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: Allow AzureOpenAIResponsesClient creation with Foundry project endpoint (#3814)

Browse Source 
* Initial plan

* feat: extend AzureOpenAIResponsesClient to support Foundry project endpoints

Add project_client and project_endpoint parameters to allow creating
the client via an Azure AI Foundry project. When provided, the client
uses AIProjectClient.get_openai_client() to obtain the OpenAI client.
The azure-ai-projects package is imported lazily and only required
when using the project endpoint path.

Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com>

* fix: address code review - remove duplicate MagicMock imports in tests

Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com>

* fix: add type field to Responses API input items and add Foundry sample

- Add 'type: message' to input items in _prepare_message_for_openai
  to comply with the Responses API schema requirement
- Filter out empty dicts from unsupported content types to prevent
  sending items with invalid empty type values
- Add azure_responses_client_with_foundry.py sample demonstrating
  AzureOpenAIResponsesClient with project_endpoint
- Update README and pyrightconfig.samples.json accordingly

* updates to response format and setup

* fix: patch AIProjectClient at correct module path in test

Patch agent_framework.azure._responses_client.AIProjectClient instead of
azure.ai.projects.aio.AIProjectClient since the import is at module level.

* docs: add Foundry sample to READMEs and document AZURE_AI_PROJECT_ENDPOINT env var

