Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
-
Updated
Jul 24, 2026 - TypeScript
Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
This project is a visual Retrieval-Augmented Generation (RAG) system that uses Cohere's Embed-4 model to semantically retrieve relevant images and PDF pages. It then leverages Google's Gemini 2.5 Flash model to provide context-aware answers based on the retrieved visual content.
Privacy-first, 100% offline PDF intelligence desktop app — Tauri 2 + React + embedded SurrealDB vector search + local llama.cpp RAG. No cloud, no API keys, no telemetry.
Add a description, image, and links to the pdf-intelligence topic page so that developers can more easily learn about it.
To associate your repository with the pdf-intelligence topic, visit your repo's landing page and select "manage topics."