length_based.py — langchain Source File

Source Code

"""Select examples based on length."""

import re
from collections.abc import Callable

from pydantic import BaseModel, Field, model_validator
from typing_extensions import Self

from langchain_core.example_selectors.base import BaseExampleSelector
from langchain_core.prompts.prompt import PromptTemplate


def _get_length_based(text: str) -> int:
    return len(re.split(r"\n| ", text))


class LengthBasedExampleSelector(BaseExampleSelector, BaseModel):
    r"""Select examples based on length.

    Example:
        ```python
        from langchain_core.example_selectors import LengthBasedExampleSelector
        from langchain_core.prompts import PromptTemplate

        # Define examples
        examples = [
            {"input": "happy", "output": "sad"},
            {"input": "tall", "output": "short"},
            {"input": "fast", "output": "slow"},
        ]

        # Create prompt template
        example_prompt = PromptTemplate(
            input_variables=["input", "output"],
            template="Input: {input}\nOutput: {output}",
        )

        # Create selector with max length constraint
        selector = LengthBasedExampleSelector(
            examples=examples,
            example_prompt=example_prompt,
            max_length=50,  # Maximum prompt length
        )

        # Select examples for a new input
        selected = selector.select_examples({"input": "large", "output": "tiny"})
        # Returns examples that fit within max_length constraint
        ```
    """

    examples: list[dict]
    """A list of the examples that the prompt template expects."""

    example_prompt: PromptTemplate
    """Prompt template used to format the examples."""

    get_text_length: Callable[[str], int] = _get_length_based
    """Function to measure prompt length. Defaults to word count."""

    max_length: int = 2048
// ... (69 more lines)