API V.S DataBase View/Procedure

[i-technology]

From what I understand, anytime you want to index custom data (word, pdf, web pages, etc) you’d use the embeddings tools and store the results locally, and when you want gtp to explain or summarize something, you’d use the api

How to feed data for completions, instead of using prompt/answer fine-tuning format?

Finally some insight, thanks Basically, if i understand, we currently need a database on our side Generate embeddings from pdfs, and whatnot, and save to a local database Generate embedding from question, and do a query against local database, and return original content Use original content as input to pre-feed prompt & add original question get result, and pay mucho tokens ^^ I hope OpenAI integrates something like this on their server backend. We need a way to simply add our content …