Awesome Azure Openai Llm Overview

A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.

🏠 Home · 🔥 Feed · 📮 Subscribe · ❤️ Sponsor · 😺 kimtth/awesome-azure-openai-llm · ⭐ 422 · 🏷️ LLM

[ Daily / Weekly / Overview ]

Azure OpenAI + LLM

GitHub last commit Azure OpenAI GitHub Created At

A comprehensive, curated collection of resources for Azure OpenAI, Large Language Models (LLMs), and their applications.

🔹Concise Summaries: Each resource is briefly described for quick understanding
🔹Chronological Organization: Resources appended with date (first commit, publication, or paper release)
🔹Monthly Updates: The list is updated monthly; candidate entries before the update are tracked in the issue.
🔹A list for Azure and Microsoft products only, linted by the official Awesome rules: Azure OpenAI & Copilot (⭐10).
🔹Applications archived or inactive for over 12 months are listed in applications.old.md. Archived Azure repositories are listed in azure.old.md.

🧭 Quick Navigation (Propedia-style)

Layer / Era What it controls Jump to sections
Weights
2022-2023		 Capabilities encoded in model parameters.
Themes: Pretraining, scaling, fine-tuning, alignment		 Model landscape · Model collection · Training & optimization · Model training
Context
2023-2024		 Instructions and knowledge supplied at inference.
Themes: Prompting, RAG, memory, long context		 Prompting · RAG · IQ, Data & Memory (Azure) · Memory · Long-context limits
Agentic Engineering
2025-2026		 How applications use models and tools to act.
Themes: Agents, MCP, skills, orchestration, evaluation		 Agent frameworks · Agent protocols · Agentic engineering · Agent best practices · Evaluation

Refereces: DailyDoseOfDS - Evolution of the Agent Landscape

1. App & Agent

🚀 RAG Systems, LLM Applications, Agents, Frameworks & Orchestration

⬆ back to top

2. Azure OpenAI & Copilot

🌌 Microsoft's Cloud-Based AI Platform and Services

⬆ back to top

3. Research & Survey

🧠 LLM Landscape, Prompt Engineering, Finetuning, Challenges & Surveys

⬆ back to top

4. Datasets, Evaluation, and Extras

🛠️ Training Data, Datasets & Evaluation Methods

⬆ back to top

5. Best Practices

📋 Curated Blogs, Patterns, and Implementation Guidelines

⬆ back to top

🧭 Start Here: Choose a Goal

Pick the outcome closest to your task and follow the links in order. Each path is a short starting point, not a required sequence.

Goal Suggested path
Build a RAG application RAG → Azure IQ, Data & Memory (AI Search) → RAG Solution Design → RAG Application
Design an AI agent Top Agent Frameworks → Agent Design Patterns → Agents & Context Engineering → Memory
Connect tools with MCP Model Context Protocol → Developer Tools, MCP & .NET → Tool Use
Build a Microsoft 365 agent Microsoft 365 Copilot → Agents & Context Engineering
Build a coding or research agent Coding → Skills → Agentic Engineering → Deep Research
Run a local model application Model Collection → Model Serving & Local Runtimes → Model Gateway → Observability & LLMOps
Train or evaluate a model Datasets for LLM Training → Training & Fine-tuning → Evaluating Large Language Models → Evaluation Metrics
Operate an application in production Architecture & Reference Designs → Safety, Security & LLMOps → LLMOps → Evaluation
Explore LLM research Model Landscape → Survey and Reference → LLM Research

📖 Legend & Notation

Symbol Meaning Symbol Meaning
github GitHub repository 🗄️ Archived files
💡🏆 Recommend 📺 Video content
📑 Academic paper 🤗 Huggingface

^ back to top ^