diff --git a/backend/alembic/versions/0010_auto_llm_source.py b/backend/alembic/versions/0010_auto_llm_source.py new file mode 100644 index 0000000..9f58e51 --- /dev/null +++ b/backend/alembic/versions/0010_auto_llm_source.py @@ -0,0 +1,25 @@ +"""Add auto_llm to ingredient_match_source_enum + +Revision ID: 0010 +Revises: 0009 +Create Date: 2026-05-11 +""" +from alembic import op + +revision = "0010" +down_revision = "0009" +branch_labels = None +depends_on = None + + +def upgrade() -> None: + # PostgreSQL 9.1+ allows adding values to existing enums. + # IF NOT EXISTS guard makes the migration idempotent. + op.execute("ALTER TYPE ingredient_match_source_enum ADD VALUE IF NOT EXISTS 'auto_llm'") + + +def downgrade() -> None: + # PostgreSQL does not support removing enum values without dropping and + # recreating the type; rows using 'auto_llm' would block the drop. + # Downgrade is intentionally a no-op. + pass diff --git a/backend/app/config.py b/backend/app/config.py index 0fe3fbd..66ff3a7 100644 --- a/backend/app/config.py +++ b/backend/app/config.py @@ -29,6 +29,11 @@ class Settings(BaseSettings): ADMIN_EMAIL: str = "" APP_BASE_URL: str = "http://localhost" + # Ollama Cloud LLM (used for ingredient→grocery LLM matching second pass) + OLLAMA_BASE_URL: str = "https://ollama.com/v1" + OLLAMA_API_KEY: Optional[str] = None + OLLAMA_MODEL: str = "kimi-k2.6:cloud" + FAMILY_EMAIL_1: Optional[str] = None FAMILY_EMAIL_2: Optional[str] = None RECIPES_EMAIL: Optional[str] = None diff --git a/backend/app/models/__init__.py b/backend/app/models/__init__.py index 21ab01c..683edf5 100644 --- a/backend/app/models/__init__.py +++ b/backend/app/models/__init__.py @@ -81,6 +81,7 @@ class EmailStatus(enum.Enum): class IngredientMatchSource(enum.Enum): AUTO = "auto" + AUTO_LLM = "auto_llm" MANUAL = "manual" diff --git a/backend/app/services/llm_matcher.py b/backend/app/services/llm_matcher.py new file mode 100644 index 0000000..7311f82 --- /dev/null +++ b/backend/app/services/llm_matcher.py @@ -0,0 +1,214 @@ +"""LLM-powered second-pass ingredient→grocery matcher. + +After the deterministic AUTO matcher runs, some ingredients remain unmatched +(catalog gaps, unusual product names). This module sends those ingredients to +an Ollama-compatible LLM with a small candidate list from the DB and stores the +best pick as source='auto_llm'. + +Manual matches (source='manual') are never touched. +""" +from __future__ import annotations + +import logging +import re +import time +import uuid as _uuid_mod +from decimal import Decimal + +import requests +from rapidfuzz import fuzz, process +from sqlalchemy.dialects.postgresql import insert as _pg_insert +from sqlalchemy.orm import Session + +from app.config import settings +from app.models import ( + GroceryItem, + Ingredient, + IngredientGroceryMatch, + IngredientMatchSource, +) +from app.services.matcher import _sig_words + +logger = logging.getLogger(__name__) + +_CANDIDATE_LIMIT = 12 # top candidates sent to the LLM +_RATE_LIMIT_SECS = 0.3 # pause between LLM calls + + +def _get_candidates( + ingredient_name: str, + grocery_rows: list[GroceryItem], +) -> list[tuple[str, object]]: + """Return up to ``_CANDIDATE_LIMIT`` grocery items ranked by fuzzy×precision. + + Uses the same combined scoring as the AUTO matcher: + combined = (partial_token_sort_ratio / 100) × (overlap_words / grocery_words) + + This ensures a specific match like "McCormick Black Pepper" outranks a + generic one like "Dr Pepper" that happens to score well on the raw fuzzy ratio. + """ + ing_sig = _sig_words(ingredient_name) + if not ing_sig: + return [] + + # Pre-filter: must share ≥1 sig word with the ingredient. + filtered: list[GroceryItem] = [ + gi for gi in grocery_rows + if ing_sig & _sig_words(gi.name) + ] + if not filtered: + return [] + + filtered_lower = [gi.name.lower() for gi in filtered] + # Run fuzzy over ALL filtered items (no limit) to get raw scores. + results = process.extract( + ingredient_name.lower(), + filtered_lower, + scorer=fuzz.partial_token_sort_ratio, + limit=len(filtered), + ) + + scored: list[tuple[float, str, object]] = [] + for _text, fuzzy_score, idx in results: + gi = filtered[idx] + gsig = _sig_words(gi.name) + if not gsig: + continue + # Precision = fraction of grocery sig-words that are relevant to the ingredient. + precision = len(ing_sig & gsig) / len(gsig) + combined = (fuzzy_score / 100.0) * precision + scored.append((combined, gi.name, gi.id)) + + scored.sort(reverse=True) + return [(name, gid) for _, name, gid in scored[:_CANDIDATE_LIMIT]] + + +def _get_unmatched_ingredients(db: Session) -> list[Ingredient]: + """Ingredients with no existing match in ingredient_grocery_match.""" + from sqlalchemy import select + matched_ids_stmt = select(IngredientGroceryMatch.ingredient_id) + return ( + db.query(Ingredient) + .filter(Ingredient.id.notin_(matched_ids_stmt)) + .all() + ) + + +def _ask_ollama(ingredient_name: str, candidates: list[str]) -> int | None: + """Ask the LLM to pick the best grocery item for the ingredient. + + Returns the 0-based index into `candidates`, or None if no good match. + """ + if not settings.OLLAMA_API_KEY: + logger.warning("OLLAMA_API_KEY not configured — skipping LLM pass") + return None + + numbered = "\n".join(f"{i + 1}. {name}" for i, name in enumerate(candidates)) + prompt = ( + f"I need '{ingredient_name}' for a home-cooked recipe at a supermarket.\n" + f"Which of these products is the closest match?\n" + f"{numbered}\n\n" + f"Reply with just the number (1–{len(candidates)}) or 'none' if none fit." + ) + + try: + resp = requests.post( + f"{settings.OLLAMA_BASE_URL}/chat/completions", + headers={ + "Content-Type": "application/json", + "Authorization": f"Bearer {settings.OLLAMA_API_KEY}", + }, + json={ + "model": settings.OLLAMA_MODEL, + "messages": [{"role": "user", "content": prompt}], + "max_tokens": 500, # kimi-k2 reasons before answering; needs headroom + "temperature": 0, + }, + timeout=30, + ) + resp.raise_for_status() + except requests.RequestException as exc: + logger.warning("Ollama API error for %r: %s", ingredient_name, exc) + return None + + content = resp.json().get("choices", [{}])[0].get("message", {}).get("content", "") + # Strip … reasoning blocks that some models emit + content = re.sub(r".*?", "", content, flags=re.DOTALL).strip() + + if "none" in content.lower(): + return None + m = re.search(r"\b(\d+)\b", content) + if not m: + return None + idx = int(m.group(1)) - 1 + return idx if 0 <= idx < len(candidates) else None + + +def run_llm_match_job( + db: Session, + *, + source_filter: str = "lucky_california", +) -> int: + """LLM second pass: match remaining unmatched ingredients. + + For each ingredient with no existing match, collects up to + ``_CANDIDATE_LIMIT`` fuzzy candidates from the grocery catalog and asks + the configured LLM to select the best one. + + Returns number of new LLM matches stored. + """ + grocery_rows = ( + db.query(GroceryItem) + .filter(GroceryItem.source == source_filter) + .all() + ) + if not grocery_rows: + return 0 + + unmatched = _get_unmatched_ingredients(db) + if not unmatched: + logger.info("LLM matcher: no unmatched ingredients — nothing to do") + return 0 + + logger.info("LLM matcher: %d unmatched ingredients to process", len(unmatched)) + written = 0 + + for ingredient in unmatched: + if not ingredient.name or not ingredient.name.strip(): + continue + + candidates = _get_candidates(ingredient.name, grocery_rows) + if not candidates: + logger.debug("LLM matcher: no candidates for %r — skip", ingredient.name) + continue + + candidate_names = [name for name, _ in candidates] + logger.info("LLM matcher: %r → %d candidates", ingredient.name, len(candidates)) + + chosen_idx = _ask_ollama(ingredient.name, candidate_names) + time.sleep(_RATE_LIMIT_SECS) + + if chosen_idx is None: + logger.info(" LLM: no match") + continue + + chosen_name, chosen_grocery_id = candidates[chosen_idx] + logger.info(" LLM: chose %r", chosen_name) + + stmt = ( + _pg_insert(IngredientGroceryMatch.__table__) + .values( + id=_uuid_mod.uuid4(), + ingredient_id=ingredient.id, + grocery_item_id=chosen_grocery_id, + confidence=Decimal("0.750"), + source=IngredientMatchSource.AUTO_LLM, + ) + .on_conflict_do_nothing(index_elements=["ingredient_id", "grocery_item_id"]) + ) + db.execute(stmt) + written += 1 + + db.commit() + logger.info("LLM matcher: %d new matches written", written) + return written diff --git a/backend/app/services/matcher.py b/backend/app/services/matcher.py index 2c4f893..2e9f680 100644 --- a/backend/app/services/matcher.py +++ b/backend/app/services/matcher.py @@ -39,16 +39,29 @@ _STOP_WORDS = frozenset({ "and", "with", "for", "the", }) +def _singularize(word: str) -> str: + """Best-effort English singularization for grocery product names. + + Handles 'tortillas'→'tortilla', 'thighs'→'thigh', 'chickpeas'→'chickpea'. + Requires length > 3 to avoid mangling