feat: add metadata field in _GenerativeModels class methods to pass the metadata down the method chain.

[vi3k6i5]

• Make sure to open an issue as a bug/issue before writing your code! That way we can discuss the change, evaluate designs, and agree on the general idea
• Ensure the tests and linter pass
• Code coverage does not decrease (if any source code was changed)
• Appropriate docs were updated (if necessary)
• Get the necessary approvals
• Once the last commit on the PR has been approved, add the "ready to pull" label to the Pull Request

Fixes #3490

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[sasha-gitg]

@vi3k6i5 Thank you for the contribution! Please update/add unit tests.

[vi3k6i5]

@sasha-gitg Can you help with the Presubmits, the PRs are in waiting state for Presubmits to finish for last 5 days. Any idea, how to resolve that ?

[josealvarez97]

@vi3k6i5 @sasha-gitg will this be merged into the Python SDK?

In the JavAscript SDK, currently it's possible to send headers and modify other request options (like the baseUrl) this way:

const model = googleGenAIClient.getGenerativeModel(
				{ model: "gemini-pro" },
				{
					customHeaders: {
						"x-param": "<PARAMETER>",
					},
					baseUrl: env.PROXY_URL,
					
				}
			);

I wonder why a similar functionality was not added to the Python SDK

It almost feels like it was close to be considered, but it was not finished.

See these links:

• There should be a RequestOptions TypedDict to explain what attributes are allowed. google-gemini/generative-ai-python#223
• https://cloud.google.com/vertex-ai/generative-ai/docs/reference/nodejs/latest/vertexai/requestoptions