Update app.py

app.py

@@ -37,29 +37,11 @@ def askme(symptoms, question):
     end_idx = response_text.find("<|im_end|>", start_idx)
     assistant_response = response_text[start_idx + len("<|im_start|>assistant"):end_idx]
     # Return only one answer
-    answers = assistant_response.split(". ")
-    return answers[0] + "."
+    #answers = assistant_response.split(". ")
+    #return answers[0] + "."
+    assistant_response
 
 
-
-def askmeold(symptoms, question):
-    sys_message = '''\
-    You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
-    provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
-    '''
-    content = "symptoms:"+ symptoms + "question:" + question
-    messages = [{"role": "system", "content": sys_message}, {"role": "user", "content": content}]
-    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    inputs = tokenizer(prompt, return_tensors="pt").to(device)  # Ensure inputs are on CUDA device
-    outputs = model.generate(**inputs, max_new_tokens=200, use_cache=True)
-    response_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0].strip() 
-    # Remove system messages and content    
-    # Extract and return the generated text, removing the prompt
-    # Extract only the assistant's response
-    #answer = response_text.split('<|im_start|>assistant')[-1].strip()
-    #answer =response_text.split("assistant")[1].strip().split("user")[0].strip()   
-    return response_text
-
 # Example usage
 symptoms = '''\
 I'm a 35-year-old male and for the past few months, I've been experiencing fatigue,