Open-Source Pre-Processing Tools for Unstructured Data

The unstructured library provides open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more. The use cases of unstructured revolve around streamlining and optimizing the data processing workflow for LLMs. unstructured modular bricks and connectors form a cohesive system that simplifies data ingestion and pre-processing, making it adaptable to different platforms and efficient in transforming unstructured data into structured outputs.

API Announcement!

We are thrilled to announce our newly launched Unstructured API, providing the Unstructured capabilities from unstructured as an API. Check out the unstructured-api GitHub repository to start making API calls. You’ll also find instructions about how to host your own API version.

While access to the hosted Unstructured API will remain free, API Keys are required to make requests. To prevent disruption, get yours here and start using it today! Check out the unstructured-api README to start making API calls.

🚀 Beta Feature: Chipper Model

We are releasing the beta version of our Chipper model to deliver superior performance when processing high-resolution, complex documents. To start using the Chipper model in your API request, you can utilize the hi_res_model_name=chipper parameter. Please refer to the documentation here.

As the Chipper model is in beta version, we welcome feedback and suggestions. For those interested in testing the Chipper model, we encourage you to connect with us on Slack community.

✴️ Quick Start

There are several ways to use the unstructured library:

• Run the library in a container or
• Install the library
  1. Install from PyPI
  2. Install for local development
• For installation with conda on Windows system, please refer to the documentation

Run the library in a container

The following instructions are intended to help you get up and running using Docker to interact with unstructured. See here if you don't already have docker installed on your machine.

NOTE: we build multi-platform images to support both x86_64 and Apple silicon hardware. docker pull should download the corresponding image for your architecture, but you can specify with --platform (e.g. --platform linux/amd64) if needed.

We build Docker images for all pushes to main. We tag each image with the corresponding short commit hash (e.g. fbc7a69) and the application version (e.g. 0.5.5-dev1). We also tag the most recent image with latest. To leverage this, docker pull from our image repository.

docker pull downloads.unstructured.io/unstructured-io/unstructured:latest

Once pulled, you can create a container from this image and shell to it.

# create the container
docker run -dt --name unstructured downloads.unstructured.io/unstructured-io/unstructured:latest

# this will drop you into a bash shell where the Docker image is running
docker exec -it unstructured bash

You can also build your own Docker image.

If you only plan on parsing one type of data you can speed up building the image by commenting out some of the packages/requirements necessary for other data types. See Dockerfile to know which lines are necessary for your use case.

make docker-build

# this will drop you into a bash shell where the Docker image is running
make docker-start-bash

Once in the running container, you can try things directly in Python interpreter's interactive mode.

# this will drop you into a python console so you can run the below partition functions
python3

>>> from unstructured.partition.pdf import partition_pdf
>>> elements = partition_pdf(filename="example-docs/layout-parser-paper-fast.pdf")

>>> from unstructured.partition.text import partition_text
>>> elements = partition_text(filename="example-docs/fake-text.txt")

Installing the library

Use the following instructions to get up and running with unstructured and test your installation.

• Install the Python SDK to support all document types with pip install "unstructured[all-docs]"

  • For plain text files, HTML, XML, JSON and Emails that do not require any extra dependencies, you can run pip install unstructured
  • To process other doc types, you can install the extras required for those documents, such as pip install "unstructured[docx,pptx]"

• Install the following system dependencies if they are not already available on your system. Depending on what document types you're parsing, you may not need all of these.

  • libmagic-dev (filetype detection)
  • poppler-utils (images and PDFs)
  • tesseract-ocr (images and PDFs, install tesseract-lang for additional language support)
  • libreoffice (MS Office docs)
  • pandoc (EPUBs, RTFs and Open Office docs)

• For suggestions on how to install on the Windows and to learn about dependencies for other features, see the installation documentation here.

At this point, you should be able to run the following code:

from unstructured.partition.auto import partition

elements = partition(filename="example-docs/eml/fake-email.eml")
print("\n\n".join([str(el) for el in elements]))

Installation Instructions for Local Development

The following instructions are intended to help you get up and running with unstructured locally if you are planning to contribute to the project.

• Using pyenv to manage virtualenv's is recommended but not necessary

  • Mac install instructions. See here for more detailed instructions.
    • brew install pyenv-virtualenv
    • pyenv install 3.10
  • Linux instructions are available here.

• Create a virtualenv to work in and activate it, e.g. for one named unstructured:

  pyenv virtualenv 3.10 unstructured
pyenv activate unstructured

• Run make install

• Optional:

  • To install models and dependencies for processing images and PDFs locally, run make install-local-inference.
  • For processing image files, tesseract is required. See here for installation instructions.
  • For processing PDF files, tesseract and poppler are required. The pdf2image docs have instructions on installing poppler across various platforms.

