agent/agent-framework
1
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: Create/Get Agent API for Azure V1 (#3192)

Browse Source 
* Added provider implementation for Azure AI V1

* Small fixes

* Fixed OpenAPI example

* Fixed local MCP example

* Fixed hosted MCP example

* Fixed file search sample

* Small fixes

* Resolved comments

* Doc updates
This commit is contained in:
Dmytro Struk
2026-01-15 14:19:03 -08:00
committed by GitHub
Unverified
parent 6e9420f614
commit 48d124efbe
32 changed files with 2119 additions and 640 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/getting_started/agents/azure_ai/azure_ai_with_response_format.py
+1 -1
View File
@@ -34,7 +34,7 @@ async def main() -> None:
name="ProductMarketerAgent",
instructions="Return launch briefs as structured JSON.",
# Specify type to use as response
options={"response_format": ReleaseBrief},
default_options={"response_format": ReleaseBrief},
)
query = "Draft a launch brief for the Contoso Note app."
python/samples/getting_started/agents/azure_ai_agent/README.md
+34 -8
View File
@@ -1,27 +1,53 @@
# Azure AI Agent Examples
This folder contains examples demonstrating different ways to create and use agents with the Azure AI chat client from the `agent_framework.azure` package. These examples use the `AzureAIAgentClient` with the `azure-ai-agents` 1.x (V1) API surface. For updated V2 (`azure-ai-projects` 2.x) samples, see the [Azure AI V2 examples folder](../azure_ai/).
This folder contains examples demonstrating different ways to create and use agents with Azure AI using the `AzureAIAgentsProvider` from the `agent_framework.azure` package. These examples use the `azure-ai-agents` 1.x (V1) API surface. For updated V2 (`azure-ai-projects` 2.x) samples, see the [Azure AI V2 examples folder](../azure_ai/).
## Provider Pattern
All examples in this folder use the `AzureAIAgentsProvider` class which provides a high-level interface for agent operations:
- **`create_agent()`** - Create a new agent on the Azure AI service
- **`get_agent()`** - Retrieve an existing agent by ID or from a pre-fetched Agent object
- **`as_agent()`** - Wrap an SDK Agent object as a ChatAgent without HTTP calls
```python
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
async with (
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="MyAgent",
instructions="You are a helpful assistant.",
tools=my_function,
)
result = await agent.run("Hello!")
```
## Examples
| File | Description |
|------|-------------|
| [`azure_ai_basic.py`](azure_ai_basic.py) | The simplest way to create an agent using `ChatAgent` with `AzureAIAgentClient`. It automatically handles all configuration using environment variables. |
| [`azure_ai_provider_methods.py`](azure_ai_provider_methods.py) | Comprehensive example demonstrating all `AzureAIAgentsProvider` methods: `create_agent()`, `get_agent()`, `as_agent()`, and managing multiple agents from a single provider. |
| [`azure_ai_basic.py`](azure_ai_basic.py) | The simplest way to create an agent using `AzureAIAgentsProvider`. It automatically handles all configuration using environment variables. Shows both streaming and non-streaming responses. |
| [`azure_ai_with_bing_custom_search.py`](azure_ai_with_bing_custom_search.py) | Shows how to use Bing Custom Search with Azure AI agents to find real-time information from the web using custom search configurations. Demonstrates how to set up and use HostedWebSearchTool with custom search instances. |
| [`azure_ai_with_bing_grounding.py`](azure_ai_with_bing_grounding.py) | Shows how to use Bing Grounding search with Azure AI agents to find real-time information from the web. Demonstrates web search capabilities with proper source citations and comprehensive error handling. |
| [`azure_ai_with_bing_grounding_citations.py`](azure_ai_with_bing_grounding_citations.py) | Demonstrates how to extract and display citations from Bing Grounding search responses. Shows how to collect citation annotations (title, URL, snippet) during streaming responses, enabling users to verify sources and access referenced content. |
| [`azure_ai_with_code_interpreter_file_generation.py`](azure_ai_with_code_interpreter_file_generation.py) | Shows how to retrieve file IDs from code interpreter generated files using both streaming and non-streaming approaches. |
| [`azure_ai_with_code_interpreter.py`](azure_ai_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure AI agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
| [`azure_ai_with_existing_agent.py`](azure_ai_with_existing_agent.py) | Shows how to work with a pre-existing agent by providing the agent ID to the Azure AI chat client. This example also demonstrates proper cleanup of manually created agents. |
| [`azure_ai_with_existing_thread.py`](azure_ai_with_existing_thread.py) | Shows how to work with a pre-existing thread by providing the thread ID to the Azure AI chat client. This example also demonstrates proper cleanup of manually created threads. |
| [`azure_ai_with_explicit_settings.py`](azure_ai_with_explicit_settings.py) | Shows how to create an agent with explicitly configured `AzureAIAgentClient` settings, including project endpoint, model deployment, credentials, and agent name. |
| [`azure_ai_with_azure_ai_search.py`](azure_ai_with_azure_ai_search.py) | Demonstrates how to use Azure AI Search with Azure AI agents to search through indexed data. Shows how to configure search parameters, query types, and integrate with existing search indexes. |
| [`azure_ai_with_file_search.py`](azure_ai_with_file_search.py) | Demonstrates how to use the HostedFileSearchTool with Azure AI agents to search through uploaded documents. Shows file upload, vector store creation, and querying document content. Includes both streaming and non-streaming examples. |
| [`azure_ai_with_existing_agent.py`](azure_ai_with_existing_agent.py) | Shows how to work with an existing SDK Agent object using `provider.as_agent()`. This wraps the agent without making HTTP calls. |
