A single node in our production database caused approximately 10-15% of all incoming calls to the LangSmith API to experience degraded performance and a small number would time out, resulting in a status 503 error. We have worked to have the offending node removed from our replica pool and performance has returned to normal.
Posted Sep 20, 2024 - 00:34 UTC
Investigating
We are currently investigating intermittent query stalls affecting the LangSmith Frontend and API.
Posted Sep 19, 2024 - 21:40 UTC
This incident affected: LangSmith Frontend and LangSmith API.