Topic hub 04

RAG and vector search

Grounding model output in your own data: pipelines, vector search and trade-offs.

Overview

Retrieval augmented generation (RAG) supplies a model with relevant documents at query time so its answers can draw on information it was never trained on. A RAG system is a pipeline: ingestion, chunking, embedding, indexing, retrieval, reranking and generation, and each stage can fail on its own.

The guides here explain the pipeline end to end, compare RAG with fine-tuning, and point to the vector databases and evaluation methods teams use in production.

RAG and vector search guides

Key terms

Full glossary

Tools and platforms

Platform directory

Other topics