Update app.py

app.py

@@ -23,15 +23,14 @@ You are a helpful bot. Your answers are clear and concise.
 
 """
 
-# Formatting function for message and history
-def format_message(message: str) -> str:
+def format_message(message: str, history: list, memory_limit: int = 3) -> str:
     
     formatted_message = f"<s>[INST] {message} [/INST]"
 
     return formatted_message
 
 # Generate a response from the Llama model
-def get_llama_response(message: str) -> str:
+def get_llama_response(message: str, history: list) -> str:
     """
     Generates a conversational response from the Llama model.
     Parameters:
@@ -40,7 +39,7 @@ def get_llama_response(message: str) -> str:
     Returns:
         str: Generated response from the Llama model.
     """
-    query = format_message(message)
+    query = format_message(message, history)
     response = ""
 
     sequences = llama_pipeline(
@@ -49,14 +48,15 @@ def get_llama_response(message: str) -> str:
         top_k=10,
         num_return_sequences=1,
         eos_token_id=tokenizer.eos_token_id,
-        max_length=256,
+        max_length=512,
     )
 
     generated_text = sequences[0]['generated_text']
     response = generated_text[len(query):]  # Remove the prompt from the output
-    
+
     print("Chatbot:", response.strip())
     return response.strip()
 
-get_llama_response("What are the key operating conditions of the reverse water gas shift (RWGS) reaction in an industrial catalytic reactor for the production of syngas from carbon dioxide (CO2) and hydrogen (H2)?")
-#gr.ChatInterface(get_llama_response).launch()
+
+gr.ChatInterface(get_llama_response).launch()
+