Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/cyclotron-azure/ai-accelerators

Generative AI Accelerators
https://github.com/cyclotron-azure/ai-accelerators

accelerators azure azureopenai generative-ai microsft

Last synced: about 1 month ago
JSON representation

Generative AI Accelerators

Awesome Lists containing this project

README 

        
# AI Accelerators Repositories



This repository contains a list of AI accelerators repositories.



| Name | URL | Description | Language | Summary |

|------|-----|-------------|----------|---------|

| llama-index-python | [https://github.com/Azure-Samples/llama-index-python](https://github.com/Azure-Samples/llama-index-python) | This sample shows how to quickly get started with LlamaIndex.ai on Azure🚀| Python | 1. **Case Scenario:** The primary use case for this project is to help users quickly get started with LlamaIndex.ai on Azure by building a serverless Azure OpenAI application. The app focuses on creating a Retrieval-Augmented Generation (RAG) chatbot that can answer questions about user-provided data, integrating it with various data sources like local files, websites, or databases. This project can be used as a starting point for developing more complex RAG applications. |

| graphrag-accelerator | [https://github.com/Azure-Samples/graphrag-accelerator](https://github.com/Azure-Samples/graphrag-accelerator) | One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure| Python | **Case Scenario:** The project "graphrag-accelerator" is designed for the one-click deployment of a Knowledge Graph powered RAG (GraphRAG) in Azure. This solution accelerator builds on the graphrag Python package and provides API endpoints hosted on Azure, which enable the triggering of indexing pipelines and querying the graphrag knowledge graph. This is intended for users and developers looking to quickly set up and utilize a powerful knowledge graph in their Azure environments. |

| gpt-video-analysis-in-a-box | [https://github.com/Azure-Samples/gpt-video-analysis-in-a-box](https://github.com/Azure-Samples/gpt-video-analysis-in-a-box) | | Bicep | 1. **Case Scenario:** The project is designed to facilitate image and video analysis using Azure OpenAI GPT-4 Turbo with Vision and Azure Data Factory. This solution is aimed at accelerating the deployment of AI and ML solutions by simplifying the adoption of AI technologies. It is intended for scenarios such as assessing insurance claims, identifying product defects in manufacturing, tracking store traffic for business analytics, and monitoring animal movement in nature preserves. The project offers a low-code solution for orchestrating Azure OpenAI service calls and |

| openai-chat-app-entra-auth-builtin | [https://github.com/Azure-Samples/openai-chat-app-entra-auth-builtin](https://github.com/Azure-Samples/openai-chat-app-entra-auth-builtin) | A simple chat application that integrates Microsoft Entra ID for user authentication. Designed for deployment on Azure Container Apps with the Azure Developer CLI.| Python | 1. **Case Scenario:** A simple chat application that integrates Microsoft Entra ID for user authentication, designed for deployment on Azure Container Apps using the Azure Developer CLI. |

| azure-functions-openai-extension | [https://github.com/Azure/azure-functions-openai-extension](https://github.com/Azure/azure-functions-openai-extension) | An extension that adds support for Azure OpenAI/ OpenAI bindings in Azure Functions for LLM (GPT-3.5-Turbo, GPT-4, etc)| C# | 1. **Case Scenario:** The "azure-functions-openai-extension" project is an extension designed to add support for integrating Azure OpenAI and OpenAI bindings within Azure Functions. This allows developers to utilize large language models (LLM) like GPT-3.5-Turbo and GPT-4 in their Azure Functions instances for various tasks such as text completion, chat completions, embedding generation, and semantic search. The extension aims to simplify the process of invoking OpenAI APIs by providing pre-defined bindings |

| enterprise-azureai | [https://github.com/Azure/enterprise-azureai](https://github.com/Azure/enterprise-azureai) | Unleash the power of Azure AI to your application developers in a secure & manageable way with Azure API Management and Azure Developer CLI.| TypeScript | **Case Scenario:** The GitHub project "Azure/enterprise-azureai" is intended to help organizations integrate Azure OpenAI into their applications securely and manageably using Azure API Management and Azure Developer CLI. It provides guidance and tools for setting up Azure OpenAI as a central capability, including infrastructure provisioning, CI/CD pipelines, secure access management, usage monitoring, and cost-control features. This repository aims to enable developers to harness Azure AI's capabilities while ensuring secure, cost-effective, and accountable usage across |

| agent-openai-python-prompty | [https://github.com/Azure-Samples/agent-openai-python-prompty](https://github.com/Azure-Samples/agent-openai-python-prompty) | A creative writing multi-agent solution to help users write articles.| Python | 1. **Case Scenario:** The primary use case for this project is to assist users in writing articles using a creative writing multi-agent solution. It leverages Azure OpenAI, Bing Search API, and Azure AI Search to research topics, find related products, and generate coherent and refined articles based on user-provided topics and instructions. |

