speaker detail

Ravi Theja

Developer Advocate Engineer

company logo

Ravi Theja is a Developer Advocate and AI Engineer at LlamaIndex. He has gained recognition for his work on Indic LLMs—Navarasa, which was showcased at GoogleIO. At LlamaIndex, Ravi implements the latest research papers, crafts insightful blog posts, interacts with developers on platforms such as GitHub and Discord, and supports clients like Springworks and Atomic Works in developing efficient RAG pipelines. Before joining LlamaIndex, he was a Senior Machine Learning Engineer, where he developed large-scale recommender systems and Generative AI applications. Holding a Master’s degree from IIIT-Bangalore in Deep Learning, NLP, and Computer Vision, he brings a wealth of expertise to the field of AI and machine learning. His thesis, “Generalised NLU using Attention Networks,” demonstrates his proficiency. Additionally, he won the NIPS-2017 Paper Implementation Challenge and achieved high rankings in competitions like the Microsoft India AI Challenge 2018.

This presentation will explore Agentic RAG, advancing beyond traditional Retrieval-Augmented Generation (RAG) systems to fully realized agent systems. We'll examine how conventional RAG systems, while effective in straightforward query scenarios, struggle with more complex, multifaceted questions that demand deep contextual understanding and dynamic response capabilities. By integrating advanced features such as query planning, contextual memory, and tool usage, Agentic RAG systems can handle sophisticated tasks beyond question-answering, including detailed comparisons and summarizations.

Additionally, we will discuss the development and capabilities of comprehensive agent systems that incorporate multiple layers of agentic reasoning for enhanced performance. These systems utilize multi-turn interactions, reflective learning, and personalization to significantly enhance functionality, enabling them to manage more nuanced and complex tasks.

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More
Book tickets View all speakers

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details