marvin VS newsboat

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 using https://newsboat.org, you can add a filter (killfile) to remedy this:

  ignore-article "*" "title =~ \"#shorts\""

I use newsboat.

> Have you used any modern RSS reader recently like inoreader, they load the content of the page without visiting the publishing website.

I'm happy with newsboat[1]; but I'm not surprised that people have integrated scraping into RSS readers.

Fundamentally, that's not a problem with RSS, that's a war between scrapers and content providers. If the email newsletter model persists long enough, I'd expect that people will come out with "newsletter readers" that scrape websites too.

I'm not sure there's a good long-term solution to the problem. Aside from constant vigilance (obfuscation).

---

1. https://newsboat.org/

So, I installed a terminal RSS reader called Newsboat and added the feed to it. I have it always running in a terminal, and the scores refresh every minute. I can open the Cricinfo link in a browser by selecting a match and typing o.

Not at the moment. There is an open Github issue asking for that feature, however, no idea if/when that will be implemented: https://github.com/newsboat/newsboat/issues/904

Here's part of my newsboat config (works great for subscriptions):

Newsboat RSS / Feed reader

Che rss feader usate? Io per il momento uso Newsboat su Desktop e Feeder su Mobile