Practical overview
When it fits
Use it when you want to turn textbooks you already have into a local searchable corpus, with the option to add cited note generation and semantic retrieval as separate stages.
Who it is for
- Readers building a personal, searchable textbook library
- Students and researchers who want structured notes grounded in textbook chapters
- Obsidian users who want to incorporate textbook-derived notes into a vault
Documented uses
- Convert textbook files into Markdown with page markers, tables and figure references.
- Search converted material by keyword.
- Generate structured notes with claims traceable to source books and chapters.
- Add semantic cross-book retrieval through a separate indexing stage.
Requirements & limits
The project is open-source under the MIT license and is intended to be self-hosted. The README lists Python 3.10+ and says CPU-only processing is supported for born-digital PDFs.
- The converter-only path needs Python dependencies but no GPU, Ollama or index.
- Scanned books and semantic search may require optional local OCR and embedding components, with hardware requirements varying by setup.
- Semantic indexing is not included in this repository; it relies on companion vault-search or another compatible indexer.
- The project supplies no textbook content, so users provide their own files and should respect their licenses.
- PyMuPDF is a required dependency under AGPL-3.0 or a commercial license, a consideration for redistribution or hosted services.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Convert a textbook to searchable Markdown
Create a Markdown version of a PDF or EPUB that can be searched by keyword.
Before you start
- Python 3.10 or later
- A PDF or EPUB textbook you have the right to use
- Install the project's Python requirements with pip
Steps
Install dependencies with the command below.
pip install -r requirements.txtRun the converter at
converter/convert.pyon your textbook.
Expected outcome
A Markdown corpus with page markers, tables and figure-reference markers that can be searched with grep.
Guide limitations
- This converter-only path does not provide semantic indexing.
- The repository does not include textbook content.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 13 October 2026
- Original website title
- drpwchen/textbook-to-note · Official homepage title · retained in its source language

