Nvidia offers blueprints from which to develop generative AI applications

Nvidia has announced pre-trained, customisable AI workflows for creating customer service avatars, for data-mining pdf documents, and for virtual drug screening.

They are the first three ‘NIM Agent Blueprints’, which the company said will be a catalogue of products to jump-start developers creating applications based on AI agents.

They include sample applications built with Nvidia’s ‘NeMo’, ‘NIM’ and partner micro-services, reference code, customisation documentation, and a Helm chart for deployment.

“Enterprises can modify NIM Agent Blueprints using their business data and run their generative AI applications across accelerated data centers and clouds,” the company said. With such blueprints, enterprises can continually refine their AI applications based on user feedback, creating a data-driven AI flywheel.”

The avatar blueprint creates ‘3d’ human-like animated faces on computer monitors that speak words provided from elsewhere.

Underlying is Nvidia’s Tokkio technology, and it features the company’s ACE, Omniverse RTX, Audio2Face and Llama 3.1 NIM microservices.

The pdf data extraction blueprint uses ‘NeMo Retriever NIM’ microservices.

The virtual drug screening blueprint is intended to help identify and optimise drug-like molecules. It incorporates NIM micro-services including AlphaFold2, MolMIM and DiffDock.

To be released monthly, said the company, blueprints are planned for applications for customer experience, content generation, software engineering, and product research and development.