Add caching functionality for model download and prediction

main.py

@@ -12,6 +12,11 @@ from huggingface_hub import hf_hub_download
 from huggingface_hub.utils import logging
 from toolz import concat, groupby, valmap
 from starlette.responses import RedirectResponse
+from cashews import cache
+from datetime import timedelta
+
+cache.setup("mem://")
+
 
 app = FastAPI()
 logger = logging.get_logger(__name__)
@@ -205,6 +210,7 @@ def root():
 
 
 @app.get("/predict_dataset_language/{hub_id}")
+@cache(ttl=timedelta(minutes=10))
 async def predict_language(
     hub_id: str,
     config: str | None = None,