Skip to content

Phase 7: LLM claim intelligence (Groq / Ollama) #1

@Medinz01

Description

@Medinz01

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.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions