Building RAG Applications with Local LLMs

Overview

Join us for a hands-on session on building RAG (Retrieval-Augmented Generation) applications using local LLMs.

What We'll Cover

• Vector Databases: Setting up and using ChromaDB and Qdrant
• Embedding Strategies: Choosing the right embedding model for your use case
• Local LLMs: Running Llama, Mistral, and other models with Ollama
• Prompt Engineering: Crafting effective prompts for RAG pipelines
• Live Demo: Building a document Q&A system from scratch

Who Should Attend

Anyone interested in AI, whether you're a beginner or experienced developer. Bring your laptop if you want to follow along!

Logistics

• Free parking available
• Light refreshments provided
• Wi-Fi available