documents
Apple releases LensVLM-9B, a document model that zooms into selected pages News
Apple released research-only LensVLM-9B weights and code for a vision-language system that keeps a compressed document overview and selectively expands pages as text, OCR, or high-resolution images.
The quiet race to turn messy documents into AI-ready text News
Mistral released a new document-reading model the same week an open-source rival surged, both chasing the unglamorous job that quietly decides how well AI can read your files.
RAGFlow Tool
An open engine for building AI question-answering over your own files and documents.
NVIDIA Nemotron 3.5 Parse Tool
A document-processing component that turns pages into structured output for indexing and retrieval; download size and running-memory requirements are not established in the dossier.
Mistral OCR 4 Tool
A hosted document-reading model that converts scanned pages, PDFs, and complex layouts into clean structured text ready for a language model. Send a document, get back tidy text with the structure preserved.
MinerU Tool
Open-source tool that converts complex PDFs and office files into clean markdown and structured data that AI models can read reliably. Run it yourself for free, with nothing leaving your machine.
LensVLM-9B Tool
Run Apple's research-only 9B vision-language model for selective page expansion across long documents.
Indra OCR Tool
Shipping CPU OCR package with an approximately 76 MB default model download; no GPU required. Code is Apache 2.0, while model weights have separate commercial restrictions.
Claude Docs Tool
Claude’s editable collaborative document surface with docx, PDF, Markdown and Google Docs export.
ChatGPT Pages Tool
Shared documents for writing, research, charts, and images on eligible Pro, Business, and Enterprise plans; launch details are in the official recap.