LogoLogo
👋 Get in touch⭐️ GitHub
  • Welcome
  • Getting Started
    • Why Superlinked?
    • Setup Superlinked
    • Basic Building Blocks
  • Run in Production
    • Overview
    • Setup Superlinked Server
      • Configuring your app
      • Interacting with app via API
    • Supported Vector Databases
      • Redis
      • Mongo DB
      • Qdrant
  • Concepts
    • Overview
    • Combining Multiple Embeddings for Better Retrieval Outcomes
    • Dynamic Parameters/Query Time weights
  • Reference
    • Overview
    • Changelog
    • Components
      • Dag
        • Period Time
      • Parser
        • Json Parser
        • Dataframe Parser
        • Data Parser
      • Schema
        • Id Schema Object
        • Schema Object
        • Schema
        • Event Schema Object
        • Event Schema
      • App
        • App
        • Interactive
          • Interactive App
        • Online
          • Online App
        • Rest
          • Rest App
        • In Memory
          • In Memory App
      • Space
        • Custom Space
        • Exception
        • Has Space Field Set
        • Number Space
        • Image Space Field Set
        • Text Similarity Space
        • Input Aggregation Mode
        • Image Space
        • Recency Space
        • Space Field Set
        • Categorical Similarity Space
        • Space
      • Executor
        • Exception
        • Executor
        • Interactive
          • Interactive Executor
        • Rest
          • Rest Descriptor
          • Rest Handler
          • Rest Executor
          • Rest Configuration
        • In Memory
          • In Memory Executor
        • Query
          • Query Executor
      • Registry
        • Superlinked Registry
        • Exception
      • Storage
        • Mongo Db Vector Database
        • Vector Database
        • Redis Vector Database
        • In Memory Vector Database
        • Qdrant Vector Database
      • Index
        • Effect
        • Index
        • Util
          • Aggregation Node Util
          • Event Aggregation Node Util
          • Event Aggregation Effect Group
          • Effect With Referenced Schema Object
          • Aggregation Effect Group
      • Source
        • Data Loader Source
        • Interactive Source
        • Types
        • In Memory Source
        • Source
        • Rest Source
      • Query
        • Param
        • Typed Param
        • Query
        • Query Weighting
        • Query Descriptor
        • Nlq Param Evaluator
        • Space Weight Param Info
        • Query Param Information
        • Query Filters
        • Nlq Pydantic Model Builder
        • Clause Params
        • Param Evaluator
        • Query Mixin
        • Query Param Value Setter
        • Query Filter Validator
        • Natural Language Query Param Handler
        • Query Filter Information
        • Query Vector Factory
        • Query Clause
        • Result
        • Query Result Converter
          • Default Query Result Converter
          • Query Result Converter
          • Serializable Query Result Converter
        • Predicate
          • Binary Op
          • Query Predicate
          • Binary Predicate
        • Query Clause
          • Similar Filter Clause
          • Overriden Now Clause
          • Looks Like Filter Clause
          • Space Weight Map
          • Nlq System Prompt Clause
          • Nlq Clause
          • Radius Clause
          • Weight By Space Clause
          • Base Looks Like Filter Clause
          • Limit Clause
          • Select Clause
          • Looks Like Filter Clause Weights By Space
          • Single Value Param Query Clause
          • Hard Filter Clause
          • Query Clause
        • Nlq
          • Nlq Compatible Clause Handler
          • Exception
          • Nlq Clause Collector
          • Nlq Handler
          • Suggestion
            • Query Suggestion Model
            • Query Suggestions Prompt Builder
          • Param Filler
            • Query Param Model Validator
            • Query Param Model Validator Info
            • Query Param Model Builder
            • Query Param Prompt Builder
            • Nlq Annotation
            • Templates
  • Recipes
    • Overview
    • Multi-Modal Semantic Search
      • Hotel Search
    • Recommendation System
      • E-Commerce RecSys
  • Tutorials
    • Overview
    • Semantic Search - News
    • Semantic Search - Movies
    • Semantic Search - Product Images & Descriptions
    • RecSys - Ecommerce
    • RAG - HR
    • Analytics - User Acquisition
    • Analytics - Keyword Expansion
  • Help & FAQ
    • Logging
    • Support
    • Discussion
  • Policies
    • Terms of Use
    • Privacy Policy
Powered by GitBook
On this page

Was this helpful?

Edit on GitHub
  1. Tutorials

Semantic Search - Product Images & Descriptions

Learn about fundamental concepts of Superlinked.

PreviousSemantic Search - MoviesNextRecSys - Ecommerce

Last updated 6 months ago

Was this helpful?

This use-case notebook shows semantic search in fashion images for e-commerce.

In e-commerce, being able to serve user queries with the most relevant results is of utmost importance. Users predominantly use text to describe what they would like and that poses a problem e-commerce websites face: products generally lack extensive textual information. However, there is no better way to describe a product than an image. Luckily, researchers also realised that, and came up with multi-modal Vision Transformers that embed text and images in the same space, thereby making us able to search with text in images of products. Namely, searching for an "elegant dress" does not require the description to contain anything similar to return the actual elegant dresses.

To demonstrate that, we are going to perform search in a fashion dataset consinsting of images with short descriptions. We will be able to search:

  • with text in the descriptions,

  • with text in the images,

  • with an image in the images

or we can combine these in the following ways:

  • search with the same or different text in the descriptions and the images

  • search with text in the descriptions, and with images in the images

we will show that multi-modal search in the text embedding AND the image embedding space is the best approach to get the most relevant results.

Follow along in this Colab

Google Colab
Logo