Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 import os
 import sys
-import json 
+import json
 import requests
 import random
 
@@ -20,7 +20,7 @@ def exception_handler(exception_type, exception, traceback):
     print("%s: %s" % (exception_type.__name__, exception))
 sys.excepthook = exception_handler
 sys.tracebacklimit = 0
-    
+
 def predict(inputs, top_p, temperature, chat_counter, chatbot, history, request:gr.Request):
     payload = {
         "model": MODEL,
@@ -53,9 +53,9 @@ def predict(inputs, top_p, temperature, chat_counter, chatbot, history, request:
             message["role"] = role
             message["content"] = data
             messages.append(message)
-        
+
         message = {}
-        message["role"] = "user" 
+        message["role"] = "user"
         message["content"] = inputs
         messages.append(message)
         payload = {
@@ -72,8 +72,8 @@ def predict(inputs, top_p, temperature, chat_counter, chatbot, history, request:
     chat_counter += 1
 
     history.append(inputs)
-    token_counter = 0 
-    partial_words = "" 
+    token_counter = 0
+    partial_words = ""
     counter = 0
 
     try:
@@ -83,7 +83,7 @@ def predict(inputs, top_p, temperature, chat_counter, chatbot, history, request:
         #if response_code.strip() != "<Response [200]>":
         #    #print(f"response code - {response}")
         #    raise Exception(f"Sorry, hitting rate limit. Please try again later. {response}")
-        
+
         for chunk in response.iter_lines():
             #print (chunk)
             #sys.stdout.flush()
@@ -103,12 +103,12 @@ def predict(inputs, top_p, temperature, chat_counter, chatbot, history, request:
                     else:
                         history[-1] = partial_words
                     token_counter += 1
-                    yield [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2) ], history, chat_counter, response, gr.update(interactive=False), gr.update(interactive=False)  # resembles {chatbot: chat, state: history}  
+                    yield [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2) ], history, chat_counter, response, gr.update(interactive=False), gr.update(interactive=False)  # resembles {chatbot: chat, state: history}
     except Exception as e:
         print (f'error found: {e}')
     yield [(history[i], history[i + 1]) for i in range(0, len(history) - 1, 2) ], history, chat_counter, response, gr.update(interactive=True), gr.update(interactive=True)
     print(json.dumps({"chat_counter": chat_counter, "payload": payload, "partial_words": partial_words, "token_counter": token_counter, "counter": counter}))
-                   
+
 
 def reset_textbox():
     return gr.update(value='', interactive=False), gr.update(interactive=False)
@@ -127,7 +127,7 @@ Assistant: <utterance>
 In this app, you can explore the outputs of a gpt-4 turbo LLM.
 """
 
-theme = gr.themes.Default(primary_hue="green")                
+theme = gr.themes.Default(primary_hue="green")
 
 with gr.Blocks(css = """#col_container { margin-left: auto; margin-right: auto;}
                 #chatbot {height: 520px; overflow: auto;}""",
@@ -137,7 +137,7 @@ with gr.Blocks(css = """#col_container { margin-left: auto; margin-right: auto;}
 
     #gr.HTML('''<center><a href="https://huggingface.co/spaces/ysharma/ChatGPT4?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>Duplicate the Space and run securely with your OpenAI API Key</center>''')
     with gr.Column(elem_id = "col_container", visible=False) as main_block:
-        #GPT4 API Key is provided by Huggingface 
+        #GPT4 API Key is provided by Huggingface
         #openai_api_key = gr.Textbox(type='password', label="Enter only your GPT4 OpenAI API key here")
         chatbot = gr.Chatbot(elem_id='chatbot') #c
         inputs = gr.Textbox(placeholder= "Hi there!", label= "Type an input and press Enter") #t
@@ -147,7 +147,7 @@ with gr.Blocks(css = """#col_container { margin-left: auto; margin-right: auto;}
                 b1 = gr.Button(visible=not DISABLED) #.style(full_width=True)
             with gr.Column(scale=3):
                 server_status_code = gr.Textbox(label="Status code from OpenAI server", )
-    
+
         #inputs, top_p, temperature, top_k, repetition_penalty
         with gr.Accordion("Parameters", open=False):
             top_p = gr.Slider( minimum=-0, maximum=1.0, value=1.0, step=0.05, interactive=True, label="Top-p (nucleus sampling)",)
@@ -155,7 +155,7 @@ with gr.Blocks(css = """#col_container { margin-left: auto; margin-right: auto;}
             #top_k = gr.Slider( minimum=1, maximum=50, value=4, step=1, interactive=True, label="Top-k",)
             #repetition_penalty = gr.Slider( minimum=0.1, maximum=3.0, value=1.03, step=0.01, interactive=True, label="Repetition Penalty", )
             chat_counter = gr.Number(value=0, visible=False, precision=0)
-    
+
     with gr.Column(elem_id = "user_consent_container") as user_consent_block:
         # Get user consent
         accept_checkbox = gr.Checkbox(visible=False)
@@ -179,11 +179,11 @@ with gr.Blocks(css = """#col_container { margin-left: auto; margin-right: auto;}
             return gr.update(visible=False), gr.update(visible=True)
 
     accept_button.click(None, None, accept_checkbox, js=js, queue=False)
-    accept_checkbox.change(fn=enable_inputs, inputs=[], outputs=[user_consent_block, main_block], queue=False)
+    accept_checkbox.change(fn=enable_inputs, inputs=[], outputs=[ main_block], queue=False)
 
     inputs.submit(reset_textbox, [], [inputs, b1], queue=False)
     inputs.submit(predict, [inputs, top_p, temperature, chat_counter, chatbot, state], [chatbot, state, chat_counter, server_status_code, inputs, b1],)  #openai_api_key
     b1.click(reset_textbox, [], [inputs, b1], queue=False)
     b1.click(predict, [inputs, top_p, temperature, chat_counter, chatbot, state], [chatbot, state, chat_counter, server_status_code, inputs, b1],)  #openai_api_key
-             
-    demo.queue(max_size=10, default_concurrency_limit=NUM_THREADS, api_open=False).launch(share=False)
+
+    demo.queue(max_size=10, default_concurrency_limit=NUM_THREADS, api_open=False).launch(share=False)