Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to build custom AI agents with an open-source Python library designed for developers creating agentic AI systems. This 19-minute tutorial from Nvidia demonstrates how to integrate agents, tools, and workflows as composable function calls, regardless of your underlying framework. Discover the toolkit's key features including its modular architecture, framework-agnostic design, custom agent definition capabilities, FastAPI integration, configuration-driven workflows, and distribution options. Follow along as the presenter walks through setting up a project workflow, creating a multi-RAG agent, instantiating a React agent, and deploying a FastAPI microservice. The tutorial provides practical guidance for both experienced developers and beginners looking to integrate advanced AI capabilities into their projects using this powerful toolkit that works with popular frameworks like LangGraph, CrewAI, and LangChain.
Syllabus
00:00 - Introduction
01:30 - Key Features of the Agent Intelligence Toolkit
03:45 - Setting Up Your Project with the Workflow
06:10 - Creating a Multi-RAG Agent
09:25 - Instantiating and Configuring a React Agent
12:40 - Setting Up a FastAPI Microservice
15:15 - Conclusion and Key Takeaways
Taught by
NVIDIA Developer