Developer Resources for Retail and CPG

A hub of news, SDKs, technical resources, and more for developers working in the retail and consumer packaged goods (CPG) industry.

A collage of developer resources for the retail and consumer packaged goods (CPG) industry

Applications and SDKs

NVIDIA NeMo for Generative AI

NVIDIA NeMo™ is an end-to-end platform for developing custom generative AI—including large language models (LLMs), multimodal, vision, and speech AI—anywhere. It delivers enterprise-ready models with precise data curation, cutting-edge customization, retrieval-augmented generation (RAG), and accelerated performance.

NVIDIA RAPIDS for Data Science

NVIDIA RAPIDS™, part of NVIDIA CUDA-X™, is an open-source suite of GPU-accelerated data science and AI libraries with APIs that match the most popular open-source data tools, such as pandas, Apache Spark, sci-kit learn, and NetworkX. It accelerates performance by orders of magnitude at scale across data pipelines.

NVIDIA Metropolis for Computer Vision

NVIDIA Metropolis brings powerful SDKs such as NVIDIA TAO, DeepStream, TensorRT™, and Triton™, microservices, and reference workflows to develop and deploy both generative AI and vision AI applications.

NVIDIA ACE for Digital Humans

NVIDIA ACE is a suite of technologies for bringing digital humans to life with generative AI. For example, James is a virtual assistant built with ACE that can provide contextually accurate responses in real time.

NVIDIA MEGA for Virtual Factories

NVIDIA MEGA is a reference architecture that combines NVIDIA Omniverse™, ACE, Metropolis, cuOpt™, and Isaac Sim™ to help developers test and refine industrial automation and generative physical AI in simulation before deploying into real-world factories and wa​​rehouses.

NVIDIA NIM

NVIDIA NIM™, part of NVIDIA AI Enterprise, is a set of easy-to-use microservices designed to accelerate the deployment of generative AI models across the cloud, data center, and workstations. Built on robust foundations, including inference engines like Triton Inference Server, TensorRT, TensorRT-LLM, and PyTorch, NIM is engineered to facilitate seamless AI inferencing at scale.

NVIDIA Retail Shopping Assistant Blueprint

Develop a generative AI-powered shopping assistant that provides interactive customer experiences using retrieval-augmented generation (RAG)—a technique that connects large language models (LLMs) to a company’s enterprise data—and NVIDIA NIM microservices. This workflow example provides an advanced starting point for generating conversational, accurate, and precise responses tailored to consumers.

Learn More

A business manager uses NVIDIA Retail Shopping Advisor on the laptop

NVIDIA Omniverse

NVIDIA Omniverse for Digital Twins and Simulation simulate warehouses, products, and packaging

Digital Twins and Simulations

NVIDIA Omniverse for digital twins and simulations revolutionizes retail planning and optimization with digital replicas of physical environments and goods. The platform simulates store layouts, warehouses, products, and packaging to cut costs and streamline operations by testing scenarios risk free, optimizing resource allocation, and streamlining supply chains.

Learn More
A leather handbag representing NVIDIA Omniverse platform for 3D design collaboration

Design Collaboration

Omniverse is an easily extensible platform for 3D design collaboration and scalable multi-GPU, real-time, true-to-reality simulation. Omniverse revolutionizes the way we create and develop as individuals and work together as teams, bringing more creative possibilities and efficiency to 3D creators, developers, and enterprises.

Learn More

Build With NVIDIA AI Enterprise

NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines development and deployment of production-grade AI applications, including generative AI. Easy-to-use microservices provide optimized model performance with enterprise-grade security, support, and stability to ensure a smooth transition from prototype to production.

Try for Free

Browse by Resource Library

Retail loss prevention AI workflow at point of sale  Image 2

Retail Loss Prevention

Prevent shrinkage and theft at the point of sale.

Learn More About
Loss Prevention
Retail shopping advisor AI workflow enhances personalized shopping experiences

Retail Shopping Assistant

Enhance personalized shopping experiences with generative AI.

Learn More About Shopping Assistants
Retail store analytics AI workflow for store business improvements

Retail Store Analytics

Gain actionable insights with advanced video analytics for retail

Learn More About
Store Analytics
Multi-camera tracking AI workflow for customer journey in stores

Multi-Camera Tracking

Track customer journeys across cameras throughout the store.

Learn More About
Multi-Camera Tracking
NIMs

Llama-3.1 8b

Language NIM: Language Generation

Advanced state-of-the art model with language understanding, superior reasoning, and text generation. It provides the benefits of low latency and high throughput, making it highly efficient for real-time applications and capable of handling large volumes of data.

NIMs

Edify (Getty)

Visual/Multimodal NIM: Image Generation

Getty Images’ API service for 4K image generation. It’s been trained on NVIDIA Edify using Getty Images' commercially safe creative libraries.

NIMs

Neva

Visual/Multimodal NIM: Language Generation and Computer Vision

Multimodal vision-language model that understands text and images and generates informative responses.

NIMs

CuOpt

Optimization/Simulation NIM: Route Optimization

World-record accuracy and performance for complex route optimization.

Frameworks

NVIDIA NeMo

Generative AI

NeMo is an end-to-end, cloud-native framework for building, customizing, and deploying generative AI models. It includes training and inferencing frameworks, guardrailing toolkits, data curation tools, and pretrained models, offering enterprises an easy, cost-effective, and fast way to adopt generative AI.

Frameworks

NVIDIA Omniverse

Simulation and Digital Twins

From designing true-to-reality 3D assets and environments to operating large-scale digital twins, Omniverse Enterprise is a computing platform that enables individuals and teams to develop Universal Scene Description (OpenUSD)-based 3D workflows and applications.