| [`azure_ai_with_existing_thread.py`](azure_ai_with_existing_thread.py) | Shows how to work with a pre-existing thread by providing the thread ID. Demonstrates proper cleanup of manually created threads. |
| [`azure_ai_with_explicit_settings.py`](azure_ai_with_explicit_settings.py) | Shows how to create an agent with explicitly configured provider settings, including project endpoint and model deployment name. |
| [`azure_ai_with_azure_ai_search.py`](azure_ai_with_azure_ai_search.py) | Demonstrates how to use Azure AI Search with Azure AI agents. Shows how to create an agent with search tools using the SDK directly and wrap it with `provider.get_agent()`. |
| [`azure_ai_with_file_search.py`](azure_ai_with_file_search.py) | Demonstrates how to use the HostedFileSearchTool with Azure AI agents to search through uploaded documents. Shows file upload, vector store creation, and querying document content. |
| [`azure_ai_with_function_tools.py`](azure_ai_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
| [`azure_ai_with_hosted_mcp.py`](azure_ai_with_hosted_mcp.py) | Shows how to integrate Azure AI agents with hosted Model Context Protocol (MCP) servers for enhanced functionality and tool integration. Demonstrates remote MCP server connections and tool discovery. |
| [`azure_ai_with_local_mcp.py`](azure_ai_with_local_mcp.py) | Shows how to integrate Azure AI agents with local Model Context Protocol (MCP) servers for enhanced functionality and tool integration. Demonstrates both agent-level and run-level tool configuration. |
| [`azure_ai_with_multiple_tools.py`](azure_ai_with_multiple_tools.py) | Demonstrates how to use multiple tools together with Azure AI agents, including web search, MCP servers, and function tools. Shows coordinated multi-tool interactions and approval workflows. |
| [`azure_ai_with_openapi_tools.py`](azure_ai_with_openapi_tools.py) | Demonstrates how to use OpenAPI tools with Azure AI agents to integrate external REST APIs. Shows OpenAPI specification loading, anonymous authentication, thread context management, and coordinated multi-API conversations using weather and countries APIs. |
| [`azure_ai_with_openapi_tools.py`](azure_ai_with_openapi_tools.py) | Demonstrates how to use OpenAPI tools with Azure AI agents to integrate external REST APIs. Shows OpenAPI specification loading, anonymous authentication, thread context management, and coordinated multi-API conversations. |
| [`azure_ai_with_response_format.py`](azure_ai_with_response_format.py) | Demonstrates how to use structured outputs with Azure AI agents using Pydantic models. |
| [`azure_ai_with_thread.py`](azure_ai_with_thread.py) | Demonstrates thread management with Azure AI agents, including automatic thread creation for stateless conversations and explicit thread management for maintaining conversation context across multiple interactions. |
## Environment Variables
python/samples/getting_started/agents/azure_ai_agent/azure_ai_basic.py
+10 -12
View File
@@ -4,14 +4,14 @@ import asyncio
from random import randint
from typing import Annotated
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
from pydantic import Field
"""
Azure AI Agent Basic Example
This sample demonstrates basic usage of AzureAIAgentClient to create agents with automatic
This sample demonstrates basic usage of AzureAIAgentsProvider to create agents with automatic
lifecycle management. Shows both streaming and non-streaming responses with function tools.
"""
@@ -28,18 +28,17 @@ async def non_streaming_example() -> None:
"""Example of non-streaming response (get the complete result at once)."""
print("=== Non-streaming Response Example ===")
# Since no Agent ID is provided, the agent will be automatically created
# and deleted after getting a response
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
async with (
AzureCliCredential() as credential,
AzureAIAgentClient(credential=credential).create_agent(
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent,
):
)
query = "What's the weather like in Seattle?"
print(f"User: {query}")
result = await agent.run(query)
@@ -50,18 +49,17 @@ async def streaming_example() -> None:
"""Example of streaming response (get results as they are generated)."""
print("=== Streaming Response Example ===")
# Since no Agent ID is provided, the agent will be automatically created
# and deleted after getting a response
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
async with (
AzureCliCredential() as credential,
AzureAIAgentClient(credential=credential).create_agent(
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent,
):
)
query = "What's the weather like in Portland?"
print(f"User: {query}")
print("Agent: ", end="", flush=True)
python/samples/getting_started/agents/azure_ai_agent/azure_ai_provider_methods.py
+142
View File
@@ -0,0 +1,142 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from random import randint
from typing import Annotated
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.aio import AgentsClient
from azure.identity.aio import AzureCliCredential
from pydantic import Field
"""
Azure AI Agent Provider Methods Example
This sample demonstrates the methods available on the AzureAIAgentsProvider class:
- create_agent(): Create a new agent on the service
- get_agent(): Retrieve an existing agent by ID
- as_agent(): Wrap an SDK Agent object without making HTTP calls
"""
def get_weather(
location: Annotated[str, Field(description="The location to get the weather for.")],
) -> str:
"""Get the weather for a given location."""
conditions = ["sunny", "cloudy", "rainy", "stormy"]
return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."
async def create_agent_example() -> None:
"""Create a new agent using provider.create_agent()."""
print("\n--- create_agent() ---")
async with (
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather assistant.",
tools=get_weather,
)
print(f"Created: {agent.name} (ID: {agent.id})")
result = await agent.run("What's the weather in Seattle?")
print(f"Response: {result}")
async def get_agent_example() -> None:
"""Retrieve an existing agent by ID using provider.get_agent()."""
