Examples: use agent to interact with Remote PDF Documents

[princeaden1]

Changes being requested

Added a new example to use agent to interact with remote pdf. This example demonstrates how to use the Open AI to understand and summarise content from a remote pdf.

What's Included

New example: examples/basic/remote_pdf.py

Why This Matters

Shows how to integrate file-based content into the agent workflow
Useful for summarising reports, papers, or legal docs hosted online
Helps users extend agent capabilities to real-world document formats

Code

import asyncio

from agents import Agent, Runner

URL = "https://www.berkshirehathaway.com/letters/2024ltr.pdf"


async def main():
    agent = Agent(
        name="Assistant",
        instructions="You are a helpful assistant.",
    )

    result = await Runner.run(
        agent,
        [
            {
                "role": "user",
                "content": [{"type": "input_file", "file_url": URL}],
            },
            {
                "role": "user",
                "content": "Can you summarize the letter?",
            },
        ],
    )
    print(result.final_output)


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

[seratch]

this aligns with https://github.com/openai/openai-agents-js/blob/main/examples/basic/remote-pdf.ts; lgtm