Allow for tesseract to run OCR in line-level mode and then query LLM with line-level data. Added option for running as MCP server, added api for multi-word text search

Minor update to cli_redact for new local OCR model options. Updated app_settings.qmd, user_guide.qmd, and readme.md with descriptions of new features

Fixed minor bugs related to Textract API calls, pyproject format. Removed print statements and fixed some future concat deprecation issues

Improved paddle and hybrid OCR analysis across all options. Tried to revise requirements for spaces

Updated requirements

Updated dependencies, github to HF workflow

Added hybrid paddle + vlm option. Optimised word segmenters for single words. Optimised package installation in pyproject.toml

Added upgraded line to word parsing algorithm. Added dependencies and framework for Huggingface spaces deployment with ZeroGPU

Updated user guide and app settings. Updated some additional lambda_entrypoint arguments. Ensured that examples are correctly displayed on GUI.

Updated paddleocr implementation to have a menu option on the GUI with a config value change. Minor package updates, favicon update, and update to Dockerfile to allow for Lambda function execution.

Fixed text inclusion in review pdf outputs from apply_redactions_to_review_df... function. Apply redaction pymupdf text/graphic/image options are now modifiable. Tables on review screen should now be able to use Gradio column filter options. Moved some functions to more logical location.

Moved from gunicorn to uvicorn for AWS deployment

Added gunicorn to requirements for when building Dockerfile based on FastAPI rather than Gradio directly. Updated minor some file path issues. Set return review PDF as default.

Added capability of loading in redaction annotations from PDF documents directly into the app. Minor function documentation improvements, GUI changes, package updates.

Removed some extraneous test steps. Improved Example loading and feedback, and redaction feedback. Minor security updates. Fixed Adobe xfdf file parsing.

Updated Windows Tesseract install location for test

Fixed duplicate page argument mismatch. Readded Windows tests. Added refresh token options to cdk. Package updates

Fixed on deprecated Github workflow functions. Applied linter and formatter to code throughout. Added tests for GUI load.

Added a test suite based on the functions in cli_redact.py

Added example data files. Greatly revised CLI redaction for redaction, deduplication, and AWS Textract batch calls. Various minor fixes and package updates.

Fix to tabular redaction, added tabular deduplication. Updated cli call capability for both

Updated review functions to update with manual reviews. Minor package update

Corrected some multiple xlsx/docx file redaction issues. package updates.

Added PaddleOCR support

Added capability to redact Word files

Package updates

Can now redact terms using a new redact search tab on the Review Redactions tab. Various minor improvements

Updated packages. Corrected CSV logger headings, can now submit custom log csv names to S3. Started work on identifying and deduplicating at the line level

Updated CDK code for custom KMS keys, new VPCs. Minor package updates.

Updated duplicate pages interface to include subdocuments and review. Updated relevant user guide. Minor package updates

Adapted Dockerfile for systems with read only file system. Minor package updates.

Update version numbers and readme

Updated version numbers

Updated version numbers, gradio package version.

Updated gradio version. Minor changes to redactor function sequence. Minor formatting and wording changes.

Upgraded version numbers

Corrected a couple of bugs. Now Textract whole document API call outputs will load also the input PDF into the app

Updated version numbers, minor text revision

Fix for image file redaction

Minor changes for cost codes, package updates. Added pyproject.toml file