hie-bios VS marvin

You're likely going to have to set up a hie-bios file in an hie.yaml file. More info here: https://github.com/haskell/hie-bios

Look here: hie-bios (its the library used by haskell-language-server to get to know your project better, iirc).

Yeah the same happened to me with previous versions of the Haskell IDE Engine that used Stack, so I ended up with several snapshots under \~/.stack that took a lot of space. Nowadays I just install HLS, Cabal and a single HLS-supported GHC with ghcup. It's a huge difference. I think there is a Windows-supported equivalent of ghcup, but I have not used it. If you also have Stack installed, remember that you can place a [`hie.yaml`](https://github.com/mpickering/hie-bios#explicit-configuration) file in your project root that can [force HLS to use cabal](https://github.com/mpickering/hie-bios#cabal) instead of stack in your project (this was needed last time I checked, complex configurations would need tuning this file a bit, though).

You can provide an alternative stack.yaml to HLS, with the specific configuration for the ide, although you have to write down an explicit hie.yaml file, take a look to https://github.com/mpickering/hie-bios#stack

Please consider testing dev builds with the WIP new vgs-bios feature, inspired by the amazing hie-bios. It reads your project hie.yaml and supports multi-component/multi-package projects.

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.