print("\n--- get_agent() ---")
async with (
AzureCliCredential() as credential,
AgentsClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as agents_client,
AzureAIAgentsProvider(agents_client=agents_client) as provider,
):
# Create an agent directly with SDK (simulating pre-existing agent)
sdk_agent = await agents_client.create_agent(
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
name="ExistingAgent",
instructions="You always respond with 'Hello!'",
)
try:
# Retrieve using provider
agent = await provider.get_agent(sdk_agent.id)
print(f"Retrieved: {agent.name} (ID: {agent.id})")
result = await agent.run("Hi there!")
print(f"Response: {result}")
finally:
await agents_client.delete_agent(sdk_agent.id)
async def as_agent_example() -> None:
"""Wrap an SDK Agent object using provider.as_agent()."""
print("\n--- as_agent() ---")
async with (
AzureCliCredential() as credential,
AgentsClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as agents_client,
AzureAIAgentsProvider(agents_client=agents_client) as provider,
):
# Create agent using SDK
sdk_agent = await agents_client.create_agent(
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
name="WrappedAgent",
instructions="You respond with poetry.",
)
try:
# Wrap synchronously (no HTTP call)
agent = provider.as_agent(sdk_agent)
print(f"Wrapped: {agent.name} (ID: {agent.id})")
result = await agent.run("Tell me about the sunset.")
print(f"Response: {result}")
finally:
await agents_client.delete_agent(sdk_agent.id)
async def multiple_agents_example() -> None:
"""Create and manage multiple agents with a single provider."""
print("\n--- Multiple Agents ---")
async with (
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
weather_agent = await provider.create_agent(
name="WeatherSpecialist",
instructions="You are a weather specialist.",
tools=get_weather,
)
greeter_agent = await provider.create_agent(
name="GreeterAgent",
instructions="You are a friendly greeter.",
)
print(f"Created: {weather_agent.name}, {greeter_agent.name}")
greeting = await greeter_agent.run("Hello!")
print(f"Greeter: {greeting}")
weather = await weather_agent.run("What's the weather in Tokyo?")
print(f"Weather: {weather}")
async def main() -> None:
print("Azure AI Agent Provider Methods")
await create_agent_example()
await get_agent_example()
await as_agent_example()
await multiple_agents_example()
if __name__ == "__main__":
asyncio.run(main())
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_azure_ai_search.py
+34 -37
View File
@@ -3,8 +3,8 @@
import asyncio
import os
from agent_framework import ChatAgent, CitationAnnotation
from agent_framework.azure import AzureAIAgentClient
from agent_framework import CitationAnnotation
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.aio import AgentsClient
from azure.ai.projects.aio import AIProjectClient
from azure.ai.projects.models import ConnectionType
@@ -41,6 +41,7 @@ async def main() -> None:
AzureCliCredential() as credential,
AIProjectClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as project_client,
AgentsClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as agents_client,
AzureAIAgentsProvider(agents_client=agents_client) as provider,
):
ai_search_conn_id = ""
async for connection in project_client.connections.list():
@@ -48,7 +49,8 @@ async def main() -> None:
ai_search_conn_id = connection.id
break
# 1. Create Azure AI agent with the search tool
# 1. Create Azure AI agent with the search tool using SDK directly
# (Azure AI Search tool requires special tool_resources configuration)
azure_ai_agent = await agents_client.create_agent(
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
name="HotelSearchAgent",
@@ -70,47 +72,42 @@ async def main() -> None:
},
)
# 2. Create chat client with the existing agent
chat_client = AzureAIAgentClient(agents_client=agents_client, agent_id=azure_ai_agent.id)
try:
async with ChatAgent(
chat_client=chat_client,
# Additional instructions for this specific conversation
instructions=("You are a helpful agent that uses the search tool and index to find hotel information."),
) as agent:
print("This agent uses raw Azure AI Search tool to search hotel data.\n")
# 2. Use provider.as_agent() to wrap the existing agent
agent = provider.as_agent(agent=azure_ai_agent)
# 3. Simulate conversation with the agent
user_input = (
"Use Azure AI search knowledge tool to find detailed information about a winter hotel."
" Use the search tool and index." # You can modify prompt to force tool usage
)
print(f"User: {user_input}")
print("Agent: ", end="", flush=True)
print("This agent uses raw Azure AI Search tool to search hotel data.\n")
# Stream the response and collect citations
citations: list[CitationAnnotation] = []
async for chunk in agent.run_stream(user_input):
if chunk.text:
print(chunk.text, end="", flush=True)
# 3. Simulate conversation with the agent
user_input = (
"Use Azure AI search knowledge tool to find detailed information about a winter hotel."
" Use the search tool and index." # You can modify prompt to force tool usage
)
print(f"User: {user_input}")
print("Agent: ", end="", flush=True)
# Collect citations from Azure AI Search responses
for content in getattr(chunk, "contents", []):
annotations = getattr(content, "annotations", [])
if annotations:
citations.extend(annotations)
# Stream the response and collect citations
citations: list[CitationAnnotation] = []
async for chunk in agent.run_stream(user_input):
if chunk.text:
print(chunk.text, end="", flush=True)
print()
# Collect citations from Azure AI Search responses
for content in getattr(chunk, "contents", []):
annotations = getattr(content, "annotations", [])
if annotations:
citations.extend(annotations)
# Display collected citation
if citations:
print("\n\nCitation:")
for i, citation in enumerate(citations, 1):
print(f"[{i}] {citation.url}")
print()
print("\n" + "=" * 50 + "\n")
print("Hotel search conversation completed!")
