# Unstructured-IO/unstructured

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models.  Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

Repository: https://github.com/Unstructured-IO/unstructured
Canonical: https://ross.abutalabs.com/products/unstructured
Homepage: https://www.unstructured.io/
Language: HTML
License: Apache-2.0
License Family: permissive
Topics: deep-learning, document-parsing, machine-learning, nlp, ocr, information-retrieval, data-pipelines, ml, preprocessing, pdf-to-text, natural-language-processing, pdf, pdf-to-json, document-image-analysis, donut, document-image-processing, document-parser, docx, langchain, llm
Last push: 2026-08-24T18:59:56+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 100
- inputs: {"age_days": 1437, "days_push": 9, "days_rel": 12, "gap_med": 4.0, "n_releases_24m": 89}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15349, forks 1307 (observed 2026-08-28T04:11:09.685205+00:00)

## What it is
Unstructured is an open-source ETL library and platform for converting complex documents (PDF, DOCX, HTML, images, and 65+ file types) into clean, structured JSON for language models. It provides partitioning, chunking, OCR, and enrichment pipelines that feed RAG and agentic AI workflows.

## Use cases
- parse resumes from pdfs
- convert pdf documents to text for llm ingestion
- extract structured  from docx and html files
- build a rag pipeline over a document corpus
- ocr scanned documents into machine-readable text
- chunk documents for vector database embedding
- preprocess documents for chatbot knowledge bases

## When to choose
- you need to turn messy documents of many formats into LLM-ready structured data
- you want an open-source document parsing pipeline with optional hosted platform
- you're building RAG or agentic AI applications that ingest PDFs, Office files, or HTML

## When to avoid
- you only need simple text extraction from plain text or well-structured markdown
- you need a lightweight tool without heavy ML dependencies
- your use case is real-time streaming transformation unrelated to documents

## Facets
- artifact type: library
- maturity: active
- function: etl, ocr, pdf, parser, rag, nlp, data-science
- domain: pdf, large-language-models
- platform: python, self-hosted, cloud
- tags: document-parsing, pdf-to-text, document-etl, chunking, preprocessing, langchain, llm-preparation, natural-language-processing, data-engineering, retrieval-augmented-generation, docker

## Member repositories
- Unstructured-IO/unstructured (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.685205+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:06:21.684738+00:00, confidence not recorded.
  - readme: https://github.com/Unstructured-IO/unstructured (fetched 2026-08-28T04:11:09.685205+00:00, sha 989b80ac88d3)
  - homepage: https://www.unstructured.io/ (fetched 2026-08-29T08:04:17.395047+00:00, sha 153a2febcdf5)
  - site_page: https://docs.unstructured.io (fetched 2026-08-29T08:04:17.406992+00:00, sha 46f768b65f2d)
  - site_page: https://www.unstructured.io/pricing (fetched 2026-08-29T08:04:17.404728+00:00, sha bcfc2067900d)
- Data as of 2026-08-30T08:39:29.467469+00:00.