Skip to content

@Unstructured-IO Unstructured

Change the repository type filter

All

    Repositories list

    41 repositories

    • docs

      Public
      Documentation for all Unstructured products and libraries
      MDX
      •25•7•0•10•Updated Jan 29, 2026Jan 29, 2026

    • notebooks

      Public
      Jupyter Notebook
      •0•2•0•0•Updated Jan 29, 2026Jan 29, 2026

    • unstructured

      Public
      Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats fo…
      nlppdfmachine-learningnatural-language-processinginformation-retrievalocrdeep-learningmldocxpreprocessing
      HTML
      •
      Apache License 2.0
      •1.1k•14k•180•49•Updated Jan 29, 2026Jan 29, 2026

    • unstructured-ingest

      Public
      HTML
      •
      Apache License 2.0
      •53•106•57•32•Updated Jan 29, 2026Jan 29, 2026

    • unstructured-js-client

      Public
      A JavaScript/Typescript client for the Unstructured Platform API
      TypeScript
      •
      MIT License
      •15•58•7•1•Updated Jan 29, 2026Jan 29, 2026

    • unstructured-python-client

      Public
      A Python client for the Unstructured Platform API
      Python
      •
      MIT License
      •20•112•14•1•Updated Jan 29, 2026Jan 29, 2026

    • unstructured-api

      Public
      Python
      •
      Apache License 2.0
      •183•868•34•11•Updated Jan 28, 2026Jan 28, 2026

    • unstructured-inference

      Public
      Python
      •
      Apache License 2.0
      •74•201•23•15•Updated Jan 28, 2026Jan 28, 2026

    • unstructured-platform-plugins

      Public
      Python
      •
      Apache License 2.0
      •3•6•0•4•Updated Jan 27, 2026Jan 27, 2026

    • base-images

      Public
      Store Dockerfiles and Packer configs for images to use as a base to build upon
      Shell
      •
      Apache License 2.0
      •3•5•1•2•Updated Jan 14, 2026Jan 14, 2026

    • unstructured-eval-metrics

      Public
      Python
      •
      Apache License 2.0
      •3•5•0•0•Updated Dec 2, 2025Dec 2, 2025

    • rag-over-evolving-enterprise-knowledge

      Public
      Jupyter Notebook
      •0•0•0•0•Updated Oct 6, 2025Oct 6, 2025

    • rag-over-hybrid-data-sources

      Public
      Two sources (S3, ElasticSearch) to RAG DB pipeline.
      Jupyter Notebook
      •1•1•0•1•Updated Sep 15, 2025Sep 15, 2025

    • UNS-MCP

      Public
      Jupyter Notebook
      •20•40•0•1•Updated Sep 9, 2025Sep 9, 2025

    • .github

      Public
      2•0•2•1•Updated Aug 20, 2025Aug 20, 2025

    • unstructured-mlk-archive-public

      Public
      HTML
      •1•8•0•0•Updated Jul 23, 2025Jul 23, 2025

    • unstructured.PaddleOCR

      Public
      Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and …
      Python
      •
      Apache License 2.0
      •9.7k•41•0•0•Updated Mar 17, 2025Mar 17, 2025

    • unstructured.pytesseract

      Public
      A Python wrapper for Google Tesseract
      Python
      •
      Apache License 2.0
      •749•4•0•0•Updated Mar 5, 2025Mar 5, 2025

    • azure-ai-hub-gateway-solution-accelerator

      Public
      Reference architecture that provides a set of guidelines and best practices for implementing a central AI API gateway to empower various line-of-business units …
      Bicep
      •
      MIT License
      •122•1•0•0•Updated Nov 22, 2024Nov 22, 2024

    • aws-blog-post-example

      Public
      Script to accompany the AWS blog post on unstructured data ETL with Unstructured Ingest library
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Oct 16, 2024Oct 16, 2024

    • pairing-technical-challenge

      Public
      Pairing Technical Challenge
      TypeScript
      •0•0•0•0•Updated Sep 4, 2024Sep 4, 2024

    • model-cards

      Public
      FedRAMP formatted model cards
      0•1•0•0•Updated Aug 29, 2024Aug 29, 2024

    • danswer

      Public
      Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.
      Python
      •
      Other
      •2.3k•11•0•1•Updated Aug 23, 2024Aug 23, 2024

    • js-client-batch

      Public
      JS Client Batch Processing
      JavaScript
      •0•0•0•0•Updated Jul 31, 2024Jul 31, 2024

    • wolfi-dev-os

      Public
      Main package repository for production Wolfi images
      C
      •
      Other
      •418•0•0•0•Updated Jul 10, 2024Jul 10, 2024

    • pipeline-sec-filings

      Public archive
      Preprocessing pipeline notebooks and API supporting text extraction from SEC documents
      Jupyter Notebook
      •
      Apache License 2.0
      •35•148•5•7•Updated Jan 1, 2024Jan 1, 2024

    • pipeline-template

      Public
      Python
      •
      Apache License 2.0
      •8•8•0•4•Updated Oct 2, 2023Oct 2, 2023

    • pipeline-oer

      Public
      Pipeline for extraction information from Army OERs
      Jupyter Notebook
      •
      Apache License 2.0
      •5•8•1•6•Updated Oct 1, 2023Oct 1, 2023

    • pipeline-paddleocr

      Public
      Pipeline for converting PDFs to raw text with PaddleOCR
      Jupyter Notebook
      •
      Apache License 2.0
      •7•23•1•5•Updated Aug 21, 2023Aug 21, 2023

    • langchain

      Public
      ⚡ Building applications with LLMs through composability ⚡
      Python
      •
      MIT License
      •21k•8•0•0•Updated Aug 18, 2023Aug 18, 2023