मल्टीमॉडल APIs के साथ काम करना

import base64
import pathlib

def call_model(parts: list) -> str:
    ...  # plug in your provider's SDK or HTTP call here
    raise NotImplementedError

PROMPT = (
    "Write alt text for this image for a screen reader user. "
    "One or two sentences, under 125 characters if possible. "
    "Describe what matters for understanding the page. "
    "Do not guess names, ages, caste, religion or health of people. "
    "If there is important text in the image, include it exactly. "
    "If the image is purely decorative, reply with exactly: DECORATIVE"
)

MEDIA = {".jpg": "image/jpeg", ".jpeg": "image/jpeg",
         ".png": "image/png", ".webp": "image/webp"}
MAX_BYTES = 2_000_000  # your own limit; check your provider's docs

def image_part(path: pathlib.Path) -> dict:
    data = path.read_bytes()
    if len(data) > MAX_BYTES:
        raise ValueError(f"{path.name} is too large; resize it first")
    encoded = base64.b64encode(data).decode("ascii")
    print(f"{path.name}: {len(data)} bytes, {len(encoded)} as base64")
    return {"type": "image", "media_type": MEDIA[path.suffix.lower()],
            "data": encoded}

def draft_alt_text(path: pathlib.Path) -> str:
    reply = call_model([image_part(path), {"type": "text", "text": PROMPT}])
    return "" if reply.strip() == "DECORATIVE" else reply.strip()

if __name__ == "__main__":
    for p in sorted(pathlib.Path("images").iterdir()):
        if p.suffix.lower() in MEDIA:
            try:
                print(p.name, "->", repr(draft_alt_text(p)))
            except NotImplementedError:
                print(p.name, "-> (plug in call_model first)")