Exploring Naive-RAG and Agentic RAG with Hands-On

Explore the transformative power of Generative AI in this exciting session, where we unravel the magic of Retrieval-Augmented Generation (RAG) in large language models (LLMs). Learn the basics of Naive RAG and Agentic RAG, discovering how these frameworks access vast knowledge bases to deliver precise answers. Through hands-on demonstrations, you’ll set up a Naive RAG system, store embeddings in vector databases, and query them with LLMs. Dive into Agentic RAG, where autonomous agents collaborate with tools to tackle complex queries. Gain practical insights to kickstart your journey in building cutting-edge GenAI applications!

Key Takeaways:

• Learn how Generative AI leverages Retrieval-Augmented Generation (RAG) for precise information retrieval and insights generation.
• Understand the fundamentals of Naive RAG and Agentic RAG, and their role in enhancing LLM capabilities.
• Gain hands-on experience in setting up Naive RAG systems, storing embeddings in vector databases, and querying with LLMs.
• Explore Agentic RAG, where autonomous agents collaborate with tools to process complex user queries, empowering GenAI application development.

Satyam Mittal is a Senior AI Engineer at Ascentt, Plano, TX, where he collaborates with clients to develop end-to-end AI applications in the domains of Retrieval-Augmented Generation (RAG) and Agentic RAG. He holds a research-oriented M.S. in Computer Science from California State University, where he extensively explored Machine Learning Metaheuristics. His research focused on designing a new version of the Buggy-Pinball Optimization Algorithm, aimed at determining global maxima and minima for complex optimization problems across continuous, non-continuous, and discrete domains in higher dimensions. Before pursuing his M.S., Satyam worked as a Senior Software Engineer at Paytm, India. You can reach him on LinkedIn.