short words like 'has', 'was'. + """ + if len(word) > 4 and word.endswith("ies"): + return word[:-3] + "y" # 'berries' → 'berry' + if len(word) > 3 and word.endswith("s") and not word.endswith("ss"): + return word[:-1] # 'tortillas' → 'tortilla' + return word + + # If any of these words appear in a grocery item's sig-words but NOT in the # ingredient's sig-words, the match is rejected outright. Prevents category # cross-contamination: "Garlic" must not match "Garlic Bread", "Lime" must not # match "Lime Margarita", etc. -_EXCLUSION_WORDS = frozenset({ +_EXCLUSION_WORDS_RAW = frozenset({ # Baked goods / bread products - "bread", "loaf", "rolls", "bun", "buns", "croissant", + "bread", "loaf", "roll", "rolls", "bun", "buns", "croissant", "cracker", "crackers", "cookie", "cookies", "cake", "cupcake", "muffin", "bagel", # Chips / snack foods - "chips", + "chip", "chips", # Pasta / noodles "pasta", "noodle", "noodles", "vermicelli", "spaghetti", "linguine", "fettuccine", "penne", "rigatoni", "macaroni", "rotini", "orzo", @@ -64,8 +77,10 @@ _EXCLUSION_WORDS = frozenset({ # Prepared poultry (prevents "Garlic Herb Rotisserie Chicken" matching "Garlic") "rotisserie", # Baby / personal care (belt-and-suspenders after stop-word rework) - "baby", "wipes", "diaper", + "baby", "wipe", "wipes", "diaper", }) +# Pre-normalize exclusion words so they match the singularized sig-word sets. +_EXCLUSION_WORDS = frozenset(_singularize(w) for w in _EXCLUSION_WORDS_RAW) @dataclass @@ -76,9 +91,13 @@ class MatchResult: def _sig_words(text: str) -> frozenset: - """Lowercase alpha tokens >2 chars, stop-words removed.""" + """Lowercase alpha tokens >2 chars, stop-words removed, plurals normalized.""" tokens = re.sub(r"[^a-z ]", " ", text.lower()).split() - return frozenset(t for t in tokens if len(t) > 2 and t not in _STOP_WORDS) + return frozenset( + _singularize(t) + for t in tokens + if len(t) > 2 and t not in _STOP_WORDS + ) def run_match_job( @@ -185,10 +204,10 @@ def run_match_job( continue # Precision penalises grocery items with many extra words. precision = len(ing_sig) / len(gsig) - # Hard floor: grocery must not have >2× the sig-words of the ingredient. - # Catches long branded products that sneak past exclusion words, e.g. - # "Garlic Herb Rotisserie Chicken" for "Garlic". - if precision < 0.45: + # Hard floor: grocery must not dwarf the ingredient in sig-word count. + # 0.30 allows "Bacon" (1 sig-word) → "Wright Brand Bacon" (3 sig-words) + # while exclusion words still block "Garlic Herb Rotisserie Chicken". + if precision < 0.30: continue combined = (score / 100.0) * precision if combined > best_combined: diff --git a/backend/app/services/scraper_service.py b/backend/app/services/scraper_service.py index 7656c01..a8021fb 100644 --- a/backend/app/services/scraper_service.py +++ b/backend/app/services/scraper_service.py @@ -89,6 +89,8 @@ def _run_scrape_in_background( try: from app.services.matcher import run_match_job run_match_job(db, source_filter="lucky_california") + from app.services.llm_matcher import run_llm_match_job + run_llm_match_job(db, source_filter="lucky_california") except Exception as e: # matcher failure must not flip scrape to FAILED import logging logging.exception("matcher failed after successful scrape: %s", e) diff --git a/docker-compose.yml b/docker-compose.yml index 6f11b4e..5733ff8 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -11,6 +11,9 @@ services: - DATABASE_URL=postgresql://mealplanner:${POSTGRES_PASSWORD}@db:5432/mealplanner - SENDGRID_API_KEY=${SENDGRID_API_KEY} - SPOONACULAR_API_KEY=${SPOONACULAR_API_KEY} + - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-https://ollama.com/v1} + - OLLAMA_API_KEY=${OLLAMA_API_KEY} + - OLLAMA_MODEL=${OLLAMA_MODEL:-kimi-k2.6:cloud} - LUCKY_CA_URL=${LUCKY_CA_URL:-https://luckysupermarkets.com} - LUCKY_STORE_ID=${LUCKY_STORE_ID:-757} - SWIFTLY_API_BASE=${SWIFTLY_API_BASE:-https://prod.swiftlyapi.net} @@ -42,6 +45,9 @@ services: - DATABASE_URL=postgresql://mealplanner:${POSTGRES_PASSWORD}@db:5432/mealplanner - SENDGRID_API_KEY=${SENDGRID_API_KEY} - SPOONACULAR_API_KEY=${SPOONACULAR_API_KEY} + - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-https://ollama.com/v1} + - OLLAMA_API_KEY=${OLLAMA_API_KEY} + - OLLAMA_MODEL=${OLLAMA_MODEL:-kimi-k2.6:cloud} - LUCKY_CA_URL=${LUCKY_CA_URL:-https://luckysupermarkets.com} - LUCKY_STORE_ID=${LUCKY_STORE_ID:-757} - SWIFTLY_API_BASE=${SWIFTLY_API_BASE:-https://prod.swiftlyapi.net}