Update app.py

app.py

@@ -33,8 +33,6 @@ BASE_SPIRITS = {
     "vermouth": [r"\bvermouth\b"],
     "other":    [r"\btriple sec\b", r"\bliqueur\b", r"\bcointreau\b", r"\baperol\b", r"\bcampari\b"],
 }
-BASE_OPTIONS = list(BASE_SPIRITS.keys())
-
 FLAVORS = {
     "citrus":      [r"lime", r"lemon", r"grapefruit", r"orange", r"\bcitrus\b"],
     "sweet":       [r"simple syrup", r"\bsugar\b", r"\bhoney\b", r"\bagave\b", r"\bmaple\b", r"\bgrenadine\b", r"\bvanilla\b", r"\bsweet\b"],
@@ -84,7 +82,6 @@ def _split_ingredient_blob(s):
     return out
 
 def _from_list_of_pairs(val):
-    # [(measure, name)] or [(name, measure)] → display + tokens
     out_disp, out_tokens = [], []
     for x in val:
         if not isinstance(x, (list, tuple)) or len(x) == 0:
@@ -112,7 +109,6 @@ def _from_list_of_pairs(val):
     return out_disp, out_tokens
 
 def _from_list_of_dicts(val):
-    # [{"name":"gin","measure":"45 ml"}] → ["45 ml gin"], tokens ["gin"]
     out_disp, out_tokens = [], []
     for x in val:
         if not isinstance(x, dict): continue
@@ -135,7 +131,6 @@ def _from_list_of_dicts(val):
     return out_disp, out_tokens
 
 def _ingredients_from_any(val):
-    # String blob
     if isinstance(val, str):
         lines = _split_ingredient_blob(val)
         tokens = []
@@ -147,15 +142,12 @@ def _ingredients_from_any(val):
                     idx = i; break
             tokens.append(" ".join(parts[idx:]).lower())
         return lines, tokens
-    # List of strings
     if isinstance(val, list) and all(isinstance(x, str) for x in val):
         disp = [x.strip() for x in val if x and x.strip()]
         tokens = [x.lower().strip() for x in disp]
         return disp, tokens
-    # List of pairs
     if isinstance(val, list) and any(isinstance(x, (list, tuple)) for x in val):
         return _from_list_of_pairs(val)
-    # List of dicts
     if isinstance(val, list) and any(isinstance(x, dict) for x in val):
         return _from_list_of_dicts(val)
     return [], []
@@ -167,7 +159,6 @@ def _get_title(row, cols):
     return "Untitled"
 
 def _get_ingredients_with_measures(row, cols):
-    # Prefer explicit tokenized + measure fields if present
     if "ingredient_tokens" in cols and row.get("ingredient_tokens"):
         toks = [str(x).strip().lower() for x in row["ingredient_tokens"] if str(x).strip()]
         for mkey in ["measure_tokens","measures","measure_list"]:
@@ -178,8 +169,7 @@ def _get_ingredients_with_measures(row, cols):
                     n = str(n).strip()
                     disp.append(_join_measure_name(m, n) if m else n)
                 return disp, toks
-        return toks, toks  # no measures available
-    # Combined "ingredients" field or variants
+        return toks, toks
     for key in ["ingredients","ingredients_raw","raw_ingredients","Raw_Ingredients","Raw Ingredients",
                 "ingredient_list","ingredients_list"]:
         if key in cols and row.get(key) not in (None, "", [], {}):
@@ -214,12 +204,11 @@ for r in ds:
     ing_disp = [x for x in ing_disp if x]
     ing_tokens = [x for x in ing_tokens if x]
 
-    # Embedding text: title + ingredient TOKENS (names only)
     fused = f"{title}\nIngredients: {', '.join(ing_tokens)}"
     DOCS.append({
         "title": title,
-        "ingredients_display": ing_disp,   # human list with measures if available
-        "ingredients_tokens": ing_tokens,  # names only (better for search)
+        "ingredients_display": ing_disp,
+        "ingredients_tokens": ing_tokens,
         "text": fused,
         "base": tag_base(fused),
         "flavors": tag_flavors(fused),
@@ -236,31 +225,55 @@ doc_embs = encoder.encode(
 ).astype("float32")
 
