How is the LLM scene with Elixir/Phoenix?

[calebjosue]

What sort of libraries are available to integrate LLMs into your Phoenix Web Framework applications? e.g. Mistral, since these guys have available these endpoints, I was thinking to just consume those within the app. But I rather post my question, I know one or two things of LangChain, but there is only support for Python and JavaScript.

Thanks!

[egze]

Is this something what you are looking for? https://www.youtube.com/watch?v=PSrzruaby1M

[jam]

There seem to be a number of libraries. I haven’t explored them in depth but here’s a sampling:

ReqLLM - Composable LLM client built on Req

Hey everyone! I’m excited to share ReqLLM - a new approach to LLM interactions in Elixir that I’ve been working on. After building agent systems with various LLM clients, I kept running into the same frustrations: they either lacked Elixir’s composability principles or didn’t integrate well with existing HTTP pipelines. Why Another LLM Client? While building out Jido features, I needed a lower-level API for making LLM requests. ReqLLM is built on Req, with each Provider built as a Req plugin t…

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

LangChain is short for Language Chain. An LLM, or Large Language Model, is the “Language” part. This library makes it easier for Elixir applications to “chain” or connect different processes, integrations, libraries, services, or functionality together with an LLM. LangChain is a framework for developing applications powered by language models. It enables applications that are: Data-aware: connect a language model to other sources of data Agentic: allow a language model to interact with its …

Responses - LLM library supporting OpenAI's and xAI's Responses API

Responses is a new client library that supports Responses API by OpenAI and xAI. It’s a successor to my previous library openai_responses, which only supported OpenAI - hence the name change. What is Responses API? Conveniently, OpenAI just published a blog titled “Why we built Responses API”. In short, it’s a modern (launched this spring), stateful, multimodal, efficient API, an upgrade to Chat Completions, a de-facto industry standard, that was designed by OpenAI in just a weekend back in 202…

Depends on your needs. Some advocate for just using Req and a GenServer.

[olivermt]

100% reqllm best option imo.

Simply because it is dead simple to alter yourself.

[mikehostetler]

Each of these libraries tackles the problem in slightly different ways.

I’m the author of ReqLLM, so I’m a bit biased - but I built it because the more advanced use cases I started building with LLMs, I needed lower-level control.

That said, Langchain is focused on higher level use cases such as chaining - which ReqLLM will not be implementing.

[mindreader]

I started rolling my own. But reqllm is exactly what I I was shooting for but way better in every way, so I guess I’ll just start using that instead.