A local PDF RAG reader that skips the vector database
Lumenfolio is a desktop AI reader for academic PDFs that keeps its work local by default. A common PDF RAG setup splits a document into chunks, creates , stores them in a , and then chats over that database. Lumenfolio starts differently for single-paper reading.
It parses a PDF into pages, blocks, lines, chunks, a structure tree, tables, figures, and position boxes. It uses , document structure, and page or block evidence instead of requiring a by default. Answers include page-level and position-level citations, so the reader can jump back to the exact area in the original PDF.
PDF indexes, notes, chat history, and metadata stay local by default. For , tables, and figures, it supports OCR, table evidence, and visual crops. Agents can use read-only document tools to search passages, open pages or sections, inspect tables and figures, and answer from evidence.
Key points
- Lumenfolio is a desktop AI reader for academic PDFs.
- It avoids requiring and a for single-paper reading.
- It uses , document structure, and page or block evidence to find relevant material.
- Answers can cite the exact page and position box in the original PDF.
- Agents get to search, open sections, inspect tables or figures, and answer from evidence.