Langchain - An Elixir LangChain-like library for integrating with LLMs like ChatGPT

OMG

Published a DEMO project for using the Elixir LangChain library.

• writes the messages to a SQLite database
• can edit/delete messages
• can resubmit a conversation after making changes
• can cancel an in-process message
• message deltas are streamed in
• uses LiveView’s new Async Operations

Check it out!

https://github.com/brainlid/langchain_demo

This is interesting, given Ex is a functional language and LangChain is a pretty Java-y mess of a library I can only see improvements out of the gate.

I’ve spent a bunch of time working with LLM’s recently and have just been writing functions to encapsulate the various steps in my pipelines. What’s the main benefit of adopting langchain in a functional language?

I’ve actually been inspired by a Python library I saw recently that makes it easy to define your LLM calls as functions and have been thinking about how to write a macro in Ex that does this, with the end result being single functions you can call to interact with the LLM. (GitHub - jackmpcollins/magentic: Seamlessly integrate LLMs as Python functions · GitHub)

This is super awesome, thank you! I might be missing it, but is there a way to return the :usage tokens for the llm from the completions endpoint?

# from the OpenAI api
"usage": { "prompt_tokens": 5, "completion_tokens": 5, "total_tokens": 10 } }

OpenAI api token usage doc

Yes, the usage token could be returned but they aren’t currently. I want to add support for a couple other LLMs and see more examples of how others work and common among them.

I updated the DEMO project to include an Agent example. In this case, it’s an AI Personal Fitness Trainer! I created a YouTube video about it and wrote up an overview in a blog post.

• Created my Personal AI Fitness Trainer in 2 Days · The Phoenix Files - blog post
• GitHub - brainlid/langchain_demo: Demo web project using the Elixir LangChain library · GitHub - demo project

Turns out ChatGPT doesn’t know anything about the date or day of the week! When that’s needed for your application, how can we solve it? See how we can make our AI apps more useful when they are date aware!

Awesome work!

Agree that the langchain abstraction are sometimes easier and sometimes more trouble than they are worth.

Also agree that FP will clean up a lot.

But I think it’s going to fall into sprawling spaghetti without an abstracted structure, at least when I think about dozens of people using it and collaborating across projects.

I was wondering if you’d be willing to look at my buddy’s project which is intended to be a graph builder (and reconfiguration system) and serialization system. If can be run on multiple runtimes and the development could be ported as well. It’s not FP today, but not bad.

If you like it, would you consider the DAG abstraction layer as a means of interoperability?

Thanks for the great work @brainlid

Assuming models will likely have different APIs and features in the upcoming future, does it make sense to include the raw model responses (or only include the uncommon attributes)?

Like @f0rest8 I was in need of calculating usage tokens, and if we had the raw responses, I could easily do the mapping myself.

Looks like a great library, giving it a try.

@brainlid how do you set the OpenAI api_key when implementing within a LiveBook?

I have the the OpenAI api key set as an environment variable in my LiveBook, but can’t set it in the map when using ChatOpenAI.new!

I must be missing something simple. Thanks for the help in advance