NVIDIA-AI-Blueprints / video-search-and-summarization
Suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications.
https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization
Suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications.
https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization
GitHub
GitHub - NVIDIA-AI-Blueprints/video-search-and-summarization: Suite of reference architectures for building GPU-accelerated vision…
Suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications. - NVIDIA-AI-Blueprints/video-search-and-summarization
Macro Evals for Agentic Systems
This cookbook outlines a macro-evaluation workflow for analyzing multi-agent systems at scale using a simulated electric vehicle order pipeline. It demonstrates how to look past individual responses and evaluate systemic behaviors such as orchestration, routing, and tool choices by combining lower-level execution checks (via Promptfoo) into population-level trace analyses to discover and...
https://developers.openai.com/cookbook/examples/partners/macro_evals_for_agentic_systems/macro_evals_for_agentic_systems
This cookbook outlines a macro-evaluation workflow for analyzing multi-agent systems at scale using a simulated electric vehicle order pipeline. It demonstrates how to look past individual responses and evaluate systemic behaviors such as orchestration, routing, and tool choices by combining lower-level execution checks (via Promptfoo) into population-level trace analyses to discover and...
https://developers.openai.com/cookbook/examples/partners/macro_evals_for_agentic_systems/macro_evals_for_agentic_systems
Openai
Macro Evals for Agentic Systems
When an agentic system fails, the problem is often larger than a single bad response. A handoff may happen too late, a specialist agent may