Resources and Industry Insights

NVIDIA's ecosystem of Omniverse, Isaac Sim, and Cosmos forms a powerful trio for robotics and AI development. Omniverse provides the collaborative 3D simulation platform, Isaac Sim enables realistic robotics testing, and Cosmos uses generative AI to accelerate synthetic data creation. This blog explains how these tools work together, their strengths, and when to use each to streamline your development workflow.

This tutorial will show you how to get started with UV: a fast Python manager for packages and projects.

Discover how to build a simple MCP server in Python to manage a to-do list example using the Model Context Protocol (MCP). This step-by-step guide walks you through creating the server, connecting it to Claude for Desktop, and enabling seamless interaction between AI models and real-world tools.

Easily switch between OpenAI and local LLMs like Ollama using the same API! This post shows how to wrap the OpenAI Python (and JavaScript) client to talk to Ollama with minimal changes, letting you develop and test locally without sacrificing the familiar OpenAI interface. Learn how to install Ollama, pull models like llama3.1, and build a unified interface that works across both platforms.

This guide will help you install CUDA in your Ubuntu machine in the simplest way.

A tutorial on how to train LLMs using Python, Hugging Face and Unsloth.

Learn to use DVC to quickly perform and compare machine learning experiments.

A walkthrough of mAP and other object detection quality metrics.

Discover how SAHI and tiled predictions can significantly improve detection performance, especially for small objects in high-resolution ima

A step by step guide on how to enable plots visualization on MMAction2 trainings.