language-models

The RAG pipeline shape

taught

Retrieval-augmented generation's core shape end to end -- chunk a document collection, embed the chunks, embed a query, search for the nearest chunks, inject the retrieved text into the prompt, then generate an answer grounded in that injected context.

Taught in

The RAG shape: chunk, embed, search, inject, generate
Wiring Language Models
A worked RAG example: end to end
Wiring Language Models

Requires

dense-retrieval-concept required
RAG's search step IS dense retrieval, applied inside a larger pipeline that also chunks documents and injects results into a prompt.

Required by

Nothing in the catalog needs this yet.

Local knowledge map

Click to expand

Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.