ruby-openai VS boxcars

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 :)

Added to the Ruby library here if any Rubyists interested! https://github.com/alexrudall/ruby-openai

currently in the same boat as you at my company, we've been looking at Boxcars and LangchainRB as our gems but they're pretty new to the scene so not sure about that. I love the idea of langchain for the extensibility of it though - we used the ruby-openai gem for a while but it didn't do what we needed. I'll come back in a week or two with with what we decide (python microservice with flask served api endpoints vs ruby all the way)

I started with Langchain, but I had a hell of time debugging and tweaking the framework to suit my needs. Next, I shifted to Boxcars, which has fewer abstractions. While Boxcars was easier to understand, I still struggled when things behaved differently than I’d expected. Finally, I said screw it…I’m not doing that much:

We ported the core of LangChain to Ruby, and while it is way more that 100 lines, I would give similar feedback as the author. Here is the repo if anyone is interested https://github.com/BoxcarsAI/boxcars