Update app.py

app.py

@@ -20,7 +20,7 @@ os.environ['AZURE_OPENAI_KEY'] = AZURE_OPENAI_KEY
 openai.api_version = "2024-02-15-preview" # change it with your own version
 openai.azure_endpoint = os.getenv('azure_endpoint')
 
-model = "gpt4o" # deployment name on Azure OPENAI Studio
+model = "gpt-4o-mini" # deployment name on Azure OPENAI Studio
 client = AzureOpenAI(azure_endpoint = openai.azure_endpoint, 
                             api_key=AZURE_OPENAI_KEY,  
                             api_version=openai.api_version)
@@ -189,8 +189,11 @@ last_interaction = gr.State(None)
 
 def chat(question, manual, history, liked):
     history = history or []
-
+    
     conv = format_chat_prompt(history)
+
+    history.append((question, ""))
+    yield history
     
     manual_list = {"Toyota_Corolla_2024_TR": -8580416610875007536, 
                    "Renault_Clio_2024_TR":-5514489544983735006, 
@@ -349,7 +352,7 @@ def chat(question, manual, history, liked):
     conv.append({"role": "assistant", "content": response})
 
 
-    history.append((question, response))  
+    history[-1].append((question, response))  
     print("Answer:--- %s seconds ---" % (time.time() - start_time))
     
     # Store the last interaction without saving to the database yet
@@ -394,10 +397,7 @@ with gr.Blocks() as demo:
     #    save_last_interaction("N/A")  # Save previous interaction before starting a new one
     #    return chat(question, manual, history, liked_state.value)
     def gradio_chat(question, manual, history):
-        save_last_interaction("N/A")  # Save previous interaction before starting a new one
-        history.append((question, ""))
-        yield "", history
-        
+        save_last_interaction("N/A")  # Save previous interaction before starting a new one        
         chat_generator = chat(question, manual, history, liked_state.value)
         final_response = ""
         final_history = history