Update app.py

app.py

@@ -39,8 +39,8 @@ with open('info.txt', 'r') as file:
 database_tag = database_content
 
 
-template = "Message: {message}\n\nConversation History: {history}\n\nDate and Time: {date_time}\n\nBitcoin Price: ${bitcoin_price}\n\nBitcoin history from 1-jan-2024 to today: {database_tag}\n\nYour system: {json_data}.\n\nResponse:"
-prompt = PromptTemplate(template=template, input_variables=["message","history", "date_time", "bitcoin_price", "database_tag", "json_data"])
+template = "Message: {message}\n\nSentiment Analysis: {sentiment}\n\nConversation History: {history}\n\nDate and Time: {date_time}\n\nBitcoin Price: ${bitcoin_price}\n\nBitcoin history from 1-jan-2024 to today: {database_tag}\n\nYour system: {json_data}.\n\nResponse:"
+prompt = PromptTemplate(template=template, input_variables=["message", "sentiment", "history", "date_time", "bitcoin_price", "database_tag", "json_data"])
 conversation_history = []
 
 MAX_HISTORY_LENGTH = 55
@@ -77,6 +77,8 @@ def submit():
 
     doc = nlp(user_input)
     tokens = [token.text for token in doc]
+
+    sentiment = TextBlob(user_input).sentiment
     
     # Add Spacy NLP processing here
     
@@ -97,7 +99,7 @@ def submit():
     history_stemmed_tokens = [ps.stem(token) for token in history_tokens]
     history_lemmatized_tokens = [lemmatizer.lemmatize(token) for token in history_tokens]
 
-    model_input = prompt.format(message=user_input, history="<br>".join(conversation_history), database_tag=database_content, date_time=current_time, bitcoin_price=bitcoin_price, json_data=json_data,history_tokens=history_tokens,history_stemmed_tokens=history_stemmed_tokens,history_lemmatized_tokens=history_lemmatized_tokens)
+    model_input = prompt.format(message=user_input, sentiment=sentiment, history="<br>".join(conversation_history), database_tag=database_content, date_time=current_time, bitcoin_price=bitcoin_price, json_data=json_data,history_tokens=history_tokens,history_stemmed_tokens=history_stemmed_tokens,history_lemmatized_tokens=history_lemmatized_tokens)
 
     response = llm(model_input, context="<br>".join(conversation_history))