Implement invoke_model_with_response_stream

[AAlvAAro]

To be able to receive the LLMs response by chunks instead of a giant block of text, the invoke_model_from_response_stream AWS gem method needs to be implemented. See reference:

https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/BedrockRuntime/Client.html#invoke_model_with_response_stream-instance_method

[webbrain-one]

Hi! 👋

I've opened PR #10 to address this. It implements the invoke_model_with_response_stream method, allowing you to receive LLM responses in chunks instead of a single block of text.

Feel free to review it and let me know if you have any feedback! 🚀