schema.py — langchain Source File

Source Code

"""Interfaces to be implemented by general evaluators."""

from __future__ import annotations

import logging
from abc import ABC, abstractmethod
from collections.abc import Sequence
from enum import Enum
from typing import Any
from warnings import warn

from langchain_core.agents import AgentAction
from langchain_core.language_models import BaseLanguageModel
from langchain_core.runnables.config import run_in_executor

from langchain_classic.chains.base import Chain

logger = logging.getLogger(__name__)


class EvaluatorType(str, Enum):
    """The types of the evaluators."""

    QA = "qa"
    """Question answering evaluator, which grades answers to questions
    directly using an LLM."""
    COT_QA = "cot_qa"
    """Chain of thought question answering evaluator, which grades
    answers to questions using
    chain of thought 'reasoning'."""
    CONTEXT_QA = "context_qa"
    """Question answering evaluator that incorporates 'context' in the response."""
    PAIRWISE_STRING = "pairwise_string"
    """The pairwise string evaluator, which predicts the preferred prediction from
    between two models."""
    SCORE_STRING = "score_string"
    """The scored string evaluator, which gives a score between 1 and 10
    to a prediction."""
    LABELED_PAIRWISE_STRING = "labeled_pairwise_string"
    """The labeled pairwise string evaluator, which predicts the preferred prediction
    from between two models based on a ground truth reference label."""
    LABELED_SCORE_STRING = "labeled_score_string"
    """The labeled scored string evaluator, which gives a score between 1 and 10
    to a prediction based on a ground truth reference label."""
    AGENT_TRAJECTORY = "trajectory"
    """The agent trajectory evaluator, which grades the agent's intermediate steps."""
    CRITERIA = "criteria"
    """The criteria evaluator, which evaluates a model based on a
    custom set of criteria without any reference labels."""
    LABELED_CRITERIA = "labeled_criteria"
    """The labeled criteria evaluator, which evaluates a model based on a
    custom set of criteria, with a reference label."""
    STRING_DISTANCE = "string_distance"
    """Compare predictions to a reference answer using string edit distances."""
    EXACT_MATCH = "exact_match"
    """Compare predictions to a reference answer using exact matching."""
    REGEX_MATCH = "regex_match"
    """Compare predictions to a reference answer using regular expressions."""
    PAIRWISE_STRING_DISTANCE = "pairwise_string_distance"
    """Compare predictions based on string edit distances."""
// ... (448 more lines)