A comprehensive, curated collection of resources for Azure OpenAI, Large Language Models (LLMs), and their applications.
This repository serves as a comprehensive guide to the rapidly evolving field of LLMs and Azure OpenAI services. Key features:
🔹Concise Summaries: Each resource is briefly described for quick understanding
🔹Chronological Organization: Resources ordered by date (first commit, publication, or paper release)
🔹Active Tracking: Regular updates to capture the latest developments
Note: Some content may become outdated due to the rapid pace of development in this field.
Retrieval-Augmented Generation - Enhancing LLMs with External Knowledge
- RAG Fundamentals - Core concepts and implementation strategies
- RAG Architecture Design - System design patterns and best practices
- RAG Applications - Real-world implementations and use cases
- GraphRAG - Graph-based retrieval approaches
- Vector Databases - Comparison and selection guide
Microsoft's Cloud-Based AI Platform and Services
- Microsoft LLM Framework - Official frameworks and SDKs
- Microsoft Copilot - Copilot products overview
- Azure AI Services - Azure AI Search, AI services
- Microsoft Research - Research publications and findings
- Reference Architectures - Proven architectural patterns and samples
Building Real-World Applications with Large Language Models
- Development Frameworks - Tools for building LLM applications
- Application Development - Implementation guides and best practices
- Code Development Tools - AI-powered coding assistants and editors
- Memory Systems - Persistent memory and context management
- Performance Optimization - Caching strategies and UX improvements
- Emerging Concepts - New paradigms like Vibe Coding and Context Engineering
- Robotics Integration - LLMs in robotic systems
- Demonstration Projects - Inspiring examples and showcases
Building Autonomous AI Agents and Multi-Agent Systems
- Design Patterns - Proven architectural approaches for agent systems
- Development Frameworks - Tools and libraries for building agents
- Agent Applications - Real-world agent implementations
- Code Interpreters - Open-source alternatives to OpenAI's Code Interpreter
- Model Context Protocol - MCP, Agent-to-Agent communication, and computer interaction
- Research Agents - AI systems for deep research and analysis
Optimizing Model Performance and Behavior
- Prompt Engineering - Techniques for effective prompt design
- Model Finetuning - PEFT (LoRA), RLHF, and supervised fine-tuning
- Model Optimization - Quantization and performance optimization
- Advanced Techniques - Mixture of Experts (MoE) and other patterns
- Visual Prompting - Working with multimodal inputs
Understanding LLM Capabilities and Limitations
- AGI and Social Impact - Discussions on artificial general intelligence
- OpenAI Ecosystem - Product roadmaps and strategic direction
- Technical Constraints - Context limitations and solutions (e.g., RoPE)
- Safety and Security - Building trustworthy AI systems
- LLM Capabilities - Understanding what LLMs can and cannot do
- Reasoning Abilities - Logical reasoning and problem-solving
Overview of Available Models and Technologies
- Model Taxonomy - Classification and comparison of LLMs
- Model Collection - Comprehensive list of available models
- Domain-Specific Models - Specialized models for software development and other domains
- Multimodal Models - Models handling text, image, audio, and video
Microsoft's Orchestration Framework and Optimization Tools
- Semantic Kernel - Microsoft's micro-orchestration framework for AI applications
- DSPy - Optimizer frameworks for systematic prompt and model optimization
Popular Open-Source Frameworks for LLM Applications
- LangChain Features - Comprehensive feature overview and cheat sheets
- LangChain Agents - Agent implementations and critical analysis
- Framework Comparisons - LangChain vs. alternative frameworks
- LlamaIndex - Micro-orchestration and RAG-focused framework
Practical Tools and Browser Extensions
Training and Evaluation Data Resources
- Training Datasets - High-quality datasets for model training and fine-tuning
Measuring and Improving LLM Performance
- Evaluation Frameworks - Methods and metrics for LLM assessment
- LLMOps - Operations and lifecycle management for LLM systems
Comprehensive Surveys and Learning Materials
- LLM Surveys - Academic surveys and systematic reviews
- Business Applications - Industry use cases and implementation strategies
- Building from Scratch - Educational resources for understanding LLM internals
- Multilingual Resources - LLM resources for Korean, Japanese, and other languages
- Learning Materials - Tutorials, courses, and supplementary resources
| Symbol | Meaning | Symbol | Meaning |
|---|---|---|---|
ref |
External URL | git |
GitHub repository |
doc |
Archived document | x-ref |
Cross reference |
cite |
Source citation | 📺 | Video content |
cnt |
Citation count | 💡🏆 | Recommended resource |
Last Updated: July 23, 2025
