Tutorials

Getting Started

Please refer to Ocrpy Quick starter Notebook for an in-depth walkthrough of how to use Ocrpy. This notebook gives an overview of how to use Ocrpy to perform:

• Document classification

• Layout Parsing

• Table extraction

• Running a full Text Ocr pipeline

• and writing the extracted output to a storage of choice.

Ocr, Index and Search

Also checkout the Ocr, index and Search Notebook for an in-depth walkthrough of how to use Ocrpy to ocr, index and do semantic search. In this Notebook, you will find how to use ocrpy to extract text and tables from your pdf’s and images and then index the extracted the data to either opensearch, elasticsearch or a mysql database & then query the indexed collection of docs via semantic search.