# Display collected citation
if citations:
print("\n\nCitation:")
for i, citation in enumerate(citations, 1):
print(f"[{i}] {citation.url}")
print("\n" + "=" * 50 + "\n")
print("Hotel search conversation completed!")
finally:
# Clean up the agent manually
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_bing_custom_search.py
+9 -8
View File
@@ -2,8 +2,8 @@
import asyncio
from agent_framework import ChatAgent, HostedWebSearchTool
from agent_framework.azure import AzureAIAgentClient
from agent_framework import HostedWebSearchTool
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
"""
@@ -37,19 +37,20 @@ async def main() -> None:
description="Search the web for current information using Bing Custom Search",
)
# 2. Use AzureAIAgentClient as async context manager for automatic cleanup
# 2. Use AzureAIAgentsProvider for agent creation and management
async with (
AzureAIAgentClient(credential=AzureCliCredential()) as client,
ChatAgent(
chat_client=client,
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="BingSearchAgent",
instructions=(
"You are a helpful agent that can use Bing Custom Search tools to assist users. "
"Use the available Bing Custom Search tools to answer questions and perform tasks."
),
tools=bing_search_tool,
) as agent,
):
)
# 3. Demonstrate agent capabilities with bing custom search
print("=== Azure AI Agent with Bing Custom Search ===\n")
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_bing_grounding.py
+10 -9
View File
@@ -2,8 +2,8 @@
import asyncio
from agent_framework import ChatAgent, HostedWebSearchTool
from agent_framework_azure_ai import AzureAIAgentClient
from agent_framework import HostedWebSearchTool
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
"""
@@ -32,11 +32,12 @@ async def main() -> None:
description="Search the web for current information using Bing",
)
# 2. Use AzureAIAgentClient as async context manager for automatic cleanup
# 2. Use AzureAIAgentsProvider for agent creation and management
async with (
AzureAIAgentClient(credential=AzureCliCredential()) as client,
ChatAgent(
chat_client=client,
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="BingSearchAgent",
instructions=(
"You are a helpful assistant that can search the web for current information. "
@@ -44,9 +45,9 @@ async def main() -> None:
"well-sourced answers. Always cite your sources when possible."
),
tools=bing_search_tool,
) as agent,
):
# 4. Demonstrate agent capabilities with web search
)
# 3. Demonstrate agent capabilities with web search
print("=== Azure AI Agent with Bing Grounding Search ===\n")
user_input = "What is the most popular programming language?"
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_bing_grounding_citations.py
+9 -8
View File
@@ -2,8 +2,8 @@
import asyncio
from agent_framework import ChatAgent, CitationAnnotation, HostedWebSearchTool
from agent_framework.azure import AzureAIAgentClient
from agent_framework import CitationAnnotation, HostedWebSearchTool
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
"""
@@ -34,11 +34,12 @@ async def main() -> None:
description="Search the web for current information using Bing",
)
# 2. Use AzureAIAgentClient as async context manager for automatic cleanup
# 2. Use AzureAIAgentsProvider for agent creation and management
async with (
AzureAIAgentClient(credential=AzureCliCredential()) as client,
ChatAgent(
chat_client=client,
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="BingSearchAgent",
instructions=(
"You are a helpful assistant that can search the web for current information. "
@@ -46,8 +47,8 @@ async def main() -> None:
"well-sourced answers. Always cite your sources when possible."
),
tools=bing_search_tool,
) as agent,
):
)
# 3. Demonstrate agent capabilities with web search
print("=== Azure AI Agent with Bing Grounding Search ===\n")
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_code_interpreter.py
+4 -4
View File
@@ -3,7 +3,7 @@
import asyncio
from agent_framework import AgentResponse, ChatResponseUpdate, HostedCodeInterpreterTool
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.models import (
RunStepDeltaCodeInterpreterDetailItemObject,
)
@@ -39,16 +39,16 @@ async def main() -> None:
# authentication option.
async with (
AzureCliCredential() as credential,
AzureAIAgentClient(credential=credential) as chat_client,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = chat_client.create_agent(
agent = await provider.create_agent(
name="CodingAgent",
instructions=("You are a helpful assistant that can write and execute Python code to solve problems."),
tools=HostedCodeInterpreterTool(),
)
query = "Generate the factorial of 100 using python code, show the code and execute it."
print(f"User: {query}")
response = await AgentResponse.from_agent_response_generator(agent.run_stream(query))
response = await agent.run(query)
print(f"Agent: {response}")
# To review the code interpreter outputs, you can access
# them from the response raw_representations, just uncomment the next line:
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_code_interpreter_file_generation.py
+71 -67
View File
@@ -1,15 +1,21 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from agent_framework import AgentResponseUpdate, ChatAgent, HostedCodeInterpreterTool, HostedFileContent
from agent_framework.azure import AzureAIAgentClient
from agent_framework import (
AgentResponseUpdate,
HostedCodeInterpreterTool,
HostedFileContent,
)
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.aio import AgentsClient
from azure.identity.aio import AzureCliCredential
"""
Azure AI Agent Code Interpreter File Generation Example
This sample demonstrates using HostedCodeInterpreterTool with AzureAIAgentClient
This sample demonstrates using HostedCodeInterpreterTool with AzureAIAgentsProvider
to generate a text file and then retrieve it.
The test flow:
@@ -23,79 +29,77 @@ The test flow:
async def main() -> None:
"""Test file generation and retrieval with code interpreter."""
async with AzureCliCredential() as credential:
client = AzureAIAgentClient(credential=credential)
async with (
AzureCliCredential() as credential,
AgentsClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as agents_client,
AzureAIAgentsProvider(agents_client=agents_client) as provider,
):
agent = await provider.create_agent(
name="CodeInterpreterAgent",
instructions=(
"You are a Python code execution assistant. "
"ALWAYS use the code interpreter tool to execute Python code when asked to create files. "
"Write actual Python code to create files, do not just describe what you would do."
