Update app.py

app.py

@@ -1,11 +1,15 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
+# Initialize OpenAI client
+token = "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"
+endpoint = "https://models.github.ai/inference"
+model = "openai/gpt-4.1"
 
+client = OpenAI(
+    base_url=endpoint,
+    api_key=token,
+)
 
 def respond(
     message,
@@ -25,20 +29,15 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    response = client.chat.completions.create(
+        messages=messages,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        model=model,
+        max_tokens=max_tokens
+    )
 
+    return response.choices[0].message.content
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface