marvin VS LocalAI

Hey HN! We just released Marvin 2.0.

Marvin is an AI toolkit for developers who want to use LLMs with traditional software. We still see significant challenges integrating LLMs because of how difficult it is to get them to reliably accept and return structured data. Marvin consists of independent, functional tools that address this problem in a variety of ways.

Marvin has always been focused on using LLMs to work with native Python datatypes and Pydantic models. In 2.0 we've expanded this significantly with dedicated APIs for the most common use cases we've seen over the last year: classification, entity extraction, transforming data to types, and generating synthetic data. Marvin 2.0 is also fully multi-modal and supports images as inputs for classification, extraction, and transformation tasks (as well as simple image and speech generation). We've also introduces a Pythonic interface to OpenAI's assistants API, which now powers all of Marvin's interactive components.

We've tried to make an LLM framework that "sparks joy" and captures that same feeling you had the first time you saw an LLM in action. Try it out and let us know what you think!

(Repo: https://github.com/PrefectHQ/marvin)

Seems a lot like https://github.com/PrefectHQ/marvin?

The prompting you do seems an awfully like:

https://www.askmarvin.ai/prompting/prompt_function/

You can try the decorator ai_fn in marvin https://github.com/PrefectHQ/marvin

Marvin: a batteries-included library for building AI-powered software. Marvin's job is to integrate AI directly into your codebase by making it look and feel like any other function (https://github.com/PrefectHQ/marvin)

Sure! I was inspired by this Python library: https://github.com/PrefectHQ/marvin

I see Langchain has support for Azure chat models, and Marvin is built on Langchain so it may not be so difficult! Tracking issue here: https://github.com/PrefectHQ/marvin/issues/189

We have a related issue open (https://github.com/PrefectHQ/marvin/issues/64) but haven't designed anything yet.

If you're running this as a server, I would recommend LocalAI https://github.com/mudler/LocalAI

LocalAI can do that: https://github.com/mudler/LocalAI

https://localai.io/features/openai-functions/

De inspirație, LocalAI, un replacement la OpenAI. E deja hot pe GitHub.

Your hardware should be fine for inferencing, as long as you don't bother trying to get the GPU working.

My $0.02 would be to try getting LocalAI running on your machine with OpenCL/CLBlas acceleration for your CPU. If you're running other things, you could limit the inferencing process to 2 or 3 threads. That should get it working; I've been able to inference even 13b models on cheap Rockchip SOCs. Your CPU should be fine, even if it's a little outdated.

LocalAI: https://github.com/mudler/LocalAI

Some decent models to start with:

TinyLlama (extremely small/fast): https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.3-GGU...

Dolphin Mistral (larger size, better responses: https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF

Neither of this really requires OpenAI. You can do it with locally-running models via something like https://github.com/mudler/LocalAI