Update app.py

app.py

@@ -1,18 +1,17 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
 def respond(
     message,
-    history: list[dict[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
+    hf_token
 ):
     """
-    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
+    Handles streaming responses from Hugging Face Inference API
     """
     client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
 
@@ -22,14 +21,14 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    for message_chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
+        choices = message_chunk.choices
         token = ""
         if len(choices) and choices[0].delta.content:
             token = choices[0].delta.content
@@ -37,28 +36,37 @@ def respond(
         response += token
         yield response
 
-
-# ChatInterface does not require the 'type' argument
-chatbot = gr.ChatInterface(
-    fn=respond,
-    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)",
-        ),
-    ],
-)
-
+# Gradio app
 with gr.Blocks() as demo:
     with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+        hf_token = gr.OAuthToken(label="Hugging Face Token")
+        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 (nucleus sampling)"
+        )
+    
+    chatbot = gr.Chatbot()
+
+    state = gr.State([])  # to hold conversation history
+
+    msg = gr.Textbox(label="Your message")
+
+    msg.submit(
+        respond,
+        inputs=[msg, state, system_message, max_tokens, temperature, top_p, hf_token],
+        outputs=[chatbot],
+        show_progress=True
+    )
 
 if __name__ == "__main__":
     demo.launch()