RAG

What retrieval-augmented generation actually is, how the indexing and query paths work, and where the evidence complicates the standard advice - hybrid search does not universally beat dense retrieval, and neither beats a bad chunking decision.

Read the RAG guide

Concepts it implements

Context window

The fixed number of tokens a model can attend to on one request, shared between the system prompt, tools, retrieved documents, history and the answer itself.

Where RAG sits

How this component relates to the rest of the stack. Items without a link are not covered here yet.

Depends on

Must be present for this to run

pgvector
Embedding model

Deployed with

Commonly run alongside

pgvector
PostgreSQL

Alternatives

Solves a similar problem differently

Long-context models
Fine-tuning