Clustering & Theme Discovery

import requests

API_URL = "https://api.mixpeek.com"
headers = {"Authorization": "Bearer YOUR_API_KEY", "X-Namespace": "your-namespace"}

# Create cluster configuration
cluster = requests.post(f"{API_URL}/v1/clusters", headers=headers, json={
    "cluster_name": "content_themes",
    "source_collection_ids": ["col_my_collection"],
    "feature_addresses": ["mixpeek://multimodal_extractor@v1/embedding"],
    "algorithm": "hdbscan",
    "algorithm_config": {"min_cluster_size": 15},
    "llm_labeling": {"provider": "openai_chat_v1", "model": "gpt-4o-mini"}
}).json()

# Execute clustering
execution = requests.post(
    f"{API_URL}/v1/clusters/{cluster['cluster_id']}/execute",
    headers=headers
).json()

# Get cluster artifacts with centroids
artifacts = requests.get(
    f"{API_URL}/v1/clusters/{cluster['cluster_id']}/executions/{execution['run_id']}/artifacts",
    headers=headers,
    params={"include_centroids": True}
).json()

# Explore discovered themes
for group in artifacts["clusters"]:
    print(f"Theme: {group['label']}")
    print(f"Size: {group['member_count']} items")
    print(f"Keywords: {', '.join(group.get('keywords', []))}")