Package profile
unstructured
- Summary: A library that prepares raw documents for downstream ML tasks.
- Author: Unstructured Technologies <devops@unstructuredai.io>
- License: Apache-2.0
- Homepage: https://github.com/Unstructured-IO/unstructured
- Source: https://github.com/Unstructured-IO/unstructured
- Number of releases: 236
- First release: 0.0.1.dev0 on 2022-09-06
- Latest release: 0.27.10 on 2026-09-27
- Latest release size: 1.6 MB (pure Python wheel)
3 known vulnerabilitiesLatest: GHSA-4mvj-m6j5-pmf7 — unstructured: Server-Side Request Forgery in the URL-based partitioning View all →
Dependencies
Unstructured has 49 dependencies, 25 of which optional.Dependent packages
| Package | Optional | Group |
|---|---|---|
| acryl-datahub | true | confluence |
| agno | true | markdown-chunking |
| airbyte-cdk | true | file-based |
| crewai-tools | true | xml |
| pueblo | true | nlp |
Similar packages
- doclingSDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
- coremltoolsCommunity Tools for Core ML
- spark-nlpJohn Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
- ml-collectionsML Collections is a library of Python collections designed for ML usecases.
- mlflowMLflow is an open source platform for the complete machine learning lifecycle
- mlflow-skinnyMLflow is an open source platform for the complete machine learning lifecycle
- transformersTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.