Update main.py

main.py

@@ -23,7 +23,7 @@ tokenizer = AutoTokenizer.from_pretrained("Open-Orca/OpenOrca-Platypus2-13B", tr
 def ask_bot(question):
   input_ids = tokenizer.encode(question, return_tensors="pt").to(device)
   with torch.no_grad():
-      output = model.generate(input_ids, max_length=100, num_return_sequences=1, do_sample=True, top_k=50)
+      output = model.generate(input_ids, max_length=200, num_return_sequences=1, do_sample=True, top_k=50)
   generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
   response = generated_text.split("->:")[-1]
   return response
@@ -155,7 +155,8 @@ def chatbot(patient_id, user_data: dict=None):
       else:
         human_input = prompt + user_input + " ->:"
       human_text =  user_input.replace("'", "")
-      response = llm._call(human_input)
+      # response = llm._call(human_input)
+      response = ask_bot(human_input)
       # response = response.replace("'", "")
       # memory.save_context({"input": user_input}, {"output": response})
       # summary = memory.load_memory_variables({})