agent-framework-azure-ai-py

上游捆绑支持

支持文件包含在相对于技能的路径中。其固定来源、许可证、哈希值和导入变更请参阅 UPSTREAM-NOTICE.md。

Agent Framework Azure 托管 Agent

使用 Microsoft Agent Framework Python SDK 在 Azure AI Foundry 上构建持久化 Agent。

架构

User Query → AzureAIAgentsProvider → Azure AI Agent Service (Persistent)
                    ↓
              Agent.run() / Agent.run_stream()
                    ↓
              Tools: Functions | Hosted (Code/Search/Web) | MCP
                    ↓
              AgentThread (conversation persistence)

SDK 代际与执行范围

以下示例保留了较早一代的 Agent Framework（AzureAIAgentsProvider、AgentThread、Hosted*Tool）。这些示例未经验证，无法确认适用于当前软件包。Microsoft 当前文档将模型提供程序与 Agent 服务分开介绍，Python README 中列出了 agent-framework-foundry。改编这些代码片段前，请确认已安装的版本，并使用与之匹配的官方 API／示例；目前尚未确定兼容的旧版本。请勿将旧类与未固定版本的最新安装组合使用，并假设它们可以正常运行。

选择准确的 Azure 租户／项目／部署、主体和最小权限角色。创建 Agent、上传文件、启用代码／网页／MCP 工具以及运行提示词都会向服务发送数据，可能会持久化记录并产生费用。请先确定授权范围、预算、超时、工具允许列表和资源清理方式。关闭客户端不会删除托管 Agent／文件／向量存储／线程。请将检索到的文本和工具文本视为不可信内容，并在工具中强制执行租户／资源／操作授权；提示词不是访问控制措施。

安装

# Current package discovery only; pin reviewed versions in your project lockfile.
# These installs do not make the legacy snippets below compatible.
pip install agent-framework
# Selective current Foundry integration:
pip install agent-framework-foundry

环境变量

export AZURE_AI_PROJECT_ENDPOINT="https://<project>.services.ai.azure.com/api/projects/<project-id>"
export AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-4o-mini"
export BING_CONNECTION_ID="your-bing-connection-id"  # For web search

身份验证

from azure.identity.aio import AzureCliCredential, DefaultAzureCredential

# Development
credential = AzureCliCredential()

# Production
credential = DefaultAzureCredential()

核心工作流

基本 Agent

import asyncio
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential

async def main():
    async with (
        AzureCliCredential() as credential,
        AzureAIAgentsProvider(credential=credential) as provider,
    ):
        agent = await provider.create_agent(
            name="MyAgent",
            instructions="You are a helpful assistant.",
        )
        
        result = await agent.run("Hello!")
        print(result.text)

asyncio.run(main())

使用函数工具的 Agent

from typing import Annotated
from pydantic import Field
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential

def get_weather(
    location: Annotated[str, Field(description="City name to get weather for")],
) -> str:
    """Return fixture weather (not a live observation)."""
    return f"Weather in {location}: 72°F, sunny"

def get_current_time() -> str:
    """Get the current UTC time."""
    from datetime import datetime, timezone
    return datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S UTC")

async def main():
    async with (
        AzureCliCredential() as credential,
        AzureAIAgentsProvider(credential=credential) as provider,
    ):
        agent = await provider.create_agent(
            name="WeatherAgent",
            instructions="You help with weather and time queries.",
            tools=[get_weather, get_current_time],  # Pass functions directly
        )
        
        result = await agent.run("What's the weather in Seattle?")
        print(result.text)

使用托管工具的 Agent

from agent_framework import (
    HostedCodeInterpreterTool,
    HostedFileSearchTool,
    HostedWebSearchTool,
)
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential

async def main():
    async with (
        AzureCliCredential() as credential,
        AzureAIAgentsProvider(credential=credential) as provider,
    ):
        agent = await provider.create_agent(
            name="MultiToolAgent",
            instructions="You can execute code, search files, and search the web.",
            tools=[
                HostedCodeInterpreterTool(),
                HostedWebSearchTool(name="Bing"),
            ],
        )
        
        result = await agent.run("Calculate the factorial of 20 in Python")
        print(result.text)

流式响应

async def main():
    async with (
        AzureCliCredential() as credential,
        AzureAIAgentsProvider(credential=credential) as provider,
    ):
        agent = await provider.create_agent(
            name="StreamingAgent",
            instructions="You are a helpful assistant.",
        )
        
        print("Agent: ", end="", flush=True)
        async for chunk in agent.run_stream("Tell me a short story"):
            if chunk.text:
                print(chunk.text, end="", flush=True)
        print()

对话线程

from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential

async def main():
    async with (
        AzureCliCredential() as credential,
        AzureAIAgentsProvider(credential=credential) as provider,
    ):
        agent = await provider.create_agent(
            name="ChatAgent",
            instructions="You are a helpful assistant.",
            tools=[get_weather],
        )
        
