Load embedding model from local hostPath to prevent HuggingFace download failures

Shipped

March 18, 2026 at 2:48 AM UTC

Author

Kamo

Commit

aa5c6c2

The embedding-model pod was in CrashLoopBackOff because it couldn't download the model from HuggingFace on startup (network/DNS issue). Mount the model from a hostPath volume with pre-downloaded files. Also fix port mismatch — set --port 8080 to match containerPort and health probes.