Update run.py

run.py

@@ -1,3 +1,4 @@
+import os
 from fastapi import FastAPI, Query
 from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
@@ -22,7 +23,9 @@ model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
 
 @app.get("/")
 def read_root():
-    return {"message": "API is live. Use the /predict endpoint.", "code": """
+    return {
+        "api_url": os.getenv("HF_INFERENCE_ENDPOINT", "") + "/predict",
+        "message": "API is live. Use the /predict endpoint.", "code": """
 import requests
 
 url = "https://<uname>-<spacename>.hf.space/predict"