| container-apps-dynamic-sessions-samples | [https://github.com/Azure-Samples/container-apps-dynamic-sessions-samples](https://github.com/Azure-Samples/container-apps-dynamic-sessions-samples) | Samples for Azure Container Apps dynamic sessions| Python | 1. **Case Scenario:** This project is intended for providing sample implementations of dynamic sessions in Azure Container Apps, with tutorials for various tools such as LangChain, LlamaIndex, Semantic Kernel, and AutoGen. |

| AI-Gateway | [https://github.com/Azure-Samples/AI-Gateway](https://github.com/Azure-Samples/AI-Gateway) | APIM ❤️ OpenAI - this repo contains a set of experiments on using GenAI capabilities of Azure API Management with Azure OpenAI and other services| Jupyter Notebook | **Case Scenario:** This project is intended for experiments exploring the use of Generative AI (GenAI) capabilities of Azure API Management in conjunction with Azure OpenAI and other services. The primary focus is on utilizing API Management strategies to maintain control, governance, and efficiency over AI service consumption, particularly for large language models (LLMs). It targets various advanced use cases, including model routing, load balancing, access control, token rate limiting, semantic caching, vector searching, response streaming, and more, |

| ai-hub-gateway-solution-accelerator | [https://github.com/Azure-Samples/ai-hub-gateway-solution-accelerator](https://github.com/Azure-Samples/ai-hub-gateway-solution-accelerator) | Reference architecture that provides a set of guidelines and best practices for implementing a central AI API gateway to empower various line-of-business units in an organization to leverage Azure AI services| Bicep | 1. Case Scenario: The primary use case for this project is to provide a reference architecture and best practices for implementing a centralized AI API gateway. The solution is designed to empower various line-of-business units within an organization to leverage Azure AI services in a secure, consistent, and scalable manner, while offering benefits such as centralized management, private connectivity, granular access control, and detailed observability. |

| rag-postgres-openai-python | [https://github.com/Azure-Samples/rag-postgres-openai-python](https://github.com/Azure-Samples/rag-postgres-openai-python) | A RAG app to ask questions about rows in a database table. Deployable on Azure Container Apps with PostgreSQL Flexible Server.| Python | 1. **Case Scenario:** This project is intended for creating a web-based chat application that utilizes OpenAI chat models to answer questions about entries in a PostgreSQL database table. It is designed to be deployed on Azure using Azure Container Apps and PostgreSQL Flexible Server. |

| contoso-chat-csharp-prompty | [https://github.com/Azure-Samples/contoso-chat-csharp-prompty](https://github.com/Azure-Samples/contoso-chat-csharp-prompty) | | Bicep | 1. **Case Scenario:** The project is intended to build, evaluate, and deploy a retail copilot application using Azure AI and Cosmos DB. It is designed for a conceptual store specializing in outdoor gear for hiking and camping enthusiasts, aimed to enhance customer engagement and sales support through an intelligent chat agent. The application integrates artificial intelligence to provide personalized and relevant responses to customers, drawing from a comprehensive product catalog and customer purchase histories. |

| summarization-openai-csharp-prompty | [https://github.com/Azure-Samples/summarization-openai-csharp-prompty](https://github.com/Azure-Samples/summarization-openai-csharp-prompty) | This solution converts speech to text and then processes and summarizes the text based on the prompt scenario.| Bicep | 1. **Case Scenario:** The primary use case for this project is to provide a solution for companies (e.g., Contoso Manufacturing) to report issues via text or speech. The solution converts speech to text, summarizes the important information, and specifies the department the report should be sent to. It leverages Azure AI Speech Service for speech-to-text translation and Azure OpenAI for text summarization. |

| aihub | [https://github.com/Azure/aihub](https://github.com/Azure/aihub) | AI Hub Executive Demo HandsOn| HTML | 1. **Case Scenario:** The AI Hub Executive Demo HandsOn project is designed to demonstrate the capabilities of various Azure AI services through multiple use cases. These use cases include chat-based document search and retrieval, call center call transcript analysis, image analysis, brand reputation analysis, document form analysis, document comparison, and content safety moderation. The project showcases how to build and deploy AI and machine learning solutions using Azure OpenAI, Cognitive Search, Container Apps, and other Azure services for scalable and intelligent applications. |

