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

Merge pull request #92 from seanpedrick-case/regex_search

Added regex search feature 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

formatter and linter applied

Merge pull request #89 from seanpedrick-case/textract_type_name_output

Added suffix to textract output files according to tasks included (e.g. signature analysis). Improved reporting when Textract client doesn't exist. Fixed display for cost and time taken. Changes to config variables to allow exclusion of PaddleOCR from display

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

Added paddle to pre-requirements.txt

Allowed for load Paddle at startup. Updated requirements for torch compatability

Updated requirements

Updated requirements for torch. Updated main hf flow to force changes to spaces repo

Updated dependencies, github to HF workflow

Updated sync to hf workflow for zero GPU space sync

Updated readme for install instructions with paddle, vlms

Merge pull request #88 from seanpedrick-case/vlm_support

formatter and linter applied

Updated word segmenter code

Similar cleanup to requirements_lightweight.txt

Cleaned requirements.txt file

Updated test suites to use the lightweight version of requirements.txt

Added text rotation capability

Optimised VLM model selection

Optimised VLM model choice and prompting/parameters

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

Improved new requirements. Improved visual OCR outputs and word-level Paddle outputs and general bounding box positioning

Initial commit for VLM support. Created visualisations for OCR output. Corrected log_file_output_paths reference.

Again revised spaCy language model load for different languages

Modified model load for custom languages with spaCy. Languages should load successfully now.

User ownership folder change to whole user folder in Dockerfile. Minor changes to documentation

Ensured that AWS credentials called correctly in logger settings.

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

head attribute added to Gradio blocks context to enable enforcement of direct vs relative file paths. Updates to direct mode/lambda entrypoint to ensure as many options as possible can be user defined

Merge pull request #80 from seanpedrick-case/main

Fix condition check for SHOW_EXAMPLES

Merge pull request #79 from seanpedrick-case/dev

formatter and lint check

Correction to PaddleOCR config variable. Minor print statement changes

Revised environment variables for consistency.

Custom env variables should now overwrite defaults for lambda function. Usage logs should now be correctly created with lambda function

Updated some config variable defaults for lambda_entrypoint (e.g. page max, min) to ensure that they are correctly parsed

cli_usage_logger should now use custom folder input

Corrected environment variable file references for log files and spacy/paddle folders for lambda_entrypoint

Added logging folders to cli_redact to ensure correct saves with read-only file systems (e.g. lambda). Updated list-based parsing of arguments in lambda_entrypoint.py

Updated lambda_entrypoint dict references. Redaction functions should now return files even if MAX_TIME_VALUE value exceeded. load_all_output_files should now return subfolder files

Updated file processing for more efficient redaction for specific page ranges. Updated lambda_entrypoint to allow for environment variables from .env files, and limits to compatible file types

Updated some config variables for lambda functions to enable successful run

Updated cdk_stack for build commands compatible with new dockerfile. Minor changes to lambda function to specify text extraction method correctly.