Live data from Hacker News

Run and create custom ChatGPT-like bots with OpenChat

github.com

61–63 of 63 posts

Re: Run and create custom ChatGPT-like bots with OpenChat

#61
post #28

Earlier quoted context omitted.

I'm curious about more sophisticated answers to this question, but the obvious approach would be to split the article or web page into sentences and do an embedding per sentence.

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.…

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.

Re: Run and create custom ChatGPT-like bots with OpenChat

#62
post #7

" Support offline open-source models (e.g., Alpaca, LLM drivers )" is already on the roadmap, which is great! There's just so much cool stuff we can try with LLMs now… What's the best discussion forum to exchange ideas, experiences and to collaborate on using and customizing (local) LLMs for (indy) gaming and other cool projects?

This was the goal with ConvoStack which allows people to implement our IAgent Express js interface with any custom Langchain agent. We saw this as an issue with other chatbot platforms which were limiting for developers. Comes with pre-built React components and Redis for caching as well to easily have production-ready chat interface. It's completely open-source too so can be self-hosted and modified to your liking.…

Looks interesting, thanks.

Re: Run and create custom ChatGPT-like bots with OpenChat

#63

Disclaimer: I am curating LLM-tools on github [1] A few thoughts: * allow for custom endpoint URLs, this way people can use open source LLMs with a fake openAI API backend like basaran[2] or llama-api-server[3] * look into better embedding methods for info-retrieval like InstructorEmbeddings or Document Summary Index * Don't use a single embedding per content item, use multiple to increase retrieval quality 1 https:/…

Using this as an opportunity to mention my own related project, perhaps it can end up on your nice list one day. :) https://github.com/lhenault/SimpleAI

added to the list :) thanks!
Post reply on HN