Update app.py

app.py

@@ -37,8 +37,8 @@ with open('ai_chatbot_data.json', 'r') as file:
     json_data = json.load(file)
 
 # Updated prompt template for Bitcoin trading
-template = "User Message: {message}\n\nUser Sentiment: {sentiment}\n\nConversation now: {history}\n\nDate and Time: {date_time}\n\nBitcoin Price: ${bitcoin_price}\n\nBTC price from 1 jan 2024 to {date_time} (DATE,OPEN,HIGH,LOW,CLOSE,ADJ CLOSE,VOLUME<br/>): {div_content}\n\nAI System Data: {json_data}\n\nResponse:"
-prompt = PromptTemplate(template=template, input_variables=["message", "sentiment", "history", "date_time", "bitcoin_price", "div_content", "json_data"])
+template = "User Message: {message}\n\nUser Sentiment: {sentiment}\n\nConversation now: {history}\n\nDate and Time: {date_time}\n\nBitcoin Price: ${bitcoin_price}\n\nBTC price from 1 jan 2024 to {date_time} (DATE,OPEN,HIGH,LOW,CLOSE,ADJ CLOSE,VOLUME<br/>): {result}\n\nAI System Data: {json_data}\n\nResponse:"
+prompt = PromptTemplate(template=template, input_variables=["message", "sentiment", "history", "date_time", "bitcoin_price", "result", "json_data"])
 conversation_history = []
 
 MAX_HISTORY_LENGTH = 55
@@ -113,7 +113,7 @@ def submit():
     history_lemmatized_tokens = [lemmatizer.lemmatize(token) for token in history_tokens]
 
     model_input = prompt.format(message=user_input, sentiment=sentiment, history="\n".join(conversation_history), 
-                                div_content=div_content, date_time=current_time, bitcoin_price=bitcoin_price, json_data=json_data)
+                                result=result, date_time=current_time, bitcoin_price=bitcoin_price, json_data=json_data)
 
     response = llm(model_input, context="<br>".join(conversation_history))
 
@@ -143,7 +143,7 @@ if __name__ == "__main__":
                          repo_id=repo_id,
                          model_kwargs={
                              "temperature": 0.5,
-                             "max_new_tokens": 256,
+                             "max_new_tokens": 512,
                              "top_p": 0.5,
                              "repetition_penalty": 1.2,
                              "num_beams": 3,