codefuse-ai / ModelCache

A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.
Other
874 stars 43 forks source link

version update #9

Closed peng3307165 closed 12 months ago

peng3307165 commented 12 months ago

Adding SQLite database; incorporating a local demo Flask service. Refining the relational database management module and resolving the table name issue. Adapting the local database for faiss integration. Adjusting the exception handling mechanism Conducting functional testing of the service.