Bring AI to your favourite database

Docs | Blog | Website | Use-Cases | Slack | Youtube | LinkedIn

What is Superduper?

Superduper (formerly SuperDuperDB) is a Python framework for integrating AI models and workflows with major databases. Implement custom AI solutions without moving your data through complex pipelines and specialized vector databases, including hosting of your own models, streaming inference and scalable model training/fine-tuning.

Transform your existing database into an AI development and deployment stack with one command, streamlining your AI workflows in one environment instead of being spread across systems and environments:

db = superduper('mongodb|postgres|mysql|sqlite|duckdb|snowflake://<your-db-uri>')

Run Superduper anywhere, or contact us to learn more about the enterprise platform for bringing your apps to production at scale.

Key features

Integration of AI with your existing data infrastructure: Integrate any AI models and APIs with your databases in a single environment, without the need for additional pre-processing steps, ETL or boilerplate code.
Inference via change-data-capture: Have your models compute outputs automatically and immediately as new data arrives, keeping your deployment always up-to-date.
Scalable model hosting: Host your own models from form HuggingFace, PyTorch and scikit-learn and safeguard your data.
Scalable model training: Train AI models on large, diverse datasets simply by querying your training data. Ensured optimal performance via in-build computational optimizations.
Model chaining: Easily setup complex workflows by connecting models and APIs to work together in an interdependent and sequential manner.
Simple Python interface: Replace writing thousand of lines of glue code with simple Python commands, while being able to drill down to any layer of implementation detail, like the inner workings of your models or your training details.
Python-first: Bring and leverage any function, program, script or algorithm from the Python ecosystem to enhance your workflows and applications.
Difficult data-types: Work directly with images, video, audio in your database, and any type which can be encoded as bytes in Python.
Feature storing: Turn your database into a centralized repository for storing and managing inputs and outputs of AI models of arbitrary data-types, making them available in a structured format and known environment.
Vector search: No need to duplicate and migrate your data to additional specialized vector databases - turn your existing battle-tested database into a fully-fledged multi-modal vector-search database, including easy generation of vector embeddings and vector indexes of your data with preferred models and APIs.

Preview

Browse the re-usable snippets to understand how to accomplish difficult AI end-functionality with few lines of code using Superduper.

Example use-cases and apps (notebooks)

The notebooks below are examples how to make use of different frameworks, model providers, databases, retrieval techniques and more. To learn more about how to use Superduper with your database, please check our Docs.

| Name | Link | |-------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------| | Multimodal vector-search with a range of models and datatypes | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/superduper-io/superduper/blob/main/docs/content/use_cases/multimodal_vector_search_image.ipynb) | | RAG with self-hosted LLM | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://github.com/superduper-io/superduper/blob/main/docs/content/use_cases/retrieval_augmented_generation.ipynb) | | Fine-tune an LLM on your database | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://github.com/superduper-io/superduper/blob/main/docs/content/use_cases/fine_tune_llm_on_database.ipynb) | | Featurization and transfer learning | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://github.com/superduper-io/superduper/blob/main/docs/content/use_cases/transfer_learning.ipynb) |

superduper-io / superduper