| agent-python-openai-prompty-langchain | [https://github.com/Azure-Samples/agent-python-openai-prompty-langchain](https://github.com/Azure-Samples/agent-python-openai-prompty-langchain) | Function calling for vector database lookup based on user question| Bicep | 1. **Case Scenario:** The primary use case for this project is to create a language model search agent that utilizes Retrieval-Augmented Generation (RAG) technology to answer user questions by performing vector database lookups using Elasticsearch and combining retrieved information with generative responses. This is accomplished by integrating Prompty, Langchain, and Elasticsearch within an Azure AI service. |

| private-openai-with-apim-for-chargeback | [https://github.com/Azure-Samples/private-openai-with-apim-for-chargeback](https://github.com/Azure-Samples/private-openai-with-apim-for-chargeback) | Open AI with Private Endpoints behind APIM and functionality to get tokens consumption for each consumer| Bicep | 1. **Case Scenario:** The project provides a solution for hosting Azure OpenAI instances privately within a customer’s Azure tenancy, using Azure API Management (APIM) to monitor and control access. It includes functionalities to measure and report token consumption for each user, allowing for chargeback and auditing within enterprises. It emphasizes secure and centralized access to Azure OpenAI services with tools to monitor usage and ensure data security through private endpoints. |

| serverless-chat-langchainjs | [https://github.com/Azure-Samples/serverless-chat-langchainjs](https://github.com/Azure-Samples/serverless-chat-langchainjs) | Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure| TypeScript | **Case Scenario:** The primary use case for the project is to build a serverless AI chat application that leverages Retrieval-Augmented Generation (RAG) using LangChain.js and Azure. The application allows users to deploy a scalable and cost-effective chatbot that can generate responses using enterprise documents hosted on Azure services. This project is intended for developers looking to create AI-driven chat experiences, particularly for enterprise applications, by utilizing serverless architecture and advanced document retrieval and response generation techniques. |

| GPT-RAG | [https://github.com/Azure/GPT-RAG](https://github.com/Azure/GPT-RAG) | Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.| Bicep | **Case Scenario:** The Azure/GPT-RAG project is intended for enabling Azure OpenAI at enterprise scale in a secure manner. It uses a Retrieval-Augmented Generation (RAG) pattern running in Azure, leveraging Azure Cognitive Search for data retrieval and Azure OpenAI large language models to create ChatGPT-style and Q&A experiences. It is designed to facilitate businesses in processing and generating responses based on new data without the need for fine-tuning, through a robust architecture that emphasizes availability, scalability, and |

| azure-sql-db-session-recommender-v2 | [https://github.com/Azure-Samples/azure-sql-db-session-recommender-v2](https://github.com/Azure-Samples/azure-sql-db-session-recommender-v2) | Build a Retrieval Augmented Generation solution using OpenAI, Azure Functions, Azure Static Web Apps, Azure SQL DB, Data API builder and Text Embeddings| Bicep | 1. **Case Scenario:** This project is intended to build a session recommender using Retrieval Augmented Generation (RAG) with OpenAI and Azure-based infrastructure. The session recommender stores and searches vector embeddings in an Azure SQL Database and is designed using Jamstack and Event-Driven architecture. It uses Azure Static Web Apps, Azure Functions, Azure SQL Database, and Data API builder to deliver a fully functional, production-ready solution. |

| AzureOpenAILogProbs | [https://github.com/bartczernicki/AzureOpenAILogProbs](https://github.com/bartczernicki/AzureOpenAILogProbs) | Examples of how-to use Azure OpenAI Log Probabilities (LogProbs) feature to enhance Generative AI - Q&A grounding.| C# | 1. **Case Scenario:** The primary use case for this project is to utilize the Azure OpenAI Log Probabilities (LogProbs) feature to enhance Generative AI applications, specifically for Q&A grounding. It involves methods to determine the confidence and accuracy of the AI's responses through techniques such as calculating token probabilities, Brier scores, weighted confidence scores, and confidence intervals. |

| azureai-assistant-tool | [https://github.com/Azure-Samples/azureai-assistant-tool](https://github.com/Azure-Samples/azureai-assistant-tool) | The Azure AI Assistant Tool is experimental Python application and middleware designed to simplify the development, experimentation, testing, and debugging of OpenAI assistants.| Python | **Case Scenario:** The Azure AI Assistant Tool is designed to simplify the development, experimentation, testing, and debugging of OpenAI assistants. It is an experimental Python application and middleware created to help developers quickly build and improve AI-powered copilot applications using the Azure OpenAI Assistants API. Suitable applications include creating AI-powered product recommenders, sales analyst apps, coding assistants, employee Q&A chatbots, and more. |

