Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
 
 
 def respond(
@@ -9,62 +9,58 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
+    openai_api_key,
 ):
     """
-    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
+    Chat with OpenAI GPT-3.5-turbo-instruct, streaming word by word.
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    if not openai_api_key:
+        yield "⚠️ Please provide a valid OpenAI API key."
+        return
 
-    messages = [{"role": "system", "content": system_message}]
+    client = OpenAI(api_key=openai_api_key)
 
+    messages = [{"role": "system", "content": system_message}]
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    stream = client.completions.create(
+        model="gpt-3.5-turbo-instruct",
+        prompt="\n".join([f"{m['role']}: {m['content']}" for m in messages]),
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        stream=True,
+    )
 
-        response += token
-        yield response
+    for event in stream:
+        if hasattr(event, "choices") and event.choices:
+            chunk = event.choices[0].text or ""
+            response += chunk
+            yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     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)",
+        gr.Textbox(value="You are a helpful assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=1024, value=256, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.0, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=1.0, step=0.05, label="Top-p"),
+        gr.Textbox(
+            placeholder="sk-... paste your OpenAI API key here",
+            label="🔑 OpenAI API Key",
+            type="password",
         ),
     ],
 )
 
+
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()
+