RAG: Retrieval-Augmented Generation

Retrieval-augmented generation grounds an LLM in your own data by retrieving relevant documents at query time. Learn chunking, embeddings, retrieval, re-ranking and evaluation by building RAG pipelines.

4 lessons across 1 courses

RAG: Retrieval-Augmented Generation lessons by course

Practical AI System Architecture: Building Intelligent Systems with LLMs, RAG, and Agent Frameworks

View course →
  1. Day 11 : The RAG Imperative: Why LLMs Need External Knowledge.
  2. Day 17 Multi-Query and HyDE RAG: Enhancing Retrieval Precision and Recall
  3. Day 18 RAG Evaluation and Metrics: Quantifying Retrieval Performance for Production

Related topics

AI Agents (27) LLM Serving & Inference (16) MLOps (9) Embeddings & Vector Databases (6) All topics →