BaseCache Class — langchain Architecture

Source Code

libs/core/langchain_core/caches.py lines 32–152

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.

                This is used to capture the invocation parameters of the LLM
                (e.g., model name, temperature, stop tokens, max tokens, etc.).

                These invocation parameters are serialized into a string representation.

        Returns:
            On a cache miss, return `None`. On a cache hit, return the cached value.
                The cached value is a list of `Generation` (or subclasses).
        """

    @abstractmethod
    def update(self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE) -> None:
        """Update cache based on `prompt` and `llm_string`.

        The `prompt` and `llm_string` are used to generate a key for the cache. The key
        should match that of the lookup method.

        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.

                This is used to capture the invocation parameters of the LLM
                (e.g., model name, temperature, stop tokens, max tokens, etc.).

                These invocation parameters are serialized into a string
                representation.
            return_val: The value to be cached.

                The value is a list of `Generation` (or subclasses).
        """

    @abstractmethod
    def clear(self, **kwargs: Any) -> None:
        """Clear cache that can take additional keyword arguments."""

    async def alookup(self, prompt: str, llm_string: str) -> RETURN_VAL_TYPE | None:
        """Async 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.