Advanced7h 35m4 modules · 18 leçons0 inscrits

RAG with NIM and NeMo Guardrails

The NVIDIA variant of the RAG course: the same patterns, deployed on NIM microservices, accelerated with TensorRT-LLM, and secured with NeMo Guardrails. You'll compile, deploy, and constrain an enterprise RAG assistant — all the way to a sovereign deployment in an air-gapped environment. For anyone industrializing RAG on the NVIDIA stack.

Par Équipe Curriculum Nexus

149€

Accès complet · Certificat inclus

S'inscrire maintenant

Programme du cours

4 modules

01
Module
NIM & Enterprise RAG Foundations
NVIDIA NIM, NeMo Retriever embeddings, the OpenAI-compatible API, and the reference RAG architecture: the building blocks you'll use to construct a reliable enterprise document assistant.
5 leçons·2h 05

Module

Building the RAG pipeline

From a pile of documents to an assistant that answers: ingestion and chunking, embedding with NIM, a vector store, reranked retrieval, then generation — each stage built and tested for real.

4 leçons·1h 40

RAG with NIM and NeMo Guardrails

Programme du cours

NIM & Enterprise RAG Foundations

Building the RAG pipeline

Securing it with NeMo Guardrails

Production: deploying, securing, and running your RAG