Superlinked

<!-- ── HERO block ── --> <div align="center"> <!-- Logo (auto dark/light) --> <picture> <source srcset="https://cdn.prod.website-files.com/65dce6831bf9f730421e2915/66ef0317ed8616151ee1d451_superlinked_logo_white.png" media="(prefers-color-scheme: dark)"> <img width="320" src="https://cdn.prod.website-files.com/65dce6831bf9f730421e2915/65dce6831bf9f730421e2929_superlinked_logo.svg" alt="Superlinked logo"> </picture> <!-- Primary CTA --> <p> <a href="https://links.superlinked.com/deep_wiki_repo" style="text-decoration:none;display:inline-block"> <img src="https://img.shields.io/badge/chat%20with%20our%20AI%20docs-%E2%86%92-72A1FF?style=for-the-badge&logo=readthedocs&logoColor=white" alt="chat with our AI docs" width="200"> </a> </p> <!-- Secondary badges --> <p style="margin:6px 0;text-decoration:none"> <a href="https://docs.superlinked.com/" style="text-decoration:none;display:inline-block"><img src="https://img.shields.io/badge/Docs-orange?logo=readthedocs" alt="Docs"></a> <a href="https://deepwiki.com/superlinked/superlinked" style="text-decoration:none;display:inline-block"><img src="https://deepwiki.com/badge.svg" alt="DeepWiki"></a> <a href="https://pypi.org/project/superlinked/" style="text-decoration:none;display:inline-block"><img src="https://img.shields.io/pypi/v/superlinked" alt="PyPI"></a> <a href="https://github.com/superlinked/superlinked/stargazers" style="text-decoration:none;display:inline-block"><img src="https://img.shields.io/github/stars/superlinked/superlinked?style=social" alt="Stars"></a> <img src="https://img.shields.io/github/last-commit/superlinked/superlinked" style="display:inline-block" alt="Last commit"> <img src="https://img.shields.io/github/license/superlinked/superlinked" style="display:inline-block" alt="License"> </p> </div> <p align="center"> <em>Build high-performance <b> AI search </b> applications for both humans and agents. </em> </p>

Quickstart

%pip install superlinked

from superlinked import framework as sl  
  
# Define schema for movie reviews  
class Review(sl.Schema):  
    id: sl.IdField  
    text: sl.String  
  
review = Review()  
space = sl.TextSimilaritySpace(text=review.text, model="all-MiniLM-L6-v2")  
index = sl.Index(space)  
query = sl.Query(index).find(review).similar(space, sl.Param("search")).select_all()  
  
# Setup and run  
source = sl.InMemorySource(review)  
app = sl.InMemoryExecutor(sources=[source], indices=[index]).run()  
  
# Add data and search  
source.put([  
    {"id": "1", "text": "Amazing acting and great story"},  
    {"id": "2", "text": "Boring plot with bad acting"}  
])  
  
result = app.query(query, search="excellent performance")  
print(sl.PandasConverter.to_pandas(result))

<details> <summary><strong>Table&nbsp;of&nbsp;Contents</strong></summary>

• Table of Contents
• Quickstart
• Overview
• Hands on tutorials
• Use-cases
• Experiment in a notebook
  • Install the superlinked library
  • Run the example:
• Run in production
  • Supported Vector Databases
• Logging
• Resources
• Support

</details>

Overview

• WHY: Improve your vector search relevance by encoding metadata together with your unstructured data into vectors.
• 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 the tutorials and use-case notebooks below for examples.

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

Hands-on Tutorials

| Level | What you’ll build & learn | Try it now | |-------|---------------------------|------------| | Start here | Embed text · images · numbers · categories · time · events. | Text embedding <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/text_embedding.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Image embedding <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/image_embedding.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Numeric (min-max) <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/number_embedding_minmax.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Numeric (similar) <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/number_embedding_similar.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Categorical <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/categorical_embedding.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Recency embedding <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/recency_embedding.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Event effects <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/event_effects.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a> | | Build & extend | Combine spaces or add custom / optional schemas. | Combine embeddings <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/combine_multiple_embeddings.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Custom space <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/custom_space.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Optional fields <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/optional_schema_fields.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a> | | Optimise relevance | Real-time updates & query-time personalisation. | Dynamic parameters <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/dynamic_parameters.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Query-time weights <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/query_time_weights.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Query result <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/query_result.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a> | | Search & filter | NL search + hard filters. | NL query <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/natural_language_querying.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Hard filtering <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/hard_filtering.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Query options <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/querying_options.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a><br>Vector parts <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/accessing_stored_vector_parts.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a> | | Analyse & export | Sample embeddings offline. | Vector sampler <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/vector_sampler.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a> | | Go multi-modal | Unified text + image space. | Multimodal search <a href="https://colab.research.google.com/github/superlinked/superlinked/blob/main/notebook/feature/image_embedding.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab"></a> |

💡 Want even more? Browse the complete list of features & concepts in our docs →
https://docs.superlinked.com/concepts/overview

Experiment in a notebook

Let's build an e-commerce product search that understands product descriptions and ratings:

Run the notebook example:

First run will take a minute to download the embedding model.

%pip install superlinked

import json
import os

from superlinked import framework as sl


class Product(sl.Schema):
    id: sl.IdField
    description: sl.String
    rating: sl.Integer


product = Product()

description_space = sl.TextSimilaritySpace(
    text=product.description, model="Alibaba-NLP/gte-large-en-v1.5"
)
rating_space = sl.NumberSpace(
    number=product.rating, min_value=1, max_value=5, mode=s