CalibratedDecisions.

Repo · Documents & research

jevpdf

Search a PDF in your own words: TypeSafe Jev asks one yes/no question per line and the matching lines light up on the page, ranked by probability.

Open github.com ↗

From the repository

Ask a PDF in your own words and watch the matching lines light up. React + pdf.js + TypeSafe Jev.

jevpdf

How builders describe it

Ask a PDF in your own words and watch the matching lines light up. React + pdf.js + TypeSafe Jev.
PDF search that asks Jev one noul per line, does this line answer the query, and ranks the lines by the returned probability, so matches highlight without embeddings, a vector index or a chunking strategy. Text is extracted locally with pdf.js and the key stays on the server.

The decision Jev makes

Assign a topic, choose a document category, or answer whether a passage supports a citation.

Where it fits

Sorting, labelling and checking documents is classic decision work: topic labels for papers, categories for files, and whether a source actually supports a claim. All 45 documents & research projects →

Related projects