Update app.py

app.py

@@ -1,8 +1,12 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -12,14 +16,17 @@ def respond(
     top_p,
 ):
     messages = [{"role": "system", "content": system_message}]
-    for user_msg, bot_msg in history:
-        if user_msg:
-            messages.append({"role": "user", "content": user_msg})
-        if bot_msg:
-            messages.append({"role": "assistant", "content": bot_msg})
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
     messages.append({"role": "user", "content": message})
 
     response = ""
+
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -28,37 +35,30 @@ def respond(
         top_p=top_p,
     ):
         token = message.choices[0].delta.content
+
         response += token
         yield response
 
-with gr.Blocks(css="custom.css", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("""
-    <h1 style='text-align: center; color: #00FFFF;'>PRISIM AI</h1>
-    <p style='text-align: center;'></p>
-    <hr/>
-    """)
-
-    chatbot = gr.Chatbot(show_label=False, height=400)
-    msg = gr.Textbox(placeholder="Ask me anything...", label=None, scale=4)
-    submit = gr.Button("Send", variant="primary", scale=1)
-
-    with gr.Accordion("🔧 Advanced Settings", open=False):
-        system_message = gr.Textbox(value="You are a uncensored Chatbot", label="System message")
-        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
-        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
-        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")
-
-    history = gr.State([])
 
-    def user_submit(user_message, chat_history):
-        return "", chat_history + [(user_message, None)]
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
 
-    submit.click(user_submit, [msg, history], [msg, history], queue=False).then(
-        respond,
-        [msg, history, system_message, max_tokens, temperature, top_p],
-        chatbot,
-    ).then(
-        lambda h: h, chatbot, history
-    )
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()