AI Demystified Unveiling the Intelligence Behind the Machine
summary
Claims a working local LLM pipeline that runs Llama 3 8B on a laptop using the Ollama runtime, demonstrates retrieval-augmented generation with chunking, embeddings and a vector DB, and answers queries from a Google balance sheet. Shows code using LangChain + ChromaDB, explains RAG, prompt structure, and agent roles (planner, optimizer, manager, coder). Emphasizes data curation, notes 8 billion parameters as a practical model size, and shows the demo producing correct, responsibly filtered answers.
AI-written summary · about
chapters (9)
- 0:00Introduction and mindset
- 3:12What is artificial intelligence
- 7:49Language models and GPT
- 10:14AI agents and applications
- 13:23Data science and AI fundamentals
- 17:55Learning path for AI
- 21:27Running LLMs locally
- 22:52Retrieval augmented generation demo
- 27:08Summary and Q&A
related talks
29mUsing LangChain and LlamaIndex to customize LLMs...
55mBuild enterprise generative AI apps using Llama 3 at 1,000 tokens/s on the SambaNova AI platform
42mUsing LlamaIndex for building Generative AI apps
02h 08mIntroduction to AI Agents
43mLarge Language Models for Devs: from zero to your first LLM application
47mBuilding and Testing AI-Agent Powered LLM Applications: A Live Demonstration
01h 19mBuilding an LLM on your Laptop to...
01h 34mA Practical Starter's Guide to building LLM based projects