Skip to content

dataelement/bisheng-unstructured

Repository files navigation

What is bisheng-unstructured?

Bisheng-unstructured is an open-source unstructured data parsing library built to power LLM applications like pretrain, finetune, prompting engineering. Bisheng-unstructured makes the unstructured data porcessing more easily and provides a consistent user experience regardless of any file types.

The project is a sub-project of bisheng.

Key features

  • High precision pdf layout parser
  • High precision table structure recovering
  • High precision OCR ability
  • More friendly for token prossing for the visual text element, like table, list

Quick start

Start With Bisheng Platform

Use as a chain node ElemUnstructureLoader

Start with DataElem Services.

We provide a open cloud service for easily use. See free trial.

Install bisheng-unstructured

Using from pre-builded image

Documentation

For guidance on installation, development, deployment, and administration, check out bisheng-unstructured Docs.

Issues

Reporting problems, asking questions We appreciate any feedback, questions or bug reporting regarding this project.

User can posting Issues, follow the process outlined in the Stack Overflow document.

For questions, we recommend posting in our community GitHub Discussions.

Acknowledgments

bisheng-unstructured adopts dependencies from the following: