b6b9d7337a
Implements new workflow to extract CreativeX quality scores from PDFs using LlamaExtract AI and store results in PostgreSQL database. Components added: - creativex_scoring_storing.py: Main script to process PDFs from Box - creativex_scores table: Database table with JSONB for full JSON storage - Database methods: store_creativex_score() and get_creativex_score_by_filename() - Email templates: creativex_complete, creativex_partial, creativex_no_files - Configuration: creativex section in config.yaml - CREATIVEX_DEPLOYMENT.md: Complete deployment and usage guide Features: - Monitors Box folder 350605024645 for PDFs - Extracts scores using LlamaExtract agent "Creativex-Extract" - Stores 4 key fields (filename, ID, URL, score) + full JSON - Deletes processed PDFs from Box after successful extraction - Sends email notifications for success/partial/no-files scenarios - Manual execution (python scripts/creativex_scoring_storing.py) Database schema: - Table: creativex_scores with 10 columns - Indexes on filename, box_file_id, status for fast lookups - JSONB column stores complete extraction for future flexibility Future integration ready: db.get_creativex_score_by_filename() available for DAM upload workflows to attach CreativeX metadata during asset processing. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
118 lines
3 KiB
YAML
118 lines
3 KiB
YAML
# Ferrero Content Scaling - Main Configuration
|
|
# All settings can be overridden by environment-specific configs
|
|
|
|
# Environment selector (set via ENV environment variable)
|
|
environment: ${ENV:-staging}
|
|
|
|
# DAM Configuration
|
|
dam:
|
|
base_url: ${DAM_BASE_URL}
|
|
# OAuth2 Authentication (default - current working method)
|
|
auth_url: ${DAM_AUTH_URL}
|
|
client_id: ${DAM_CLIENT_ID}
|
|
client_secret: ${DAM_CLIENT_SECRET}
|
|
# mTLS Certificate Authentication (optional - use with --auth-pfx flag)
|
|
mtls_base_url: ${DAM_MTLS_BASE_URL:-}
|
|
mtls_cert_path: ${DAM_MTLS_CERT_PATH:-}
|
|
mtls_cert_password: ${DAM_MTLS_CERT_PASSWORD:-}
|
|
timeout_seconds: 120
|
|
|
|
# Box Configuration
|
|
box:
|
|
enterprise_id: ${BOX_ENTERPRISE_ID}
|
|
client_id: ${BOX_CLIENT_ID}
|
|
client_secret: ${BOX_CLIENT_SECRET}
|
|
jwt_key_id: ${BOX_JWT_KEY_ID}
|
|
rsa_private_key_path: ../Box-config.json
|
|
passphrase: ${BOX_PASSPHRASE}
|
|
# Separate folders for different workflows
|
|
root_folder_a1_a2: ${BOX_ROOT_FOLDER_A1_A2} # For downloaded Local master assets (348304357505)
|
|
root_folder_a2_a3: ${BOX_ROOT_FOLDER_A2_A3} # For agency uploads to process (348526703108)
|
|
root_folder_b1_b2: ${BOX_ROOT_FOLDER_B1_B2} # For downloaded Global master assets (349261192115)
|
|
webhook_signature_keys:
|
|
- ${BOX_WEBHOOK_PRIMARY_KEY:-}
|
|
- ${BOX_WEBHOOK_SECONDARY_KEY:-}
|
|
|
|
# Database Configuration
|
|
database:
|
|
host: ${DB_HOST:-localhost}
|
|
port: ${DB_PORT:-5437}
|
|
database: ferrero_tracking
|
|
user: ${DB_USER}
|
|
password: ${DB_PASSWORD}
|
|
|
|
# Polling Configuration (A1→A2)
|
|
polling:
|
|
enabled: true
|
|
interval_seconds: 300 # 5 minutes
|
|
max_campaigns_per_run: 10
|
|
|
|
# Webhook Configuration (A2→A3 receiver)
|
|
webhook_receiver:
|
|
enabled: true
|
|
host: 0.0.0.0
|
|
port: ${WEBHOOK_RECEIVER_PORT:-5555}
|
|
validate_signatures: true
|
|
|
|
# Outgoing Webhooks (we call these)
|
|
webhooks:
|
|
campaign_status_update:
|
|
enabled: true
|
|
url: ${CAMPAIGN_STATUS_WEBHOOK_URL}
|
|
timeout_seconds: 10
|
|
retry_on_failure: true
|
|
max_retries: 3
|
|
auth:
|
|
type: none # bearer, basic, or none
|
|
token: ${WEBHOOK_AUTH_TOKEN:-}
|
|
|
|
# Retry Configuration
|
|
retry:
|
|
max_attempts: 3
|
|
backoff: exponential # exponential, linear, fixed
|
|
initial_delay_seconds: 5
|
|
max_delay_seconds: 60
|
|
|
|
# Notification Configuration
|
|
notifications:
|
|
enabled: true
|
|
smtp:
|
|
server: ${SMTP_SERVER}
|
|
port: ${SMTP_PORT}
|
|
user: ${SMTP_USER}
|
|
password: ${SMTP_PASSWORD}
|
|
sender_email: ${SENDER_EMAIL}
|
|
recipients:
|
|
success:
|
|
- ${REPORT_EMAILS}
|
|
errors:
|
|
- ${ERROR_EMAIL}
|
|
critical:
|
|
- ${ERROR_EMAIL}
|
|
templates_path: config/email_templates.yaml
|
|
|
|
# Field Configuration
|
|
fields:
|
|
mappings_file: config/field_mappings.yaml
|
|
|
|
# CreativeX Configuration
|
|
creativex:
|
|
llama_api_key: ${LLAMA_CLOUD_API_KEY}
|
|
agent_name: Creativex-Extract
|
|
box_folder_id: "350605024645"
|
|
|
|
# Logging Configuration
|
|
logging:
|
|
level: INFO
|
|
format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
|
|
file:
|
|
directory: logs
|
|
max_bytes: 10485760 # 10MB
|
|
backup_count: 5
|
|
console: true
|
|
|
|
# Temp File Configuration
|
|
temp:
|
|
directory: temp/downloads
|
|
cleanup_after_hours: 24
|
|
max_size_mb: 1000
|