Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from gradio_client import Client
 from huggingface_hub import InferenceClient
-import random  # Add this line to import the random module
+import random
 
 ss_client = Client("https://omnibus-html-image-current-tab.hf.space/")
 
@@ -27,7 +27,7 @@ def load_models(inp):
         print(models[inp])
     return gr.update(label=models[inp])
 
-def format_prompt(message, history, cust_p):
+def format_prompt(message, history):
     prompt = ""
     if history:
         for user_prompt, bot_response in history:
@@ -35,10 +35,10 @@ def format_prompt(message, history, cust_p):
             prompt += f"<start_of_turn>model{bot_response}<end_of_turn>"
             if VERBOSE==True:
                 print(prompt)
-    prompt+=cust_p.replace("USER_INPUT",message)
+    prompt += message
     return prompt
 
-def chat_inf(system_prompt,prompt,history,memory,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem,cust_p):
+def chat_inf(system_prompt,prompt,history,memory,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem):
     hist_len=0
     client=clients[int(client_choice)-1]
     if not history:
@@ -64,10 +64,7 @@ def chat_inf(system_prompt,prompt,history,memory,client_choice,seed,temp,tokens,
             do_sample=True,
             seed=seed,
         )
-        if system_prompt:
-            formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", memory[0-chat_mem:],cust_p)
-        else:
-            formatted_prompt = format_prompt(prompt, memory[0-chat_mem:],cust_p)
+        formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", memory[0-chat_mem:])
         stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
         output = ""
         for response in stream:
@@ -106,8 +103,6 @@ with gr.Blocks() as app:
         with gr.Row():
             with gr.Column(scale=3):
                 inp = gr.Textbox(label="Prompt")
-                sys_inp = gr.Textbox(label="System Prompt (optional)")
-                custom_prompt=gr.Textbox(label="Modify Prompt Format", info="For testing purposes. 'USER_INPUT' is where 'SYSTEM_PROMPT, PROMPT' will be placed", lines=3,value="<start_of_turn>userUSER_INPUT<end_of_turn><start_of_turn>model")                
                 btn = gr.Button("Chat")
             with gr.Column(scale=1):
                 with gr.Group():
@@ -123,7 +118,7 @@ with gr.Blocks() as app:
     client_choice.change(load_models,client_choice,[chat_b])
     app.load(load_models,client_choice,[chat_b])
     
-    chat_sub=inp.submit(check_rand,[rand,seed],seed).then(chat_inf,[sys_inp,inp,chat_b,memory,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem,custom_prompt],[chat_b,memory])
-    go=btn.click(check_rand,[rand,seed],seed).then(chat_inf,[sys_inp,inp,chat_b,memory,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem,custom_prompt],[chat_b,memory])
+    chat_sub=inp.submit(check_rand,[rand,seed],seed).then(chat_inf,[inp,inp,chat_b,memory,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem],[chat_b,memory])
+    go=btn.click(check_rand,[rand,seed],seed).then(chat_inf,[inp,inp,chat_b,memory,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem],[chat_b,memory])
 
     app.queue(default_concurrency_limit=10).launch()