Sign in Publish

What is RAG?

What is it?

A RAG (retrieval-augmented generation) pipeline lets a model answer from your documents: they are chunked and embedded, then for each question the useful excerpts are retrieved and given to the model.

When to use it

  • Have an assistant answer from internal docs or a product catalog.
  • Reduce hallucinations by making the model cite its sources.

Page fields

SourcesDocuments used and how they are updated.
ChunkingChunk size and overlap.
Embeddings and vector storeThe embedding model and where vectors are stored.
RetrievalNumber of excerpts kept and optional reranking.
Prompt templateThe text sent to the model, with {{context}} and {{question}}.

How to use it

“Use” tab: download the JSON config; the Python example describes each step.

Browse RAG →