{"id":13465472,"url":"https://github.com/Azure/AI-in-a-Box","last_synced_at":"2025-03-25T16:32:03.033Z","repository":{"id":207824906,"uuid":"685709378","full_name":"Azure/AI-in-a-Box","owner":"Azure","description":"AI-in-a-Box leverages the expertise of Microsoft across the globe to develop and provide AI and ML solutions to the technical community.  Our intent is to present a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction.","archived":false,"fork":false,"pushed_at":"2024-12-12T17:15:34.000Z","size":29055,"stargazers_count":562,"open_issues_count":16,"forks_count":191,"subscribers_count":23,"default_branch":"main","last_synced_at":"2025-03-23T23:35:17.010Z","etag":null,"topics":["ai","azd","azd-templates","azure","chat-bot","chatbot","chatgpt","custom-vision","document-intelligence","edge-ai","edge-computing","langchain","machine-learning","openai","semantic-kernel"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Azure.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":"SUPPORT.md","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-31T20:39:57.000Z","updated_at":"2025-03-20T17:41:36.000Z","dependencies_parsed_at":"2023-11-30T00:22:08.222Z","dependency_job_id":"7c2d8ad8-e2d6-437c-8781-e69af11380c4","html_url":"https://github.com/Azure/AI-in-a-Box","commit_stats":{"total_commits":293,"total_committers":17,"mean_commits":"17.235294117647058","dds":0.689419795221843,"last_synced_commit":"52ff38a2333df2ae1d918f0db4da18e9e717ca57"},"previous_names":["azure/ai-in-a-box"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Azure%2FAI-in-a-Box","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Azure%2FAI-in-a-Box/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Azure%2FAI-in-a-Box/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Azure%2FAI-in-a-Box/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Azure","download_url":"https://codeload.github.com/Azure/AI-in-a-Box/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245500321,"owners_count":20625555,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","azd","azd-templates","azure","chat-bot","chatbot","chatgpt","custom-vision","document-intelligence","edge-ai","edge-computing","langchain","machine-learning","openai","semantic-kernel"],"created_at":"2024-07-31T15:00:30.716Z","updated_at":"2025-03-25T16:32:02.348Z","avatar_url":"https://github.com/Azure.png","language":"Jupyter Notebook","funding_links":[],"categories":["**Section 2** : Azure OpenAI and Reference Architecture","Open Source Projects","machine-learning","Solution Accelerators","ai"],"sub_categories":["**Azure Reference Architectures**"],"readme":"# AI-in-a-Box\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"media/images/ai-in-a-box.png\" alt=\"FTA AI-in-a-Box: Deployment Accelerator\" style=\"width: 15%\" /\u003e\n\u003c/p\u003e\n\n*AI-in-a-Box* leverages the collective expertise of Microsoft Customer Engineers and Architects across the globe to develop and provide AI and ML solutions to the technical community.\n\nOur intent is to present a curated collection of solution accelerators that can help engineers establish their AI/ML environments and solutions rapidly and with minimal friction, while maintaining the highest standards of quality and efficiency.\n\nAs we continue to learn from the market, the contributors will look to equip the community with the tools and resources necessary to succeed in the ever-evolving AI and ML landscape.\n\n## Why AI-in-a-Box?\n\n* Accelerated Deployment: Speed up your solutions with our proven, ready-to-use patterns.\n* Cost Savings: Maximize your budget by reusing existing code and patterns.\n* Enhanced Quality \u0026 Reliability: Trust in our solutions, validated through real-world scenarios.\n* Competitive Advantage: Outpace competitors by accelerating solution deployment.\n\n\u003cp align=\"center\"\u003e\n  \n  ![FTA AI-in-a-Box: Deployment Accelerator](/media/images/aibxtable.png)\n\n\u003c/p\u003e\n\n## Available Guidance\n\n|Topic|Description|\n|---|---|\n|[Responsible AI](./guidance/responsible-ai/) | This provides essential guidance on the responsible use of AI and LLM technologies. |\n|[Security for Generative AI Applications](./guidance/genai-security/)| This document provides specific security guidance for Generative AI (GenAI) applications. |\n|[Scaling OpenAI Applications](./guidance/scaling/)| This document contains best practices for scaling OpenAI applications within Azure. |\n\n## Available “-in-a-Box” accelerators\n\n|Pattern|Description|Supported Use Cases and Features|\n|---|---|---|\n|[Azure ML Operationalization in-a-box](https://github.com/Azure-Samples/ml-ops-in-a-box)|Boilerplate Data Science project from model development to deployment and monitoring|\u003cli\u003eEnd-to-end MLOps project template \u003cli\u003eOuter Loop (infrastructure setup) \u003cbr /\u003e\u003cli\u003eInner Loop (model creation and deployment lifecycle)|\n|[Edge AI in-a-box](./edge-ai/)|Edge AI from model creation to deployment on Edge Device(s) |\u003cli\u003eCreate a model and deploy to Edge Device.\u003cli\u003eOuter Loop Infrastructure Setup (IoT Hub, IoT Edge, Edge VM, Container Registry, Azure ML) \u003cbr /\u003e\u003cli\u003eInner Loop (model creation and deployment)|\n|[AML Edge in-a-box](https://github.com/Azure-Samples/aml-edge-in-a-box)|Edge AI from model creation to deployment on Edge Device(s) |Orchestrate the entire Edge AI model lifecycle—from creation to deployment—using Azure ML, IoT Edge, and IoT Hub, while leveraging Azure ML CLI V2 for streamlined management.