Feature/expanded text ingestion#62

Closed

HatmanStack wants to merge 12 commits intoaws-solutions-library-samples:mainfrom

HatmanStack:feature/expanded-text-ingestion

Commits on Sep 23, 2025

Refactor: Create Standalone, Intelligent Text Extraction Module
google-labs-jules[bot]
committed
Added expanded text ingestion for text based pdfs

HatmanStack
authored and
HatmanStack
committed
Native Text Extraction Tested

HatmanStack
authored and
HatmanStack
committed
Added document text to textConfidence.json as that appears to be what BKB is pulling vectors from

HatmanStack
authored and
HatmanStack
committed
Inadvertent change to assessment properties

HatmanStack
authored and
HatmanStack
committed
revert dual toggles assesment UI

HatmanStack
authored and
HatmanStack
committed

Commits on Sep 24, 2025

Init of pdf native text extraction with hybrid intelligent image handling

HatmanStack
authored and
HatmanStack
committed

Commits on Sep 30, 2025

Implement efficient text-based PDF processing path
google-labs-jules[bot]
committed

Commits on Oct 1, 2025

Expanded text supported formats | documentation upgrade | Hybrid filtering logic for embedded images

HatmanStack
authored and
HatmanStack
committed

Commits on Oct 2, 2025

Parallel Processing | Metering

HatmanStack
authored and
HatmanStack
committed
cleaned up excess files | moved text_extraction into ocr module

HatmanStack
authored and
HatmanStack
committed
revert to standard ocr for pdf's when using textract

HatmanStack
authored and
HatmanStack
committed