# Superlinked

> Python framework for AI Engineers building high-performance search and recommendation applications that combine structured and unstructured data through vector compute.

- **URL:** https://superlinked.com
- **Category:** SDKs & Libraries
- **Tags:** vector-compute, Multi Modal, Python
- **Updated:** 2026-03-24 13:36
- **Canonical page:** https://vectordb.ever.works/items/superlinked

## Details

## Overview

Superlinked is a Python framework for AI Engineers building high-performance search & recommendation applications that combine structured and unstructured data. It's described as "compute tooling for vector-powered apps."

## Key Features

**Purpose and Functionality:**
- The framework improves vector search relevance by encoding metadata together with unstructured data into vectors.
- It's both a framework and a self-hostable REST API server that connects your data, vector database and backend services.

**Technical Approach:**
- It allows you to construct custom data & query embedding models from pre-trained encoders from sentence-transformers, open-clip and custom encoders for numbers, timestamps and categorical data.
- Users can combine text, images and structured metadata into multi-modal vectors that fully describe entities in their complex context.

## Funding

The company announced they raised a $9.5M Seed round led by Index Ventures, with significant contributions from Tomasz Tunguz at Theory Ventures.

## Integrations

The framework is actively maintained on GitHub and includes integrations with various vector databases, offering both in-memory execution for development and server deployment for production use.

## Pricing

Open-source framework available on GitHub.

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/superlinked._