gorilla-cli VS llm

Hello HN! I know this project is a super simple wrapper around LangChain/OpenAI but I just found myself wanting this badly myself: a super simple `pip install` package that I can use to get command suggestions within the terminal as I'm being productive doing other things.

The implementation is literally one short glue of LangChain and InquirerPy for interactive CLI.

I'm curious which ideas you all have to make this smarter/better. MIT licensed, if you're keen on contributing please feel free to do so. It's a pure hobby project for me.

Some key objectives: never automatically run shell code, I want to see what I run before I run it, present me with some alternatives, a simple path to using local models in the future (Llama 2 Code soon?).

Will add I was inspired by the great https://github.com/gorilla-llm/gorilla-cli project, but didn't like that it sent the prompt to some IP based endpoint.

Very cool product! Have you consider relying on Gorilla for integrations?

https://github.com/gorilla-llm/gorilla-cli

gorilla-cli: LLMs for your CLI (https://github.com/gorilla-llm/gorilla-cli)

That's a great use case, you might be able to do this if you've got a copy and paste on the command line with

https://github.com/simonw/llm

In between. An alias like pdfwtf translating to "paste | llm command | copy"

I added support for this model to my LLM CLI tool via a new plugin: https://github.com/simonw/llm-command-r

So now you can do this:

    pipx install llm

If you're willing to use the CLI, Simon Willison's llm library[0] should do the trick.

[0] https://github.com/simonw/llm

I'm not thrilled about https://github.com/GoogleCloudPlatform/localllm/blob/main/ll... calling their Python package "llm" and installing "llm" as a CLI command, when my similar https://llm.datasette.io/ project has that namespace reserved on PyPI already: https://pypi.org/project/llm/

I've been gleefully exploring the intersection of LLMs and CLI utilities for a few months now - they are such a great fit for each other! The unix philosophy of piping things together is a perfect fit for how LLMs work.

I've mostly been exploring this with my https://llm.datasette.io/ CLI tool, but I have a few other one-off tools as well: https://github.com/simonw/blip-caption and https://github.com/simonw/ospeak

I'm puzzled that more people aren't loudly exploring this space (LLM+CLI) - it's really fun.

Seems nice if you're using c# or java. It also supports python, but for that Simon's llm library is nice because he designed it as both a library and a command line tool: https://github.com/simonw/llm