| Build-Modern-AI-Apps | [https://github.com/Azure/Build-Modern-AI-Apps](https://github.com/Azure/Build-Modern-AI-Apps) | Microsoft Official Build Modern AI Apps reference solutions and content. Demonstrate how to build Copilot applications that incorporate Hero Azure Services including Azure OpenAI Service, Azure Container Apps (or AKS) and Azure Cosmos DB for NoSQL with Vector Search.|  | **Case Scenario:** Demonstrating how to build Copilot applications using Hero Azure Services, specifically targeting AI-enabled applications. It includes reference solutions and content for integrating services such as Azure OpenAI Service, Azure Container Apps (or AKS), and Azure Cosmos DB for NoSQL with Vector Search. The project also provides solution accelerators and hackathons for building prototypes and learning the technical skills needed for Generative-AI applications in various scenarios like retail, payment processing, and medical claims processing. |

| openai-apim-lb | [https://github.com/Azure-Samples/openai-apim-lb](https://github.com/Azure-Samples/openai-apim-lb) | Smart load balancing for OpenAI endpoints and Azure API Management| Bicep | **Case Scenario:** This project addresses the challenge of API call limits and rate limiting by implementing a smart load balancing solution for managing OpenAI endpoints through Azure API Management. It dynamically reroutes traffic to non-throttling backends based on priority and availability, ensuring efficient usage of quotas and maintaining application performance. |

| openai-aca-lb | [https://github.com/Azure-Samples/openai-aca-lb](https://github.com/Azure-Samples/openai-aca-lb) | Smart load balancing for Azure OpenAI endpoints| Bicep | 1. **Case Scenario:** The project is designed for smart load balancing for Azure OpenAI endpoints. It aims to manage and optimize API request distribution among multiple OpenAI backends, addressing issues like throttling and ensuring efficient usage of provisioned and fallback resources. This is particularly useful in scenarios where service limits (token per minute and requests per minute) might be exhausted, as it dynamically reroutes requests to available endpoints. |

| Microsoft-Semantic-Kernel-Community-dotnet | [https://github.com/Azure-AI-Community/Microsoft-Semantic-Kernel-Community-dotnet](https://github.com/Azure-AI-Community/Microsoft-Semantic-Kernel-Community-dotnet) | | C# | **Case Scenario:** The Microsoft-Semantic-Kernel-Community project is designed as a versatile platform that supports various plugins and connectors, enabling functionalities like YouTube video searches, speech-to-text conversion, text translation, and more. This is primarily intended for developers looking to integrate these functionalities into their applications using the Microsoft Semantic Kernel NuGet package. |

| ai-rag-chat-evaluator | [https://github.com/Azure-Samples/ai-rag-chat-evaluator](https://github.com/Azure-Samples/ai-rag-chat-evaluator) | Tools for evaluation of RAG Chat Apps using Azure AI Evaluate SDK and OpenAI | Python | 1. **Case Scenario:** Tools for evaluating RAG (Retrieval-Augmented Generation) Chat Apps using the Azure AI Evaluate SDK and OpenAI. |

| SQL-AI-samples | [https://github.com/Azure-Samples/SQL-AI-samples](https://github.com/Azure-Samples/SQL-AI-samples) | Samples using AI and Azure SQL DB| HTML | The primary use case for the Azure-Samples/SQL-AI-samples GitHub repository is to provide sample applications and workflows that integrate AI with Azure SQL Database. These samples are designed to help users build AI-driven applications that leverage Azure SQL data along with other popular AI components within the Azure ecosystem, such as Azure OpenAI, Azure Cognitive Services, and Prompt Flow. They demonstrate technical concepts and methodologies, such as product recommendations, retrieval augmented generation (RAG), content moderation, and similarity searches, |

| azureai-samples | [https://github.com/Azure-Samples/azureai-samples](https://github.com/Azure-Samples/azureai-samples) | Official community-driven Azure AI Examples| Jupyter Notebook | 1. **Case Scenario:** The primary use case for Azure AI Samples is to provide developers with official, community-driven examples and sample code for using Azure AI. This repository includes notebooks and code snippets for various Azure AI scenarios, allowing developers to try out these examples on their local machines and potentially contribute to the repository. |

| contoso-web | [https://github.com/Azure-Samples/contoso-web](https://github.com/Azure-Samples/contoso-web) | Contoso Outdoors Company web application shown at Microsoft Ignite| TypeScript | **Case Scenario:** This project is intended as a web application for the Contoso Outdoors Company showcased at the Microsoft Ignite conference. The application features various chat functionalities, including regular chat, grounded chat, and visual chat. It is built using Next.js and Tailwind CSS and integrates multiple AI services, such as those from Azure, to enhance interaction and user experience. |

