Application Examples#

End-to-end applications built on Nemotron models, including agentic workflows, RAG systems, and fine-tuning pipelines. Each card links to its directory in the Nemotron GitHub repository.

Nemotron 3 Super Getting Started Guide

Introductory notebook covering Nemotron 3 Super’s reasoning features: thinking, reasoning budget, low effort mode, streaming responses, tool-call streaming, and Perplexity Search integration using the OpenAI-compatible API.

https://github.com/NVIDIA-NeMo/nemotron/tree/main/use-case-examples/Nemotron-3-Super-Getting-Started-Guide
SQL LoRA Fine-tuning and Deployment

End-to-end LoRA fine-tuning of Nemotron 3 Nano on Text2SQL (BIRD SQL) with deployment via NVIDIA NIM or vLLM using NeMo AutoModel or Megatron Bridge.

https://github.com/NVIDIA-NeMo/nemotron/tree/main/use-case-examples/sql-lora-finetuning-and-deployment
Intelligent Document Processing

IDP pipeline that extracts and queries complex enterprise documents — financial reports, charts, and tables — using NeMo Retriever and multimodal Nemotron models.

https://github.com/NVIDIA-NeMo/nemotron/tree/main/use-case-examples/Intelligent%20Document%20Processing%20with%20Nemotron%20RAG
Voice RAG Agent

End-to-end voice-driven RAG agent combining speech-to-text, multimodal retrieval, 1M-token reasoning, and safety guardrails using open Nemotron models.

https://github.com/NVIDIA-NeMo/nemotron/tree/main/use-case-examples/nemotron-voice-rag-agent-example
Simple Nemotron 3 Nano Usage

Introductory notebook covering basic inference, reasoning mode toggling, and multi-agent systems using the OpenAI-compatible API via OpenRouter and LangChain.

https://github.com/NVIDIA-NeMo/nemotron/tree/main/use-case-examples/Simple%20Nemotron-3-Nano%20Usage%20Example
Data Science ML Agent

Natural language-driven ML agent built on Nemotron Nano 9B with GPU-accelerated data exploration and model training using RAPIDS cuDF and cuML.

https://github.com/NVIDIA-NeMo/nemotron/tree/main/use-case-examples/Data%20Science%20ML%20Agent
RAG Agent

Production-ready RAG agent using local Hugging Face embedding and reranking models with NVIDIA AI Endpoints for LLM inference, built on LangGraph.

https://github.com/NVIDIA-NeMo/nemotron/tree/main/use-case-examples/RAG%20Agent%20with%20Nemotron%20RAG%20Models