How it works
- You ask a question.
- A search step finds the most relevant passages in a set of documents.
- Those passages go into the model's context window together with your question.
- The model answers from them, and can cite them.
When it helps
RAG suits up-to-date information, company knowledge and anything that needs sources. Its answers are only as good as what the search step finds. With MCP, an assistant can do its own retrieval by calling a search tool.