Metadata Enrichment Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

namespace = client.namespaces.create(name="enriched-data")
collection = client.collections.create(
    namespace_id=namespace.id,
    name="customer-feedback",
    extractors=[
        "entity-extraction",
        "topic-classification",
        "sentiment-analysis",
        "language-detection"
    ]
)

# Upload content - metadata extracted automatically
client.buckets.upload(
    collection_id=collection.id,
    url="s3://your-bucket/feedback/"
)

# Query enriched data
positive_feedback = client.documents.search(
    namespace_id=namespace.id,
    filters={
        "sentiment": "positive",
        "topic": "product-quality"
    }
)