| AI-in-a-Box | [https://github.com/Azure/AI-in-a-Box](https://github.com/Azure/AI-in-a-Box) | | Jupyter Notebook | **Case Scenario:** The "AI-in-a-Box" project from Azure is designed to aid technical communities in rapidly establishing AI and ML environments and solutions with minimal friction. It provides curated solution accelerators aimed at speeding up deployment, maximizing cost savings, enhancing quality and reliability, and maintaining a competitive advantage. The project includes guidance and accelerators for various use cases such as MLOps, Edge AI, document processing, image and video analysis, cognitive services, chatbots, NLP to SQL conversions, |

| semantic-kernel-bot-in-a-box | [https://github.com/Azure/semantic-kernel-bot-in-a-box](https://github.com/Azure/semantic-kernel-bot-in-a-box) | Extensible Semantic Kernel Bot Solution Accelerator| C# | **Case Scenario:** The primary use case for the "Semantic Kernel Bot in-a-box" project is to deploy an extensible bot template to Azure, which leverages Azure Bot Services, a .NET application with a Semantic Kernel Stepwise Planner, and Azure OpenAI for handling and routing user messages. This setup is particularly suited for applications requiring integration and processing of varied data sources like Cognitive Search or Azure SQL and aims to support functionalities such as knowledge retrieval, structured data retrieval, document uploading, and image |

| intro-to-intelligent-apps | [https://github.com/Azure/intro-to-intelligent-apps](https://github.com/Azure/intro-to-intelligent-apps) | This repository introduces and helps organizations get started with building Intelligent Apps and incorporating Large Language Models (LLMs) via AI Orchestration into them.| Jupyter Notebook | 1. **Case Scenario:** The primary use case for this project is to help organizations get started with building Intelligent Apps and incorporating Large Language Models (LLMs) via AI Orchestration. Specifically, it involves practicing realistic AI orchestration scenarios, using prompt engineering techniques, leveraging AI orchestrators, and enhancing LLM responses with business data and context. |

| aoai-net-starterkit | [https://github.com/Azure-Samples/aoai-net-starterkit](https://github.com/Azure-Samples/aoai-net-starterkit) | Azure OpenAI Starter Kit for .NET Developers| C# | **Case Scenario:** The Azure OpenAI Starter Kit for .NET Developers is designed to help developers integrate AI capabilities into their applications using Azure AI services like Azure OpenAI. It provides instructional polyglot notebooks to explain fundamental concepts and more intricate end-to-end scenarios, serving as practical templates for application development. The kit is particularly aimed at infusing existing applications with AI or building new AI-powered applications from scratch. |

| Vector-Search-AI-Assistant | [https://github.com/Azure/Vector-Search-AI-Assistant](https://github.com/Azure/Vector-Search-AI-Assistant) | Microsoft Official Build Modern AI Apps reference solutions and content. Demonstrate how to build Copilot applications that incorporate Hero Azure Services including Azure OpenAI Service, Azure Container Apps (or AKS) and Azure Cosmos DB for NoSQL with Vector Search.| C# | 1. **Case Scenario:** This project is designed to demonstrate how to build modern AI applications, specifically Copilot applications, using key Azure services including Azure OpenAI Service, Azure Container Apps (or AKS), and Azure Cosmos DB for NoSQL with Vector Search. The primary scenario illustrated is an "Intelligent Agent" for a retail bike shop, showcasing a generative AI solution that can handle tasks such as managing conversational context, performing vector searches, and integrating transactional data with Azure services. |

| communication-services-AI-customer-service-sample | [https://github.com/Azure-Samples/communication-services-AI-customer-service-sample](https://github.com/Azure-Samples/communication-services-AI-customer-service-sample) | A sample app for the customer support center running in Azure, using Azure Communication Services and Azure OpenAI for text and voice bots.| C# | 1. **Case Scenario:** This project is intended as a sample application for a customer support center. It showcases the integration of Azure Communication Services and Azure OpenAI to create intelligent text and voice bots. The application aims to facilitate customer interactions, including answering questions, initiating calls, and providing summaries using a company's knowledge base and customer conversation data. |

| azure-search-openai-javascript | [https://github.com/Azure-Samples/azure-search-openai-javascript](https://github.com/Azure-Samples/azure-search-openai-javascript) | A TypeScript sample app for the Retrieval Augmented Generation pattern running on Azure, using Azure AI Search for retrieval and Azure OpenAI and LangChain large language models (LLMs) to power ChatGPT-style and Q&A experiences.| TypeScript | 1. **Case Scenario:** The project provides a sample application meant for creating ChatGPT-like and Q&A experiences using the Retrieval Augmented Generation pattern. It utilizes Azure AI Search for data retrieval and Azure OpenAI, along with LangChain large language models (LLMs), tailored for scenarios such as customer support interaction where users can ask questions and receive answers based on indexed data. The sample uses a fictitious company called Contoso Real Estate and includes documents such as terms of service, privacy policy, |

