What is a RAG corpus?
What is it?
A corpus is a set of documents already split into chunks, each with its text and source. It is ready to embed for RAG, and every answer can cite where it comes from.
When to use it
- Build an assistant that answers from official texts or documentation.
- Share a clean, sourced chunking.
Page fields
| Chunks | One JSON line per chunk: id, text, source. |
|---|---|
| Chunking | The rule used (per article, per paragraph…). |
How to use it
Download the JSONL file, embed each text and keep the source to cite it.