AutoSelectionScorer#

class langchain_experimental.rl_chain.base.AutoSelectionScorer[source]#

Bases: SelectionScorer[Event], BaseModel

Auto selection scorer.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param llm_chain: LLMChain [Required]#
param prompt: BasePromptTemplate | None = None#
param scoring_criteria_template_str: str | None = None#
static get_default_prompt() → ChatPromptTemplate[source]#
Return type:

ChatPromptTemplate

static get_default_system_prompt() → SystemMessagePromptTemplate[source]#
Return type:

SystemMessagePromptTemplate

score_response(inputs: Dict[str, Any], llm_response: str, event: Event) → float[source]#
Parameters:

  • inputs (Dict[str, Any])

  • llm_response (str)

  • event (Event)

Return type:

float