nat.experimental.test_time_compute.selection.llm_based_plan_selector#

Attributes#

logger

Classes#

LLMBasedPlanSelector

Functions#

register_llm_based_plan_selection(config, builder)

Register the LLMBasedPlanSelector with the provided configuration.

Module Contents#

logger#

class LLMBasedPlanSelector( config: nat.data_models.ttc_strategy.TTCStrategyBaseConfig, )#

Bases: nat.experimental.test_time_compute.models.strategy_base.StrategyBase

llm_bound = None#

async build_components(builder: nat.builder.builder.Builder) → None#: Build the components required for the selector.

supported_pipeline_types() → [nat.experimental.test_time_compute.models.stage_enums.PipelineTypeEnum]#

stage_type() → nat.experimental.test_time_compute.models.stage_enums.StageTypeEnum#

async ainvoke(items: list[nat.experimental.test_time_compute.models.ttc_item.TTCItem], original_prompt: str | None = None, agent_context: str | None = None, \*\*kwargs) → [nat.experimental.test_time_compute.models.ttc_item.TTCItem]#

Select the planning items based on the selection strategy.

Args:: original_prompt (str): The prompt the user provided the agent. agent_context (str): The context of the agent, if applicable. items (list[TTCItem]): The list of planning items to select from.
Returns:: TTCItem: The selected planning item.

async register_llm_based_plan_selection( config: nat.experimental.test_time_compute.models.selection_config.LLMBasedPlanSelectionConfig, builder: nat.builder.builder.Builder, )#: Register the LLMBasedPlanSelector with the provided configuration.