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.

Upload a PDF and ask questions about it in a chat; the free account is needed to start.

Extracts text and structure from documents using the MinerU document extraction toolkit.

Runs the DeepSeek-OCR-2 model on PDFs or images to read the text they contain.

Reads text from images with a choice of OCR models, including olmOCR and Qwen2-VL-OCR.

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

Playground for an API that recognizes and reads ID documents from an uploaded image.

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

Extracts text from document images using several OCR models, including MonkeyOCR.

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.

Pulls text out of images and documents, letting you pick among several OCR models such as SmolDocling and Nanonets.

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

Extract text from complex documents and images with a multimodal OCR model.

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.