Skip to content
@ucbepic

EPIC Data Lab

Effective Programming Interaction and Computation with Data

Popular repositories Loading

  1. docetl docetl Public

    A system for agentic LLM-powered data processing and ETL

    Python 4.1k 441

  2. TWIX 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

    Python 230 20

  3. DataAgentBench DataAgentBench Public

    Benchmark for data agents

    Python 159 50

  4. BARGAIN BARGAIN Public

    Low-Cost LLM-Powered Data Processing with Theoretical Guarantees

    Python 60 11

  5. data-agent-benchmark-study data-agent-benchmark-study Public

    Welcoming contributions from practitioners building AI/data systems - share your real-world problems, document where current tools fail, and help improve the benchmark taxonomy across the enterpris…

    Python 14 3

  6. pdf_parser 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 10 3

Repositories

Showing 10 of 12 repositories
  • DataAgentBench Public

    Benchmark for data agents

    ucbepic/DataAgentBench's past year of commit activity
    Python 159 50 6 6 Updated Sep 7, 2026
  • docetl Public

    A system for agentic LLM-powered data processing and ETL

    ucbepic/docetl's past year of commit activity
    Python 4,081 MIT 441 31 (1 issue needs help) 14 Updated Sep 5, 2026
  • attune Public

    interactive steering of LLM-powered scoring

    ucbepic/attune's past year of commit activity
    TypeScript 0 MIT 0 0 0 Updated Aug 1, 2026
  • clean-doc-classifier Public
    ucbepic/clean-doc-classifier's past year of commit activity
    Python 1 0 0 0 Updated Jul 30, 2026
  • clean-pipelines Public
    ucbepic/clean-pipelines's past year of commit activity
    Python 4 MIT 0 0 0 Updated Jun 30, 2026
  • BARGAIN Public

    Low-Cost LLM-Powered Data Processing with Theoretical Guarantees

    ucbepic/BARGAIN's past year of commit activity
    Python 60 MIT 11 0 0 Updated Jun 11, 2026
  • 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

    ucbepic/TWIX's past year of commit activity
    Python 230 20 4 4 Updated May 10, 2026
  • task-cascades Public
    ucbepic/task-cascades's past year of commit activity
    Python 4 1 0 0 Updated Jan 1, 2026
  • data-agent-benchmark-study Public

    Welcoming contributions from practitioners building AI/data systems - share your real-world problems, document where current tools fail, and help improve the benchmark taxonomy across the enterprise data categories.

    ucbepic/data-agent-benchmark-study's past year of commit activity
    Python 14 3 3 0 Updated Sep 4, 2025
  • docetl-examples Public

    Examples of docetl pipelines

    ucbepic/docetl-examples's past year of commit activity
    Python 3 2 0 0 Updated Apr 22, 2025
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.