set_llm_cache

langchain_core.globals.set_llm_cache(value: BaseCache | None) → None

Set a new LLM cache, overwriting the previous value, if any.

Parameters:

value (BaseCache | None) – The new LLM cache to use. If None, the LLM cache is disabled.

Return type:

None

Examples using set_llm_cache

• Astra DB

• Cassandra

• Couchbase

• DSPy

• How to cache LLM responses

• How to cache chat model responses

• Model caches

• Momento

• MongoDB Atlas

• Redis