Skip to main content
Open In ColabOpen on GitHub

SingleStoreSemanticCache

This example demonstrates how to get started with the SingleStore semantic cache.

Integration Overview​

SingleStoreSemanticCache leverages SingleStoreVectorStore to cache LLM responses directly in a SingleStore database, enabling efficient semantic retrieval and reuse of results.

Integration details​

ClassPackageJS support
SingleStoreSemanticCachelangchain_singlestore❌

Installation​

This cache lives in the langchain-singlestore package:

%pip install -qU langchain-singlestore

Usage​

from langchain_core.globals import set_llm_cache
from langchain_singlestore import SingleStoreSemanticCache

set_llm_cache(
    SingleStoreSemanticCache(
        embedding=YourEmbeddings(),
        host="root:pass@localhost:3306/db",
    )
)
API Reference:set_llm_cache
%%time
# The first time, it is not yet in cache, so it should take longer
llm.invoke("Tell me a joke")
%%time
# The second time, while not a direct hit, the question is semantically similar to the original question,
# so it uses the cached result!
llm.invoke("Tell me one joke")

Was this page helpful?