Granite 4.1 LLMs: How They’re Built
•
66
Enterprise-grade AI models
ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
RAG example using Granite [vision, embedding, instruct]
Extract and convert document content from images
Convert document images to HTML with Docling
Transcribe or translate spoken audio to text in your browser
Extract and convert document content from images
Convert document images to HTML with Docling
Transcribe or translate spoken audio to text in your browser
RAG example using Granite [vision, embedding, instruct]