Update app.py

app.py

@@ -1,64 +1,57 @@
 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("lambdaindie/lambdai")
 
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    messages = [{"role": "system", "content": system_message}] if system_message else []
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    for user, assistant in history:
+        if user:
+            messages.append({"role": "user", "content": user})
+        if assistant:
+            messages.append({"role": "assistant", "content": assistant})
 
     messages.append({"role": "user", "content": message})
-
     response = ""
 
-    for message in client.chat_completion(
+    for chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
+        token = chunk.choices[0].delta.content
         response += token
         yield response
 
-
-"""
-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="", 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)",
-        ),
-    ],
-)
-
+with gr.Blocks() as demo:
+    gr.Markdown("# 🧠 lambdai — Chat Demo")
+    
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        system_msg = gr.Textbox(label="System message", placeholder="e.g. You are a helpful assistant.")
+    with gr.Row():
+        max_tokens = gr.Slider(1, 2048, value=512, step=1, label="Max tokens")
+        temperature = gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature")
+        top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p")
+    msg = gr.Textbox(placeholder="Ask something...", label="Your message")
+
+    state = gr.State([])
+
+    def user_submit(user_message, history):
+        return "", history + [[user_message, None]]
+
+    def generate_response(message, history, sys_msg, max_tokens, temperature, top_p):
+        gen = respond(message, history, sys_msg, max_tokens, temperature, top_p)
+        return gen, history
+
+    msg.submit(user_submit, [msg, state], [msg, state], queue=False).then(
+        generate_response,
+        [msg, state, system_msg, max_tokens, temperature, top_p],
+        [chatbot, state]
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()