Mixpeek Logo
    Similar

    Image Similarity Search Pipeline

    Deploy a visual search engine that finds similar images using state-of-the-art embedding models. Perfect for product catalogs, stock photo libraries, and visual discovery.

    image
    Single Tier
    4.5K runs
    Deploy Recipe
    from mixpeek import Mixpeek
    client = Mixpeek(api_key="YOUR_API_KEY")
    # 1. Create collection with image embeddings
    namespace = client.namespaces.create(name="image-search")
    collection = client.collections.create(
    namespace_id=namespace.id,
    name="products",
    extractors=["image-embedding-v2"]
    )
    # 2. Upload images
    client.buckets.upload(
    collection_id=collection.id,
    url="s3://your-bucket/product-images/"
    )
    # 3. Search by text or image
    results = client.retrievers.execute(
    retriever_id=retriever.id,
    query="red leather handbag with gold hardware"
    )

    Feature Extractors

    Retriever Stages