langchain.cache.RedisCache

class langchain.cache.RedisCache(redis_: Any, *, ttl: Optional[int] = None)[source]

Cache that uses Redis as a backend.

Initialize an instance of RedisCache.

This method initializes an object with Redis caching capabilities. It takes a redis_ parameter, which should be an instance of a Redis client class, allowing the object to interact with a Redis server for caching purposes.

Parameters
  • redis (Any) – An instance of a Redis client class (e.g., redis.Redis) used for caching. This allows the object to communicate with a Redis server for caching operations.

  • ttl (int, optional) – Time-to-live (TTL) for cached items in seconds. If provided, it sets the time duration for how long cached items will remain valid. If not provided, cached items will not have an automatic expiration.

Methods

__init__(redis_, *[, ttl])

Initialize an instance of RedisCache.

clear(**kwargs)

Clear cache.

lookup(prompt, llm_string)

Look up based on prompt and llm_string.

update(prompt, llm_string, return_val)

Update cache based on prompt and llm_string.

__init__(redis_: Any, *, ttl: Optional[int] = None)[source]

Initialize an instance of RedisCache.

This method initializes an object with Redis caching capabilities. It takes a redis_ parameter, which should be an instance of a Redis client class, allowing the object to interact with a Redis server for caching purposes.

Parameters
  • redis (Any) – An instance of a Redis client class (e.g., redis.Redis) used for caching. This allows the object to communicate with a Redis server for caching operations.

  • ttl (int, optional) – Time-to-live (TTL) for cached items in seconds. If provided, it sets the time duration for how long cached items will remain valid. If not provided, cached items will not have an automatic expiration.

clear(**kwargs: Any) None[source]

Clear cache. If asynchronous is True, flush asynchronously.

lookup(prompt: str, llm_string: str) Optional[Sequence[Generation]][source]

Look up based on prompt and llm_string.

update(prompt: str, llm_string: str, return_val: Sequence[Generation]) None[source]

Update cache based on prompt and llm_string.

Examples using RedisCache