Frameworks

NVIDIA ACE

Digital Humans With Generative AI

ACE is a suite of technologies for bringing digital humans to life with generative AI.

Frameworks

NVIDIA Metropolis

Computer Vision AI

Metropolis brings powerful SDKs such as TAO, DeepStream, TensorRT, and Triton, microservices, and reference workflows to develop and deploy both generative AI and vision AI applications.

Frameworks

NVIDIA RAPIDS

Data Science Software

RAPIDS, part of CUDA-X, is an open-source suite of GPU-accelerated data science and AI libraries with APIs that match the most popular open-source data tools. It accelerates performance by orders of magnitude at scale across data pipelines.

Frameworks

NVIDIA Triton Inference Server

AI Model Deployment

Triton Inference Server lets teams run inference on trained machine learning or deep learning models from any framework on any processor—GPU, CPU, or other. It’s open-source software that standardizes AI model deployment and execution across every workload.

Frameworks

NVIDIA Riva

Multimodal Conversational AI

Riva empowers developers to voice their conversational AI applications—Q&A assistants, contact center agent assists, virtual assistants, digital humans, and AI robots—and transform them into natural polyglots. To ensure the best possible accuracy, Riva GPU-accelerated microservices offer flexible customization to specific languages, accents, and domains.

Frameworks

NVIDIA Isaac Sim

Robotics Simulation and Synthetic Data

Isaac Sim is a reference application that enables developers to design, simulate, test, and train AI-based robots and autonomous machines in a physically based virtual environment.

Frameworks

NVIDIA cuOpt

Accelerated Optimization

cuOpt helps teams solve complex routing problems with multiple constraints and delivers new capabilities, like dynamic rerouting, job scheduling, and robotic simulations, with subsecond solver response times.

Frameworks

NVIDIA Morpheus

Cybersecurity

Morpheus is an open application framework that helps cybersecurity developers create optimized AI pipelines for filtering, processing, and classifying large volumes of real-time data. Morpheus uses AI to identify, capture, and act on threats and anomalies that were previously impossible to identify.

SDKs

NVIDIA NeMo

NeMo is an end-to-end platform for developing custom generative AI anywhere. It includes tools for training, customization, and RAG, guardrailing and toolkits, data curation tools, and model pretraining, offering enterprises an easy, cost-effective, and fast way to adopt generative AI.

SDKs

NVIDIA RAPIDS

RAPIDS, part of CUDA-X, is an open-source suite of GPU-accelerated data science and AI libraries with APIs that match the most popular open-source data tools. It accelerates performance by orders of magnitude at scale across data pipelines.

SDKs

NVIDIA DeepStream SDK

The DeepStream SDK is a complete streaming analytics toolkit based on GStreamer for AI-based multi-sensor processing and video, audio, and image understanding. It’s ideal for vision AI developers, software partners, startups, and OEMs building intelligent video analytics (IVA) apps and services.

SDKs

NVIDIA TAO Toolkit

The open-source TAO Toolkit, built on TensorFlow and PyTorch, uses the power of transfer learning while simplifying model training and optimizing for inference throughput on practically any platform. The result is an ultra-streamlined workflow that can take any model, adapt it to real or synthetic data, and optimize it for inference throughput—without AI expertise or large training datasets.

SDKs

NVIDIA Riva

Riva empowers developers to voice their conversational AI applications—Q&A assistants, contact center agent assists, virtual assistants, digital humans, and AI robots—and transform them into natural polyglots. To ensure the best possible accuracy, Riva GPU-accelerated microservices offer flexible customization to specific languages, accents, and domains.


Browse by Resource Type

Accelerating End-to-End Data Science Workflows

Learn how to build and execute end-to-end, GPU-accelerated data science workflows that let you quickly explore, iterate, and move your work into production. In this self-paced lab, you’ll learn how to use RAPIDS accelerated data science libraries to perform data analysis at scale with a wide variety of GPU-accelerated algorithms.

Generative AI Explained

Explore generative AI, which has recently taken the world by storm. Using neural networks to identify patterns and structures within existing data, it generates new content based on a variety of inputs. In this course, you’ll learn generative AI concepts, applications, and the challenges and opportunities of this exciting field.

Synthetic Data Generation for Training Computer Vision Models

Streamline synthetic data generation (SDG) using 3D assets into a single application—and modify the appearance and format of the data—with NVIDIA Omniverse Replicator. This lab highlights one of the ways deep learning tools and Omniverse can be used together to streamline deep learning workloads.


Programs for You

Access Developer Resources

The NVIDIA Developer Program provides the advanced tools and training needed to successfully build applications on all NVIDIA technology platforms. This includes access to hundreds of SDKs, a network of like-minded developers in our community forums, and more.

Get Technical Training

NVIDIA RAPIDS™, part of NVIDIA CUDA-X™, is an open-source suite of GPU-accelerated data science and AI libraries with APIs that match the most popular open-source data tools, such as pandas, Apache Spark, sci-kit learn, and NetworkX. It accelerates performance by orders of magnitude at scale across data pipelines.

Accelerate Your Startup

NVIDIA Inception—an acceleration platform for AI, data science, and high-performance computing (HPC) startups—supports over 19,000 startups worldwide with go-to-market support, expertise, and technology. Startups get access to training through the DLI, preferred pricing on hardware, and invitations to exclusive networking events.

Get Started

Take the Next Steps

Stay Up to Date on NVIDIA News for Retail

Subscribe Now

Request a Consultation

Our experts can help your business unlock potential and unleash innovation.

Join the NVIDIA Developer Program to take a free self-paced course.

Join Now