81 lines
3.6 KiB
Python
81 lines
3.6 KiB
Python
"""
|
|
CLI entry point for Feature 1/4/15's retrieval pipeline - fetches
|
|
verified nutrition data (Open Food Facts) for every product in the
|
|
catalog, computes transparent scores/insights, and persists them.
|
|
|
|
Usage:
|
|
python scripts/enrich_nutrition.py
|
|
python scripts/enrich_nutrition.py --max-products 200 --no-narrative
|
|
python scripts/enrich_nutrition.py --force # re-fetch even already-verified products
|
|
|
|
# Catalogue-wide, past ACTIVE_BRANDS. Without this the run cannot reach
|
|
# Britannia, Parle or ITC at all, because enrich_all_products reads through
|
|
# vector_store.list_available_brands(), which honours that filter.
|
|
python scripts/enrich_nutrition.py --include-inactive
|
|
python scripts/enrich_nutrition.py --brands "Britannia,Parle"
|
|
python scripts/enrich_nutrition.py --categories "Fruits & Vegetables,Eggs"
|
|
|
|
Non-consumables (soap, shampoo, mosquito repellent, flowers) are skipped and
|
|
reported separately - see app/services/consumability.py.
|
|
|
|
Equivalent to POST /api/admin/nutrition-intelligence/enrich.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import logging
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
|
|
|
from app.services.nutrition_db import ensure_nutrition_schema # noqa: E402
|
|
from app.services.nutrition_enrichment_service import enrich_all_products # noqa: E402
|
|
|
|
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def _progress(done: int, total: int) -> None:
|
|
if total and (done % 25 == 0 or done == total):
|
|
logger.info(f"Enrichment progress: {done}/{total}")
|
|
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(description="Enrich the catalog with verified nutrition data")
|
|
parser.add_argument("--force", action="store_true", help="Re-fetch even products already marked 'verified'")
|
|
parser.add_argument("--no-narrative", action="store_true", help="Skip the LLM narrative step (facts/scores/tags only)")
|
|
parser.add_argument("--max-products", type=int, default=None, help="Cap the number of products processed (for a quick test run)")
|
|
parser.add_argument("--brands", default=None,
|
|
help="Comma-separated brand display names to enrich (default: whatever ACTIVE_BRANDS allows)")
|
|
parser.add_argument("--include-inactive", action="store_true",
|
|
help="Enrich every brand table, ignoring ACTIVE_BRANDS. Needed to reach "
|
|
"brands the app does not currently display.")
|
|
parser.add_argument("--categories", default=None,
|
|
help="Comma-separated categories to restrict the run to, e.g. 'Fruits & Vegetables,Eggs'")
|
|
args = parser.parse_args()
|
|
|
|
ensure_nutrition_schema()
|
|
result = enrich_all_products(
|
|
skip_if_verified=not args.force,
|
|
generate_narrative=not args.no_narrative,
|
|
progress_cb=_progress,
|
|
max_products=args.max_products,
|
|
brands=[b for b in (args.brands or "").split(",") if b.strip()] or None,
|
|
include_inactive=args.include_inactive,
|
|
categories=[c for c in (args.categories or "").split(",") if c.strip()] or None,
|
|
)
|
|
|
|
logger.info(
|
|
f"Done in {result.duration_seconds}s - "
|
|
f"{result.verified} verified, {result.partial} partial, {result.unavailable} unavailable "
|
|
f"of {result.total_products} total products "
|
|
f"({result.skipped_non_consumable} non-consumable skipped)"
|
|
)
|
|
if result.errors:
|
|
logger.warning(f"{len(result.errors)} errors (showing up to 10): {result.errors[:10]}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|