Artifacts

Upload PDFs, build a retrieval index and ask questions about them with a hosted language model.

Demo of GOT-OCR 2.0 reading text, formulas and tables from an image.

Compare several OCR engines side by side on one image, with optional preprocessing.

Scene and document text recognition with PaddlePaddle PP-OCRv5.

Converts a document image into structured markdown including tables and equations.

Converts an uploaded PDF into Markdown text.

Try several OCR models on Arabic documents and images.

Runs Chandra, Nanonets, olmOCR and Dots OCR models on a page image to extract text.

Lightweight OCR demo based on ONNX models that reads text from images.

Classic Tesseract OCR: upload an image and get the recognized text.

Reads Japanese text from an image, including manga-style text.

Fills out a 1099-NEC form for contractor payments and downloads it as PDF; states data stays in the browser.

Dutch-language viewer that renders a dropped .md file as a readable page, locally in the browser.

Combines several PDF files into one document in the browser.

Privacy-friendly PDF tools that keep files on your device: organize, convert and compress.

Shrink PDF size without uploading the file.

Combine PDFs into one document with no uploads.

Split a PDF into separate files with no uploads.

Turns pasted or typed text into a multi-page PDF, fully in the browser.

Fills out an IRS W-9 form online and downloads it as PDF; states data stays in the browser.

Extracts text from an image in many languages.

A toolbox of 92 free browser-based tools for PDF, image, video, audio and text work.

Creates a bill of lading document for a shipment.

Asks a few questions about how others may reuse your work and returns the matching Creative Commons license.