This repository contains the documentation how you can use the Archery to load documents from "real life".

In today's data-driven landscape, navigating the complexities of semi-structured documents poses a significant challenge for organizations. These documents, characterized by diverse formats and a lack of standardization, often require specialized skills for effective manipulation and analysis. However, we propose a novel framework to address this challenge. By leveraging innovative algorithms and machine learning techniques, Archery offers a solution that gives you control over the data extraction process with tweakable and repeatable settings. Moreover, by automating the extraction process, it not only saves time but also minimizes errors, particularly beneficial for industries dealing with large volumes of such documents. Crucially, this framework integrates with machine learning workflows, unlocking new possibilities for data enrichment and predictive modeling. By leveraging determinist algorithms, this framework is perfect to prepare your data for training processes in a predictive and reproductible manner. Aligned with the paradigm of data as a service, it offers a scalable and efficient means of managing semi-structured data, thereby expanding the toolkit of data services available to organizations.

Visit our full documentation and learn more about how it works, try our tutorials and find a full list of plugins and models.

• Python 3.8.2 or above.
• Pip 20.0.2 or above.
• Just 1.24.0 or above.

To install MkDocs, run the following command from the command line:

pip install mkdocs

For more details, see the Installation Guide.

For more details, see the Installation Guide.

Run the following command line:

just serve

Run the following command line:

just build

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

• Romuald Rousseau, [email protected]

• 1.0
• Initial Release

• Complete articles
  • Article - Revolutionizing Data Management: The Transformative Potential of a Novel Framework for Semi-Structured Documents
• Complete tutorials
  • Tutorial 1 - Getting Started
  • Tutorial 2 - Data extraction with a complex semi-structured layout
  • Tutorial 3 - Data extraction with defects
  • Tutorial 4 - Data extraction with tags
  • Tutorial 5 - Data extraction with pivot
  • Tutorial 6 - More complex noise reduction
  • Tutorial 7 - Data extraction from PDF
  • Tutorial 8 - Make a classifier
• Completes white papers
  • Table Layout Regular Expression - Layex
  • Semi-structured Document Feature Extraction
  • Stats in white paper Layex
  • Add capillarity in the feature extraction
  • Amend merged cell in white paper Layex
• Completes patents
  • [-] Patent 1 - Patent 1 - Method to Consistently and Efficiently Extract Table Layout Feature
  • [-] Patent 2 - Patent 2 - Method to Extract Semi-structured Document Features
• Build and Deploy site
  • Write justfile
  • svg -> png
  • [-] Add pivot options in tutorial 5