No Code AI Workflow Automation with n8n and OpenVINO Model Server for GPU and NPU

This project integrates n8n, a no-code workflow automation platform, with OpenVINO Model Server to let users build AI-powered workflows that run on Intel GPUs and NPUs. The core is a custom n8n node package that connects to OVMS - users pick a model, choose a target device, and the node handles inference. The system is deployed through Podman Compose with one command. The primary workflow is a Smart Document Processing Pipeline: it watches a folder for incoming documents, runs text extraction on NPU, classifies and extracts entities using an LLM on GPU, and saves results locally. OpenVINO's AUTO plugin handles device selection automatically based on availability and load. Deliverables: custom n8n node package with GPU/NPU/AUTO device selection, Podman Compose deployment, the document processing pipeline, 2-3 additional workflow templates (RAG chatbot, multimodal content analysis), and documentation with installation guide and tutorials."