Using LLMs on the command line

Показать описание

In this video, we're going to learn how to use Simon Willison's library, which lets us run almost any LLM model from the command line. OpenAI, Claude, Grok, Ollama, they're all covered!

We'll see how to run basic commands, how to have the LLM summarise the output of the tree command, and finally I'll share some shell scripts that use the tool.

Learn Data with Mark

Рекомендации по теме

Комментарии

This is absolutely awesome. I have been using this to do one shots, and piping them to piper for TTS. Mark I may not always understand everything but by in far you have educated me the most out of everyone I follow. It's good when I don't understand because it encourages me to push further, thus I end up learning more. Thank you so much for putting all this stuff together!

Steamfactory

To have my companion directly on the command line like grep is awesome. Seems to be quite straight forward and very easy to use, what is a great plus.

DannyGerst

Hi Mark, this very much reminds me of fabric, but at more ease. For a proposal, create a script that writes a list of pytest unit files for a set of files (or a directory), execute them and debug it, until they run and if they run, show the result :)

Basically feed the results of the execution back in the llm (I think there is even a option for that -c)

MaksimBronsky

It is very much like Aider. Does it support OpenRouter api keys ? Can it create or update new files on the folder where you run it ? . Does it work fast with Ollama local Ais ? I have tried Ollam local Ais and they are very slow ? do you know how to speed them up ?

totomomo

Very cool I have plenty of directories that need checking

paulmiller

I prefer "aichat" (sigoden/aichat), written in Rust and with a bunch of cool features

ricardokullock

Using LLMs on the command line

Using LLMs on the command line

EASIEST Way to Fine-Tune a LLM and Use It With Ollama

Connecting LLMs to tools

Learn Ollama in 15 Minutes - Run LLM Models Locally for FREE

What is Ollama? Running Local LLMs Made Simple

How to Use Local LLM in Cursor

How to Build a Local AI Agent With Python (Ollama, LangChain & RAG)

Building LLM Agents with Tool Use

First Steps With LangChain: Setting Up and Assembling Instructions

Every LLM in Emacs, with gptel

Creating a Structured AI Log Analysis System with Python & LLMs

Generative AI 03: Offline LLMs using #Ollama commandline and python

How To Build an API with Python (LLM Integration, FastAPI, Ollama & More)

This will change how you use LLMs #coding #ollama #llm #ai #chatgpt

How LLMs Execute Code & Commands On Your Computer | Using Python Exec Tools Part 2

Ollama Python Library: Use LLMs on your Local Computer | llama2 | mistral

PDF Reader LLM in 5 Lines of Code! #ollama #llm #chatgpt #coding #python #programming #software

Use LLaVA LLM with Ollama 🦙 Part 1 #shorts #ai #technology

How to Install AI Models Locally in 20 Seconds #coding #programming #code #ai #llm #lmstudio #dev

How To Run LLMs (GGUF) Locally With LLaMa.cpp #llm #ai #ml #aimodel #llama.cpp

Highlighting text on the command line using rg (ripgrep) and the passthru option - super useful!

OpenAI GPT-4: THE SECRET PROMPT You Need To Know 🤐 #shorts

Create a LOCAL Python AI Chatbot In Minutes Using Ollama

Don't Make an AI LLM - Do This Instead