),
tools=[HostedCodeInterpreterTool()],
)
try:
async with ChatAgent(
chat_client=client,
instructions=(
"You are a Python code execution assistant. "
"ALWAYS use the code interpreter tool to execute Python code when asked to create files. "
"Write actual Python code to create files, do not just describe what you would do."
),
tools=[HostedCodeInterpreterTool()],
) as agent:
# Be very explicit about wanting code execution and a download link
query = (
"Use the code interpreter to execute this Python code and then provide me "
"with a download link for the generated file:\n"
"```python\n"
"with open('/mnt/data/sample.txt', 'w') as f:\n"
" f.write('Hello, World! This is a test file.')\n"
"'/mnt/data/sample.txt'\n" # Return the path so it becomes downloadable
"```"
)
print(f"User: {query}\n")
print("=" * 60)
# Be very explicit about wanting code execution and a download link
query = (
"Use the code interpreter to execute this Python code and then provide me "
"with a download link for the generated file:\n"
"```python\n"
"with open('/mnt/data/sample.txt', 'w') as f:\n"
" f.write('Hello, World! This is a test file.')\n"
"'/mnt/data/sample.txt'\n" # Return the path so it becomes downloadable
"```"
)
print(f"User: {query}\n")
print("=" * 60)
# Collect file_ids from the response
file_ids: list[str] = []
# Collect file_ids from the response
file_ids: list[str] = []
async for chunk in agent.run_stream(query):
if not isinstance(chunk, AgentResponseUpdate):
continue
async for chunk in agent.run_stream(query):
if not isinstance(chunk, AgentResponseUpdate):
continue
for content in chunk.contents:
if content.type == "text":
print(content.text, end="", flush=True)
elif content.type == "hosted_file":
if isinstance(content, HostedFileContent):
file_ids.append(content.file_id)
print(f"\n[File generated: {content.file_id}]")
for content in chunk.contents:
if content.type == "text":
print(content.text, end="", flush=True)
elif content.type == "hosted_file" and isinstance(content, HostedFileContent):
file_ids.append(content.file_id)
print(f"\n[File generated: {content.file_id}]")
print("\n" + "=" * 60)
print("\n" + "=" * 60)
# Attempt to retrieve discovered files
if file_ids:
print(f"\nAttempting to retrieve {len(file_ids)} file(s):")
for file_id in file_ids:
try:
file_info = await client.agents_client.files.get(file_id)
print(f" File {file_id}: Retrieved successfully")
print(f" Filename: {file_info.filename}")
print(f" Purpose: {file_info.purpose}")
print(f" Bytes: {file_info.bytes}")
except Exception as e:
print(f" File {file_id}: FAILED to retrieve - {e}")
else:
print("No file IDs were captured from the response.")
# List all files to see if any exist
print("\nListing all files in the agent service:")
# Attempt to retrieve discovered files
if file_ids:
print(f"\nAttempting to retrieve {len(file_ids)} file(s):")
for file_id in file_ids:
try:
files_list = await client.agents_client.files.list()
count = 0
for file_info in files_list.data:
count += 1
print(f" - {file_info.id}: {file_info.filename} ({file_info.purpose})")
if count == 0:
print(" No files found.")
file_info = await agents_client.files.get(file_id)
print(f" File {file_id}: Retrieved successfully")
print(f" Filename: {file_info.filename}")
print(f" Purpose: {file_info.purpose}")
print(f" Bytes: {file_info.bytes}")
except Exception as e:
print(f" Failed to list files: {e}")
print(f" File {file_id}: FAILED to retrieve - {e}")
else:
print("No file IDs were captured from the response.")
finally:
await client.close()
# List all files to see if any exist
print("\nListing all files in the agent service:")
try:
files_list = await agents_client.files.list()
count = 0
for file_info in files_list.data:
count += 1
print(f" - {file_info.id}: {file_info.filename} ({file_info.purpose})")
if count == 0:
print(" No files found.")
except Exception as e:
print(f" Failed to list files: {e}")
if __name__ == "__main__":
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_existing_agent.py
+13 -22
View File
@@ -3,8 +3,7 @@
import asyncio
import os
from agent_framework import ChatAgent
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.aio import AgentsClient
from azure.identity.aio import AzureCliCredential
@@ -17,37 +16,29 @@ agent IDs, showing agent reuse patterns for production scenarios.
async def main() -> None:
print("=== Azure AI Chat Client with Existing Agent ===")
print("=== Azure AI Agent with Existing Agent ===")
# Create the client
# Create the client and provider
async with (
AzureCliCredential() as credential,
AgentsClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as agents_client,
AzureAIAgentsProvider(agents_client=agents_client) as provider,
):
# Create an agent on the service with default instructions
# These instructions will persist on created agent for every run.
azure_ai_agent = await agents_client.create_agent(
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
# Create remote agent with default instructions
# These instructions will persist on created agent for every run.
instructions="End each response with [END].",
)
chat_client = AzureAIAgentClient(agents_client=agents_client, agent_id=azure_ai_agent.id)
try:
async with ChatAgent(
chat_client=chat_client,
# Instructions here are applicable only to this ChatAgent instance
# These instructions will be combined with instructions on existing remote agent.
# The final instructions during the execution will look like:
# "'End each response with [END]. Respond with 'Hello World' only'"
instructions="Respond with 'Hello World' only",
) as agent:
query = "How are you?"
print(f"User: {query}")
result = await agent.run(query)
# Based on local and remote instructions, the result will be
# 'Hello World [END]'.
print(f"Agent: {result}\n")
# Wrap existing agent instance using provider.as_agent()
agent = provider.as_agent(azure_ai_agent)
query = "How are you?"