| azure-openai-rag-workshop | [https://github.com/Azure-Samples/azure-openai-rag-workshop](https://github.com/Azure-Samples/azure-openai-rag-workshop) | Create your own ChatGPT with Retrieval-Augmented-Generation workshop| Bicep | 1. **Case Scenario:** The primary use case of this repository is to demonstrate how to build an AI chat experience using Retrieval-Augmented Generation (RAG) with OpenAI language models. This is done through a workshop that guides users to create their own ChatGPT-like application, utilizing Azure services such as Azure Static Web Apps, Azure Container Apps, and Azure AI Search, along with LangChain.js and Fastify. |

| azure-search-power-skills | [https://github.com/Azure-Samples/azure-search-power-skills](https://github.com/Azure-Samples/azure-search-power-skills) | A collection of useful functions to be deployed as custom skills for Azure Cognitive Search| C# | 1. **Case Scenario:** This project is intended for developers working with Azure Cognitive Search (renamed Azure AI Search) who need to deploy custom skills to enhance the search capabilities. The collection of skills can be used as templates or starting points, or they can be applied directly if they fit the requirements. These skills cover various functions like text analysis, image processing, and utility operations, aiming to improve search functionality and data processing. |

| openai-at-scale | [https://github.com/Azure/openai-at-scale](https://github.com/Azure/openai-at-scale) | Simple ChatGPT UI application| TypeScript | 1. **Case Scenario:** The primary use case for this project is to help customers build and deploy a simple ChatGPT UI application on Azure. This involves setting up a user interface for ChatGPT, configuring system prompts and hyperparameters, authenticating users with Azure Active Directory, collecting application logs with Azure Log Analytics, and optionally storing prompt log data in Azure Cosmos DB. It is intended as a practical guide and workshop for leveraging Azure resources to create scalable AI-based applications. |

| azure-openai-samples | [https://github.com/Azure/azure-openai-samples](https://github.com/Azure/azure-openai-samples) | Azure OpenAI Samples is a collection of code samples illustrating how to use Azure Open AI in creating AI solution for various use cases across industries. This repository is mained by a community of volunters. We welcomed your contributions. | Jupyter Notebook | 1. **Case Scenario:** The primary use case for the Azure OpenAI Samples project is to provide code samples and resources for developers to illustrate how to use Azure OpenAI in creating AI solutions for various use cases across industries. The repository features examples such as chatbots, customer service, content generation, question answering, text summarization, and sentiment analysis, aimed at easing the integration of GPT-3.5 and soon GPT-4 into business applications. |

| aistudio-copilot-sample | [https://github.com/Azure/aistudio-copilot-sample](https://github.com/Azure/aistudio-copilot-sample) | Sample quickstart repo for getting started building an enterprise chat copilot in Azure AI Studio| Python | 1. **Case Scenario:** This project is intended as a sample quickstart repository for building an enterprise chat copilot using Azure AI Studio. It aims to guide users through setting up their development environment, creating Azure AI resources, building search indexes, running sample copilots, evaluating results, and deploying the implementation. The copilot can leverage company data and APIs to provide tailored responses and intelligence. |

| azure-search-vector-samples | [https://github.com/Azure/azure-search-vector-samples](https://github.com/Azure/azure-search-vector-samples) | A repository of code samples for Vector search capabilities in Azure AI Search.| Jupyter Notebook | **Case Scenario:** The Azure/azure-search-vector-samples project is intended for demonstrating and providing code samples for utilizing vector search capabilities in Azure AI Search. This includes vector indexing, vector queries, data chunking, embedding, and various other features related to enhancing search functionalities using vector data. It supports multiple programming languages such as Python, C#, JavaScript, and Java and offers various examples for integrating vector search with Azure's ecosystem. |

| azure-search-knowledge-mining | [https://github.com/Azure-Samples/azure-search-knowledge-mining](https://github.com/Azure-Samples/azure-search-knowledge-mining) | Azure Search Knowledge Mining Accelerator| CSS | 1. **Case Scenario:** The primary use case for the Azure Search Knowledge Mining Accelerator project is to help developers quickly build an initial Knowledge Mining prototype using Azure AI Search. This includes providing templates and resources for deploying Azure resources, creating search indexes, developing custom skills, and creating a web app and reports to monitor search solution performance, thus facilitating effective data indexing and exploration. |

