marvin VS ddgr

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.

Using the shell commands plugin and ddgr, I managed to create a nice trick, which allows you to add the link to selected text without having to google it (hard to describe, but the gif should give you the idea). Here is how it works: - install the shell commands plugin https://obsidian.md/plugins?id=obsidian-shellcommands - install ddgr https://github.com/jarun/ddgr - add the following code as shell command: bash query="{{selection}}" link=$(ddgr --num=1 --json "$query" | grep "url" | cut -d'"' -f4) mdlink="[$query]($link)" echo -n "$mdlink" - in the settings for that shell command, set the stdout to "current file: caret position" - you are good to go. (Maybe give it a hotkey)

search from the CLI is hardly new.. some examples by jarun: - google: https://github.com/jarun/googler - duckduckgo: https://github.com/jarun/ddgr

Leveraging filter commands (i.e. :!) to easily/quickly manipulate lines or entire buffers/files. For example, :!date will run the external date and show you results, but :.!date (which is done by typing !! then date will run the external date command and put the result on the current line. But, also, if you have the word date on a line, then you can run :.!bash (which is done by typing !! then bash), which will execute the command date and replace the current line with the result. There are infinite uses for this, like :!sort (for sorting text), :!column -t (for aligning/tabulating text), :!awk for text manipulation, :!ddgr duckduckgo cli, ...etc

I like ddgr https://github.com/jarun/ddgr. Duckduckgo for the terminal. googler (https://github.com/jarun/googler) was great but google seem to have crippled it, at least for me. ddgr --site youtube.com QUERY .... You can use the builtin URL handler, or the JSON output, to pass the URL to a video player like mpv. yt-dlp is required for mpv to launch the video from URL.

Here is link number 1 - Previous text "Yes"