Update app.py

app.py

@@ -1,70 +1,37 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
 
+client = OpenAI(
+    base_url="https://k0b11x1cc5f1ygmu.us-east4.gcp.endpoints.huggingface.cloud/v1/",
+    api_key=os.getenv("HUGGING_FACE_API_KEY")
+)
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
+def chat_with_streaming(message, history):
+    # Convert history to OpenAI format
+    messages = [{"role": msg["role"], "content": msg["content"]} for msg in history]
     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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+    # Create streaming completion inside the function
+    chat_completion = client.chat.completions.create(
+        model="qwen3-1-7b-gwo",
+        messages=messages,
+        max_tokens=150,
+        temperature=0.7,
+        stream=True,  # Enable streaming
+    )
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
+    response = ""
+    for chunk in chat_completion:
+        if chunk.choices[0].delta.content:
+            response += chunk.choices[0].delta.content
+            yield response  # Send partial response to Gradio
+
+# Create streaming interface
+demo = gr.ChatInterface(
+    fn=chat_with_streaming,
     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)",
-        ),
-    ],
+    title="Streaming Chat with Inference Endpoints",
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()