ruby-openai VS discourse-ai

What’s the relationship, if any, with https://github.com/alexrudall/ruby-openai ?

That gem is actively maintained and widely used. It’s a good gem! But by definition they’re always playing catch up.

If you are using Open AI's API, this tokenizer is more accurate than the one coming with `ruby-openai` gem.

ruby-openai

If you can just interact with OpenAI api directly without langchain then that eliminates need for python. Here’s a gem for interacting with the OpenAI api : https://github.com/alexrudall/ruby-openai

There is a gem developed by Alex - https://github.com/alexrudall/ruby-openai.

I've been playing with ruby-openai, a Ruby gem (ie, library) that interfaces with the OpenAI API. I'm building myself a small movie-recommendation tool, just a personal need, as well as to teach myself how this stuff works. It's unlikely I'll ever build it into a proper app, as I'm okay with interacting in the shell and with text files, versus a web-based thing. But if there's interest, I'll push my tool up to Github.

Can use https://github.com/alexrudall/ruby-openai to do this sort of thing also :)

That's super cool, thanks for sharing! I will share this as an easy to follow example of what we can with AI.

> Allowing a Q&A interface using these embeddings over the post contents could speed up research over the community posts (if you know the right questions to ask :P). Let's view some posts similar to this one complaining about function calling

That's indeed a great thing to surface, and that's exactly how the the OpenAI forum selects the "Related Topics" to show at the end of every topic. We use embeddings for this feature, and the entire thing is open-source: https://github.com/discourse/discourse-ai/blob/main/lib/embe...

We also embeddings for suggesting tags, categories, HyDE search and more. It's by far my favorite tech of this new AI/ML gen so far in terms of applicability.

> Using Twitter-roBERTa-base for sentiment analysis, we generated a post_sentiment label (negative, positive, neutral) and post_sentiment_score confidence score for each post.

We do the same, with even the same model, and conveniently show that information on the admin interface of the forum. Again all open source: https://github.com/discourse/discourse-ai/tree/main/lib/sent...

Disclaimer: I'm the tech lead on the AI parts of Discourse, the open source software that powers OpenAI's community forum.

Embedding cost and model choice makes this a very compelling choice. I'm working on leveraging embeddings in https://github.com/discourse/discourse-ai where it powers offering related topics, semantic search, tag and category recommendations among other things.

A cheap offering like this can make it a lot more reasonable for self-hosters.