Update app1.py

app1.py

@@ -3,34 +3,32 @@ from huggingface_hub import InferenceClient
 
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-def respond(message, history, 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]})
-    messages.append({"role": "user", "content": message})
-    response = ""
-    for message in client.chat_completion(messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p):
-        token = message.choices[0].delta.content
-        response += token
-    yield response
+with gr.Blocks() as demo:
+    system_message = gr.Textbox(value="You are a friendly 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")
+    chat_history = gr.Markdown(label="Chat History")
+    message = gr.Textbox(label="Message")
+    chatbot = gr.Chatbot()
+    clear = gr.Button("Clear")
 
-def clear_history():
-    return [], ""
+    def respond(system_message, message, max_tokens, temperature, top_p, chat_history):
+        messages = [{"role": "system", "content": system_message}]
+        for val in chat_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, stream=True, temperature=temperature, top_p=top_p):
+            token = message.choices[0].delta.content
+            response += token
+        chat_history.append((message, response))
+        return chat_history
 
-demo = gr.Interface(
-    respond,
-    title="MediPro",
-    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="MediPro"),
-    ],
-    outputs=gr.Markdown(label="Chat History"),
-    layout="chat",  # Use the "chat" layout
-)
-if __name__ == "__main__":
-    demo.launch()
+    message.submit(respond, inputs=[system_message, message, max_tokens, temperature, top_p, chat_history], outputs=[chat_history, chatbot])
+    clear.click(lambda: [], outputs=[message, chatbot, chat_history])
+
+demo.launch()