3fec052c12
Organized the application into separate frontend and backend directories for cleaner deployment and better separation of concerns. Frontend Directory (frontend/): - index.html: Single-page web interface (renamed from web_ui.html) - README.md: Frontend deployment guide - Total size: ~113 KB (self-contained) - Smart base path detection (works at / or /ai_qc/) - No configuration changes required Backend Directory (backend/): - All Python files (api_server.py, llm_config.py, etc.) - visual_qc_apps/: 33 QC check modules - profiles/: 6 QC profile configurations - brand_guidelines/: Reference asset storage - config/: Environment configurations - scripts/: Deployment automation - uploads/, output/: Data directories - requirements.txt, ai_qc.service, apache_config.conf - Complete documentation New Documentation: - FOLDER_STRUCTURE.md: Comprehensive guide to new structure - frontend/README.md: Frontend deployment instructions - backend/BACKEND_README.md: Backend deployment guide Deployment Mapping: - frontend/ → /var/www/html/ai_qc/ (web root) - backend/ → /opt/ai_qc/ (application directory) Benefits: - Clear separation of concerns - Backend code not in web-accessible directory - Independent frontend/backend updates - Matches server's existing patterns (/opt/veo3, /opt/voice2text) - Industry-standard architecture - Easy to deploy and maintain Original files preserved in root directory for reference. Ready for production deployment following MIGRATION_GUIDE.md. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
86 lines
No EOL
3.8 KiB
Python
Executable file
86 lines
No EOL
3.8 KiB
Python
Executable file
import os
|
|
import sys
|
|
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
|
|
|
|
from visual_qc_apps.flask_app_template import FlaskAppTemplate
|
|
|
|
class InclusiveApp(FlaskAppTemplate):
|
|
"""
|
|
Inclusive Representation QC Tool - Evaluates content using the Unstereotype 3Ps Framework
|
|
Analyzes Presence, Perspective, and Personality for inclusive representation
|
|
"""
|
|
|
|
def __init__(self):
|
|
prompt = """
|
|
You are a visual quality control expert specializing in inclusive representation analysis using the Unstereotype 3Ps Framework. Your task is to evaluate this image for inclusive representation across three key dimensions: Presence, Perspective, and Personality.
|
|
|
|
EVALUATION FRAMEWORK - The Unstereotype 3Ps:
|
|
|
|
1. PRESENCE - Equal and Authentic Representation:
|
|
- Assess representation across gender, race, ethnicity, age, ability, sexual orientation
|
|
- Evaluate balance of screen time and visibility for different groups
|
|
- Check if diverse people are shown in varied roles (workplace, home, leadership)
|
|
- Examine representation in both primary and background roles
|
|
- Consider intersectionality - multiple identity aspects working together
|
|
- Look for tokenism vs. meaningful inclusion
|
|
|
|
2. PERSPECTIVE - Diverse Viewpoints and Agency:
|
|
- Evaluate if diverse viewpoints and cultural experiences are shown
|
|
- Check for stereotypical storylines and narratives
|
|
- Assess if people are portrayed as empowered agents vs. passive subjects
|
|
- Examine agency and decision-making representation
|
|
- Evaluate if traditional power dynamics are challenged appropriately
|
|
- Analyze camera angles and framing for objectification or diminishment
|
|
|
|
3. PERSONALITY - Multi-dimensional Characterization:
|
|
- Assess if characters are portrayed as full, complex individuals
|
|
- Check for avoidance of one-dimensional stereotypical traits
|
|
- Evaluate realistic emotions, motivations, and behaviors
|
|
- Examine representation of human experience complexity
|
|
- Assess authenticity vs. tokenistic characterization
|
|
- Look for depth beyond surface-level diversity
|
|
|
|
EVALUATION PROCESS:
|
|
1. Carefully examine all people visible in the image
|
|
2. Identify the context, setting, and apparent narrative
|
|
3. Analyze each of the 3Ps dimensions systematically
|
|
4. Consider both what is shown and what might be missing
|
|
5. Evaluate the overall inclusive representation quality
|
|
|
|
SCORING METHODOLOGY:
|
|
|
|
For each of the 3Ps, provide a score from 1-5:
|
|
1. PRESENCE - Equal and Authentic Representation (1-5)
|
|
2. PERSPECTIVE - Diverse Viewpoints and Agency (1-5)
|
|
3. PERSONALITY - Multi-dimensional Characterization (1-5)
|
|
|
|
INDIVIDUAL P SCORING (1-5):
|
|
- 5: Exemplary implementation with outstanding inclusive representation
|
|
- 4: Strong implementation with minor areas for improvement
|
|
- 3: Adequate implementation meeting basic inclusive standards
|
|
- 2: Limited implementation with significant representation issues
|
|
- 1: Poor implementation with harmful stereotypes or exclusion
|
|
- N/A: Not applicable/no people or relevant content to evaluate
|
|
|
|
OVERALL SCORING (1-10):
|
|
Calculate overall score from the average of applicable P scores, scaled to 1-10.
|
|
If any P is not applicable (e.g., no people visible, no narrative context), exclude it from scoring.
|
|
|
|
Provide your analysis in JSON format with:
|
|
- Individual scores for each of the 3Ps (1-5 or "N/A")
|
|
- Overall inclusive representation score (1-10) calculated from applicable Ps
|
|
- Detailed assessment explaining each P score
|
|
- List of which Ps were excluded and why
|
|
- Specific observations about representation
|
|
- Recommendations for improvement
|
|
- Potential concerns or red flags
|
|
|
|
Be thorough, constructive, and sensitive in your evaluation while maintaining professional objectivity.
|
|
"""
|
|
|
|
super().__init__(__name__, prompt)
|
|
|
|
if __name__ == "__main__":
|
|
app = InclusiveApp()
|
|
app.run(debug=True) |