E-commerce Catalog Enrichment

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY", namespace="catalog")

# 1. A bucket for product photos, and a collection whose Gemini step writes a
#    caption, colors, visible objects and packaging text per photo
bucket = client.buckets.create(
    bucket_name="products",
    bucket_schema={"properties": {"photo": {"type": "image"}}},
)
collection = client.collections.create(
    collection_name="products",
    source={"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    feature_extractor={
        "feature_extractor_name": "multimodal_extractor",
        "version": "v1",
        "parameters": {
            "run_video_description": True,
            "description_prompt": "Describe this product for a catalog listing.",
            "response_shape": {
                "type": "object",
                "properties": {
                    "caption": {"type": "string"},
                    "colors": {"type": "array", "items": {"type": "string"}},
                    "objects": {"type": "array", "items": {"type": "string"}},
                    "packaging_text": {"type": "string"},
                },
            },
        },
    },
)

# 2. Upload and process
client.buckets.upload(
    bucket["bucket_id"],
    blobs=[{"property": "photo", "type": "image", "data": "s3://your-bucket/product-images/IMG_0001.jpg"}],
)
client.collections.trigger(collection["collection_id"])

# 3. Read the enriched attributes
docs = client.documents.list(collection["collection_id"], page_size=50)
for doc in docs["results"]:
    attrs = doc.get("json_output") or {}
    print(attrs.get("caption"), attrs.get("colors"), attrs.get("objects"))