print(f"User: {query}")
result = await agent.run(query)
print(f"Agent: {result}\n")
finally:
# Clean up the agent manually
await agents_client.delete_agent(azure_ai_agent.id)
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_existing_thread.py
+14 -14
View File
@@ -5,8 +5,7 @@ import os
from random import randint
from typing import Annotated
from agent_framework import ChatAgent
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.aio import AgentsClient
from azure.identity.aio import AzureCliCredential
from pydantic import Field
@@ -28,28 +27,29 @@ def get_weather(
async def main() -> None:
print("=== Azure AI Chat Client with Existing Thread ===")
print("=== Azure AI Agent with Existing Thread ===")
# Create the client
# Create the client and provider
async with (
AzureCliCredential() as credential,
AgentsClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as agents_client,
AzureAIAgentsProvider(agents_client=agents_client) as provider,
):
# Create an thread that will persist
# Create a thread that will persist
created_thread = await agents_client.threads.create()
try:
async with ChatAgent(
# passing in the client is optional here, so if you take the agent_id from the portal
# you can use it directly without the two lines above.
chat_client=AzureAIAgentClient(agents_client=agents_client),
# Create agent using provider
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent:
thread = agent.get_new_thread(service_thread_id=created_thread.id)
assert thread.is_initialized
result = await agent.run("What's the weather like in Tokyo?", thread=thread)
print(f"Result: {result}\n")
)
thread = agent.get_new_thread(service_thread_id=created_thread.id)
assert thread.is_initialized
result = await agent.run("What's the weather like in Tokyo?", thread=thread)
print(f"Result: {result}\n")
finally:
# Clean up the thread manually
await agents_client.threads.delete(created_thread.id)
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_explicit_settings.py
+11 -15
View File
@@ -5,8 +5,7 @@ import os
from random import randint
from typing import Annotated
from agent_framework import ChatAgent
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
from pydantic import Field
@@ -27,26 +26,23 @@ def get_weather(
async def main() -> None:
print("=== Azure AI Chat Client with Explicit Settings ===")
print("=== Azure AI Agent with Explicit Settings ===")
# Since no Agent ID is provided, the agent will be automatically created
# and deleted after getting a response
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
model_deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
credential=credential,
agent_name="WeatherAgent",
should_cleanup_agent=True, # Set to False if you want to disable automatic agent cleanup
),
AzureAIAgentsProvider(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
credential=credential,
) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent,
):
)
result = await agent.run("What's the weather like in New York?")
print(f"Result: {result}\n")
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_file_search.py
+32 -43
View File
@@ -1,10 +1,12 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from pathlib import Path
from agent_framework import ChatAgent, HostedFileSearchTool, HostedVectorStoreContent
from agent_framework.azure import AzureAIAgentClient
from agent_framework import HostedFileSearchTool, HostedVectorStoreContent
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.aio import AgentsClient
from azure.ai.agents.models import FileInfo, VectorStore
from azure.identity.aio import AzureCliCredential
@@ -24,67 +26,54 @@ USER_INPUTS = [
async def main() -> None:
"""Main function demonstrating Azure AI agent with file search capabilities."""
client = AzureAIAgentClient(credential=AzureCliCredential())
file: FileInfo | None = None
vector_store: VectorStore | None = None
try:
# 1. Upload file and create vector store
pdf_file_path = Path(__file__).parent.parent / "resources" / "employees.pdf"
print(f"Uploading file from: {pdf_file_path}")
async with (
AzureCliCredential() as credential,
AgentsClient(endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"], credential=credential) as agents_client,
AzureAIAgentsProvider(agents_client=agents_client) as provider,
):
try:
# 1. Upload file and create vector store
pdf_file_path = Path(__file__).parent.parent / "resources" / "employees.pdf"
print(f"Uploading file from: {pdf_file_path}")
file = await client.agents_client.files.upload_and_poll(file_path=str(pdf_file_path), purpose="assistants")
print(f"Uploaded file, file ID: {file.id}")
file = await agents_client.files.upload_and_poll(file_path=str(pdf_file_path), purpose="assistants")
print(f"Uploaded file, file ID: {file.id}")
vector_store = await client.agents_client.vector_stores.create_and_poll(
file_ids=[file.id], name="my_vectorstore"
)
print(f"Created vector store, vector store ID: {vector_store.id}")
vector_store = await agents_client.vector_stores.create_and_poll(file_ids=[file.id], name="my_vectorstore")
print(f"Created vector store, vector store ID: {vector_store.id}")
# 2. Create file search tool with uploaded resources
file_search_tool = HostedFileSearchTool(inputs=[HostedVectorStoreContent(vector_store_id=vector_store.id)])
# 2. Create file search tool with uploaded resources
file_search_tool = HostedFileSearchTool(inputs=[HostedVectorStoreContent(vector_store_id=vector_store.id)])
# 3. Create an agent with file search capabilities
agent = await provider.create_agent(
name="EmployeeSearchAgent",
instructions=(
"You are a helpful assistant that can search through uploaded employee files "
"to answer questions about employees."
),
tools=file_search_tool,
)
# 3. Create an agent with file search capabilities
# The tool_resources are automatically extracted from HostedFileSearchTool
async with ChatAgent(
chat_client=client,
name="EmployeeSearchAgent",
instructions=(
"You are a helpful assistant that can search through uploaded employee files "
"to answer questions about employees."
