Content Clustering Pipeline

from mixpeek import Mixpeek

client = Mixpeek(api_key="YOUR_API_KEY")

namespace = client.namespaces.create(name="clusters")
collection = client.collections.create(
    namespace_id=namespace.id,
    name="articles",
    extractors=["text-embedding-v2"]
)

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

# Create clusters
cluster_job = client.clusters.create(
    namespace_id=namespace.id,
    collection_ids=[collection.id],
    num_clusters=20,
    algorithm="kmeans"
)

# Get cluster assignments
clusters = client.clusters.list(namespace_id=namespace.id)
for cluster in clusters:
    print(f"Cluster: {cluster.label} ({cluster.document_count} docs)")