Choosing EPUB or markdown for a new RAG agent build
A is being built on to answer questions about a specific religious sect. The source material is made up of books and related documents, and the current tool is Onyx. The builder can use Python and SQL, but is not working at the level of a software engineer or .
The main decision is whether existing EPUB files can be loaded directly, or whether converting them to markdown would give much better results. A staged path is also being considered: load all EPUB files now, then slowly convert them to markdown later.
Key points
- The project is a question-answering hosted on .
- The source material is books and documents about a religious sect.
- Onyx is the current tool for the build.
- The main choice is direct EPUB loading versus markdown .
- A gradual approach is under consideration: use EPUB first, then convert to markdown over time.