Azure OpenAI Resources
Introduction
Azure OpenAI is a collaboration between Microsoft Azure and OpenAI, a leading research organization in artificial intelligence. It is a cloud-based platform that enables developers and data scientists to build and deploy AI models quickly and easily. With Azure OpenAI, users can access a wide range of AI tools and technologies to create intelligent applications, including natural language processing (NLP), computer vision, and deep learning.
Azure OpenAI is designed to accelerate the development of AI applications, allowing users to focus on creating innovative solutions that deliver value to their organizations and customers.
Request Access
- Rate Increase: Azure OpenAI Service: Request for Quota Increase (microsoft.com)
- GPT4: GPT-4 and GPT-4-32k are now available to all Azure OpenAI Service customers. You no longer need to request access to use GPT-4 and GPT-4-32k. Availability is currently limited by region to ensure a smooth rollout. You still need to apply for the AOAI Service if you do not have that already.
Keeping Up (April 2024 Update📰)
- In Recent News: Accelerate your productivity with the Whisper model in Azure AI now generally available. Whisper is a speech-to-text model from OpenAI that developers can use to transcribe audio files. Developers can begin using the generally available Whisper API in both Azure OpenAI Service as well as Azure AI Speech services on production workloads, knowing that it is backed by Azure’s enterprise-readiness promise. Azure OpenAI Service enables developers to run OpenAI’s Whisper model in Azure, mirroring the OpenAI Whisper model functionalities including fast processing time, multi-lingual support, and transcription and translation capabilities. OpenAI Whisper in Azure OpenAI Service is ideal for processing smaller size files for time-sensitive workloads and use-cases.
- DALL-E 3 is now generally available, available in East US, Sweden Central, and Australia East – providing service reliability for production scenarios, annotations for content filtering, and continuing to deliver high-quality generated images.
- Azure AI announces Prompt Shields for Jailbreak and Indirect prompt injection attacks – Our Azure OpenAI Service and Azure AI Content Safety teams are excited to launch a new Responsible AI capability called Prompt Shields. Prompt Shields protect applications, powered by Foundation Models, from two types of attacks: direct (jailbreak) and indirect attacks, both of which are now available in Public Preview.
- Azure OpenAI Service model deprecations and retirements – Learn about models that are currently available, deprecated, and retired.
Please visit our Academy page to see Code Snippets & Architecture Examples: AI & ML Academy.
- What’s New in Azure OpenAI
- Azure OpenAI – YouTube
- Model Availability
- Quotas & Limitations: Azure OpenAI Service Quotas & Limits – Azure Cognitive Services
- Pricing: Azure OpenAI Service Pricing
Fundamentals
- Azure OpenAI Documentation – Overview, QuickStart, tutorials, how-to guides, API reference
- Video: Combining OpenAI models with the power of Azure
- Introduction to Azure OpenAI Service – Microsoft Learn
- How to ground models
- ChatGPT Enterprise: Revolutionize your Enterprise Data with ChatGPT: Next-gen Apps w/ Azure OpenAI and Cognitive Search – Microsoft Community Hub
- GPT4 Model: How to work with the GPT-35-Turbo and GPT-4 models — Azure OpenAI Service
Evaluating models:
- LangChain Lib: Evaluation — 🦜🔗
- Evals framework for evaluating LLMs and LLM systems
- Leverage Prompt Flow to evaluate your model
Responsible AI:
- Code of Conduct for the Azure OpenAI Service
- Data, privacy, and security for Azure OpenAI Service
- Transparency Note for Azure OpenAI Service
- Content Filtering: Azure OpenAI Content Filtering
- Microsoft Azure Legal Information
AI Business Material:
Tooling:
- The Azure OpenAI benchmarking tool helps you test and measure the performance of your provisioned throughput deployments. These deployments give you a fixed amount of model compute, but the actual performance depends on factors like prompt size, generation size, and call rate. The tool sends test traffic to your deployment and shows you the throughput, latency, and utilization statistics. You can use it to try different traffic patterns and find the best settings for your prompt size, generation size, and PTUs.
Associate
- How to generate text with Azure OpenAI - Learn how to generate or manipulate text, including code with Azure OpenAI
- How to prepare a dataset for Azure OpenAI custom model training - Learn how to prepare your dataset for fine-tuning
- Semantic Kernel Library - .NET Code Snippets
- LLMOps - Operational capabilities and infrastructure required to fine-tune existing foundational models
- JARVIS - Collaborative system that uses an LLM as the controller
- Can ChatGPT work with your enterprise data? - Bring OpenAI’s ChatGPT model in Azure to your own enterprise-grade app experiences with precise control over the knowledge base, for in-context and relevant responses. Interact with your organization’s private internal data, while respecting the information protection controls put in place.
Past Events
- Microsoft AI Tour 2024 In-person
- The First Annual Microsoft Fabric Community Conference In-person March 26-28, 2024: See firsthand how Microsoft Fabric and the data and AI products at Microsoft can help your organization prepare for the era of AI. You’ll hear from leading Microsoft and community experts from around the world and receive hands-on experiences with the latest features from Microsoft Fabric, Power BI, Databases, Azure AI, Microsoft Purview, and more.
- Microsoft Ignite 2023: Watch the recordings for various sessions, covering updates on services, product announcements, and demos.
- Microsoft Build: Catch the recordings from the event. See Microsoft Build 2023 Recommended AI Session Guide
- Azure OpenAI What the Hack (WTH): This introductory hackathon will provide participants with hands-on experience on how to integrate the Azure OpenAI offering
Demos & Code Samples
- Customer Service Conversational Insights with Azure OpenAI — Architecture Example
- OpenAI End-to-End Code Snippets
- OpenAI Use Cases & ChatGPT Demo
- AI-powered Call Center Architecture Example
- Business Process Automation Accelerator - Provides a no-code Studio for users to quickly build complex, multi-stage AI pipelines across multiple Azure AI and ML Services
- Microsoft Tech Community: Azure OpenAI (GPT) with Power Apps - Build a Power App to create a demo or Personal Knowledge Bot
- Build a low-code conversational SMS bot with Azure Communication Services & Azure OpenAI
- Q&A using Azure OpenAI & document’s vector embeddings
- Create a chatbot using enterprise data with DevOps best practices
Community Resources
- AI – Azure Platform Blog – Microsoft Community Hub
- AI – Azure AI Services Blog – Microsoft Community Hub
- Microsoft Q&A - Get answers to your questions using the tag: azure-openai
- OpenAI Python Library - examples · PyPI
- OpenAI Cookbook
- Awesome ChatGPT Prompts
- Tokenizer for Python & NodeJS
Interesting Reads
- New Microsoft Copilot Studio Implementation Guide
- Vector Similarity Search with Azure SQL database and OpenAI
- Using Microsoft Fabric’s Lakehouse Data and prompt flow in Azure Machine Learning Service to create RAG applications – Microsoft Fabric Blog
- Azure AI Search: Outperforming vector search with hybrid retrieval and ranking capabilities – Microsoft Community Hub
- Building GPT-3 applications — beyond the prompt