What is RAG?
What is it?
A RAG (retrieval-augmented generation) pipeline lets a model answer from your documents: they are chunked and embedded, then for each question the useful excerpts are retrieved and given to the model.
When to use it
- Have an assistant answer from internal docs or a product catalog.
- Reduce hallucinations by making the model cite its sources.
Page fields
| Sources | Documents used and how they are updated. |
|---|---|
| Chunking | Chunk size and overlap. |
| Embeddings and vector store | The embedding model and where vectors are stored. |
| Retrieval | Number of excerpts kept and optional reranking. |
| Prompt template | The text sent to the model, with {{context}} and {{question}}. |
How to use it
“Use” tab: download the JSON config; the Python example describes each step.