A comprehensive implementation of Microsoft Agent Framework featuring interactive research agents, AI-powered blog generation, and sequential orchestration workflows. This sample demonstrates how to build production-ready AI agents using Azure AI Foundry and Azure OpenAI services with an integrated DevUI for testing and interaction.
This is an unsupported, experimental, and not an official Microsoft product. It is provided "as is", without support and without any warranties, whether express or implied. This includes, but is not limited to, warranties of merchantability, fitness for a particular purpose, and non-infringement.
In no event shall the authors or copyright holders be liable for any claims, damages, or other liabilities, whether in contract, tort, or otherwise, arising from, out of, or in connection with the Software or the use or other dealings in the Software.
⚠️ Important Note:
This is a sample demo application created for demonstration purposes. It is deployed into Microsoft Azure and intended solely for integration with Microsoft Agent Framework during prototyping or sample scenarios. This component is not part of any official Microsoft product and is not available for production use.
- Interactive Research Agent: Conversational research with context retention using Azure AI Foundry
- Advanced Research Tools: Custom tools for academic search, statistics, and timeline analysis
- Streaming Responses: Real-time response streaming for better user experience
- LangChain Blog Agent: Advanced blog writing using LangChain with Azure OpenAI
- Multiple Writing Styles: Professional, casual, technical, and SEO-optimized content
- Content Formatting: Automatic markdown formatting with proper structure
- Sequential Workflow: Research-to-blog pipeline combining multiple specialized agents
- End-to-End Pipeline: Complete content creation from research topic to published blog post
- Error Handling: Robust error handling and graceful degradation
- Interactive Web Interface: Built-in DevUI for testing and interacting with agents
- OpenTelemetry Tracing: Full observability and debugging capabilities
- Real-time Testing: Live agent testing at
http://localhost:8082
- Azure AI Foundry project set up with model deployment
- Azure OpenAI service with chat completion deployment
- Azure CLI installed and authenticated (
az login) - Python 3.8+ installed
git clone https://github.com/biswapm/Microsoft-Agent-Framework-Sample.git
cd Microsoft-Agent-Framework-Sample
# Create virtual environment
python -m venv .venv
.venv\Scripts\activate # Windows
# or
source .venv/bin/activate # Linux/Mac
# Install dependencies
pip install -r requirements.txt# Copy environment template
cp .env.example .env
# Edit .env with your Azure settings
# - AZURE_AI_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
# - AZURE_AI_MODEL_DEPLOYMENT_NAME: Your model deployment (e.g., gpt-4o)
# - AZURE_OPENAI_ENDPOINT: Your Azure OpenAI endpoint
# - AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: Your chat deployment name# Start DevUI with all agents
python main.py
# Access the web interface
# Open browser to: http://localhost:8082Analyze the current state of large language models in 2025. What are the key developments in efficiency, multimodality, and reasoning capabilities?
Research the impact of quantum computing on cryptography. What are the timeline and implications for current security systems?
Investigate the latest developments in autonomous vehicle technology. What are the main technical challenges and regulatory hurdles?
Create a comprehensive blog post about the future of AI coding assistants and their impact on software development
Write a blog post explaining edge computing for business leaders - what it is, why it matters, and how to implement it
Create a blog post about building effective remote teams in the hybrid work era, including tools and strategies
Microsoft-Agent-Framework-Sample/
├── src/
│ ├── interactive_researcher.py # Azure AI Foundry research agent
│ ├── langchain_blog_agent.py # LangChain blog writing agent
│ ├── research_blog_orchestrator.py # Sequential workflow orchestrator
│ ├── researcher_with_tools.py # Advanced research with custom tools
│ ├── devui_config.py # DevUI configuration
│ └── utils.py # Shared utilities
├── agents/ # Agent package modules
│ ├── interactive_researcher/
│ └── research_blog_orchestrator/
├── main.py # DevUI entry point with all agents
├── devui_launcher.py # Alternative DevUI launcher
├── setup_agents.py # Agent setup and configuration
├── requirements.txt # Dependencies including agent-framework
├── .env.example # Environment template
├── .gitignore # Comprehensive gitignore for AI projects
└── README.md # This documentation
# Azure AI Foundry (for Research Agent)
AZURE_AI_PROJECT_ENDPOINT="https://your-project.services.ai.azure.com/api/projects/YourProject"
AZURE_AI_MODEL_DEPLOYMENT_NAME=gpt-4o
# Azure OpenAI (for Blog Agent)
AZURE_OPENAI_ENDPOINT=https://your-openai.openai.azure.com
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=gpt-4o
OPENAI_API_VERSION=2024-02-01
# Optional: Agent-specific settings
# AZURE_AI_AGENT_ID=asst_your_agent_id # Use existing agent
# AZURE_OPENAI_API_KEY=your_key # If not using Azure CLI auth| Agent | Service | Capabilities |
|---|---|---|
| Research Agent | Azure AI Foundry | Interactive research, context retention, conversational follow-ups |
| Blog Agent | Azure OpenAI + LangChain | Content creation, formatting, SEO optimization, multiple styles |
| Orchestrator | Sequential Workflow | Research-to-blog pipeline, error handling, result aggregation |
# Interactive research session
python src/interactive_researcher.py
# Advanced research with custom tools
python src/researcher_with_tools.py# Standalone blog generation
python src/langchain_blog_agent.py
# Complete research-to-blog workflow
python src/research_blog_orchestrator.py# Launch DevUI with all agents
python main.py
# Alternative launcher
python devui_launcher.py- OpenTelemetry Tracing: Enabled by default when running DevUI
- Agent Logs: Available in the DevUI interface
- Error Handling: Comprehensive error messages with troubleshooting guidance
- Health Checks: Built-in health monitoring for all services
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit changes:
git commit -m 'Add amazing feature' - Push to branch:
git push origin feature/amazing-feature - Open a Pull Request
- Microsoft Agent Framework Documentation
- Azure AI Foundry
- Azure OpenAI Service
- LangChain Documentation
MIT License - see LICENSE file for details.
Built with ❤️ using Microsoft Agent Framework, Azure AI, and LangChain