Support multimodal inputs for inference

[isaac-chung]

Support multimodal inputs for inference without using private methods

from clarifai.client.model import Model
from clarifai.client.input import Inputs

prompt = "What time of day is it?"
image_url = "https://samples.clarifai.com/metro-north.jpg"
inference_params = dict(temperature=0.2, max_tokens=100)

-text_pb = Inputs.get_input_from_bytes("", text_bytes=prompt.encode()).data.text
-image_pb = Inputs.get_input_from_url("", image_url= image_url).data.image

# Model Predict
model_prediction = Model("https://clarifai.com/openai/chat-completion/models/openai-gpt-4-vision").
-    predict(inputs = [Inputs._get_proto(input_id="",imagepb=image_pb,text_pb=text_pb)],
+    predict(inputs = [Inputs.get_multimodal_input(input_id="",image_url=image_url, raw_text=prompt)],
inference_params=inference_params)

print(model_prediction.outputs[0].data.text.raw)

[sainivedh]

lgtm