| azure-sql-db-openai | [https://github.com/Azure-Samples/azure-sql-db-openai](https://github.com/Azure-Samples/azure-sql-db-openai) | Samples on how to use Azure SQL database with Azure OpenAI| TSQL | 1. **Case Scenario:** The project demonstrates how to use an Azure SQL database in conjunction with Azure OpenAI to perform vector similarity searches. This involves generating vector embeddings for text using Azure OpenAI and calculating cosine similarity to find related topics, particularly applied to Wikipedia articles. |

| Build-Modern-AI-Apps-Hackathon | [https://github.com/Azure/Build-Modern-AI-Apps-Hackathon](https://github.com/Azure/Build-Modern-AI-Apps-Hackathon) | A 1-2 day hackathon to help users learn the concepts and technical skills to build AI-enabled applications and services in Azure.| C# | 1. **Case Scenario:** The project is intended for a 1-2 day hackathon aimed at helping users learn the concepts and technical skills required to build AI-enabled applications and services in Azure. Specifically, the scenario centers around creating a proof of concept (POC) for a chat interface with an "Intelligent Agent" that allows users to ask questions and retrieve product and account information using data stored in Azure Cosmos DB. |

| semantic-kernel-rag-chat | [https://github.com/Azure-Samples/semantic-kernel-rag-chat](https://github.com/Azure-Samples/semantic-kernel-rag-chat) | Tutorial for ChatGPT + Enterprise Data with Semantic Kernel, OpenAI, and Azure Cognitive Search| C# | 1. **Case Scenario:** The primary use case of this project is to build an AI chat application that leverages enterprise data, using Semantic Kernel, OpenAI, and Azure Cognitive Search. The tutorial guides users through developing a ChatGPT-like application that can ingest, index, and retrieve enterprise data to provide more accurate and contextually relevant responses. This involves integrating various technologies and creating a minimal implementation for enterprise data ingestion, long-term memory, plugins, and more. |

| azure-search-openai-demo | [https://github.com/Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo) | A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models  to power ChatGPT-style and Q&A experiences.| Python | 1. **Case Scenario:** This project is intended to create ChatGPT-style and Q&A experiences using the Retrieval-Augmented Generation pattern. It leverages Azure AI Search for data retrieval and Azure OpenAI's large language models to handle queries and generate answers, particularly useful within organizational settings to help employees access information about benefits, internal policies, job descriptions, and roles. |

| intelligent-app-workshop | [https://github.com/Azure/intelligent-app-workshop](https://github.com/Azure/intelligent-app-workshop) | Immersive workshop showcasing the remarkable potential of integrating SoTA foundation models to enhance product experiences and streamline backend workflows. Leverages Microsoft's Copilot stack, Semantic Kernel and Azure primitives to offer an engaging and comprehensive introduction to AI-infused app development and deployment| Python | 1. **Case Scenario:** This project is an immersive workshop designed to showcase the potential of integrating state-of-the-art foundation models to enhance product experiences and optimize backend workflows. It leverages Microsoft's Copilot stack, Semantic Kernel, and Azure services to provide a comprehensive introduction to AI-driven app development and deployment. |

| openai-chat-app-quickstart | [https://github.com/Azure-Samples/openai-chat-app-quickstart](https://github.com/Azure-Samples/openai-chat-app-quickstart) | A simple chat application that uses managed identity for Azure OpenAI access. Designed for deployment on Azure Container Apps with the Azure Developer CLI.| Bicep | 1. **Case Scenario:** The primary use case for this project is to provide a simple chat application that leverages Azure OpenAI with managed identity for secure and efficient access. It is designed for easy deployment on Azure Container Apps using the Azure Developer CLI. |

| chat-with-your-data-solution-accelerator | [https://github.com/Azure-Samples/chat-with-your-data-solution-accelerator](https://github.com/Azure-Samples/chat-with-your-data-solution-accelerator) | A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.| Python | 1. **Case Scenario:** The primary use case for this project is to provide a solution accelerator for creating a conversational search experience using Azure AI Search and Azure OpenAI large language models. The main aim is to enable users to query their own data with natural language through a ChatGPT-style interface, which includes common requirements and best practices for setting up and deploying such a system. This tool is suitable for developers looking to customize and implement the Retrieval Augmented Generation (RAG) pattern for various business applications |

| miyagi | [https://github.com/Azure-Samples/miyagi](https://github.com/Azure-Samples/miyagi) | Sample to envision intelligent apps with Microsoft's Copilot stack for AI-infused product experiences.| Jupyter Notebook | 1. **Case Scenario:** The primary use case of the project "miyagi" is to envision and develop intelligent applications utilizing Microsoft's Copilot stack for AI-infused product experiences. The project offers a comprehensive workshop aimed at designing, developing, and deploying enterprise-grade intelligent apps, integrating generative and traditional machine learning models to enhance productivity and personalization. |

