Using vector dbs to index large content for LLM interaction

This is an article I just found that reminded me of some things @brig_mecham was trying to accomplish.

1 Like

where is the article?

Ha! Question Answering as a Service with Cohere and Qdrant - Qdrant

This is right up my alley.

I was able to do the same thing locally with bioGPT and huggingface. But, the services outlined in the article make it much easier.

For anyone who is interested, here is a link to a similar example in the bioGPT github repo:

1 Like