working huggingface inference endpoint

app.py

@@ -7,21 +7,30 @@ import subprocess
 from threading import Timer
 from functools import partial
 import time
+from huggingface_hub import InferenceClient
 
 from gradio_motioncanvasplayer import MotionCanvasPlayer
 
 # Just some example project that servers as a placholder in the beginning
 example_project_path = "https://prathje-gradio-motioncanvasplayer.hf.space/gradio_api/file=/home/user/app/public/project-3.17.2.js"
 
-def slow_echo(message, history):
-    for i in range(len(message)):
-        time.sleep(0.3)
-        yield "You typed: " + message[: i+1]
 
-gr.ChatInterface(
-    fn=slow_echo, 
-    type="messages"
-).launch()
+client = InferenceClient(
+    provider="hf-inference",
+    api_key=os.environ["HF_TOKEN"],
+)
+
+def get_completion(prompt, history):
+    completion = client.chat.completions.create(
+        model="Qwen/Qwen2.5-Coder-32B-Instruct",
+        messages=[
+            {
+                "role": "user",
+                "content": "What is the capital of France?"
+            }
+        ],
+    )
+    return completion.choices[0].message
 
 def load_example(example):
     return example['project_path'], example['code'], ""
@@ -32,8 +41,7 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as app:
     with gr.Row():
         with gr.Column():
             gr.Markdown("## Chat")
-            chat = gr.ChatInterface(fn=slow_echo, type="messages")
-
+            chat = gr.ChatInterface(fn=get_completion, type="messages")
         
             gr.Markdown("### TypeScript Code for Your Scene")
             code = gr.Code(value="", language="typescript")