Update app.py

app.py

@@ -331,9 +331,15 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 def answer_medical_query(query):
     try:
         inputs = tokenizer(query, return_tensors="pt")
-        outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.7, top_k=50)
+        outputs = model.generate(
+            inputs.input_ids,
+            max_length=50,
+            temperature=0.7,
+            num_return_sequences=1,
+            pad_token_id=tokenizer.eos_token_id  # Avoid errors if padding is required
+        )
         response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return response
+    return response
     except Exception as e:
         return f"An error occurred while generating a response: {e}"