Welcome

Superlinked is a Python framework for AI Engineers building high-performance search & recommendation applications that combine structured and unstructured data.

• WHY: Improve your vector search relevance by encoding metadata together with your unstructured data into vectors. Read more at Why Superlinked

• WHAT: A framework and a self-hostable REST API server that connects your data, vector database and backend services.

• HOW: Construct custom data & query embedding models from pre-trained encoders from sentence-transformers, open-clip and custom encoders for numbers, timestamps and categorical data. See concepts and use cases for examples.

If you like what we do, give us a star! ⭐

Superlinked framework diagram

Discover Superlinked

Getting Started

Begin your journey with Superlinked by setting up and understanding the basics.

Concepts

Explore the core ideas and principles behind Superlinked's functionality.

Use Cases

Learn how Superlinked can be applied to solve real-world problems.

Reference

Access detailed documentation for Superlinked's components.

Changelog

View the changelog for Superlinked.

Resources

VectorHub

free and open-sourced learning hub for people interested in adding vector retrieval to their ML stack.

Vector DB Comparison

Open-source collaborative comparison of vector databases by Superlinked