Session

Retrieval Augmented Generation (RAG) with Azure AI Search

In this presentation, we will explore the concept of Retrieval Augmented Generation (RAG) and how it can leveraged particularly in the context of enterprise solutions. RAG architecture provides the ability to create generative AI to your own proprietary content, which ensure that the information used to generate responses is tailored to specific business needs.

The key to a successful RAG architecture is the information retrieval system, which determines the inputs to the LLM. We will discuss the critical requirements for this system, including scalable indexing strategies, relevant query capabilities, security, global reach, and seamless integration with embedding and chat/language models. Azure AI Search emerges as the ideal solution. Microsoft offers several built-in approaches for using Azure AI Search in a RAG solution, such as Azure AI Studio, Azure OpenAI Studio, and Azure Machine Learning. We will also explore a custom RAG pattern that gives you more control over the architecture. This pattern outlines a step-by-step process of sending the user's prompt to Azure AI Search, retrieving the most relevant information, and then passing it to the LLM to generate the final response.

By the end of this presentation, you will have a comprehensive understanding of how to leverage Azure AI Search within a RAG architecture, empowering you to build enterprise-grade generative AI solutions that harness the power of your own proprietary content.

Nagaraj Sengodan

Solution Architect, Capgemini

Watford, United Kingdom

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top