Changing the code to 2 way chatting

Code copied from: https://huggingface.co/spaces/exnrt/com-Chatbot/blob/main/app.py

app.py

@@ -1,18 +1,50 @@
+from huggingface_hub import InferenceClient
 import gradio as gr
-import random
-import time
 
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox()
-    clear = gr.ClearButton([msg, chatbot])
+client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-    def respond(message, chat_history):
-        bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
-        chat_history.append((message, bot_message))
-        time.sleep(2)
-        return "", chat_history
+def format_prompt(message, history, system_prompt=None):
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    if system_prompt:
+        prompt += f"[SYS] {system_prompt} [/SYS]"
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
 
-    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+def generate(
+    prompt, history, system_prompt=None, temperature=0.2, max_new_tokens=1024, top_p=0.95, repetition_penalty=1.0,
+):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
 
-demo.launch()
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    formatted_prompt = format_prompt(prompt, history, system_prompt)
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        yield output
+    return output
+
+mychatbot = gr.Chatbot( bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True,)
+
+demo = gr.ChatInterface(
+    fn=generate,
+    chatbot=mychatbot
+)
+
+demo.queue().launch(show_api=False)