Skip to content
Change the repository type filter

All

    Repositories list

    • TypeScript
      0102Updated Jan 28, 2025Jan 28, 2025
    • 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
      Apache License 2.0
      3127Updated Jan 28, 2025Jan 28, 2025
    • Execution environment for attribute calculation in refinery. Containerized function as a service to build custom attributes derived from the original data.
      Python
      Apache License 2.0
      1018Updated Jan 28, 2025Jan 28, 2025
    • TypeScript
      0001Updated Jan 27, 2025Jan 27, 2025
    • Data model for refinery. Manages entities and their access for multiple services, e.g. the gateway.
      Python
      Apache License 2.0
      1205Updated Jan 24, 2025Jan 24, 2025
    • TypeScript
      0001Updated Jan 21, 2025Jan 21, 2025
    • Embedder for refinery. Manages the creation of document- and token-level embeddings using the embedders library.
      Python
      Apache License 2.0
      11017Updated Jan 17, 2025Jan 17, 2025
    • Evaluates whether a user has access to certain resources.
      Python
      Apache License 2.0
      2000Updated Jan 17, 2025Jan 17, 2025
    • Neural search for refinery. Manages similarity search powered by Qdrant and outlier detection, both based on vector representations of the project records.
      Python
      Apache License 2.0
      1502Updated Jan 17, 2025Jan 17, 2025
    • Updater for refinery. Manages migration logic to new versions if required.
      Python
      Apache License 2.0
      1001Updated Jan 17, 2025Jan 17, 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
      Apache License 2.0
      1101Updated Jan 17, 2025Jan 17, 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
      Apache License 2.0
      1001Updated Jan 17, 2025Jan 17, 2025
    • Gateway proxy for refinery. Manages incoming requests and forwards them to the gateway. Used by the Python SDK.
      Python
      Apache License 2.0
      2000Updated Jan 17, 2025Jan 17, 2025
    • Execution environment for labeling functions in refinery. Containerized function as a service to execute user-defined Python scripts.
      Python
      Apache License 2.0
      1009Updated Jan 17, 2025Jan 17, 2025
    • Dockerfile
      Apache License 2.0
      0001Updated Jan 17, 2025Jan 17, 2025
    • Scripts used for Kern AI CI/CD efforts
      Shell
      0011Updated Jan 17, 2025Jan 17, 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
      Apache License 2.0
      10113Updated Jan 17, 2025Jan 17, 2025
    • Defines parent image for the Docker images of the refinery services that require torch (gpu).
      Shell
      Apache License 2.0
      0000Updated Jan 17, 2025Jan 17, 2025
    • Defines parent image for the Docker images of the refinery services that require torch (cpu).
      Shell
      Apache License 2.0
      0000Updated Jan 17, 2025Jan 17, 2025
    • Defines parent image for the Docker images of the refinery services which provide an execution environment.
      Shell
      Apache License 2.0
      0000Updated Jan 17, 2025Jan 17, 2025
    • Defines parent image for the Docker images of the refinery services with the smallest set of requirements.
      Shell
      Apache License 2.0
      0000Updated Jan 17, 2025Jan 17, 2025
    • bricks

      Public
      Open-source natural language enrichments at your fingertips.
      Python
      Apache License 2.0
      234557310Updated Jan 14, 2025Jan 14, 2025
    • TypeScript
      0002Updated Jan 13, 2025Jan 13, 2025
    • Submodule which contains the requirements of the different parent images of refinery.
      Python
      Apache License 2.0
      0107Updated Dec 13, 2024Dec 13, 2024
    • Defines parent image for the Docker images of the refinery services which require the integration of the model and the s3 submodule.
      Shell
      Apache License 2.0
      0001Updated Dec 13, 2024Dec 13, 2024
    • 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
      Apache License 2.0
      691.4k700Updated Dec 9, 2024Dec 9, 2024
    • A PDF to Markdown converter
      JavaScript
      214000Updated Dec 9, 2024Dec 9, 2024
    • Websocket module for refinery. Enables asynchronous notifications inside the application.
      Go
      Apache License 2.0
      1000Updated Dec 9, 2024Dec 9, 2024
    • Official Python SDK for Kern AI refinery.
      Python
      Apache License 2.0
      31801Updated Nov 14, 2024Nov 14, 2024
    • refinery-config

      Public archive
      Configuration of refinery. Manages amongst others endpoints and available language models for spaCy.
      Python
      Apache License 2.0
      1110Updated Nov 7, 2024Nov 7, 2024