langchain_experimental.rl_chain.base.AutoSelectionScorer

class langchain_experimental.rl_chain.base.AutoSelectionScorer

Bases: SelectionScorer[Event], BaseModel

Auto selection scorer.

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

Raises ValidationError if the input data cannot be parsed to form a valid model.

param llm_chain: LLMChain [Required]

param prompt: Optional[BasePromptTemplate] = None

param scoring_criteria_template_str: Optional[str] = None

static get_default_prompt() → ChatPromptTemplate

Return type

ChatPromptTemplate

static get_default_system_prompt() → SystemMessagePromptTemplate

Return type

SystemMessagePromptTemplate

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

Parameters

• inputs (Dict[str, Any]) –

• llm_response (str) –

• event (Event) –

Return type

float