Is RAG Still Needed? Choosing the Best Approach for LLMs

Are massive context windows replacing RAG? 🤔 Martin Keen breaks down RAG vs. long context in LLM workflows. Explore how vector databases, semantic search, and embedding models impact AI performance to help you choose the right solution for your applications. 🚀

Intermediate - 11 min - AI & Data - IBM Technology

The full course: Learn LLM Apps & Agents free

What you'll need

• Laptop stand: Screen at eye level for long study sessions.
• Noise-cancelling headphones: Focus through long video lessons.
• Second monitor: Video on one screen, practice on the other.
• Wireless keyboard and mouse: Comfortable for hours of typing.

Books

1. AI Engineering by Chip Huyen - View on Amazon
2. Build a Large Language Model (From Scratch) by Sebastian Raschka - View on Amazon
3. Hands-On Large Language Models by Jay Alammar - View on Amazon
4. Prompt Engineering for LLMs by John Berryman - View on Amazon

Next lessons

• How I use LLMs (131 min, Andrej Karpathy, Intermediate)
• Run your own AI (but private) (22 min, NetworkChuck, Intermediate)
• [1hr Talk] Intro to Large Language Models (60 min, Andrej Karpathy, Beginner)
• you need to learn MCP RIGHT NOW!! (Model Context Protocol) (39 min, NetworkChuck, Intermediate)
• Deep Dive into LLMs like ChatGPT (211 min, Andrej Karpathy, Advanced)
• host ALL your AI locally (24 min, NetworkChuck, Intermediate)
• AI Agents, Clearly Explained (10 min, Jeff Su, Intermediate)
• Build and Deploy Your Own ChatGPT AI App in JavaScript | OpenAI, Machine Learning (62 min, JavaScript Mastery, Intermediate)