Building a Gen AI product for enterprise requirements may seem easy at first, but when you start thinking about deployment at scale in an enterprise production environment - things can get more complicated.
In this talk I will show how Vectara tackles this problem and makes it easy to build a GenAI application with Vectara, based on the RAG or retrieval-augmented-generation flow. For this example, I will use the yelp reviews dataset and will show how to configure vectara-ingest to crawl and ingest this data, and how to use vectara-answer to build a question-answering user interface around the data ingested.
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).