Skip to main content
RAG (Retrieval-Augmented Generation) gives an LLM the right facts at answer time. Instead of relying on what the model memorized, you retrieve relevant passages from your own content and hand them to the model. Ragrails runs that as a pipeline:

​
The pipeline, stage by stage

1

Ingest

Pull in your raw content (scraped websites, documents, or API responses) and normalize it into clean text.
2

Chunk

Split each document into small, focused passages.
Why: search works best on focused passages, not whole files. Chunking lets a query match the one paragraph that answers it instead of a 50-page PDF.
3

Embed

Convert each chunk into a vector, a list of numbers that captures meaning.
Why: vectors let “how do I get my money back” match a chunk titled “Refund policy” even with no shared words.
4

Store

Save the vectors in a vector database so they can be searched fast.
5

Retrieve

Embed the user’s question the same way, then find the closest chunks by meaning.
6

Answer

Hand those chunks to an LLM as context. The model answers grounded in your data.

​
Core terms

​
When you need capabilities

The basic pipeline works out of the box. Reach for these when you hit the matching problem:

​
Next

Quickstart

Build it now.

Features

Tune each stage.