| qdrant-azure | [https://github.com/Azure-Samples/qdrant-azure](https://github.com/Azure-Samples/qdrant-azure) | Qdrant Vector Database on Azure Cloud| Shell | 1. **Case Scenario:** This project is designed to facilitate the deployment of the Qdrant Vector Database on Microsoft Azure Cloud. It aims to integrate Vector Search and Embeddings storage into AI products by leveraging Azure Kubernetes Service or Docker for both local and cloud environments. Users can deploy Qdrant using containers either locally via Docker or in the cloud using Azure's Kubernetes or Container Services. |

| contoso-real-estate | [https://github.com/Azure-Samples/contoso-real-estate](https://github.com/Azure-Samples/contoso-real-estate) | Intelligent enterprise-grade reference architecture for JavaScript, featuring OpenAI integration, Azure Developer CLI template and Playwright tests.| JavaScript | 1. **Case Scenario:** This project is designed as an intelligent enterprise-grade reference architecture for JavaScript applications. It features OpenAI integration, an Azure Developer CLI template, and Playwright tests. The architecture supports modern composable frontends, cloud-native applications, AI chatbots, payment integration with Stripe, real-time notifications, and a headless CMS and blog. |

| azure-search-openai-demo-csharp | [https://github.com/Azure-Samples/azure-search-openai-demo-csharp](https://github.com/Azure-Samples/azure-search-openai-demo-csharp) | A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. | C# | 1. **Case Scenario:** This project is intended for creating ChatGPT-style and Q&A experiences over a user's own data leveraging the Retrieval-Augmented Generation pattern. It uses Azure Cognitive Search for data indexing and retrieval and Azure OpenAI Service for generating responses with large language models. The main use case is to build intelligent applications that allow querying and interacting with internal data, demonstrated with a fictitious company scenario in the sample app. |

| AzureSpeechReactSample | [https://github.com/Azure-Samples/AzureSpeechReactSample](https://github.com/Azure-Samples/AzureSpeechReactSample) | This sample shows how to integrate the Azure Speech service into a sample React application. This sample shows design pattern examples for authentication token exchange and management, as well as capturing audio from a microphone or file for speech-to-text conversions.| JavaScript | 1. **Case Scenario:** Integrate Azure Speech service into a sample React application. The project demonstrates design patterns for authentication token exchange and management, and provides functionality to capture audio from a microphone or a file for speech-to-text conversions. |

| azure-search-javascript-samples | [https://github.com/Azure-Samples/azure-search-javascript-samples](https://github.com/Azure-Samples/azure-search-javascript-samples) | Azure Search Javascript sample code| JavaScript | 1. **Case Scenario:** This project provides sample JavaScript code for working with Azure Cognitive Search. It includes examples such as creating, loading, and querying a search index, as well as adding search functionality to a web application. These samples are designed for developers to get started with Azure AI Search services using Node.js and related technologies. |

| azure-search-dotnet-samples | [https://github.com/Azure-Samples/azure-search-dotnet-samples](https://github.com/Azure-Samples/azure-search-dotnet-samples) | Azure Search .NET sample code| C# | **Case Scenario:** This project provides C# sample code to demonstrate the use of Azure AI Search, primarily for creating, loading, and querying search indexes. It includes quickstarts and tutorials for scenarios such as full text search, semantic search, AI enrichment pipelines, server-side search behaviors, and building search-capable websites. The samples are primarily intended to help developers get started with Azure AI Search functionalities and implement those capabilities in .NET applications. |

| Serverless-microservices-reference-architecture | [https://github.com/Azure-Samples/Serverless-microservices-reference-architecture](https://github.com/Azure-Samples/Serverless-microservices-reference-architecture) | This reference architecture walks you through the decision-making process involved in designing, developing, and delivering a serverless application using a microservices architecture through hands-on instructions for configuring and deploying all of the architecture's components along the way. The goal is to provide practical hands-on experience in working with several Azure services and the technologies that effectively use them in a cohesive and unified way to build a serverless-based microservices architecture.| C# | 1. **Case Scenario:** The project is designed to provide practical, hands-on experience in designing, developing, and delivering a serverless application using a microservices architecture, specifically in the context of building a ride share application for a fictional company, Relecloud. This involves deploying and configuring various Azure services as part of a comprehensive serverless-based microservices architecture. The project aims to educate users on effective use of serverless technologies, microservices patterns, and Azure components to build scalable applications with minimal |

| azd-ai-starter | [ https://github.com/Azure-Samples/azd-ai-starter]( https://github.com/Azure-Samples/azd-ai-starter) |  Creates an Azure AI Service and deploys the specified models. |  Bicep | 1. **Case Scenario:** Creates an Azure AI Service and deploys the specified models. |