azure-ai-agents-py
by thegovind
DevOps & CloudBrief
Build AI agents using the Azure AI Agents Python SDK.
Description
What This Skill Does
Python SDK for building agents hosted on Azure AI Foundry. Handles the full agent lifecycle: creating agents, managing conversation threads, processing runs, and streaming responses. Supports tools including Code Interpreter, File Search, Bing Grounding, Azure AI Search, Function Calling, OpenAPI, and MCP.
Gives direct SDK access to Azure AI Foundry's agent infrastructure with full control over thread management, tool configuration, and streaming, without higher-level framework abstractions.
When to Use It
- Building a document Q&A agent over uploaded PDFs using File Search
- Running on-demand Python code execution via Code Interpreter
- Grounding agent responses with live web search via Bing
- Streaming real-time agent replies in a chat interface
- Calling internal REST APIs from an agent using the OpenAPI tool
Example Workflow
User asks: 'What is the weather in Seattle?'
- 1
Create an agent with a FunctionTool wrapping a get_weather Python function
- 2
Create a conversation thread and add the user message
- 3
Call create_and_process with the toolset to auto-execute the function
- 4
Retrieve completed run assistant messages from the thread
- 5
Return the weather response text
Weather in Seattle: 58F, cloudy
Requirements
- Azure subscription
- Azure AI Foundry project with a deployed model
- PROJECT_ENDPOINT environment variable (from Azure AI Foundry project settings)
- MODEL_DEPLOYMENT_NAME environment variable (name of your deployed model)
Installation
clawhub install thegovind/azure-ai-agents-pyRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.