caches.py — langchain Source File

Source Code

"""Optional caching layer for language models.

Distinct from provider-based [prompt caching](https://docs.langchain.com/oss/python/langchain/models#prompt-caching).

!!! warning "Beta feature"

    This is a beta feature. Please be wary of deploying experimental code to production
    unless you've taken appropriate precautions.

A cache is useful for two reasons:

1. It can save you money by reducing the number of API calls you make to the LLM
    provider if you're often requesting the same completion multiple times.
2. It can speed up your application by reducing the number of API calls you make to the
    LLM provider.
"""

from __future__ import annotations

from abc import ABC, abstractmethod
from collections.abc import Sequence
from typing import Any

from typing_extensions import override

from langchain_core.outputs import Generation
from langchain_core.runnables import run_in_executor

RETURN_VAL_TYPE = Sequence[Generation]


class BaseCache(ABC):
    """Interface for a caching layer for LLMs and Chat models.

    The cache interface consists of the following methods:

    - lookup: Look up a value based on a prompt and `llm_string`.
    - update: Update the cache based on a prompt and `llm_string`.
    - clear: Clear the cache.

    In addition, the cache interface provides an async version of each method.

    The default implementation of the async methods is to run the synchronous
    method in an executor. It's recommended to override the async methods
    and provide async implementations to avoid unnecessary overhead.
    """

    @abstractmethod
    def lookup(self, prompt: str, llm_string: str) -> RETURN_VAL_TYPE | None:
        """Look up based on `prompt` and `llm_string`.

        A cache implementation is expected to generate a key from the 2-tuple
        of `prompt` and `llm_string` (e.g., by concatenating them with a delimiter).

        Args:
            prompt: A string representation of the prompt.

                In the case of a chat model, the prompt is a non-trivial
                serialization of the prompt into the language model.
            llm_string: A string representation of the LLM configuration.
// ... (213 more lines)