from vllm import LLM, SamplingParams
from PIL import Image
from dataclasses import dataclass
from typing import Literal


@dataclass(frozen=True)
class ImageAssetLocal:
    name: Literal["stop_sign", "cherry_blossom"]
    @property
    def pil_image(self) -> Image.Image:
        return Image.open(f"tools/ci/ci_files/{self.name}.jpg")


def run_llava():
    llm = LLM(model="/data/AE/llm/models/llava-1.5-7b-hf/")
    sampling_params = SamplingParams(max_tokens=100)

    prompt = "USER: <image>\nWhat is the content of this image?\nASSISTANT:"
    image = ImageAssetLocal("stop_sign").pil_image
    outputs = llm.generate({
        "prompt": prompt,
        "multi_modal_data": {
            "image": image
        },
    }, sampling_params=sampling_params)

    for o in outputs:
        generated_text = o.outputs[0].text
        print(generated_text)


if __name__ == "__main__":
    run_llava()