# Retrieval augmented generation

Retrieval-augmented generation, RAG, is the pattern of fetching relevant content at request time and
putting it in the model's context before it answers. Documents are split into chunks, each chunk is
embedded into a vector, and the chunks sit in an index. At request time the question is embedded the
same way, the index returns the closest chunks, and the model generates its answer from what came
back.

It helps an agent because a model's weights hold only what it was trained on, and context windows
are finite, so an agent can't carry its whole knowledge base into every request. RAG hands it
exactly the slice a request needs, from internal docs, past tickets, or a product catalog, without
retraining anything, and the corpus can be updated at any time.

RAG is bad at questions whose answers aren't localized in a few passages. Retrieval returns a top
handful of chunks, so anything that needs aggregating across many documents, counting, or
summarizing a whole corpus won't work. It's also weak when the question's wording doesn't resemble
the document's wording, since similarity search leans on phrasing. And when the corpus holds stale
or contradictory content, the model will faithfully answer from the wrong version.

## Questions answered under this concept

- [Does RAG stop a model from hallucinating?](https://tessary.ai/answers/retrieval-augmented-generation/does-rag-stop-a-model-from-hallucinating)
- [How do I tell a stale RAG index apart from a truncated context window?](https://tessary.ai/answers/retrieval-augmented-generation/stale-rag-index-vs-truncated-context-window)
- [What can retrieval grading over traces not tell me?](https://tessary.ai/answers/retrieval-augmented-generation/what-can-retrieval-grading-over-traces-not-tell-me)
- [What is retrieval-augmented generation?](https://tessary.ai/answers/retrieval-augmented-generation/what-is-retrieval-augmented-generation)
- [Why can't I just increase the context window instead of using RAG?](https://tessary.ai/answers/retrieval-augmented-generation/why-cant-i-just-increase-the-context-window-instead-of-using-rag)
- [Why did my RAG answer miss the exception to the rule?](https://tessary.ai/answers/retrieval-augmented-generation/why-did-my-rag-answer-miss-the-exception-to-the-rule)

---

Source: https://tessary.ai/answers/retrieval-augmented-generation
All concepts: https://tessary.ai/answers
From Tessary, agent reliability for AI agents in production: https://tessary.ai