Feature: Multi-modal support, process image & document attachments, etc.

[coreylane]

1. Only image data (png | jpeg | gif | webp) is currently supported, so files like PDFs, MS Office docs, etc. wouldn't be in scope.

   • https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ContentBlock.html
   • https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ImageBlock.html

2. Claude 3 models are the only models that support "Vision" capabilities https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html#conversation-inference-supported-models-features

Code example:

    message = {
        "role": "user",
        "content": [
            {
                "text": input_text
            },
            {
                    "image": {
                        "format": 'png',
                        "source": {
                            "bytes": image
                        }
                    }
            }
        ]
    }

    messages = [message]

    # Send the message.
    response = bedrock_client.converse(
        modelId=model_id,
        messages=messages
    )