Upload folder using huggingface_hub

inference.py

@@ -43,7 +43,7 @@ from openai import OpenAI
 
 IMAGE_NAME   = os.getenv("IMAGE_NAME")
 API_KEY      = (
-    os.getenv("HF_TOKEN") or
+    # os.getenv("HF_TOKEN") or 
     os.getenv("OPENAI_API_KEY")
     or os.getenv("API_KEY")
 )
@@ -159,7 +159,7 @@ def start_container(image_name: str, port: int = 8000) -> Optional[str]:
     try:
         result = subprocess.run(
             ["docker", "run", "-d", "--rm", "-p", f"{port}:{port}", image_name],
-            capture_output=True, text=True, timeout=30,
+            capture_output=True, text=True, timeout=120,
         )
         if result.returncode == 0:
             cid = result.stdout.strip()
@@ -340,7 +340,7 @@ def main() -> None:
             print("[DEBUG] Could not start container — assuming server already running.", flush=True)
 
     # Wait for server to be ready
-    if not wait_for_server(BASE_URL, retries=20, delay=3.0):
+    if not wait_for_server(BASE_URL, retries=40, delay=3.0):
         print("ERROR: Server never became ready.", file=sys.stderr)
         if container_id:
             stop_container(container_id)

server/inference.py

@@ -22,7 +22,7 @@ except ImportError:
 # ---------------------------------------------------------------------------
 
 IMAGE_NAME   = os.getenv("IMAGE_NAME")
-API_KEY      =  os.getenv("OPENAI_API_KEY") 
+API_KEY      = os.getenv("HF_TOKEN") or os.getenv("OPENAI_API_KEY") 
 API_BASE_URL = os.getenv("API_BASE_URL", "https://router.huggingface.co/v1")
 MODEL_NAME   = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-72B-Instruct")
 BASE_URL     = os.getenv("ENV_BASE_URL", "http://localhost:8000")