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: eavanvalkenburg <13749212+eavanvalkenburg@users.noreply.github.com>
Co-authored-by: eavanvalkenburg <github@vanvalkenburg.eu>
This commit is contained in:
Copilot
2026-02-11 16:46:25 +01:00
committed by GitHub
Unverified
parent 235c578059
commit a427af91a9
12 changed files with 349 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/README.md
+1
View File
@@ -78,6 +78,7 @@ This directory contains samples demonstrating the capabilities of Microsoft Agen
| [`getting_started/agents/azure_openai/azure_responses_client_image_analysis.py`](./getting_started/agents/azure_openai/azure_responses_client_image_analysis.py) | Azure OpenAI Responses Client with Image Analysis Example |
| [`getting_started/agents/azure_openai/azure_responses_client_with_code_interpreter.py`](./getting_started/agents/azure_openai/azure_responses_client_with_code_interpreter.py) | Azure OpenAI Responses Client with Code Interpreter Example |
| [`getting_started/agents/azure_openai/azure_responses_client_with_explicit_settings.py`](./getting_started/agents/azure_openai/azure_responses_client_with_explicit_settings.py) | Azure OpenAI Responses Client with Explicit Settings Example |
| [`getting_started/agents/azure_openai/azure_responses_client_with_foundry.py`](./getting_started/agents/azure_openai/azure_responses_client_with_foundry.py) | Azure OpenAI Responses Client with Foundry Project Example |
| [`getting_started/agents/azure_openai/azure_responses_client_with_function_tools.py`](./getting_started/agents/azure_openai/azure_responses_client_with_function_tools.py) | Azure OpenAI Responses Client with Function Tools Example |
| [`getting_started/agents/azure_openai/azure_responses_client_with_hosted_mcp.py`](./getting_started/agents/azure_openai/azure_responses_client_with_hosted_mcp.py) | Azure OpenAI Responses Client with Hosted Model Context Protocol (MCP) Example |
| [`getting_started/agents/azure_openai/azure_responses_client_with_local_mcp.py`](./getting_started/agents/azure_openai/azure_responses_client_with_local_mcp.py) | Azure OpenAI Responses Client with local Model Context Protocol (MCP) Example |
python/samples/getting_started/agents/azure_openai/README.md
+4
View File
@@ -22,6 +22,7 @@ This folder contains examples demonstrating different ways to create and use age
| [`azure_responses_client_with_code_interpreter.py`](azure_responses_client_with_code_interpreter.py) | Shows how to use `AzureOpenAIResponsesClient.get_code_interpreter_tool()` with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
| [`azure_responses_client_with_explicit_settings.py`](azure_responses_client_with_explicit_settings.py) | Shows how to initialize an agent with a specific responses client, configuring settings explicitly including endpoint and deployment name. |
| [`azure_responses_client_with_file_search.py`](azure_responses_client_with_file_search.py) | Demonstrates using `AzureOpenAIResponsesClient.get_file_search_tool()` with Azure OpenAI Responses Client for direct document-based question answering and information retrieval from vector stores. |
| [`azure_responses_client_with_foundry.py`](azure_responses_client_with_foundry.py) | Shows how to create an agent using an Azure AI Foundry project endpoint instead of a direct Azure OpenAI endpoint. Requires the `azure-ai-projects` package. |
| [`azure_responses_client_with_function_tools.py`](azure_responses_client_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_responses_client_with_hosted_mcp.py`](azure_responses_client_with_hosted_mcp.py) | Shows how to integrate Azure OpenAI Responses Client with hosted Model Context Protocol (MCP) servers using `AzureOpenAIResponsesClient.get_mcp_tool()` for extended functionality. |
| [`azure_responses_client_with_local_mcp.py`](azure_responses_client_with_local_mcp.py) | Shows how to integrate Azure OpenAI Responses Client with local Model Context Protocol (MCP) servers using MCPStreamableHTTPTool for extended functionality. |
@@ -35,6 +36,9 @@ Make sure to set the following environment variables before running the examples
- `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME`: The name of your Azure OpenAI chat model deployment
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME`: The name of your Azure OpenAI Responses deployment
For the Foundry project sample (`azure_responses_client_with_foundry.py`), also set:
- `AZURE_AI_PROJECT_ENDPOINT`: Your Azure AI Foundry project endpoint
Optionally, you can set:
- `AZURE_OPENAI_API_VERSION`: The API version to use (default is `2024-02-15-preview`)
- `AZURE_OPENAI_API_KEY`: Your Azure OpenAI API key (if not using `AzureCliCredential`)
python/samples/getting_started/agents/azure_openai/azure_responses_client_with_foundry.py
+113
View File
@@ -0,0 +1,113 @@
# Copyright (c) Microsoft. All rights reserved.
import asyncio
import os
from random import randint
from typing import Annotated
from agent_framework import tool
from agent_framework.azure import AzureOpenAIResponsesClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from pydantic import Field
"""
Azure OpenAI Responses Client with Foundry Project Example
This sample demonstrates how to create an AzureOpenAIResponsesClient using an
Azure AI Foundry project endpoint. Instead of providing an Azure OpenAI endpoint
directly, you provide a Foundry project endpoint and the client is created via
the Azure AI Foundry project SDK.
This requires:
- The `azure-ai-projects` package to be installed.
- The `AZURE_AI_PROJECT_ENDPOINT` environment variable set to your Foundry project endpoint.
- The `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` environment variable set to the model deployment name.
"""
load_dotenv() # Load environment variables from .env file if present
# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
@tool(approval_mode="never_require")
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 non_streaming_example() -> None:
"""Example of non-streaming response (get the complete result at once)."""
print("=== Non-streaming Response Example ===")
# 1. Create the AzureOpenAIResponsesClient using a Foundry project endpoint.
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
credential = AzureCliCredential()
agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
credential=credential,
).as_agent(
instructions="You are a helpful weather agent.",
tools=get_weather,
)
# 2. Run a query and print the result.
query = "What's the weather like in Seattle?"
print(f"User: {query}")
result = await agent.run(query)
print(f"Result: {result}\n")
async def streaming_example() -> None:
"""Example of streaming response (get results as they are generated)."""
print("=== Streaming Response Example ===")
# 1. Create the AzureOpenAIResponsesClient using a Foundry project endpoint.
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option.
credential = AzureCliCredential()
agent = AzureOpenAIResponsesClient(
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
credential=credential,
).as_agent(
instructions="You are a helpful weather agent.",
tools=get_weather,
)
# 2. Stream the response and print each chunk as it arrives.
query = "What's the weather like in Portland?"
print(f"User: {query}")
print("Agent: ", end="", flush=True)
async for chunk in agent.run(query, stream=True):
if chunk.text:
print(chunk.text, end="", flush=True)
print("\n")
async def main() -> None:
print("=== Azure OpenAI Responses Client with Foundry Project Example ===")
await non_streaming_example()
await streaming_example()
if __name__ == "__main__":
asyncio.run(main())
"""
Sample output:
=== Azure OpenAI Responses Client with Foundry Project Example ===
=== Non-streaming Response Example ===
User: What's the weather like in Seattle?
Result: The weather in Seattle is cloudy with a high of 18°C.
=== Streaming Response Example ===
User: What's the weather like in Portland?
Agent: The weather in Portland is sunny with a high of 25°C.
"""