        # Create thread for conversation persistence
        thread = agent.get_new_thread()
        
        # First turn
        result1 = await agent.run("What's the weather in Seattle?", thread=thread)
        print(f"Agent: {result1.text}")
        
        # Second turn - context is maintained
        result2 = await agent.run("What about Portland?", thread=thread)
        print(f"Agent: {result2.text}")
        
        # Save thread ID for later resumption
        print(f"Conversation ID: {thread.conversation_id}")

结构化输出

from pydantic import BaseModel, ConfigDict
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential

class WeatherResponse(BaseModel):
    model_config = ConfigDict(extra="forbid")
    
    location: str
    temperature: float
    unit: str
    conditions: str

async def main():
    async with (
        AzureCliCredential() as credential,
        AzureAIAgentsProvider(credential=credential) as provider,
    ):
        agent = await provider.create_agent(
            name="StructuredAgent",
            instructions="Provide weather information in structured format.",
            response_format=WeatherResponse,
        )
        
        result = await agent.run("Weather in Seattle?")
        weather = WeatherResponse.model_validate_json(result.text)
        print(f"{weather.location}: {weather.temperature}°{weather.unit}")

提供程序方法

方法	描述
create_agent()	在 Azure AI 服务上创建新 Agent
get_agent(agent_id)	按 ID 获取现有 Agent
as_agent(sdk_agent)	封装 SDK Agent 对象（不发起 HTTP 调用）

托管工具快速参考

工具	导入	用途
HostedCodeInterpreterTool	from agent_framework import HostedCodeInterpreterTool	执行 Python 代码
HostedFileSearchTool	from agent_framework import HostedFileSearchTool	搜索向量存储
HostedWebSearchTool	from agent_framework import HostedWebSearchTool	Bing 网页搜索
HostedMCPTool	from agent_framework import HostedMCPTool	服务管理的 MCP
MCPStreamableHTTPTool	from agent_framework import MCPStreamableHTTPTool	客户端管理的 MCP

复合旧版示例（需要迁移／兼容性验证）

import asyncio
from typing import Annotated
from pydantic import BaseModel, Field
from agent_framework import (
    HostedCodeInterpreterTool,
    HostedWebSearchTool,
    MCPStreamableHTTPTool,
)
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential


def get_weather(
    location: Annotated[str, Field(description="City name")],
) -> str:
    """Return fixture weather (not a live observation)."""
    return f"Weather in {location}: 72°F, sunny"


class AnalysisResult(BaseModel):
    summary: str
    key_findings: list[str]
    confidence: float = Field(ge=0.0, le=1.0)


async def main():
    async with (
        AzureCliCredential() as credential,
        MCPStreamableHTTPTool(
            name="Docs MCP",
            url="https://learn.microsoft.com/api/mcp",
        ) as mcp_tool,
        AzureAIAgentsProvider(credential=credential) as provider,
    ):
        agent = await provider.create_agent(
            name="ResearchAssistant",
            instructions="You are a research assistant with multiple capabilities.",
            tools=[
                get_weather,
                HostedCodeInterpreterTool(),
                HostedWebSearchTool(name="Bing"),
                mcp_tool,
            ],
        )
        
        thread = agent.get_new_thread()
        
        # Non-streaming
        result = await agent.run(
            "Search for Python best practices and summarize",
            thread=thread,
        )
        print(f"Response: {result.text}")
        
        # Streaming
        print("\nStreaming: ", end="")
        async for chunk in agent.run_stream("Continue with examples", thread=thread):
            if chunk.text:
                print(chunk.text, end="", flush=True)
        print()
        
        # Structured output
        result = await agent.run(
            "Analyze findings",
            thread=thread,
            response_format=AnalysisResult,
        )
        analysis = AnalysisResult.model_validate_json(result.text)
        print(f"\nModel self-rating (not calibrated reliability): {analysis.confidence}")


if __name__ == "__main__":
    asyncio.run(main())

当前参考资料：Microsoft 提供程序模型、Python 安装与示例。

约定

• 始终使用异步上下文管理器：async with provider:
• 将函数直接传递给 tools= 参数（自动转换为 AIFunction）
• 函数参数使用 Annotated[type, Field(description=...)]
• 多轮对话使用 get_new_thread()
• 服务管理的 MCP 优先使用 HostedMCPTool，客户端管理的 MCP 使用 MCPStreamableHTTPTool

参考文件

• references/tools.md：托管工具的详细模式
• references/mcp.md：MCP 集成（托管 + 本地）
• references/threads.md：线程与对话管理
• references/advanced.md：OpenAPI、引用、结构化输出

适用场景

此技能适用于执行概述中描述的工作流或操作。

限制

• 仅当任务明确符合上述范围时，才使用此技能。
• 不要将输出视为特定环境验证、测试或专家评审的替代品。
• 如果缺少必需的输入、权限、安全边界或成功标准，请停止并请求澄清。