Unsupervised Clustering & Theme Discovery

from mixpeek import Mixpeek

client = Mixpeek(api_key="your-api-key")

# Create collection with embeddings
collection = client.collections.create(
    collection_name="unlabeled_corpus",
    feature_extractor={
        "feature_extractor_name": "multimodal_extractor",
        "version": "v1"
    }
)

# Run clustering
clusters = client.analytics.cluster(
    collection_id=collection.id,
    algorithm="hdbscan",
    min_cluster_size=15,
    return_outliers=True
)

# Generate cluster summaries with LLM
for cluster in clusters:
    summary = client.llm.summarize(
        cluster_id=cluster.id,
        sample_size=10
    )

# Search within a cluster
results = client.retrievers.execute(
    retriever_id="cluster-search",
    inputs={
        "cluster_id": "cluster_42",
        "query_text": "specific theme"
    }
)