Ways to Get Started With NVIDIA NeMo

Use the right tools and technologies to take generative AI models from development to production.

The Journey From AI Models to Generative AI Insights

Experience the end-to-end, enterprise-ready platform for generative AI.

1

Try NVIDIA-optimized foundation models.

Learn More

2

Customize models with NVIDIA NeMo™.

Learn More

3

Jump-start building your AI solutions with NVIDIA Blueprints.

Learn More

4

Run in production with NVIDIA AI Enterprise.

Learn More

1. Try AI models.

Experience Optimized, Production-Grade Generative AI Models

Start prototyping with leading NVIDIA-built and open-source generative AI models that have been tuned for high performance and efficiency. AI models from the NVIDIA API catalog can be deployed using NVIDIA NIM™ microservices and customized with NeMo.

Try Now

2. Pull NeMo tools and microservices.

Customize With NeMo Microservices and Framework

NeMo Curator

GPU-Accelerated Data Curation

Use this GPU-accelerated data curation toolkit to prepare large-scale, high-quality text and image datasets for pretraining generative AI models.

Download Now

NeMo Customizer

Simplified Model Alignment

Industry-standard APIs for fine-tuning and alignment of large language models (LLMs) for domain-specific use cases with this high-performance, scalable microservice.

Get Notified

NeMo Evaluator

Model Assessment Microservice

Evaluate custom LLMs and retrieval-augmented generation (RAG) efficiently and reliably across diverse academic and custom benchmarks with APIs.

Get Notified

NeMo Retriever

Retrieval-Augmented Generation

Access world-class retrieval models for embedding, reranking, and ingestion to quickly unlock accurate insights from massive volumes of enterprise data.

Experience Now

NeMo Guardrails

Safeguard AI Applications

Microservice to orchestrate multiple LLM guardrails, ensuring the security, safety, accuracy and topical relevance of LLM interactions.

Get Notified

Build Custom Generative AI Models with NVIDIA NeMo

NeMo Framework

Build Custom Models

Start development of generative AI with scalable data processing and accelerated model training techniques, and easily align models for reasoning and human preferences with NeMo-Aligner library.

Get Container

3. Jump-start building your AI solutions.

Fast-Forward to Generative AI With NVIDIA Blueprints

NVIDIA Blueprints are comprehensive reference workflows built with NVIDIA AI and Omniverse™ libraries, SDKs, and microservices. Each blueprint includes reference code, deployment tools, customization guides, and a reference architecture, accelerating the deployment of AI solutions like AI agents and digital twins, from prototype to production.

Try the Blueprints

4. Run in production.

Deploy in Production With NVIDIA AI Enterprise

NVIDIA AI Enterprise is the end-to-end software platform that brings generative AI into every enterprise, providing the fastest and most efficient runtime for generative AI foundation models. It includes NeMo and NVIDIA NIM to streamline adoption with security, stability, manageability, and support.

Request a free 90-day license to access generative AI solutions and enterprise support today.

Request a 90-Day License

Resources

Documentation

Find a collection of documents, guides, manuals, how-to’s, and other informational resources in the NeMo Documentation Hub.

Explore Docs

Sessions

Check out NVIDIA On-Demand, which features free content on NeMo from GTC and other technology conferences from around the world.

Watch Now

Must-Reads

Read how NeMo enables you to build, customize, and deploy large language models.

Explore Technical Blogs

Training

Learn how to set up end-to-end projects with hands-on learning and get certified on the latest generative AI technologies.

Get Started With Training

FAQs

NVIDIA NeMo is an end-to-end, cloud-native framework as well as a set of microservices for building, customizing, and deploying generative AI models anywhere. It includes data curation at scale, accelerated training with advanced customization techniques, guardrailing, and optimized inference offering enterprises an easy, cost-effective, and fast way to adopt generative AI.

NeMo Curator improves generative AI model accuracy by curating high-quality multimodal datasets. It consists of a set of Python modules expressed as APIs that make use of Dask, cuDF, cuGraph, and Pytorch to scale data curation tasks, such as data download, text extraction, cleaning, filtering, exact/fuzzy deduplication, and text classification to thousands of compute cores.

NeMo Guardrails is a microservice to ensure appropriateness and security in smart applications with large language models. It safeguards organizations overseeing LLM systems.

NeMo Guardrails lets developers set up three kinds of boundaries:

Topical guardrails prevent apps from veering off into undesired areas. For example, they keep customer service assistants from answering questions about the weather.
Safety guardrails ensure apps respond with accurate, appropriate information. They can filter out unwanted language and enforce that references are made only to credible sources.
Security guardrails ensure apps only connect to external third-party applications known to be safe.

