Skip to content
Change the repository type filter

All

    Repositories list

    • Gateway for refinery. Manages incoming requests and holds the workflow logic. To interact with the gateway, the UI or Python SDK can be used.
      Python
      3127Updated Sep 26, 2025Sep 26, 2025
    • TypeScript
      0002Updated Sep 26, 2025Sep 26, 2025
    • TypeScript
      0002Updated Sep 26, 2025Sep 26, 2025
    • TypeScript
      0001Updated Sep 26, 2025Sep 26, 2025
    • Embedder for refinery. Manages the creation of document- and token-level embeddings using the embedders library.
      Python
      1101Updated Sep 25, 2025Sep 25, 2025
    • Execution environment for the active learning module in refinery. Containerized function as a service to build active learning models using scikit-learn and sequence-learn.
      Python
      1010Updated Sep 25, 2025Sep 25, 2025
    • Defines parent image for the Docker images of the refinery services that require torch (cpu).
      Shell
      0000Updated Sep 25, 2025Sep 25, 2025
    • Submodule which contains the requirements of the different parent images of refinery.
      Python
      0100Updated Sep 25, 2025Sep 25, 2025
    • Defines parent image for the Docker images of the refinery services that require torch (gpu).
      Shell
      0000Updated Sep 25, 2025Sep 25, 2025
    • Data model for refinery. Manages entities and their access for multiple services, e.g. the gateway.
      Python
      1207Updated Sep 25, 2025Sep 25, 2025
    • Updater for refinery. Manages migration logic to new versions if required.
      Python
      1001Updated Sep 25, 2025Sep 25, 2025
    • Evaluates whether a user has access to certain resources.
      Python
      2001Updated Sep 25, 2025Sep 25, 2025
    • Neural search for refinery. Manages similarity search powered by Qdrant and outlier detection, both based on vector representations of the project records.
      Python
      1501Updated Sep 25, 2025Sep 25, 2025
    • Weak supervision for refinery. Manages the integration of heuristics such as labeling functions, active learners or zero-shot classifiers. Uses the weak-nlp library for the actual integration logic and algorithms.
      Python
      1001Updated Sep 25, 2025Sep 25, 2025
    • Tokenizer for refinery. Manages the creation and storage of spaCy tokens for text-based record attributes and supports multiple language models. It is used by the gateway.
      Python
      1101Updated Sep 25, 2025Sep 25, 2025
    • Scripts used for Kern AI CI/CD efforts
      Shell
      0011Updated Sep 24, 2025Sep 24, 2025
    • Defines parent image for the Docker images of the refinery services which require the integration of the model and the s3 submodule.
      Shell
      0000Updated Sep 24, 2025Sep 24, 2025
    • JavaScript
      0001Updated Sep 18, 2025Sep 18, 2025
    • Execution environment for labeling functions in refinery. Containerized function as a service to execute user-defined Python scripts.
      Python
      1000Updated Sep 11, 2025Sep 11, 2025
    • Execution environment for attribute calculation in refinery. Containerized function as a service to build custom attributes derived from the original data.
      Python
      1010Updated Sep 11, 2025Sep 11, 2025
    • TypeScript
      0100Updated Sep 11, 2025Sep 11, 2025
    • Dockerfile
      0001Updated Sep 4, 2025Sep 4, 2025
    • Defines parent image for the Docker images of the refinery services which provide an execution environment.
      Shell
      0000Updated Jul 23, 2025Jul 23, 2025
    • Defines parent image for the Docker images of the refinery services with the smallest set of requirements.
      Shell
      0000Updated Jul 23, 2025Jul 23, 2025
    • S3 related AWS and Minio logic.
      Python
      1000Updated Jul 21, 2025Jul 21, 2025
    • embedders

      Public
      With embedders, you can easily convert your texts into sentence- or token-level embeddings within a few lines of code. Use cases for this include similarity search between texts, information extraction such as named entity recognition, or basic text classification.
      Python
      22111Updated Jul 14, 2025Jul 14, 2025
    • Gateway proxy for refinery. Manages incoming requests and forwards them to the gateway. Used by the Python SDK.
      Python
      2000Updated Jul 10, 2025Jul 10, 2025
    • bricks

      Public
      Open-source natural language enrichments at your fingertips.
      Python
      244607310Updated Jan 14, 2025Jan 14, 2025
    • refinery

      Public
      The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.
      Python
      741.5k700Updated Dec 9, 2024Dec 9, 2024
    • A PDF to Markdown converter
      JavaScript
      263000Updated Dec 9, 2024Dec 9, 2024