🔥 A curated list of awesome links to essential info, insights, knowledge, learning, and tooling related to GenAI on Azure.
- Essentials
- Integration
- Model Services
- Open source models on Azure
- Model Customization
- Prompting
- Applications and Development Tools
- Prompt flow
- RAG and Retrieval
- Copilot
- Security
- Responsibility
- Azure OpenAI Performance
- Operations
- Contributing
- What is Azure OpenAI Service?
- Azure OpenAI Service models
- What is Azure AI Foundry?
- What is an Azure Landing Zone?
- Baseline OpenAI end-to-end chat reference architecture
- AI workloads on Azure
- Azure Machine Learning model catalog
- Azure OpenAI Service quotas and limits
- Optimizing Azure OpenAI: A Guide to Limits, Quotas, and Best Practices
- Azure OpenAI Service model deprecations and retirements
- Baseline OpenAI end-to-end chat reference architecture
- Azure Well-Architected Framework perspective on Azure OpenAI
- Azure Well-Architected Framework perspective on Azure Machine Learning
- HAX design library for Human-AI interaction guidelines
- APIM AI gateway labs
- Manage traffic with spillover for provisioned deployment
- AI Hub Gateway Landing Zone solution accelerator for implementing a central AI API gateway
- Azure OpenAI with APIM scaling special sauce
- How to configure a private link for Azure AI Foundry hubs
- Customize a model with fine tuning
- Fine tuning with Azure OpenAI
- Fine Tuning with Function Calling on Azure OpenAI Service
- Cost Optimized hosting of Fine-tuned LLMs in Production
- What is AI Foundry?
- How to create a secure AI Foundry Hub
- Collection of Azure AI Foundry solution examples
- Get started with Function Calling through Assistants API on Azure OpenAI
- Unveiling Generative AI Bulk Processing and Ingestion Pattern
- Choosing the right tool: a comparitive analysis of the Assistants API and Chat Completions API
- Azure OpenAI samples GitHub repo
- Azure-OpenAI-demos GitHub repo
- ChatGPT + Enterprise data with Azure OpenAI and AI Search
- Azure sample OpenAI end-to-end baseline reference implementation
- Securely use Azure OpenAI on your data
- Assistants API to build custom AI assistants with Azure OpenAI Service
- Analyze Videos with Azure Open AI GPT-4 Turbo with Vision and Azure Data Factory
- Generate embeddings with the Azure AI Vision multi-modal embeddings API
- Sentiment Analysis with Durable Functions
- Unlocking Advanced Document Insights with Azure AI Document Intelligence
- A collection of Azure AI templates deployed with the Azure Developer CLI
- GitHub accelerator for building your own assistants and researchers
- GitHub accelerator for building your own multi-modal customer service agent
- GitHub accelerator for enterprise RAG
- GitHub accelerator for AuthAuth and prior authorisation
- GitHub accelerator for creating AI assistants for document generation
- GitHub accelerator for creating multi-agent MVPs, using AutoGen
- GitHub accelerator for mining unstructured customer data for greater insight
- GitHub accelerator for document mining
- GitHub accelerator for multi-agent RAG
- GitHub accelerator for RAG chat
- Azure’s PromptFlow: Deploying LLM Applications in Production
- Part 1 of Prompt Flow in Azure Machine Learning: Industry-grade prompt management
- Build, benchmark, evaluate and deploy real-time inference endpoint with Prompt Flow
- Running batches with promptflow
- Combine Semantic Kernel with Azure Machine Learning prompt flow
- Troubleshooting prompt flow
- Repo with promptflow templates for building LLM-infused apps
- Retrieval Augmented Generation (RAG) in Azure AI Search
- Azure OpenAI RAG workshop
- GraphRAG: Unlocking LLM discovery on narrative private data
- Elevating RAG and Search: The Synergy of Azure AI Document Intelligence and Azure OpenAI
- Voice RAG with AI Search and gpt4o-realtime-preview
- The best retrieval strategies for generative AI. Hint: you need more than just vector search
- Building a RAG App with VS Code and Prompt Flow extension
- Blog on building intelligent RAG For multimodality and complex document structure
- Blog on advanced RAG with AI Search and LlamaIndex
- Blog on step-by-step guide to evaluating RAG with Azure AI Search, Azure OpenAI, LlamaIndex, and Tonic AI
- Learnings from ingesting millions of technical pages for RAG on Azure
- Load testing RAG based GenAI applications
- SuperRAG – How to achieve higher accuracy with Retrieval Augmented Generation
- Advanced RAG with Azure AI Search and LlamaIndex
- GPT-RAG solution accelerator
- Faceted navugation with AI Search
- Evaluation of generative AI applications
- Samples evaluating Generative AI output with the azure-ai-evaluation SDK
- Blog multi-agent collab with selection and termination strategy blog
- Multi-agent collaboration
- Multi-agent with AI Agent and Semantic Kernel blog
- Semantic Kernal chat completion auto function calling
- Observability in Semantic Kernel
- Moneta - Semantic Kernel AI-Agentic Assistant for Insurance and Banking
- Semantic Kernel python examples
- Creating a GenAI Enterprise Co-pilot
- Building smarter Copilots with Copilot Studio and Azure OpenAI integration
- Microsoft Copilot personal and work experiences explained
- Repo for creating copilot enterprise chat API using custom Python code to ground copilot responses in your company data & APIs
- An end-to-end example of a Legal Research Copilot application
- Azure PyRIT Python Risk Identification Toolkit for red teaming generative AI
- Security Best Practices for GenAI Applications (OpenAI) in Azure
- Data Security, Protection and Model Management – with Azure OpenAI
- Load testing Azure OpenAI endpoints
- Azure OpenAI latency
- Azure OpenAI PTUs (Provisioned Throughput Units)
- Best practice guidance for PTU
- Right-size your PTU deployment and save big
- Azure OpenAI Best Practices Insights from Customer Journeys
- The LLM Latency Guidebook: Optimizing Response Times for GenAI Applications
- Calulating business unit chargebacks using shared Azure OpenAI instance
- An Introduction to LLMOps: Operationalizing and Managing Large Language Models using Azure ML
- Achieve generative AI operational excellence with the LLMOps maturity model
- Elevate Your LLM Applications to Production via LLMOps
- Elevate Your LLM Applications to Production via LLMOps and promptflow
- LLMOps Using Azure Machine Learning Prompt Flow — NER Task
- LLMOps promptflow template
- Deploy your Azure Machine Learning prompt flow on virtually any platform
- Enable GPT failover with Azure OpenAI and Azure API Management
- Blog on Azure OpenAI best practices for production
- Code-first LLMOps
Your contributions are welcome! Please take a look at the contribution guidelines first.