Description

Allow customer to pass custom client to OpenAIModel and GeminiModel. This solves the issue of [BUG] OpenAI Implementation does not support passing custom HTTP client.

Note

1. It will be customer's responsibility to close the client as SDK will not close it.
2. Based on the discussion in the main issue, we would extend client to be a client_factory in the future. Just as of now, this change only support the single client.

Example

Users can now pass custom http client to the OpenAIModel and GeminiModel. Below is the example of the OpenAIModel.

import asyncio
import httpx
from strands import Agent
from strands.models.openai import OpenAIModel

client = httpx.AsyncClient()

agent = Agent(
    model=OpenAIModel(
        model_id="gpt-4o-mini-2024-07-18",
        client=client
    )
)

async def chat(prompt: str):
    result = await agent.invoke_async(prompt)
    print(result)

async def main():
    await chat("this works")
    await chat("this should work too")
    # close the client
    client.close()

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

Related Issues

#1036
Some parts of #1103

Documentation PR

Will update the documentation for this change.

Type of Change

New feature

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.