← Latest products

Irpapers

Visual embeddings vs. OCR trade-offs in scientific PDFs. Tools for various benchmarking scenarios of Weaviate's Query Agent. Processing PDFs in production usually involves stringing together brittle OCR heuristics.

Open source

17 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Crop and OCR PDFs in the Browser

    pdf.darefail.com

    Hacker News5 pts

  2. PageIndex OCR

    pageindex.ai

    The First Long-Context OCR Model

    Hacker News10 pts

  3. Emboss

    github.com

    a Python PDF engine that keeps documents as structured data

    Hacker News6 pts

  4. Extractor Studio

    medium.com

    The Fastest Way to Build PDF Extractors

    Hacker News10 pts

  5. (YC S23) OCR that works on the messiest PDFs

    trycardinal.ai

    Hacker News21 pts