Skip to content

@ucbepic EPIC Data Lab

Change the repository type filter

All

    Repositories list

    6 repositories

    • docetl

      Public
      A system for agentic LLM-powered data processing and ETL
      pythonworkflowdataetlsemantic-dataeltdata-pipelinesagentsdocument-processingllm
      Python
      •
      MIT License
      •254•2.6k•24•6•Updated Aug 1, 2025Aug 1, 2025

    • TWIX

      Public
      TWIX is an open-source data extraction tool that reconstructs structured data from documents at scale, accurately and at low cost, by inferring the shared underlying visual template across documents
      document-processingdocument-data-extraction
      Python
      •12•200•3•1•Updated May 29, 2025May 29, 2025

    • BARGAIN

      Public
      Low-Cost LLM-Powered Data Processing with Theoretical Guarantees
      dataaidocument-processingllm
      Python
      •
      MIT License
      •3•20•0•0•Updated May 1, 2025May 1, 2025

    • docetl-examples

      Public
      Examples of docetl pipelines
      Python
      •0•2•0•0•Updated Apr 22, 2025Apr 22, 2025

    • pdf_parser

      Public
      Parse PDFs using computer vision, layout analysis, and other state-of-the-art document intelligence techniques. WebApp implemented in Flask/Jinja2 with infer and train pipelines managed by FlorDB
      JavaScript
      •
      Apache License 2.0
      •1•8•0•0•Updated Jul 26, 2024Jul 26, 2024

    • ml_tutorial

      Public
      Introduction to Flordb with PyTorch and TensorFlow
      Jupyter Notebook
      •
      Apache License 2.0
      •0•0•0•0•Updated Apr 9, 2024Apr 9, 2024