In this session we’ll walk you through how to build Generative AI applications in C# that can scale from the very small to a practically infinite level of size and scale. We will also cover many key concepts and implementation details required to build this new generation of applications including:

* Vector embeddings and how do they work in representing semantically similar data.
* Vectorize, index and store for effective and efficient vector queries to find semantically relevant data in a vector-enabled database.
* Enable natural conversational interactions with an LLM using a context window (chat history) for users.
* Manage request payload sizes for Azure OpenAI Service for effective token management.
* Building a semantic cache for improved performance and cost.

Growing from zero to infinity requires an architecture and design that can scale. We will cover key aspects for how to achieve this, including how to design a data model that can scale with a distributed NoSQL database, Azure Cosmos DB, which powers OpenAI's ChatGPT and allowed it to scale to 180M daily active users.

Throughout this session we will walk through the code for how to implement all of this and provide you with the code you need to learn and do this yourself.

If you want to learn how to build the next generation of AI-enabled applications in C# and Azure, attend this session to accelerate your AI readiness for the future!