- Improves documentation and adds additional tutorials and examples. - Adds support for layout parsing via publaynet models
0.3.8
- Adds documentation for missing codebase. - Update Document classifier and table extractor interface.
0.3.7
- Minor updates to setup.py and README. - Update Missing requirements.
0.3.6
- Adds an experimental DocumentClassifier Module: that lets users classify documents into 16 different categories like invoice, newspaper, resume, reserch-paper etc. - minor refactoring
0.3.5
- Minor improvements to codebase. - Improves Table Parser - adds support for csv formatter. - Adds Pipeline Config. - Improves TextOcrPipeline - provides pipeline run info and refactoring. - Adds alternate pipeline load and run methods via ocrpy config - yaml files.