I’ve got a database of a few hundred email newsletters I’ve sent over the years, including open rates, unsubscribes, etc. I want to query stuff like “what are the common themes between emails with the highest open rates?” I can’t do that with the sql index alone or simple vector index. That’s where I’m stuck. I’ve tried using sql and vector as tools in langchain but the agent can’t figure it out. I think I need metadata in my simple vector but can’t that out. Can anyone point me in the right direction? Or have a similar use case?
It’s good for returning data but not for doing anything creative like I can with the vector store. Was hoping for the best of both worlds. Hyrbid vector store + sql