 # ========================
-# Recommendation
+# Pretty ingredient formatting
 # ========================
+_MEASURE_RE = re.compile(
+    r"^\s*(?P<meas>(?:\d+(\.\d+)?|\d+\s*/\s*\d+|\d+\s*\d*/\d+)\s*(?:ml|oz|tsp|tbsp)?|\d+\s*(?:ml|oz|tsp|tbsp)|(?:dash|dashes|drop|drops|barspoon)s?)\b[\s\-–:]*",
+    flags=re.I
+)
+
+def _split_measure_name_line(line: str):
+    if not isinstance(line, str): return None, line
+    m = _MEASURE_RE.match(line.strip())
+    if m:
+        meas = _norm_measure(m.group("meas"))
+        name = line[m.end():].strip()
+        return meas, name or ""
+    return "", line.strip()
+
 def _format_ingredients_markdown(lines):
     if not lines:
         return "—"
-    return "\n".join([f"- {line}" for line in lines])
+    formatted = []
+    for ln in lines:
+        meas, name = _split_measure_name_line(ln)
+        if meas and name:
+            formatted.append(f"- **{meas}** — {name}")
+        elif name:
+            formatted.append(f"- {name}")
+        else:
+            formatted.append(f"- {ln}")
+    return "\n".join(formatted)
 
-def recommend(base_alcohol, flavor, top_k=3):
-    if base_alcohol not in BASE_OPTIONS:
-        return "Please choose a base alcohol."
+# ========================
+# Recommendation
+# ========================
+def recommend(base_alcohol_text, flavor, top_k=3):
+    # Map user-typed base to our internal base tags; fallback to 'other'
+    inferred_base = tag_base(base_alcohol_text or "")
     if flavor not in FLAVOR_OPTIONS:
         return "Please choose a flavor."
 
-    # hard filter by base (fallback to all)
-    idxs = [i for i, d in enumerate(DOCS) if d["base"] == base_alcohol]
-    if not idxs:
+    # hard filter by inferred base (fallback to all if 'other' or no matches)
+    idxs = [i for i, d in enumerate(DOCS) if d["base"] == inferred_base]
+    if inferred_base == "other" or not idxs:
         idxs = list(range(len(DOCS)))
 
-    # query steered by constraints
-    q_text = f"Base spirit: {base_alcohol}. Flavor: {flavor}. Cocktail recipe."
+    q_text = f"Base spirit: {base_alcohol_text}. Flavor: {flavor}. Cocktail recipe."
     q_emb = encoder.encode([q_text], normalize_embeddings=True, convert_to_numpy=True).astype("float32")[0]
 
     sims = doc_embs[idxs].dot(q_emb)  # cosine since normalized
 
-    # flavor boost
     scored = []
     for pos, i in enumerate(idxs):
         base_score = float(sims[pos])
@@ -290,25 +303,25 @@ def recommend(base_alcohol, flavor, top_k=3):
 # UI
 # ========================
 with gr.Blocks() as demo:
-    gr.Markdown("# 🍹 AI Bartender — Base + Flavor (Ingredients with Measures)")
+    gr.Markdown("# 🍹 AI Bartender — Type a Base + Flavor (Clear Ingredients)")
 
     with gr.Row():
-        base = gr.Dropdown(choices=BASE_OPTIONS, value="gin", label="Base alcohol")
+        base_text = gr.Textbox(value="gin", label="Base alcohol (type any spirit, e.g., 'gin', 'white rum', 'bourbon')")
         flavor = gr.Dropdown(choices=FLAVOR_OPTIONS, value="citrus", label="Flavor")
         topk = gr.Slider(1, 10, value=3, step=1, label="Number of recommendations")
 
     with gr.Row():
-        ex1 = gr.Button("Gin + Citrus")
-        ex2 = gr.Button("Rum + Fruity")
-        ex3 = gr.Button("Mezcal + Smoky")
+        ex1 = gr.Button("Example: Gin + Citrus")
+        ex2 = gr.Button("Example: Rum + Fruity")
+        ex3 = gr.Button("Example: Mezcal + Smoky")
 
     out = gr.Markdown()
-    gr.Button("Recommend").click(recommend, [base, flavor, topk], out)
+    gr.Button("Recommend").click(recommend, [base_text, flavor, topk], out)
 
     # Quick-fill examples
-    ex1.click(lambda: ("gin", "citrus", 3), outputs=[base, flavor, topk])
-    ex2.click(lambda: ("rum", "fruity", 3), outputs=[base, flavor, topk])
-    ex3.click(lambda: ("mezcal", "smoky", 3), outputs=[base, flavor, topk])
+    ex1.click(lambda: ("gin", "citrus", 3), outputs=[base_text, flavor, topk])
+    ex2.click(lambda: ("white rum", "fruity", 3), outputs=[base_text, flavor, topk])
+    ex3.click(lambda: ("mezcal", "smoky", 3), outputs=[base_text, flavor, topk])
 
 if __name__ == "__main__":
     demo.launch()