Update app.py

app.py

@@ -40,36 +40,36 @@ class PDFAnalyzer:
         return [text[i:i+500] for i in range(0, len(text), 500)]
 
     def query(self, question):
-    if not self.active_doc:
+        if not self.active_doc:
+            return json.dumps({
+                "status": 400,
+                "message": "No document uploaded",
+                "results": []
+            })
+        
+        ques_emb = self.model.encode(question)
+        similarities = cosine_similarity([ques_emb], self.embeddings)[0]
+        best_idx = np.argmax(similarities)
+        
+        # Convert NumPy types to native Python types
+        confidence = float(similarities[best_idx].item())  # Convert to native float
+        best_idx = int(best_idx.item())  # Convert to native int
+        
+        full_answer = self.text_chunks[best_idx]
+        
         return json.dumps({
-            "status": 400,
-            "message": "No document uploaded",
-            "results": []
-        })
-    
-    ques_emb = self.model.encode(question)
-    similarities = cosine_similarity([ques_emb], self.embeddings)[0]
-    best_idx = np.argmax(similarities)
-    
-    # Convert NumPy types to native Python types
-    confidence = float(similarities[best_idx].item())  # Convert to native float
-    best_idx = int(best_idx.item())  # Convert to native int
-    
-    full_answer = self.text_chunks[best_idx]
-    
-    return json.dumps({
-        "status": 200,
-        "message": "Success",
-        "results": [{
-            "text": self._format_answer(full_answer, question),
-            "confidence": confidence,
-            "document_id": str(hash(self.active_doc)),  # Convert to string
-            "metadata": {
-                "chunk_index": best_idx,
-                "document": self.active_doc
-            }
-        }]
-    }, default=lambda x: str(x))  # Fallback string conversion
+            "status": 200,
+            "message": "Success",
+            "results": [{
+                "text": self._format_answer(full_answer, question),
+                "confidence": confidence,
+                "document_id": str(hash(self.active_doc)),  # Convert to string
+                "metadata": {
+                    "chunk_index": best_idx,
+                    "document": self.active_doc
+                }
+            }]
+        }, default=lambda x: str(x))  # Fallback string conversion
     
     def _format_answer(self, text, question):
         # Extract focused answer with 100-word context