Getting Started with Azure AI Studio.pptx
- 1. Swaminathan Vetri Lead Platform Architect, Maersk
- 2. About Me • Swaminathan Vetri (Swami) • Lead Platform Architect – Maersk • Building Order Handling platform using Cloud native event driven architecture on k8s, Azure PaaS services • Dad of 2 little princess • Microsoft MVP (2016-2022) • Twitter - @svswaminathan • GiHub - @swaminathanvetri • LinkedIn – SwaminathanVetri • Blogging, Public Speaking, Community engagements, Photography, Dancing, Table tennis
- 4. What is Azure AI Studio AI Studio is a trusted and inclusive platform that empowers developers of all abilities and preferences to innovate with AI and shape the future.
- 5. Why Azure AI Studio? • Build generative AI applications on an enterprise-grade platform. • Directly from the studio you can interact with a project code-first via Visual Studio Code (Web). • Seamlessly explore, build, test, and deploy using cutting-edge AI tools and ML models, grounded in responsible AI practices. • Build together as one team. Your AI Studio hub provides enterprise-grade security, and a collaborative environment with shared files and connections to pretrained models, data and compute. • Organize your way. Your AI Studio project helps you save state, allowing you iterate from first idea, to first prototype, and then first production deployment. Also easily invite others to collaborate along this journey.
- 6. What does it offer? • API and model choice • Azure AI services • Azure OpenAI Service • Build Intelligent Apps with Industry leading APIs • Model catalog • Managed compute and serverless APIs • Model benchmarks • Compare models by performance and key parameters • Discover models for your use cases • Deploy serverless models
- 7. Complete AI toolchain • Azure AI Search • Fine-tuning • Ground models on your secure data • Prompt flow • Orchestrate and debug AI workflows • Open frameworks • Tracing and debugging • Evaluations • Streamline model and app evaluations
- 8. Responsible AI tools and practices • Responsible AI principles • Design apps responsibly • Azure AI Content Safety • Safeguard apps with Configurable filters and controls
- 9. Enterprise grade production at scale Collaborative hubs LLMOps Deploy to Production Monitoring & observability Operationalize and monitor workflows IT governance Enable developer agility and enterprise governance at scale Security & privacy RBAC Microsoft Copilot Copyright Commitment
- 10. Azure AI Studio - Overview Unified platform Comprehensive AI Tools Code-centric Developer experiences Data & search Data integration Hybrid vector search Foundation models Best in class and open model catalog Multimodal Safe & responsible AI Content classification Model monitoring Jailbreak risk detection Full development lifecycle Prompt flow LLMOps Model monitoring
- 11. Azure AI studio Architecture Source: learn.microsoft.com/en-us/azure/ai-studio/media/concepts/resource-provider-connected-resources.svg
- 12. Is it yet another Studio ? Azure Open AI Studio Azure ML Studio Copilot Studio
- 13. Demo – Intro to Azure AI Studio
- 14. Get started skilling with AI on Microsoft Learn Build AI skills, connect with the community, earn Microsoft Credentials, learn from experts, and take the Cloud Skills Challenge. aka.ms/LearnAtAITour
- 15. Connect with fellow enthusiasts, engage with Microsoft experts and MVPs, discuss your favorite sessions, and delve into AI discussions. Your space to ask, share, and explore! aka.ms/AzureAI/Discord Join the Azure AI Community on Discord
- 16. Microsoft wants to hear from YOU! Attendee Survey Season of AI | Microsoft Community 2024 aka.ms/AttendeeSurveySeasonOfAI
- 17. 🙋🏻♀️ ?? 🙏 X -@svswaminathan GitHub/ LinkedIn - @swaminathanvetri
Editor's Notes
- Azure AI Studio unifies various AI services for a seamless experience, catering to diverse AI models and data sources. Incorporates Microsoft's data and search technologies, OpenAI foundation models and other opensource AI and models from partners. Emphasizes the importance of building AI responsibly with advanced safety tools. Development lifecycle that supports emerging trends, like LLMOps for managing lifecycle and versioning of AI systems.
- Tab 1: - Create projects - Show settings (Azure AI Resource / Connections / Compute Infrastructure) - Show Deployments - Show Playground (Select deployments) -- Ask question: How much do the TrailWalker hiking shoes cost? Tab 2: - Ground model with own data (Connected to data source) - Ask question: How much do the TrailWalker hiking shoes cost? - Show in documentation Tab 3: - Translate questions to Greek -- Ask question: Πόσο κοστίζουν τα παπούτσια πεζοπορίας TrailWalker; Tab 4: - Show system prompt You are an AI assistant You always response in a rhyme. You are friendly and funny - Ask what can you tell me about Greece? Tab 4: - Evaluation - Click manual evaluation in playground - Show manual evaluation output