docs: Add dependencies example to load-balanced endpoint pattern (#575)

Co-authored-by: promptless[bot] <179508745+promptless[bot]@users.noreply.github.com>
Co-authored-by: Mo King <muhsinking@gmail.com>

Author: promptless[bot]

flash/create-endpoints.mdx

@@ -65,12 +65,13 @@ from runpod_flash import Endpoint, GpuType
 api = Endpoint(
     name="inference-api",
     gpu=GpuType.NVIDIA_GEFORCE_RTX_4090,
-    workers=(1, 5)
+    workers=(1, 5),
+    dependencies=["torch"]
 )
 
 @api.post("/predict")
 async def predict(data: dict) -> dict:
-    import torch
+    import torch  # Import inside the function body
     # Run inference
     return {"prediction": "result"}