Artifacts

Demo of JavaScript OCR that reads text from images in many languages.

Turns an uploaded document image into structured Markdown using a vision model.

Extracts text from long or dense document images with Baidu OCR models.

Chat with an uploaded PDF using retrieval over its text with an open language model.

General OCR model that reads text, tables, formulas and sheet music from images.

Convert document page images to structured text with IBM's compact Granite-Docling model.

Convert page images into structured document markup with a small vision-language model.

Parses text, tables and formulas from document images with PaddleOCR-VL.

Converts a document page image into structured Docling markup using a 258M model run in the browser.

Chat with a PDF from an upload or URL; you provide your own OpenAI API key.

OCRs a scanned PDF and returns the recognised text.

Reads text and layout from document images with the dots.ocr model.

Converts an image or PDF page to Markdown with a compact OCR model.

Extracts text and images from PDFs or images with the Mistral OCR API; needs your Mistral key.

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.

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