zylon-ai / private-gpt

Interact with your documents using the power of GPT, 100% privately, no data leaks

Home Page:https://docs.privategpt.dev

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Has anyone had any success with creating a questions file feeding PrivateGPT?

avalonweblon opened this issue · comments

Discussed in #922

Originally posted by lsimcoates August 1, 2023
Hi, looking at whether it is feasible to supply private GPT with a text file which contains a list of queries, which it can then work its way through and answer all the questions, then producing an output document.
Currently I have a lot of source data and querying can be slow, so would like to just input a number of questions and let it just run till its done. Saves me having to go check on it a lot.

if your backend uses python language like fastapi, you can use their SDK and put the contents into a variable array then looping it or you can do the old way of fetching it with your api too.

As for the slow ingestion part, its because the default embedding model in ollama is nomic which is heavy on lower end device, might as well as downgrade yourself on using znbang/bge:small-en-v1.5-q8_0.

hope it helps pal