Deploy app with recommendation + slogan generator

app.py

@@ -33,9 +33,79 @@ def recommend(query, top_k=3):
     results["score"] = scores[0]
     return results[["name", "tagline", "description", "score"]]
 
-def generate_slogan(description):
-    # Very simple slogan generator – can be replaced with FLAN-T5 later
-    return "Fresh Ideas for " + description.split()[0]
+def generate_slogan(query_text, neighbors_df=None, n_samples=16):
+    ctx = _neighbor_context(neighbors_df)
+    prompt = (
+        "You are a creative brand copywriter. Write short, original, memorable startup slogans (max 8 words).
+"
+        "Forbidden words: app, assistant, platform, solution, system, marketplace, AI, machine learning, augmented reality, virtual reality, decentralized, empower.
+"
+        "Focus on clear benefits and vivid verbs. Do not copy the description. Return ONLY a list, one slogan per line.
+
+"
+        "Good Examples:
+"
+        "Description: AI assistant for doctors to prioritize patient cases
+"
+        "Slogan: Less Guessing. More Healing.
+
+"
+        "Description: Payments for small online stores
+"
+        "Slogan: Built to Grow with Your Cart.
+
+"
+        "Description: Neurotech headset to boost focus
+"
+        "Slogan: Train Your Brain to Win.
+
+"
+    )
+    if ctx:
+        prompt += f"Similar taglines (style only):
+{ctx}
+
+"
+    prompt += f"Description: {query_text}
+Slogans:"
+
+    input_ids = GEN_TOK(prompt, return_tensors="pt").input_ids.to(DEVICE)
+    outputs = GEN_MODEL.generate(
+        input_ids,
+        max_new_tokens=24,
+        do_sample=True,
+        top_k=60,
+        top_p=0.92,
+        temperature=1.2,
+        num_return_sequences=n_samples,
+        repetition_penalty=1.08
+    )
+
+    raw_cands = [GEN_TOK.decode(o, skip_special_tokens=True) for o in outputs]
+
+    cand_set = set()
+    for txt in raw_cands:
+        for line in txt.split("
+"):
+            s = _clean_slogan(line)
+            if not s:
+                continue
+            if len(s.split()) < 2 or len(s.split()) > 8:
+                continue
+            if _is_blocked_slogan(s):
+                continue
+            cand_set.add(_titlecase_soft(s))
+
+    if not cand_set:
+        return _clean_slogan(GEN_TOK.decode(outputs[0], skip_special_tokens=True))
+
+    scored = _score_candidates(query_text, sorted(cand_set), neighbors_df)
+    if not scored:
+        return _clean_slogan(GEN_TOK.decode(outputs[0], skip_special_tokens=True))
+
+    scored.sort(key=lambda x: x[1], reverse=True)
+    return scored[0][0]
+
 
 def pipeline(user_input):
     recs = recommend(user_input, top_k=3)