Update app.py

app.py

@@ -4,12 +4,12 @@ import gradio as gr
 client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
 
 def generate(
     prompt, history, temperature=0.2, max_new_tokens=30000, top_p=0.95, repetition_penalty=1.0,
@@ -30,22 +30,12 @@ def generate(
 
     formatted_prompt = format_prompt(prompt, history)
 
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
     output = ""
 
     for response in stream:
-        output += response.token.text
+        output += response["generated_text"]
         yield output
-    return output
 
-mychatbot = gr.Chatbot(
-    avatar_images=["./user.png", "./botm.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
-
-demo = gr.ChatInterface(fn=generate, 
-                        chatbot=mychatbot,
-                        title="Matteo's Mixtral 8x7b Chat",
-                        retry_btn=None,
-                        undo_btn=None
-                       )
-
-demo.queue().launch(show_api=True)
+iface = gr.Interface(fn=generate, inputs=["text", "text", "number", "number", "number", "number"], outputs="text", title="Text Generation")
+iface.launch()