paper-corpus-rag
Build grounded question answering over your own collection of research papers, with answers that cite the exact paper, page and passage. Use when a user wants to chat with or search a folder of PDFs, summarize what a set of papers says, synthesize evidence across a literature corpus, find which paper says X, convert PDFs to citable Markdown with a quality grade, handle scanned PDFs or damaged tables, decide whether a vector database is needed, evaluate whether a paper-QA pipeline is any good, or build a hybrid index (SQLite FTS5 BM25 plus embeddings fused by reciprocal rank). Search locates papers; the agent then reads the full converted file before synthesizing.
- Version
- 1.1
- License
- MIT
- Compatibility
- Python 3.9+ with SQLite FTS5 (standard in CPython builds). Optional pymupdf4llm or pypdf for PDF conversion; optional numpy and sentence-transformers for hybrid search.
Pinned to revision a74b0dbe5fa8, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/paper-corpus-rag/SKILL.md
- skills/paper-corpus-rag/scripts/paper_convert.py
- skills/paper-corpus-rag/scripts/paper_index.py
Every link opens the file at its source, pinned to the revision this page describes.