Additionally, if you're planning to contribute to unstructured, we provide you an optional pre-commit configuration file to ensure your code matches the formatting and linting standards used in unstructured. If you'd prefer not to have code changes auto-tidied before every commit, you can use make check to see whether any linting or formatting changes should be applied, and make tidy to apply them.

If using the optional pre-commit, you'll just need to install the hooks with pre-commit install since the pre-commit package is installed as part of make install mentioned above. Finally, if you decided to use pre-commit you can also uninstall the hooks with pre-commit uninstall.

In addition to develop in your local OS we also provide a helper to use docker providing a development environment:

make docker-start-dev

This starts a docker container with your local repo mounted to /mnt/local_unstructured. This docker image allows you to develop without worrying about your OS's compatibility with the repo and its dependencies.

👏 Quick Tour

Documentation

This README overviews how to install, use and develop the library. For more comprehensive documentation, visit https://unstructured-io.github.io/unstructured/ .

Concepts Guide

Bricks 🧱 in unstructured are the foundational elements that drive the data processing workflow within the system. These components provide users with the building blocks to build pipelines targeted at the documents they care about. The bricks fall into three categories:

• 🧩 Partitioning bricks break raw documents into standard, structured elements.
• 🧹 Cleaning bricks remove unwanted text from documents, such as boilerplate and sentence fragments.
• 🎭 Staging bricks format data for downstream tasks, such as ML inference and data labeling.

These bricks create a cohesive, streamlined process that enables effective data handling and analysis. Check out the available bricks and how to use them from the Bricks documentation.

The Connectors 🔗 in unstructured serve as vital links between the pre-processing pipeline and various data storage platforms. They allow for the batch processing of documents across various sources, including cloud services, repositories, and local directories. Each connector is tailored to a specific platform, such as Azure, Google Drive, or Github, and comes with unique commands and dependencies. To see the list of Connectors available in unstructured library, please check out the Connectors GitHub folder and documentation

PDF Document Parsing Example

The following examples show how to get started with the unstructured library. You can parse over a dozen document types with one line of code! Use this Colab notebook to run the example below.

The easiest way to parse a document in unstructured is to use the partition brick. If you use partition brick, unstructured will detect the file type and route it to the appropriate file-specific partitioning brick. If you are using the partition brick, you may need to install additional parameters via pip install unstructured[local-inference]. Ensure you first install libmagic using the instructions outlined here partition will always apply the default arguments. If you need advanced features, use a document-specific brick.

from unstructured.partition.auto import partition

elements = partition("example-docs/layout-parser-paper.pdf")

Run print("\n\n".join([str(el) for el in elements])) to get a string representation of the output, which looks like:

LayoutParser : A Unified Toolkit for Deep Learning Based Document Image Analysis

Zejiang Shen 1 ( (cid:0) ), Ruochen Zhang 2 , Melissa Dell 3 , Benjamin Charles Germain Lee 4 , Jacob Carlson 3 , and
Weining Li 5

Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural
networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation.
However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy
reuse of important innovations by a wide audience. Though there have been ongoing efforts to improve reusability and
simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none
of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA
is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper
introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applications.
The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models
for layout detection, character recognition, and many other document processing tasks. To promote extensibility,
LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digitization
pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in
real-word use cases. The library is publicly available at https://layout-parser.github.io

Keywords: Document Image Analysis · Deep Learning · Layout Analysis · Character Recognition · Open Source library ·
Toolkit.

Introduction

Deep Learning(DL)-based approaches are the state-of-the-art for a wide range of document image analysis (DIA) tasks
including document image classification [11,

See the partitioning section in our documentation for a full list of options and instructions on how to use file-specific partitioning functions.

💂‍♂️ Security Policy

See our security policy for information on how to report security vulnerabilities.

🐛 Reporting Bugs

Encountered a bug? Please create a new GitHub issue and use our bug report template to describe the problem. To help us diagnose the issue, use the python scripts/collect_env.py command to gather your system's environment information and include it in your report. Your assistance helps us continuously improve our software - thank you!

📚 Learn more

Section	Description
Company Website	Unstructured.io product and company info
Documentation	Full API documentation
Batch Processing	Ingesting batches of documents through Unstructured

📈 Analytics

We’ve partnered with Scarf (https://scarf.sh) to collect anonymized user statistics to understand which features our community is using and how to prioritize product decision-making in the future. To learn more about how we collect and use this data, please read our Privacy Policy.