Mixpeek Logo

    Multimodal Content Moderation

    Automated content moderation pipeline that analyzes text, images, and video for policy violations. Uses hierarchical taxonomy classification to label content as safe, sensitive, or prohibited across multiple categories simultaneously.

    text
    image
    video
    Multi-Stage
    2.9K runs
    Deploy Recipe
    from mixpeek import Mixpeek
    client = Mixpeek(api_key="YOUR_API_KEY")
    # Create a taxonomy with moderation categories
    taxonomy = client.taxonomies.create(
    namespace_id="ns_your_namespace",
    name="content_moderation",
    taxonomy_type="hierarchical",
    hierarchy=[
    {"node_id": "safe", "collection_id": "col_safe_examples"},
    {"node_id": "sensitive", "collection_id": "col_sensitive_examples"},
    {"node_id": "prohibited", "collection_id": "col_prohibited_examples"},
    ]
    )
    # Apply taxonomy to your UGC collection
    client.collections.apply_taxonomy(
    collection_id="col_user_content",
    taxonomy_id=taxonomy["taxonomy_id"]
    )
    # Check moderation status on new uploads
    results = client.retrievers.execute(
    retriever_id="ret_moderation",
    query={"image_url": "https://example.com/user-upload.jpg"}
    )
    verdict = results["results"][0]["taxonomy_enrichment"]
    print(f"Category: {verdict['category']}, Confidence: {verdict['confidence']:.2f}")

    Feature Extractors

    Retriever Stages

    aggregate

    Compute aggregations (COUNT, SUM, AVG, etc.) on pipeline results

    reduce