),
tools=file_search_tool,
) as agent:
# 4. Simulate conversation with the agent
for user_input in USER_INPUTS:
print(f"# User: '{user_input}'")
response = await agent.run(user_input)
print(f"# Agent: {response.text}")
finally:
# 5. Cleanup: Delete the vector store and file
try:
if vector_store:
await client.agents_client.vector_stores.delete(vector_store.id)
await agents_client.vector_stores.delete(vector_store.id)
if file:
await client.agents_client.files.delete(file.id)
await agents_client.files.delete(file.id)
except Exception:
# Ignore cleanup errors to avoid masking issues
pass
finally:
# 6. Cleanup: Delete the vector store and file in case of earlier failure to prevent orphaned resources.
# Refreshing the client is required since chat agent closes it
client = AzureAIAgentClient(credential=AzureCliCredential())
try:
if vector_store:
await client.agents_client.vector_stores.delete(vector_store.id)
if file:
await client.agents_client.files.delete(file.id)
except Exception:
# Ignore cleanup errors to avoid masking issues
pass
finally:
await client.close()
if __name__ == "__main__":
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_function_tools.py
+19 -14
View File
@@ -5,8 +5,7 @@ from datetime import datetime, timezone
from random import randint
from typing import Annotated
from agent_framework import ChatAgent
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
from pydantic import Field
@@ -42,12 +41,14 @@ async def tools_on_agent_level() -> None:
# authentication option.
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="AssistantAgent",
instructions="You are a helpful assistant that can provide weather and time information.",
tools=[get_weather, get_time], # Tools defined at agent creation
) as agent,
):
)
# First query - agent can use weather tool
query1 = "What's the weather like in New York?"
print(f"User: {query1}")
@@ -76,12 +77,14 @@ async def tools_on_run_level() -> None:
# authentication option.
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="AssistantAgent",
instructions="You are a helpful assistant.",
# No tools defined here
) as agent,
):
)
# First query with weather tool
query1 = "What's the weather like in Seattle?"
print(f"User: {query1}")
@@ -110,12 +113,14 @@ async def mixed_tools_example() -> None:
# authentication option.
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="AssistantAgent",
instructions="You are a comprehensive assistant that can help with various information requests.",
tools=[get_weather], # Base tool available for all queries
) as agent,
):
)
# Query using both agent tool and additional run-method tools
query = "What's the weather in Denver and what's the current UTC time?"
print(f"User: {query}")
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_hosted_mcp.py
+3 -3
View File
@@ -4,7 +4,7 @@ import asyncio
from typing import Any
from agent_framework import AgentProtocol, AgentResponse, AgentThread, HostedMCPTool
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
"""
@@ -42,9 +42,9 @@ async def main() -> None:
"""Example showing Hosted MCP tools for a Azure AI Agent."""
async with (
AzureCliCredential() as credential,
AzureAIAgentClient(credential=credential) as chat_client,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = chat_client.create_agent(
agent = await provider.create_agent(
name="DocsAgent",
instructions="You are a helpful assistant that can help with microsoft documentation questions.",
tools=HostedMCPTool(
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_local_mcp.py
+27 -24
View File
@@ -2,8 +2,8 @@
import asyncio
from agent_framework import ChatAgent, MCPStreamableHTTPTool
from agent_framework.azure import AzureAIAgentClient
from agent_framework import MCPStreamableHTTPTool
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
"""
@@ -27,12 +27,12 @@ async def mcp_tools_on_run_level() -> None:
name="Microsoft Learn MCP",
url="https://learn.microsoft.com/api/mcp",
) as mcp_server,
ChatAgent(
chat_client=AzureAIAgentClient(credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="DocsAgent",
instructions="You are a helpful assistant that can help with microsoft documentation questions.",
) as agent,
):
)
# First query
query1 = "How to create an Azure storage account using az cli?"
print(f"User: {query1}")
@@ -47,34 +47,37 @@ async def mcp_tools_on_run_level() -> None:
async def mcp_tools_on_agent_level() -> None:
"""Example showing tools defined when creating the agent."""
"""Example showing local MCP tools passed when creating the agent."""
print("=== Tools Defined on Agent Level ===")
# Tools are provided when creating the agent
# The agent can use these tools for any query during its lifetime
# The agent will connect to the MCP server through its context manager.
# The ChatAgent will connect to the MCP server through its context manager
# and discover tools at runtime
async with (
AzureCliCredential() as credential,
AzureAIAgentClient(credential=credential).create_agent(
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="DocsAgent",
instructions="You are a helpful assistant that can help with microsoft documentation questions.",
tools=MCPStreamableHTTPTool( # Tools defined at agent creation
tools=MCPStreamableHTTPTool(
name="Microsoft Learn MCP",
url="https://learn.microsoft.com/api/mcp",
),
) as agent,
):
# First query
query1 = "How to create an Azure storage account using az cli?"
print(f"User: {query1}")
result1 = await agent.run(query1)
print(f"{agent.name}: {result1}\n")
print("\n=======================================\n")
# Second query
query2 = "What is Microsoft Agent Framework?"
print(f"User: {query2}")
result2 = await agent.run(query2)
print(f"{agent.name}: {result2}\n")
)
# Use agent as context manager to connect MCP tools
async with agent:
# First query
query1 = "How to create an Azure storage account using az cli?"
print(f"User: {query1}")
result1 = await agent.run(query1)
print(f"{agent.name}: {result1}\n")
print("\n=======================================\n")
# Second query
query2 = "What is Microsoft Agent Framework?"
print(f"User: {query2}")
result2 = await agent.run(query2)
print(f"{agent.name}: {result2}\n")
async def main() -> None:
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_multiple_tools.py
+3 -3
View File
@@ -10,7 +10,7 @@ from agent_framework import (
HostedMCPTool,
HostedWebSearchTool,
)
from agent_framework.azure import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
"""
@@ -67,9 +67,9 @@ async def main() -> None:
"""Example showing Hosted MCP tools for a Azure AI Agent."""
