What would you like to find?

Nomic Layout v1 parses document structure, then OCR and embeddings power semantic search. Inference runs locally in your browser, powered by Muna.

Preparing AI models0/3

Layout Detectionnomic-layout-v1

Text Embeddingsnomic-embed-v1.5

Text Recognitionrapid-ocr

Models are cached after first download

Reading PDF

Extracting pages and text layers with pdf.js, entirely in your browser.

Analyzing Layout

Nomic Layout v1 detects headings, text blocks, tables, and images entirely in your browser.

Creating Embeddings

Nomic Embed v1.5 builds a semantic vector index locally in the browser.

Searching

Finding the most relevant regions using vector similarity search.

All processing runs locally via WebAssembly. Your documents never leave your device.