf TYPE REF TO /AWS1/CL_BDZQUERYTRANSFMTION00 /AWS1/CL_BDZQUERYTRANSFMTION00

To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.

io_performanceconfig TYPE REF TO /AWS1/CL_BDZPERFORMANCECONF /AWS1/CL_BDZPERFORMANCECONF

The latency configuration for the model.

Queryable Attributes

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.

Accessible with the following methods

Method Description
GET_PROMPTTEMPLATE() Getter for PROMPTTEMPLATE

inferenceConfig

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

Accessible with the following methods

Method Description
GET_INFERENCECONFIG() Getter for INFERENCECONFIG

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.

Accessible with the following methods

Method Description
GET_ADDLMODELREQUESTFIELDS() Getter for ADDITIONALMODELREQUESTFIELDS, with configurable d
ASK_ADDLMODELREQUESTFIELDS() Getter for ADDITIONALMODELREQUESTFIELDS w/ exceptions if fie
HAS_ADDLMODELREQUESTFIELDS() Determine if ADDITIONALMODELREQUESTFIELDS has a value

queryTransformationConfiguration

To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.

Accessible with the following methods

Method Description
GET_QUERYTRANSFORMATIONCONF() Getter for QUERYTRANSFORMATIONCONF

performanceConfig

The latency configuration for the model.

Accessible with the following methods

Method Description
GET_PERFORMANCECONFIG() Getter for PERFORMANCECONFIG