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.
from mixpeek import Mixpeekclient = Mixpeek(api_key="YOUR_API_KEY")# 1. Create collection with image embeddingsnamespace = client.namespaces.create(name="image-search")collection = client.collections.create(namespace_id=namespace.id,name="products",extractors=["image-embedding-v2"])# 2. Upload imagesclient.buckets.upload(collection_id=collection.id,url="s3://your-bucket/product-images/")# 3. Search by text or imageresults = client.retrievers.execute(retriever_id=retriever.id,query="red leather handbag with gold hardware")
Feature Extractors
Retriever Stages
Use Cases Using This Recipe
Visual Product Search for E-commerce
Let shoppers find products by uploading a photo instead of typing keywords
+30% for visual search queries
Search-to-cart conversion rate
E-commerce platforms, online retailers, and marketplace operators managing catalogs of 50K+ SKUs who want to offer camera-based product discovery
Visual Search for Retail
Bridge the gap between in-store inspiration and online purchase
+35% higher than text search
In-app visual search conversion
Omnichannel retailers, retail apps, and brands with physical and digital presence looking to connect in-store browsing with online purchasing
Fashion Visual Product Discovery
Search for fashion by style, not just by name or brand
3x more products viewed per session
Product discovery engagement
Fashion e-commerce platforms, apparel retailers, and personal styling services managing catalogs of 100K+ products where visual style drives purchase decisions
Related Recipes & Resources
Explore these related resources to deepen your understanding and discover more powerful features
Image Embedding
Generate visual embeddings for similarity search and clustering
Object Detection
Identify and locate objects within images with bounding boxes
Image Captioning
Generate descriptive captions for images automatically
Facial Recognition
Detect and identify faces in images with high accuracy
Image Segmentation
Partition images into multiple segments for detailed analysis
Visual Question Answering
Answer natural language questions about image content