# SPDX-FileCopyrightText: 2024-2025 ModelCloud.ai
# SPDX-FileCopyrightText: 2024-2025 qubitium@modelcloud.ai
# SPDX-License-Identifier: Apache-2.0
# Contact: qubitium@modelcloud.ai, x.com/qubitium

import base64
from io import BytesIO

import requests
from PIL import Image


def extract_vision_info(conversations: list[dict] | list[list[dict]]) -> list[dict]:
    vision_infos = []
    if isinstance(conversations[0], dict):
        conversations = [conversations]
    for conversation in conversations:
        for message in conversation:
            if isinstance(message["content"], list):
                for ele in message["content"]:
                    if (
                            "image" in ele
                            or "image_url" in ele
                            or "video" in ele
                            or ele["type"] in ("image", "image_url", "video")
                    ):
                        vision_infos.append(ele)
    return vision_infos


def fetch_image(
    ele: dict[str, str | Image.Image],
    image_patch_size: int | None = None,
) -> Image.Image:
    # Some multimodal model adapters forward image-related kwargs here even
    # though local image loading does not need them.
    del image_patch_size
    if "image" in ele:
        image = ele["image"]
    else:
        image = ele["image_url"]
    image_obj = None
    if isinstance(image, Image.Image):
        image_obj = image
    elif image.startswith("http://") or image.startswith("https://"):
        image_obj = Image.open(requests.get(image, stream=True).raw)
    elif image.startswith("file://"):
        image_obj = Image.open(image[7:])
    elif image.startswith("data:image"):
        if "base64," in image:
            _, base64_data = image.split("base64,", 1)
            data = base64.b64decode(base64_data)
            image_obj = Image.open(BytesIO(data))
    else:
        image_obj = Image.open(image)
    if image_obj is None:
        raise ValueError(f"Unrecognized image input, support local path, http url, base64 and PIL.Image, got {image}")
    return image_obj