Multimodal generative AI has recently seen significant advancements, enabling the creation of realistic images, videos, and audio from textual or other inputs. However, due to the complexity of these models, understanding how they function and how to apply them in practical settings can be challenging. During this talk, Ekaterina will shed light on the inner workings of multimodal generative AI models by discussing key concepts and techniques used in their development. She will also explore various applications and use cases of this technology. The talk is intended for anyone interested in the current state of AI and its potential to produce realistic and immersive multimedia experiences.

This session will focus on the application of OpenAI’s powerful language models in developing AI-powered applications. OpenAI embeddings provide a rich representation of natural language that can be used for a wide range of Natural Language Processing (NLP) tasks, including sentiment analysis, named entity recognition, and text classification. The session will begin with an overview of OpenAI embeddings and their capabilities. Next, we will build an end-to-end sample using OpenAI and Azure Search. By the end of the session, attendees will have a comprehensive understanding of how OpenAI embeddings can be used to develop intelligent applications and the benefits of incorporating them into their development workflows.

What comes after ChatGPT? Vector database projects like Weaviate, Pinecone, and Chroma recently got millions of dollars of funding for their projects. But what are vector databases? And why will they be so important in the future? Let us see how Vector Databases can help you define and run your machine learning business use cases. We will explore some real-world use cases and try to understand the potential of vectors and vector databases. Not exactly sure what a vector is ? No worries, you will learn everything you need about vectors . A brief hands-on demonstration just using open source will give you an idea, of how to use the new generation of databases in praxis. We will also cover how vector databases can work together with chatGPT and helps you to overcome some limitations of chatGPT.

Generative AI has taken the hard part of AI out of the lifecycle of AI products. There is so much abstraction, that it gets harder to decide what to do first, when the only programming language need is English. What should Product managers of large enterprises have to keep in mind, while evaluating models, and building for themselves Generative AI applications for 100,000 employees How Product managers can go about researching and building the best products for their teams and businesses Which methods worked for AI and Data product building at Google and at Telus.