Taxonomy Enrichment Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

# Create taxonomy
taxonomy = client.taxonomies.create(
    name="content-categories",
    categories=[
        {"label": "Technology", "children": [
            {"label": "AI/ML"},
            {"label": "Cloud Computing"},
            {"label": "Cybersecurity"}
        ]},
        {"label": "Business", "children": [
            {"label": "Finance"},
            {"label": "Marketing"},
            {"label": "Operations"}
        ]}
    ]
)

# Apply taxonomy to collection
namespace = client.namespaces.create(name="enriched-content")
collection = client.collections.create(
    namespace_id=namespace.id,
    name="articles",
    extractors=["text-embedding-v2"],
    taxonomy_id=taxonomy.id
)

# Content is auto-classified on ingestion
client.buckets.upload(
    collection_id=collection.id,
    url="s3://your-bucket/articles/"
)