Goal
Upgrade claim classification from regex rules to LLM reasoning in the Celery worker.
What to build
- Integrate Groq free tier (llama3-8b-8192) or Ollama into backend/worker/celery_app.py
- Deep claim classification: efficacy, comparative, superlative, ingredient sourcing
- Study citation extraction for claims like 'clinically proven' or '50% faster absorption'
- Upgrade integrity_score to reflect LLM-verified results
Key file
backend/worker/celery_app.py -> verify_claims_task()
Celery skeleton and ClaimVerification table already in place.
Goal
Upgrade claim classification from regex rules to LLM reasoning in the Celery worker.
What to build
Key file
backend/worker/celery_app.py -> verify_claims_task()
Celery skeleton and ClaimVerification table already in place.