Clusters in Mixpeek are groups of similar features automatically discovered or manually defined. They enable efficient organization, search, and analysis of your multimodal features.

​
How Clustering Works

1

Feature Extraction

Assets are processed into features representing:

  • Visual content
  • Objects
  • Spoken Words
  • Metadata
  • etc.
2

Similarity Calculation

Features are compared using:

  • Vector similarity
  • Semantic relationships
  • Temporal proximity
3

Cluster Formation

Similar features are grouped based on:

  • Distance thresholds
  • Density patterns
  • User-defined rules

​
Use Cases

Content Organization

Automatically organize video libraries by:

  • Content type
  • Visual similarity
  • Semantic themes

Pattern Discovery

Uncover hidden patterns in your content:

  • Common scenes
  • Recurring themes
  • Related sequences

Search Enhancement

Improve search efficiency through:

  • Cluster-based filtering
  • Contextual recommendations
  • Similar content discovery

Quality Control

Monitor and maintain content quality by:

  • Identifying outliers
  • Detecting anomalies
  • Validating content consistency

​
Implementation

# Discover clusters automatically
POST /entities/cluster/discover
{
  "collection_name": "video_features",
  "method": "dbscan",
  "settings": {
    "sample_size": 1000,
    "neighbor_limit": 20
  }
}

​
Architecture

​
Performance Considerations

Clustering large feature sets can be computationally intensive. Mixpeek uses Qdrant’s optimized distance matrix calculations and supports sample-based clustering for better performance.

When using manual clusters, ensure your taxonomy terms are specific enough to avoid overlapping clusters that could impact search precision.

​
Advanced Features

​
Hierarchical Organization

Features can belong to multiple clusters and cluster hierarchies:

{
  "clusters": [
    {
      "cluster_id": "clu_123",
      "path": "sports/tennis/serve",
      "confidence": 0.95
    },
    {
      "cluster_id": "clu_123",
      "path": "training/technique",
      "confidence": 0.88
    }
  ]
}

Use cluster hierarchies to create intuitive navigation structures for your content.

​
Best Practices

1

Preparation

  • Clean and normalize your feature data
  • Choose appropriate clustering parameters
  • Define clear taxonomy rules
2

Implementation

  • Start with sample-based clustering
  • Validate cluster quality
  • Monitor cluster distributions
3

Optimization

  • Adjust parameters based on results
  • Refine taxonomy terms
  • Balance cluster sizes

​
Updates and Maintenance

Keep your clusters up to date by periodically running the clustering process on new content. Mixpeek handles incremental updates efficiently.

Was this page helpful?

TaxonomiesAvailable Models