RAG

Whether companies are manufacturing semiconductor chips, airplanes, automobiles, smartphones, or food or beverages, quality and throughput are key benefits of optimization.

Modern deep learning challenges leverage increasingly larger datasets and more complex models.

Agents powered by large language models (LLMs) have shown great retrieval capability for using tools, looking at documents, and plan their approaches.

Agents powered by large language models (LLMs) have shown great retrieval capability for using tools, looking at documents, and plan their approaches.

In this introductory course, we will provide a high-level overview of Retrieval Augmented Generation and how it improves Generative AI (GenAI).

The course focuses on teaching production-level deployment of LLM applications especially enterprise-grade deployment of RAG pipelines.

Learn techniques that can take your RAG system from an interesting proof-of-concept to a serious asset.

Retrieval-Augmented Generation (RAG) pipelines are revolutionizing enterprise operations.

Learn how to write, compile, and run GPU-accelerated code, leverage CUDA core libraries to harness the power of massive parallelism provided by modern GPU accelerators, optimize memory migration between CPU and GPU, and implement your own algorithms.

Bridge the gap between simulation and real-world robotics using ROS 2, Isaac Sim, and NVIDIA Jetson with HIL.

Learn how foundation models can reveal novel biological insights, while leveraging NVIDIA’s platform to accelerate the entire workflow for fast, scalable results.

As large language models (LLMs) and retrieval-augmented generation (RAG) systems become integral to enterprise AI applications, the need for rigorous, domain-aware evaluation grows rapidly.

Learn how clustering algorithms like K-Means, DBSCAN, and HDBSCAN are used to uncover patterns in data and power real-world applications, while leveraging NVIDIA GPUS to accelerate the entire workflow for fast, scalable results.

Learn how to integrate large language models (LLMs) with NVIDIA Inference Microservices (NIM) and cuGraph to create cutting-edge, graph-based AI solutions for handling complex, interconnected data.

Learn how to optimize vector database workloads on the GPU.

Paid live cohort from Maven covering RAG and LLM systems, sourced from Agentic AI for Engineers, Agentic AI for Product Managers.

Paid live cohort from Maven covering RAG and LLM systems, sourced from Agentic AI for Engineers.

DeepLearning.AI's official study resource covering RAG.

DeepLearning.AI's official study resource covering RAG and evaluation.

Microsoft Learn's official study resource covering RAG and copilots.

Microsoft Learn's official study resource covering RAG.

Perplexity's official cookbook with practical examples for building search-augmented AI experiences using the Perplexity API.

Learn retrieval pipelines, chunking, ranking, and evaluation for RAG applications.