Open JacobGoldenArt opened 1 year ago
Hi Jacob,
Thanks for the feedback and great idea - I think this would be helpful for others as well, certainly. There's also a number of ways to implement chat history via tools like LangChain and others - I'll discuss this with the team :+1:
@JacobGoldenArt as @zackproser suggests Langchain has a pretty good toolkit to do this and it can also be done in a more 'raw' fashion too.
If we retrieve the vector id for each upsert of our chat and insert a new chat record with that id in something like mongoDB atlas (or any db really), then we can use the returning matching topN rows from the db to further reinforce RAG precision and provide chat history.
An alternative is to use combined memory classes with Langchain: https://js.langchain.com/docs/modules/memory/how_to/multiple_memory
The only setbacks are response times and cost for each call to the openAI, which can be bigger if you include a large historical data set from your db.
Is this your first time submitting a feature request?
Describe the feature
Thanks for the really nice tutorial. I was just wondering how we might add a chat history feature. I'm not sure if this would be stored in Pinecone or maybe a vercel database?
Describe alternatives you've considered
No response
Who will this benefit?
No response
Are you interested in contributing this feature?
No response
Anything else?
No response