All speakers

Ofer Mendelevitch

Head of Developer Relations, Vectara

Ofer Mendelevitch leads developer relations at Vectara. He has extensive hands-on experience in machine learning, data science and big data systems across multiple industries, and has focused on developing products using large language models since 2019. Prior to Vectara he built and led data science teams at Syntegra, Helix, Lendup, Hortonworks and Yahoo! Ofer holds a B.Sc. in computer science from Technion and M.Sc. in EE from Tel Aviv university, and is the author of "Practical data science with Hadoop" (Addison Wesley).

Ofer Mendelevitch

Sessions / 2025 / 1 talk

  • Building Enterprise Agentic RAG Applications with Reduced Hallucinations

    As AI continues to evolve, agentic frameworks are becoming essential tools for developing intelligent and autonomous systems that can reason, plan, and act dynamically. In this workshop, we will explore how to leverage Vectara’s Agentic RAG framework to build context-aware, AI assistants and agents, with reduced hallucinations that enhance productivity and automate enterprise workflows. We will provide a step-by-step walkthrough on how to build Agentic RAG applications, delving into the technical details with a real-world example, and discuss the challenges developers might face, such as reducing hallucinations. Whether you are an AI developer, researcher, or enthusiast, this workshop will equip you with the practical skills to harness agentic AI for your enterprise.

Sessions / 2024 / 1 talk

  • How to build a GenAI Application with Vectara - a Step-by-Step Guide

    Building a Gen AI enterprise product may seem easy at first, but when you need to consider scalability, security and upgrades in an enterprise production environment - things can get complicated pretty quickly. In this talk I will explain what retrieval augmented generation (RAG) is, how it helps reduce hallucinations, and why Vectara's RAG-as-a-service approach makes it easy to build a GenAI application at enterprise scale. I will show how to build a RAG application with Vectara step-by-step, using data from Richard Feynman's lectures on physics, and how tools like vectara-ingest and React-chat can help accelerate your success.

Ready to take this stage?

The next edition is programmed by practitioners. Tell us what you built and what you learned.

Apply to be a speaker