superlinked 37.5.0

The Superlinked vector computing library

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

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))

Table of Contents

• 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

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  Image embedding  Numeric (min-max)  Numeric (similar)  Categorical  Recency embedding  Event effects
Build & extend	Combine spaces or add custom / optional schemas.	Combine embeddings  Custom space  Optional fields
Optimise relevance	Real-time updates & query-time personalisation.	Dynamic parameters  Query-time weights  Query result
Search & filter	NL search + hard filters.	NL query  Hard filtering  Query options  Vector parts
Analyse & export	Sample embeddings offline.	Vector sampler
Go multi-modal	Unified text + image space.	Multimodal search

💡 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=sl.Mode.MAXIMUM
)
index = sl.Index([description_space, rating_space], fields=[product.rating])


# Define your query and parameters to set them directly at query-time
# or let an LLM fill them in for you using the `natural_language_query` param.
# Don't forget to set your OpenAI API key to unlock this feature.
query = (
    sl.Query(
        index,
        weights={
            description_space: sl.Param("description_weight"),
            rating_space: sl.Param("rating_weight"),
        },
    )
    .find(product)
    .similar(
        description_space,
        sl.Param(
            "description_query",
            description="The text in the user's query that refers to product descriptions.",
        ),
    )
    .limit(sl.Param("limit"))
    .with_natural_query(
        sl.Param("natural_language_query"),
        sl.OpenAIClientConfig(api_key=os.environ["OPEN_AI_API_KEY"], model="gpt-4o")
    )
)

# Run the app in-memory (server & Apache Spark executors available too!).
source = sl.InMemorySource(product)
executor = sl.InMemoryExecutor(sources=[source], indices=[index])
app = executor.run()


# Ingest data into the system - index updates and other processing happens automatically.
source.put([
    {
        "id": 1,
        "description": "Budget toothbrush in black color. Just what you need.",
        "rating": 1,
    },
    {
        "id": 2,
        "description": "High-end toothbrush created with no compromises.",
        "rating": 5,
    },
    {
        "id": 3,
        "description": "A toothbrush created for the smart 21st century man.",
        "rating": 3,
    },
])

result = app.query(query, natural_query="best toothbrushes", limit=1)

# Examine the extracted parameters from your query
print(json.dumps(result.metadata, indent=2))

# The result is the 5-star rated product.
sl.PandasConverter.to_pandas(result)

Use-cases

Dive deeper with our notebooks into how each use-case benefits from the Superlinked framework.

• RAG: HR Knowledgebase
• Semantic Search: Movies, Business News, Product Images & Descriptions
• Recommendation Systems: E-commerce
• Analytics: User Acquisition, Keyword expansion

You can check a full list of examples here.

Run in production

With a single command you can run Superlinked as a REST API Server locally or in your cloud with Superlinked Server. Get data ingestion and query APIs, embedding model inference and deep vector database integrations for free!

Unify your evaluation, ingestion and serving stacks with a single declarative python codebase. Superlinked enables this by letting you define your data schema, vector indexes and the compute DAG that links them all at once and then choose the right executor for the task - in-memory or server.

If you are interested in learning more about running at scale, Book a demo for early access to our managed cloud.

Supported Vector Databases

Superlinked stores your vectors in your vector database, with deep integrations for:

• Redis
• MongoDB
• Qdrant
• TopK
• Which one should we support next?

Curious about vector database pros & cons in general? Our community compared 44 Vector Databases on 30+ features.

Logging

The Superlinked framework logs include contextual information, such as the process ID and package scope. Personally Identifiable Information (PII) is filtered out by default but can be exposed with the SUPERLINKED_EXPOSE_PII environment variable to true.

Resources

• Vector DB Comparison: Open-source collaborative comparison of vector databases by Superlinked.
• VectorHub: VectorHub is a free and open-sourced learning hub for people interested in adding vector retrieval to their ML stack

Support

Need help? We're here to support you:

• Report a bug by creating an issue
• Request a new feature here
• Start a discussion about your ideas or questions

Please create separate issues/discussions for each topic to help us better address your feedback. Thank you for contributing!