AGRAGstill growing

Retrieval-augmented generation

Explain how RAG puts fresh and private data in front of a model, and choose between RAG, long context and agentic retrieval.

For Developers who know what an LLM is but have not built retrieval around one.

PrerequisitesAGCTX Context engineering

8 notes, in order. Each one assumes the one before it. Still growing: more notes may be added.

Notes in this trail

Start the trail
  1. I · The pieces
    Why RAG, not yet read
  2. Embeddings, not yet read
  3. Vector databases, not yet read
  4. II · The pipeline
    RAG ingestion, not yet read
  5. RAG at query time, not yet read
  6. III · Beyond one shot
    RAG versus long context, not yet read
  7. Agentic RAG, not yet read
  8. Context reranking, not yet read
    AGCTX