Multimodal Deduplication & Near-Duplicate Discovery

from mixpeek import Mixpeek

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

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

# Search for near-duplicates
results = client.retrievers.execute(
    retriever_id="dedup-retriever",
    inputs={
        "query_embedding": reference_embedding,
        "similarity_threshold": 0.92
    },
    limit=100
)

# Get duplicate clusters
clusters = client.analytics.cluster(
    collection_id=collection.id,
    algorithm="connected_components",
    similarity_threshold=0.95
)