Update app.py

app.py

@@ -26,25 +26,28 @@ class SomaliQA:
             return parts[0].replace("Su'aal:", "").strip(), parts[1].strip()
         return None, None
 
+    def clean_text(self, text):
+        return text.strip().lower().rstrip("?").replace("’", "'").replace("  ", " ")
+
     def answer(self, user_question):
         if not user_question.strip().endswith("?"):
             user_question += "?"
 
-        cleaned_question = user_question.strip().rstrip("?")
+        user_clean = self.clean_text(user_question)
 
         # Step 1: Exact match
         for text in self.texts:
             su_aal, jawaab = self.extract_qa(text)
-            if su_aal and cleaned_question.lower() == su_aal.lower():
-                return jawaab  # ✅ Return exact answer from dataset
+            if su_aal and user_clean == self.clean_text(su_aal):
+                return jawaab  # ✅ Return exact dataset answer
 
         # Step 2: Semantic match
-        user_emb = self.embedder.encode(cleaned_question, convert_to_tensor=True)
+        user_emb = self.embedder.encode(user_clean, convert_to_tensor=True)
         hits = util.semantic_search(user_emb, self.embeddings, top_k=1)
         if hits and len(hits[0]) > 0:
             idx = hits[0][0]['corpus_id']
             su_aal, jawaab = self.extract_qa(self.texts[idx])
-            return jawaab  # ✅ Return answer from dataset (not generated)
+            return jawaab  # ✅ Return semantically matched answer
 
         return "Ma helin jawaab ku habboon su’aashaada."
 
@@ -60,7 +63,7 @@ gr.Interface(
     fn=qa_interface,
     inputs="text",
     outputs="text",
-    title="Somali QA Chatbot (Dataset-based)",
-    description="Weydii su’aal la xiriirta beeralayda — jawaabta waxa laga soo saaraa dataset-kaaga (GPT2 fine-tuned).",
+    title="Somali GPT-2 QA System (Dataset-based)",
+    description="Weydii su’aal ku saabsan beeraha — waxaad helaysaa jawaab sax ah oo laga soo qaaday dataset-kaaga.",
     theme="compact"
 ).launch()