Metro AI Suite Developer Workflow#
Metro AI Suite is a developer stack for edge vision AI, generative AI, and physical AI.
This section describes the Metro AI Suite workflow for developers. See the repository-wide suite overview and application index in Metro AI Suite; application-specific details remain in each application’s documentation.
Create and Acquire Models#
You have the following options:
Build a model using visual prompting with Intel® Geti™ software.
Select a model from the Metro Analytics Catalog and OpenVINO Model Collections hosted in the Hugging Face hub.
Bring your own model. See Model Convertion Guides and Agent Skills.
Choose Platform#
Intel recommends the following steps:
Evaluate Hardware: Evaluate your hardware using the Visual Pipeline and Platform Evaluation Tool.
Search AI-Ready Qualified Systems: Search for AI-ready qualified systems in the Recommended Hardware Catalog.
Access Pre-Benchmarked Results from Metro AI Suite Benchmarks and OpenVINO benchmarks.
Build Faster#
Jumpstart Solutions with AI Sample Applications and Blueprints#
For example, use Live Video Caption & Search and Video Search and Summarization.
You can explore other sample applications and blueprints in the Metro AI Suite.
Build Production-Grade AI Pipelines Modularly#
Use Vision and AI SDKs, which include:
Microservices
Libraries
Tools
Third-party components for video and AI workloads
Build Software with Coding Agents#
Add Capabilities#
Make Solutions Autonomous with Agentic AI#
Use a Live Video Alert Agent.
Use a Smart Route Planning Agent.
Integrate AI with a Video Management System (VMS)#
See VMS Integrations and Smart NVR.
Bring AI into the Physical World#
Use Scenescape.
Optimize#
Maximize performance for edge deployment:
Refer to Performance Blueprints.
Use the Deep Learning Streamer (DL Streamer).
Migration and Modernization#
The suite supports migration from NVIDIA-based stacks to Intel-native execution. See the guide for more information.