With NeMo Retriever, a collection of generative AI microservices built with NVIDIA NIM, enterprises can seamlessly connect custom models to diverse business data to deliver highly accurate responses. NeMo Retriever provides world-class information retrieval with the lowest latency, highest throughput, and maximum data privacy, enabling organizations to make better use of their data and generate real-time business insights. NeMo Retriever enhances AI applications with enterprise-grade retrieval-augmented generation capabilities, connecting them to business data wherever it resides.

NVIDIA NIM, part of NVIDIA AI Enterprise, is an easy-to-use runtime designed to accelerate the deployment of generative AI across enterprises. This versatile microservice supports a broad spectrum of AI models—from open-source community models to NVIDIA AI Foundation models, as well as bespoke custom AI models. Built on the robust foundations of the inference engines, it’s engineered to facilitate seamless AI inferencing at scale, ensuring that AI applications can be deployed across the cloud, data center, and workstation.

NeMo Evaluator is a microservice designed for fast and reliable assessment of custom LLMs and RAGs. It spans diverse benchmarks with predefined metrics, including human evaluations and LLMs-as-a-judge techniques. Multiple evaluation jobs can be simultaneously deployed on Kubernetes across preferred cloud platforms or data centers via API calls, enabling efficient aggregated results.

Retrieval-augmented generation is a technique that lets LLMs create responses from the latest information by connecting them to the company’s knowledge base. NeMo works with various third-party and community tools, including Milvus, Llama Index, and LangChain, to extract relevant snippets of information from the vector database and feed them to the LLM to generate responses in natural language. Explore the AI Chatbot Using RAG Workflow page to get started building production-quality AI chatbots that can accurately answer questions about your enterprise data.

NVIDIA offers AI workflows—cloud-native, packaged reference examples that illustrate how NVIDIA AI frameworks can be leveraged to build AI solutions. With pretrained models, training and inference pipelines, Jupyter Notebooks, and Helm charts, AI workflows accelerate the path to delivering AI solutions.

Quickly build your generative AI solutions with these end-to-end workflows:

NVIDIA Blueprints are comprehensive reference workflows built with NVIDIA AI and Omniverse libraries, SDKs, and microservices. Each blueprint includes reference code, deployment tools, customization guides, and a reference architecture, accelerating the deployment of AI solutions like AI agents and digital twins, from prototype to production.

NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines the development and deployment of production-grade AI applications, including generative AI, computer vision, speech AI, and more. It includes best-in-class development tools, frameworks, pretrained models, microservices for AI practitioners, and reliable management capabilities for IT professionals to ensure performance, API stability, and security.

Stay up to date on the latest generative AI news from NVIDIA.

Get the Inside Scoop on Generative AI News and More

Get developer updates, announcements, and more from NVIDIA sent directly to your inbox.

Section

Section

First Name

Last Name

Business Email Address

Organization / University Name

You are signing up to receive news and announcements for developers. Do you also want the same created for enterprise interests?

Send me the latest enterprise news, announcements, and more from NVIDIA. I can unsubscribe at any time.

NVIDIA Privacy Policy

Cloud Services

Data Center

Embedded Systems

Gaming and Creating

Graphics Cards and GPUs

Laptops

Networking

Professional Workstations

Software

Tools

Artificial Intelligence

Cloud and Data Center

Design and Simulation

High-Performance Computing

Robotics and Edge AI

Autonomous Vehicles

Industries

Ways to Get Started With NVIDIA NeMo

The Journey From AI Models to Generative AI Insights

1

2

3

4

1. Try AI models.

Experience Optimized, Production-Grade Generative AI Models

2. Pull NeMo tools and microservices.

Customize With NeMo Microservices and Framework

GPU-Accelerated Data Curation

Simplified Model Alignment

Model Assessment Microservice

Retrieval-Augmented Generation

Safeguard AI Applications

Build Custom Models

3. Jump-start building your AI solutions.

Fast-Forward to Generative AI With NVIDIA Blueprints

4. Run in production.

Deploy in Production With NVIDIA AI Enterprise

Resources

Documentation

Sessions

Must-Reads

Training

FAQs

What is NVIDIA NeMo?

How much does NeMo cost?

What AI models can be customized with NeMo?

How can customers get NeMo with NVIDIA Business-Standard Support?

What enterprise services are available for NeMo?

What is NeMo Curator?

What are NeMo Guardrails?

What is NeMo Retriever?

What is NVIDIA NIM?

What is NeMo Evaluator?

What is NeMo Customizer?

Does NeMo support retrieval-augmented generation?

What is the fastest way to get started?

What are NVIDIA Blueprints?

What is NVIDIA AI Enterprise?

What is the NVIDIA API Catalog?

Get the Inside Scoop on Generative AI News and More