About

Join us for a hands-on walkthrough to build your first RAG pipeline using RedisVL. Learn how retrieval-augmented generation improves LLM accuracy by combining models with real-time, external data. Using Redis as your vector database, you’ll build a complete GenAI app from scratch, ready to fork, run, and power production-grade AI pipelines.

Key topics

1. Preprocess a real financial document (Nike’s 10-K)
2. Generate vector embeddings using sentence transformers
3. Store and query those embeddings with RedisVL
4. Retrieve relevant context and generate grounded responses using OpenAI
5. See exactly how each step maps to a real RAG architecture