Explore innovative ways to build robust applications using Azure Cosmos DB. Dive into an exciting demo that showcases the use of the Retrieval-Augmented Generation (RAG) pattern for integrating Azure OpenAI services with custom data stored in Azure Cosmos DB NoSQL API. In this session, we'll demonstrate how to leverage a vector database within a NoSQL database to store, index, and query embeddings alongside their corresponding original data. This integration offers a streamlined solution, eliminating the need for a separate pure vector database and reducing extra costs associated with data replication. By keeping the vector embeddings and original data together, we not only enhance data consistency but also enable seamless multi-modal data operations. This approach ensures superior scale and performance, allowing your applications to harness the full potential of both structured and unstructured data.
We will cover the following: - Introduction of Apache managed instance Cassandra, what is the offering about, features etc (Dileep). - A quick demo on how it will fit in todays AI with vector indexing and search capabilities. Short demo (Dileep). - Cassandra migration opportunities (Tomas)
In this session we will demonstrate & detail GraphSQL + Vector Search with Azure Cosmos DB
In this session we will walk you through the assessment and Mongo Migration tools and help understand the approach of migration
Demonstration and walkthrough of AI Agent solution focuses on Azure Cosmos DB
In this we will walk you through the monitoring metrics
In this we will walk you through the cost calculation and optimization strategies across all APIs and Mongo VCore
