metadata-processing.py

import base64
import json
from openai import OpenAI
import time

# --------------------
# Setup
# --------------------

with open("api-keys/openai-key.txt", 'r') as f:
    openai_key = f.read()    

openai_key = openai_key.strip()

client = OpenAI(api_key=openai_key)


# 입력: accesslens-metadata.json
with open("accesslens-metadata.json", "r") as f:
    db = json.load(f)

enriched_docs = []

for obj, contexts in db.items():
    for ctx, designs in contexts.items():
        for i, d in enumerate(designs):
            title = d.get("title", "")
            image_url = d.get("image_url", "")
            design_url = d.get("design_url", "")

            prompt = f"""
You are helping enrich metadata for accessibility-related design objects.
Object: {obj}
Context: {ctx}
Title: {title}

Task: Based on the title, object, context, and the attached image, write a short natural language description (2–3 sentences).
The description should explain how the design works, what accessibility need it addresses, and in what situation it might be useful.
"""

            try:
                response = client.chat.completions.create(
                    model="gpt-4o-mini",
                    messages=[
                        {"role": "system", "content": "You are an assistant generating enriched descriptions for accessibility design metadata."},
                        {"role": "user", "content": [
                            {"type": "text", "text": prompt},
                            {"type": "image_url", "image_url": {"url": image_url}}
                        ]}
                    ],
                    temperature=0.7
                )
                description = response.choices[0].message["content"]

            except Exception as e:
                print(f"Error on {design_url}: {e}")
                description = ""

            enriched_docs.append({
                "id": f"{obj}__{ctx}__{i}",
                "object": obj,
                "context": ctx,
                "title": title,
                "description": description,
                "design_url": design_url,
                "image_url": image_url
            })

            time.sleep(1)  # API rate-limit 보호용 (조정 가능)

# 출력: enriched_accesslens.json 저장
with open("enriched_accesslens.json", "w") as f:
    json.dump(enriched_docs, f, indent=2, ensure_ascii=False)

print("✅ Enrichment complete! Saved to enriched_accesslens.json")