A sample for implementing retrieval augmented generation using Azure Open AI to generate embeddings, Azure Cosmos DB for MongoDB vCore to perform vector search, and semantic kernel.

Multi-agents banking assistant with Dotnet and Semantic Kernel

This project demonstrates summarizing large documents with Azure OpenAI and Durable Functions, using a Fan-out/Fan-in pattern to process sections in parallel and compile a cohesive summary. It ensures scalable and efficient document handling with Azure services.

This repository offers a solution for deploying a Generative AI (GenAI) system on Azure using Retrieval-Augmented Generation (RAG). It features a RAG Chat API integrated with CosmosDB and HTML files, enabling customer support teams to resolve issues effectively.

Sample AI Agent built on Semantic Kernel SDK for Python, using APIM as AI gateway with load balanced AI Foundry backend instances.

Deploying a Retrieval-Augmented Generation (RAG) solution on Azure, featuring a RAG Chat API that uses customer data and technical HTML files to enhance customer support troubleshooting. It leverages Azure AI Search for vector storage and Azure OpenAI for model inference, ensuring security, scalability, and adherence to best practices.