9f9777240a
Adds Tesseract-based OCR pre-processing that computes pixel-level text positions, margins, spacing, and alignment before LLM analysis. This enables detection of subtle layout differences that vision models miss (e.g. 2.8% vs 6.4% headline margin, 83px vs 39px date gap). OCR measurements injected into 10 checks across all client profiles: - Amazon: margins, typography, headline_layout - Static General: element_alignment, safety_area, visual_hierarchy_general, text_readability_general, text_edge_clearance - L'Oreal: text_readability - Diageo/Unilever KV: visual_hierarchy Non-blocking: if Tesseract is unavailable, checks run with visual estimation only. Production requires: sudo apt install tesseract-ocr Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
17 lines
No EOL
309 B
Text
Executable file
17 lines
No EOL
309 B
Text
Executable file
openai>=1.3.0,<2.0.0
|
|
google-generativeai>=0.3.0
|
|
Pillow>=9.0.0
|
|
PyMuPDF>=1.23.0
|
|
opencv-python>=4.0.0
|
|
python-dotenv>=1.0.0
|
|
flask>=2.2.3
|
|
hypercorn>=0.14.3
|
|
waitress>=2.1.2
|
|
requests>=2.28.2
|
|
python-multipart>=0.0.5
|
|
colorama>=0.4.4
|
|
openpyxl>=3.1.0
|
|
watchdog>=2.1.0
|
|
PyJWT>=2.8.0
|
|
cryptography>=41.0.0
|
|
pytesseract>=0.3.10 |