Files
agent-framework/python/samples/02-agents/multimodal_input/azure_responses_multimodal.py
T
Dmytro Struk 2dd731f90f Python: Fixed middleware and multimodal input samples (#4022)
* Fix streaming branch in weather override middleware sample

The streaming branch of weather_override_middleware only prefixed the
original weather data via a transform hook instead of replacing the
content with the 'perfect weather' override like the non-streaming
branch does. Replace with a new ResponseStream that yields the override
content as ChatResponseUpdate chunks.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fixed exception handling middleware sample

* Fixed runtime context delegation middleware example

* Fixed multimodal input examples

* Small update

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-02-18 00:49:33 +00:00

78 lines
2.6 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
import asyncio
from pathlib import Path
from agent_framework import Content, Message
from agent_framework.azure import AzureOpenAIResponsesClient
from azure.identity import AzureCliCredential
ASSETS_DIR = Path(__file__).resolve().parents[2] / "shared" / "sample_assets"
def load_sample_pdf() -> bytes:
"""Read the bundled sample PDF for tests."""
pdf_path = ASSETS_DIR / "sample.pdf"
return pdf_path.read_bytes()
def create_sample_image() -> str:
"""Create a simple 1x1 pixel PNG image for testing."""
# This is a tiny yellow pixel in PNG format
png_data = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8/5+hHgAHggJ/PchI7wAAAABJRU5ErkJggg=="
return f"data:image/png;base64,{png_data}"
async def test_image() -> None:
"""Test image analysis with Azure OpenAI Responses API."""
# For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
# authentication option. Requires AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME
# environment variables to be set.
# Alternatively, you can pass deployment_name explicitly:
# client = AzureOpenAIResponsesClient(credential=AzureCliCredential(), deployment_name="your-deployment-name")
client = AzureOpenAIResponsesClient(credential=AzureCliCredential())
image_uri = create_sample_image()
message = Message(
role="user",
contents=[
Content.from_text(text="What's in this image?"),
Content.from_uri(uri=image_uri, media_type="image/png"),
],
)
response = await client.get_response([message])
print(f"Image Response: {response}")
async def test_pdf() -> None:
"""Test PDF document analysis with Azure OpenAI Responses API."""
client = AzureOpenAIResponsesClient(credential=AzureCliCredential())
pdf_bytes = load_sample_pdf()
message = Message(
role="user",
contents=[
Content.from_text(text="What information can you extract from this document?"),
Content.from_data(
data=pdf_bytes,
media_type="application/pdf",
additional_properties={"filename": "sample.pdf"},
),
],
)
response = await client.get_response([message])
print(f"PDF Response: {response}")
async def main() -> None:
print("=== Testing Azure OpenAI Responses API Multimodal ===")
print("The Responses API supports both images AND PDFs")
await test_image()
await test_pdf()
if __name__ == "__main__":
asyncio.run(main())