boxcars VS langchain

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

Langchain and the implementation of Custom Tools also is a great (and very efficient) way to setup a dedicated Q&A (for example for chat purpose) agent.

We're using it via langchain talking to Amazon Bedrock which is hosting Claude 1.x. It's comparable to GPT3.x, not bad. The integration doesn't seem to be fully there though, I think langchain is expecting "Human:" and "AI:", but Claude uses "Assistant:".

https://github.com/hwchase17/langchain/issues/2638

Depending on how much work you want to put into it, you can get started at HuggingFace with their models and datasets, but you'd need compute power, multiple MLOps, etc. I was introduced to the concept in this video, since Google has their Vertex AI tools on Google Cloud, and there's always LangChain but I'm not sure about anything recent.

a documentation chatbot proof of concept using GPT3.5 and LangChain

I encourage everyone to pay attention to the Langchain open-source project and leverage it to achieve tasks that ChatGPT cannot handle.

Yeah I never know where memory goes exactly in langchain, it's not exactly clear all the time. But sure, the main insight I remember is this, take a look at their MULTI_PROMPT_ROUTER_TEMPLATE: https://github.com/hwchase17/langchain/blob/560c4dfc98287da1...

It's a lot of instructions for an LLM, they seem to forget an LLM is an auto-completion machine, and which data it is trained on. Using <<>> for sections is not a normal thing, it's not markdown, which probably the thing read way more often on the internet, instead of open json comments, why not type signatures, instead of so many rules, why not give it examples? It is an autocomplete machine!

They are relying too much on the LLM being smart because they probably only test stuff in GPT-4 and 3.5, but with GPT4All models this prompt was not working at all, so I had to rewrite it, for simple routing, we don't even need json, carying the `next_inputs` here is weird if you don't need it.

So this is my version of it: https://gist.github.com/rogeriochaves/b67676977eebb1936b9b5c...

It's so basic it's dumb, yet it is more powerful, as it does not rely on GPT-4 level intelligence, it's just what I needed