Run and create custom ChatGPT-like bots with OpenChat

Re:Run and create custom ChatGPT-like bots with OpenChat by mrtranscendence on Wednesday June 07, 2023 @10:06AM (#36226944)

When I was playing around with search via embeddings (as a test I was using Vampire the Masquerade V5 sourcebooks, and asking rules questions), I got the best results -- in terms of correct answers -- by using sentence embeddings. I'd search the query against the sentence embeddings, and then retrieve more context surrounding the winning sentence(s). That context would be passed to the LLM.

It wasn't perfect, though. I'm tempted to try the avenue of having an LLM generate questions for each passage and then use those embeddings, but it sounds a bit expensive to set up given the length of the books.

[ Parent | on HN ]

Re:Run and create custom ChatGPT-like bots with OpenChat by lgas on Friday June 09, 2023 @09:04PM (#36266498)

Sentence embeddings + retrieving context makes sense.

By any chance, have you done any work with indexing code using embeddings? I'd like to do something similar there, but there's no obvious notion of "sentence", especially across languages.

Probably the closest analogue is just lines of code, but breaking lines on newlines might break an expression in the middle removing meaning from both halves.

I was planning on trying indexing overlapping groups of lines but haven't had time yet.

[ Parent | on HN ]