cache GPT calls - Githubissues

BaranziniLab / KG_RAG

Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks

Apache License 2.0

687 stars 93 forks source link

cache GPT calls #4

Closed namin closed 11 months ago

namin commented 11 months ago

This caches all GPT calls. We may want to do that specifically for entity extraction only. We may also want to not have a cache all exception when fetching from the API.