Update app.py

app.py

@@ -7,8 +7,6 @@ from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from simple_salesforce import Salesforce, SalesforceLogin
 import random
 import datetime
-import uuid
-import json
 
 # Load environment variables
 load_dotenv()
@@ -34,8 +32,8 @@ PDF_DIRECTORY = 'data'
 os.makedirs(PDF_DIRECTORY, exist_ok=True)
 os.makedirs(PERSIST_DIR, exist_ok=True)
 
-# Variable to store current chat conversation
-current_chat_history = []
+# Variable to store current chat conversation in a dictionary
+current_chat_history = {}
 kkk = random.choice(['Clara', 'Lily'])
 
 def data_ingestion_from_directory():
@@ -65,7 +63,7 @@ def handle_query(query):
 
     # Use chat history to enhance response
     context_str = ""
-    for past_query, response in reversed(current_chat_history):
+    for past_query, response in reversed(current_chat_history.values()):
         if past_query.strip():
             context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"
 
@@ -79,38 +77,33 @@ def handle_query(query):
     else:
         response = "Sorry, I couldn't find an answer."
 
-    # Update current chat history
-    current_chat_history.append((query, response))
+    # Update current chat history dictionary (use unique ID as key)
+    chat_id = str(datetime.datetime.now().timestamp())
+    current_chat_history[chat_id] = (query, response)
 
     return response
 
-def save_chat_history(history):
-    # Save the chat history to a local file or Firebase
-    session_id = str(uuid.uuid4())
-    chat_history_path = f"chat_history_{session_id}.json"
-    
-    with open(chat_history_path, 'w') as f:
-        json.dump(history, f)
-    print(f"Chat history saved as {chat_history_path}")
-
-    # Save to Salesforce
-    save_to_salesforce(current_chat_history)
-
-def save_to_salesforce(history):
+def save_chat_history_to_salesforce():
     username =os.getenv("username")
     password =os.getenv("password")
     security_token =os.getenv("security_token")
-    domain = 'test'  
+    domain = 'test' 
 
+    # Log in to Salesforce
     session_id, sf_instance = SalesforceLogin(username=username, password=password, security_token=security_token, domain=domain)
+
+    # Create Salesforce object
     sf = Salesforce(instance=sf_instance, session_id=session_id)
-    for past_query, response in history:
+
+    # Iterate over chat history dictionary and push to Salesforce
+    for chat_id, (user_message, bot_response) in current_chat_history.items():
         data = {
             'Name': 'Chat with user',
-            'Bot_Message__c': response,
-            'User_Message__c': past_query,
+            'Bot_Message__c': bot_response,
+            'User_Message__c': user_message,
             'Date__c': str(datetime.datetime.now().date())
         }
+        # Insert into the custom object (replace 'Chat_History__c' with your custom object's API name)
         sf.Chat_History__c.create(data)
 
 # Define the function to handle predictions
@@ -123,9 +116,7 @@ def predict(message, history):
     response = handle_query(message)
     response_with_logo = f'<div class="response-with-logo">{logo_html}<div class="response-text">{response}</div></div>'
     
-    # Save the updated history
-    save_chat_history(current_chat_history)
-    
+    # Return the response with the logo
     return response_with_logo
 
 # Define your Gradio chat interface function
@@ -134,9 +125,6 @@ def chat_interface(message, history):
         # Process the user message and generate a response
         response = handle_query(message)
 
-        # Update the history and save it
-        save_chat_history(current_chat_history)
-
         # Return the bot response
         return response
     except Exception as e:
@@ -172,14 +160,13 @@ div.svelte-rk35yg {display: none;}
 div.progress-text.svelte-z7cif2.meta-text {display: none;}
 '''
 
-demo = gr.ChatInterface(chat_interface, 
-                        css=css,
-                        description="Lily",
-                        clear_btn=None, undo_btn=None, retry_btn=None,
-)
-
-# Add a button to save chat history
-gr.Button("Close Chat").click(fn=save_chat_history)
+# Use Gradio Blocks to wrap components
+with gr.Blocks() as demo:
+    chat = gr.ChatInterface(chat_interface, css=css, description="Lily", clear_btn=None, undo_btn=None, retry_btn=None)
+    
+    # Add a button to save chat history
+    save_button = gr.Button("Save History")
+    save_button.click(fn=save_chat_history_to_salesforce)
 
-# Launch the interface
+# Launch the Gradio interface
 demo.launch()