This repository provides a production-ready, full-stack Retrieval-Augmented Generation (RAG) chat application built with Python FastAPI and React TypeScript. It demonstrates how to use Azure OpenAI (or OpenAI.com, or Ollama) to answer questions about data stored in Azure Database for PostgreSQL with the pgvector extension. The system supports both a simple RAG flow (embedding + direct search) and an advanced flow that uses OpenAI function calling to rewrite queries and apply column filters (brand, price). It features hybrid search combining full-text search and vector similarity via Reciprocal Rank Fusion. The backend is a monolith serving API endpoints and a React frontend, designed for deployment to Azure Container Apps using the Azure Developer CLI. The codebase includes comprehensive unit tests, end-to-end tests with Playwright, evaluation scripts, load testing with locust, and safety evaluation using Azure AI Red Teaming. The architecture is cleanly separated into reusable modules, making it a solid reference architecture for building RAG applications on Azure.

The AKS Store Demo is a polyglot microservices application designed to demonstrate deployment patterns on Azure Kubernetes Service (AKS). It simulates an online pet store where users can browse products, place orders, and administrators can manage inventory and view orders. The system comprises multiple independently deployable services: a Vue.js storefront and admin panel, a Node.js order service, a Go makeline service for order processing, a Rust product service for catalog management, a Python AI service for optional generative AI features, and Rust-based virtual customer and worker services for traffic simulation. Services communicate via REST APIs and a message queue (RabbitMQ or Azure Service Bus), with data persisted in DocumentDB (Azure Cosmos DB with MongoDB API). The application showcases strong engineering practices through its use of infrastructure-as-code (Terraform and Bicep), Kubernetes manifests managed via Kustomize for environment-specific configuration, and Azure Developer CLI (azd) hooks for automated provisioning and deployment. Each service includes health checks, Docker multi-stage builds, and observability hooks. The polyglot nature allows each service to use the most suitable language for its function, while the clear separation of concerns and well-defined interfaces enable independent development and scaling. The repository includes comprehensive unit, end-to-end, and traffic simulation tests to ensure reliability.

This repository contains a sophisticated COBOL modernization toolkit that uses AI agents to analyze, extract business logic from, and convert legacy COBOL code to modern Java (Quarkus) or C# (.NET) applications. The system features an agent-based architecture with specialized agents for structural analysis, business logic extraction, dependency mapping, and code conversion. It includes a web portal for monitoring migration progress, visualizing dependency graphs, and interacting with AI assistants. The toolkit handles large COBOL files through intelligent semantic chunking that preserves code context across chunks, and uses a hybrid persistence approach (SQLite for metadata, Neo4j for graph visualization) to store migration artifacts. Key innovations include a three-tier complexity reasoning system that dynamically adjusts AI effort based on code complexity, semantic unit-aware chunking, and cross-chunk consistency mechanisms for type mappings and signatures.

This repository implements a multi-agent orchestrator system for healthcare workflows, specifically designed for cancer care/tumor board scenarios. The system coordinates specialized AI agents (Patient History, Radiology, Patient Status, Clinical Guidelines, Report Creation, Clinical Trials, Medical Research) via Semantic Kernel group chat, with an Orchestrator agent facilitating collaboration. It provides both Microsoft Teams integration and a React/Vite web interface for user interaction. The architecture includes a Python/FastAPI backend handling WebSocket connections and Bot Framework messages, agent-specific tools for data access and external API integration, and an evaluation framework for assessing agent performance. Infrastructure is provisioned via Azure Bicep templates deploying AI services, storage, compute, and networking resources.