|\n|[Custom Vision Edge in-a-box](https://github.com/Azure-Samples/customvision-edge-in-a-box)|Edge AI from model creation to deployment on Edge Device(s) |Edge AI mitigates cloud latency by shifting analysis closer to the data source for faster responses. This accelerator demonstrates using [Custom Vision](https://www.customvision.ai/) to train a model and export it in formats like ONNX or Dockerfile for edge deployment.|\n|[Doc Intelligence in-a-box](https://github.com/Azure-Samples/doc-intelligence-in-a-box) | This accelerator enables companies to automate PDF form processing, modernize operations, save time, and cut costs as part of their digital transformation journey.|\u003cli\u003eReceive PDF Forms\u003cbr /\u003e\u003cli\u003eFunction App and Logic App for Orchestration\u003cbr /\u003e\u003cli\u003eDocument Intelligence Model creation for form processing and content extraction \u003cbr /\u003e\u003cli\u003e Saves PDF data in Azure Cosmos DB |\n|[Image and Video Analysis in-a-box](https://github.com/Azure-Samples/gpt-video-analysis-in-a-box) | Extracts information from images and videos with Azure AI Vision and sends the results along with the prompt and system message to Azure GPT-4 Turbo with Vision. |\u003cli\u003eOrchestration through Azure Data Factory\u003cbr /\u003e\u003cli\u003eLow code solution, easily extensible for your own use cases through ADF parameters\u003cbr /\u003e\u003cli\u003e Reuse same solution and deployed resources for many different scenarios\u003cbr /\u003e\u003cli\u003e Saves GPT4-V results to Azure CosmosDB|\n|[Cognitive Services Landing Zone in-a-box](https://github.com/Azure-Samples/ai-landing-zone-in-a-box)|Minimal enterprise-ready networking and AI Services setup to support most Cognitive Services scenarios in a secure environment|\u003cli\u003eHub-and-Spoke Vnet setup and peering \u003cbr /\u003e\u003cli\u003eCognitive Service deployment \u003cbr /\u003e\u003cli\u003ePrivate Endpoint setup \u003cbr /\u003e\u003cli\u003ePrivate DNS integration with PaaS DNS resolver|\n|[Semantic Kernel Bot in-a-box](https://github.com/Azure-Samples/gen-ai-bot-in-a-box)|Extendable solution accelerator for advanced Azure OpenAI Bots|\u003cli\u003eDeploy Azure OpenAI bot to multiple channels (Web, Teams, Slack, etc) \u003cbr /\u003e\u003cli\u003eBuilt-in Retrieval-Augmented Generation (RAG) support \u003cbr /\u003e\u003cli\u003eImplement custom AI Plugins|\n[NLP to SQL in-a-box](https://github.com/Azure-Samples/nlp-sql-in-a-box)|Unleash the power of a cutting-edge speech-enabled SQL query system with Azure OpenAI, Semantic Kernel, and Azure Speech Services. Simply speak your data requests in natural language, and let the magic happen.|\u003cli\u003eAllows users to verbally express natural language queries \u003cbr /\u003e \u003cli\u003eTranslate into SQL statements using Azure Speech \u0026 AOAI\u003cbr /\u003e\u003cli\u003e Execute  on an Azure SQL DB |\n|[Assistants API notebooks](./gen-ai/Assistants/notebooks)|Harnessing the simplicity of the Assistants API, developers can seamlessly integrate assistants with diverse functionalities, from executing code to retrieving data, empowering users with versatile and dynamic digital assistants tailored to their needs.| \u003cli\u003eOffers three main capabilities: Code Interpreter (tech tasks), Retrieval (finding info), and Function calling (task execution) \u003cbr /\u003e\u003cli\u003eThese powers combine to form a versatile super-assistant for handling diverse tasks |\n|[Assistants API Bot in-a-box](https://github.com/Azure-Samples/gen-ai-bot-in-a-box)|This sample provides a step-by-step guide on how to deploy a virtual assistant leveraging the Azure OpenAI Assistants API. It covers the infrastructure deployment, configuration on the AI Studio and Azure Portal, and end-to-end testing examples.| \u003cli\u003eDeploy the necessary infrastructure to support an Azure OpenAI Assistant \u003cbr /\u003e\u003cli\u003eConfigure as Assistant with the required tools.\u003cli\u003eConnect a Bot Framework application to your Assistant to deploy the chat to multiple channels |\n\n## Key Contacts \u0026 Contributors\n\nIf you have any questions or would like to contribute please reach out to: `aibox@microsoft.com`\n\n| Contact | GitHub ID | Email |\n|--------------|------|-----------|\n| Alex Morales | @msalemor | `alemor@microsoft.com` |\n| Andre Dewes  | @andredewes | `andredewes@microsoft.com` |\n| Andrés Padilla | @AndresPad | `andres.padilla@microsoft.com` |\n| Chris Ayers | @codebytes | `chrisayers@microsoft.com` |\n| Eduardo Noriega | @EduardoN | `ednorieg@microsoft.com` |\n| Franklin Guimaraes | @franklinlindemberg | `fguimaraes@microsoft.com` |\n| Jean Hayes | @jehayesms | `jean.hayes@microsoft.com` |\n| Marco Aurélio Bigélli Cardoso  | @MarcoABCardoso | `macardoso@microsoft.com` |\n| Maria Vrabie  | @MariaVrabie | `mavrabie@microsoft.com` |\n| Neeraj Jhaveri | @neerajjhaveri | `neeraj.jhaveri@microsoft.com` |\n| Thiago Rotta | @rottathiago | `thiago.rotta@microsoft.com` |\n| Victor Santana | @Welasco | `vsantana@microsoft.com` |\n| Sabyasachi Samaddar | @ssamadda | `ssamadda@microsoft.com` |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAzure%2FAI-in-a-Box","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAzure%2FAI-in-a-Box","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAzure%2FAI-in-a-Box/lists"}