langchain_community.cache.RedisCache

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

Cache that uses Redis as a backend. Allows to use a sync redis.Redis client.

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 (redis.Redis), allowing the object to interact with a Redis server for caching purposes.

Parameters

• redis (Any) – An instance of a Redis client class (redis.Redis) to be 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.

• redis_ (Any) –

Methods

__init__(redis_, *[, ttl])	Initialize an instance of RedisCache.
aclear(**kwargs)	Clear cache that can take additional keyword arguments.
alookup(prompt, llm_string)	Look up based on prompt and llm_string.
aupdate(prompt, llm_string, return_val)	Update cache based on prompt and llm_string.
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)

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 (redis.Redis), allowing the object to interact with a Redis server for caching purposes.

Parameters

• redis (Any) – An instance of a Redis client class (redis.Redis) to be 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.

• redis_ (Any) –

async aclear(**kwargs: Any) → None

Clear cache that can take additional keyword arguments.

Parameters

kwargs (Any) –

Return type

None

async alookup(prompt: str, llm_string: str) → Optional[Sequence[Generation]]

Look up based on prompt and llm_string.

Parameters

• prompt (str) –

• llm_string (str) –

Return type

Optional[Sequence[Generation]]

async aupdate(prompt: str, llm_string: str, return_val: Sequence[Generation]) → None

Update cache based on prompt and llm_string.

Parameters

• prompt (str) –

• llm_string (str) –

• return_val (Sequence[Generation]) –

Return type

None

clear(**kwargs: Any) → None

Clear cache. If asynchronous is True, flush asynchronously.

Parameters

kwargs (Any) –

Return type

None

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

Look up based on prompt and llm_string.

Parameters

• prompt (str) –

• llm_string (str) –

Return type

Optional[Sequence[Generation]]

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

Update cache based on prompt and llm_string.

Parameters

• prompt (str) –

• llm_string (str) –

• return_val (Sequence[Generation]) –

Return type

None

Examples using RedisCache

• LLM Caching integrations

• Redis