Subject
3 entries
Bookmarks
annotateai
annotateai is a Python package that uses LLMs to automatically annotate research papers — highlighting key claims, methodology sections, results, and limitations. Useful for quickly mapping what a paper is about before reading it in full.
PDFTriage: Question Answering over Long, Structured Documents
PDFTriage is a method for question answering over long, structured PDF documents that uses the document's structure (pages, sections, tables of contents) as a triage layer before retrieval — letting the LLM navigate the document intelligently rather than relying on flat embedding search.
Introducing Tabula
Tabula is an open-source tool for extracting tabular data from PDFs — a specific but critical pain point for data journalists and researchers working with government and scientific publications that publish data as PDFs instead of structured files.