async with (
AzureCliCredential() as credential,
AzureAIAgentClient(credential=credential) as chat_client,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = chat_client.create_agent(
agent = await provider.create_agent(
name="DocsAgent",
instructions="You are a helpful assistant that can help with microsoft documentation questions.",
tools=[
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_openapi_tools.py
+18 -16
View File
@@ -5,8 +5,7 @@ import json
from pathlib import Path
from typing import Any
from agent_framework import ChatAgent
from agent_framework_azure_ai import AzureAIAgentClient
from agent_framework.azure import AzureAIAgentsProvider
from azure.ai.agents.models import OpenApiAnonymousAuthDetails, OpenApiTool
from azure.identity.aio import AzureCliCredential
@@ -40,8 +39,11 @@ async def main() -> None:
# 1. Load OpenAPI specifications (synchronous operation)
weather_openapi_spec, countries_openapi_spec = load_openapi_specs()
# 2. Use AzureAIAgentClient as async context manager for automatic cleanup
async with AzureAIAgentClient(credential=AzureCliCredential()) as client:
# 2. Use AzureAIAgentsProvider for agent creation and management
async with (
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
# 3. Create OpenAPI tools using Azure AI's OpenApiTool
auth = OpenApiAnonymousAuthDetails()
@@ -62,8 +64,7 @@ async def main() -> None:
# 4. Create an agent with OpenAPI tools
# Note: We need to pass the Azure AI native OpenApiTool definitions directly
# since the agent framework doesn't have a HostedOpenApiTool wrapper yet
async with ChatAgent(
chat_client=client,
agent = await provider.create_agent(
name="OpenAPIAgent",
instructions=(
"You are a helpful assistant that can search for country information "
@@ -73,18 +74,19 @@ async def main() -> None:
),
# Pass the raw tool definitions from Azure AI's OpenApiTool
tools=[*openapi_countries.definitions, *openapi_weather.definitions],
) as agent:
# 5. Simulate conversation with the agent maintaining thread context
print("=== Azure AI Agent with OpenAPI Tools ===\n")
)
# Create a thread to maintain conversation context across multiple runs
thread = agent.get_new_thread()
# 5. Simulate conversation with the agent maintaining thread context
print("=== Azure AI Agent with OpenAPI Tools ===\n")
for user_input in USER_INPUTS:
print(f"User: {user_input}")
# Pass the thread to maintain context across multiple agent.run() calls
response = await agent.run(user_input, thread=thread)
print(f"Agent: {response.text}\n")
# Create a thread to maintain conversation context across multiple runs
thread = agent.get_new_thread()
for user_input in USER_INPUTS:
print(f"User: {user_input}")
# Pass the thread to maintain context across multiple agent.run() calls
response = await agent.run(user_input, thread=thread)
print(f"Agent: {response.text}\n")
if __name__ == "__main__":
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_response_format.py
+55
View File
@@ -0,0 +1,55 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
from pydantic import BaseModel, ConfigDict
"""
Azure AI Agent Provider Response Format Example
This sample demonstrates using AzureAIAgentsProvider with default_options
containing response_format for structured outputs.
"""
class WeatherInfo(BaseModel):
"""Structured weather information."""
location: str
temperature: int
conditions: str
recommendation: str
model_config = ConfigDict(extra="forbid")
async def main() -> None:
"""Example of using default_options with response_format in AzureAIAgentsProvider."""
async with (
AzureCliCredential() as credential,
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherReporter",
instructions="You provide weather reports in structured JSON format.",
default_options={"response_format": WeatherInfo},
)
query = "What's the weather like in Paris today?"
print(f"User: {query}")
result = await agent.run(query)
if isinstance(result.value, WeatherInfo):
weather = result.value
print("Agent:")
print(f"Location: {weather.location}")
print(f"Temperature: {weather.temperature}")
print(f"Conditions: {weather.conditions}")
print(f"Recommendation: {weather.recommendation}")
if __name__ == "__main__":
asyncio.run(main())
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_thread.py
+27 -19
View File
@@ -4,8 +4,8 @@ import asyncio
from random import randint
from typing import Annotated
from agent_framework import AgentThread, ChatAgent
from agent_framework.azure import AzureAIAgentClient
from agent_framework import AgentThread
from agent_framework.azure import AzureAIAgentsProvider
from azure.identity.aio import AzureCliCredential
from pydantic import Field
@@ -33,12 +33,14 @@ async def example_with_automatic_thread_creation() -> None:
# authentication option.
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent,
):
)
# First conversation - no thread provided, will be created automatically
first_query = "What's the weather like in Seattle?"
print(f"User: {first_query}")
@@ -62,12 +64,14 @@ async def example_with_thread_persistence() -> None:
# authentication option.
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent,
):
)
# Create a new thread that will be reused
thread = agent.get_new_thread()
@@ -103,12 +107,14 @@ async def example_with_existing_thread_id() -> None:
# authentication option.
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent,
):
)
# Start a conversation and get the thread ID
thread = agent.get_new_thread()
first_query = "What's the weather in Paris?"
@@ -123,15 +129,17 @@ async def example_with_existing_thread_id() -> None:
if existing_thread_id:
print("\n--- Continuing with the same thread ID in a new agent instance ---")
# Create a new agent instance but use the existing thread ID
# Create a new provider and agent but use the existing thread ID
async with (
AzureCliCredential() as credential,
ChatAgent(
chat_client=AzureAIAgentClient(thread_id=existing_thread_id, credential=credential),
AzureAIAgentsProvider(credential=credential) as provider,
):
agent = await provider.create_agent(
name="WeatherAgent",
instructions="You are a helpful weather agent.",
tools=get_weather,
) as agent,
):
)
# Create a thread with the existing ID
thread = AgentThread(service_thread_id=existing_thread_id)