fix(app): adjust inference endpoint address

app.py

@@ -14,7 +14,7 @@ if not 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
 """
 client = InferenceClient(
-    model="https://mw6ztcar07ths6bp.us-east-1.aws.endpoints.huggingface.cloud",
+    base_url="https://mw6ztcar07ths6bp.us-east-1.aws.endpoints.huggingface.cloud/v1/",
     token=token
 )