unstructured
A library that prepares raw documents for downstream ML tasks.
Decision gist · record as of 2026-08-14
Yes, with conditions. Install if you need to process multiple document formats and can manage the 24 runtime dependencies and system-level tools. The active maintenance, permissive license, and broad format support make it a solid choice for LLM data preparation pipelines. Skip if you only need to parse a single format (use a lighter, format-specific library instead) or if your environment cannot accommodate the dependency footprint.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- System dependencies required for full functionality: libmagic-dev (filetype detection), poppler-utils (PDFs/images), tesseract-ocr (OCR), libreoffice (MS Office).
- Minimal install works for text, HTML, XML, JSON, emails only.
- Low friction installation with a pure Python wheel.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most production and proprietary projects.
last release 2026-08-03 (11 days) · last repo commit 2026-08-14 · 15,312 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 5,518,206 downloads/mo, #2,084 on PyPI
Alternatives
Verify before relying
pip install unstructured
from unstructured.partition.auto import partition
elements = partition(filename="document.pdf")
for el in elements:
print(el)- Whether all 60+ file types mentioned in the description are fully supported in version 0.25.2 or if some require paid/enterprise features
- Performance characteristics and memory footprint when processing large documents or batches
- Whether the MCP server integration mentioned in the description is included in the PyPI package or requires separate installation
What it is and what it does
Unstructured is a document processing library that converts raw files in many formats into structured, machine-readable elements. It handles PDFs, Word documents, HTML, emails, images, and dozens of other formats, extracting text and metadata while preserving document structure. The library is designed to prepare unstructured data for downstream machine learning tasks, particularly for large language models.
The package works by partitioning documents into semantic elements (paragraphs, tables, headers, etc.), then optionally enriching and chunking them for vector databases or other ML workflows. It ships with 24 runtime dependencies including parsing libraries (beautifulsoup4, lxml, html5lib), NLP tools (spacy, langdetect), and numerical computing (numpy, numba). Installation requires system-level dependencies for full format support, though a minimal install handles text and markup formats without them.
Use it for
- Extract and structure text from PDFs and scanned documents for ingestion into vector databases or RAG systems
- Parse email messages and attachments to prepare them for LLM analysis or archival processing
- Convert Word documents, PowerPoint slides, and other office formats into structured text for batch processing
- Chunk long documents into semantically meaningful segments for embedding and retrieval workflows
- Detect and extract tables from PDFs and images for structured data extraction pipelines
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
Install if you need to process multiple document formats and can manage the 24 runtime dependencies and system-level tools. The active maintenance, permissive license, and broad format support make it a solid choice for LLM data preparation pipelines. Skip if you only need to parse a single format (use a lighter, format-specific library instead) or if your environment cannot accommodate the dependency footprint.
Install
unstructured on PyPI
Before you install
Low friction installation with a pure Python wheel. Active maintenance with a release 11 days ago and 15312 GitHub stars. Requires 24 runtime dependencies including heavy libraries (spacy, numba, numpy, lxml), so initial install may take time despite the wheel format.
System dependencies required for full functionality: libmagic-dev (filetype detection), poppler-utils (PDFs/images), tesseract-ocr (OCR), libreoffice (MS Office). Minimal install works for text, HTML, XML, JSON, emails only.
License in practice
Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most production and proprietary projects.
Quickstart
pip install unstructured
from unstructured.partition.auto import partition
elements = partition(filename="document.pdf")
for el in elements:
print(el)Verify before relying
- Whether all 60+ file types mentioned in the description are fully supported in version 0.25.2 or if some require paid/enterprise features
- Performance characteristics and memory footprint when processing large documents or batches
- Whether the MCP server integration mentioned in the description is included in the PyPI package or requires separate installation
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.14,>=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 24 packagesbeautifulsoup4charset-normalizeremojifilelockfiletypehtml5libinstallerlangdetectlxmlnh3numbanumpypsutilpython-iso639python-magicpython-oxmsgrapidfuzzregexrequestsspacytqdmtyping-extensionsunstructured-clientwrapt |
| Maintenance | Actively maintained 11 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 5,518,206 / month, #2,084 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: unstructured-0.25.2-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “document parsing and preprocessing”
- unstructuredIngests and pre-processes unstructured documents (PDFs, HTML, Word,…
- unstructured-inferenceRuns inference on layout-parsing and document-analysis models to…
- textacytextacy extends spaCy's NLP capabilities with pre- and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also unstructured-client · unstructured-inference · unstructured-ingest · langchain-unstructured · pymupdf4llm · llama-parse · chonkie · kreuzberg · pdftext · mineru