All Systems Operational
Uptime over the past 90 days. View historical uptime.
LangSmith Run Ingestion ? Operational
90 days ago
99.94 % uptime
Today
LangSmith Frontend ? Operational
LangSmith Playground ? Operational
LangSmith API ? Operational
Operational
Degraded Performance
Partial Outage
Major Outage
Maintenance
Major outage
Partial outage
No downtime recorded on this day.
No data exists for this day.
had a major outage.
had a partial outage.

No incidents or maintenance related to this downtime.

Past Incidents
May 16, 2024

No incidents reported today.

May 15, 2024

No incidents reported.

May 14, 2024
LangSmith Playground inaccessible
Resolved - From approximately 1717 to 1837 UTC on Tuesday, May 14 the LangSmith Playground was unavailable due to a failure of an automated process to provision a new certificate. An alternate certificate was manually provisioned and the issue has been mitigated.
May 14, 18:56 UTC
Investigating - We are currently investigating an issue that is blocking access to the LangSmith Playground.
May 14, 18:05 UTC
May 13, 2024

No incidents reported.

May 12, 2024

No incidents reported.

May 11, 2024
LangSmith API Error 500 on Run Ingest
Resolved - From 1559 to 1602 UTC on Saturday, May 11, a database migration unexpectedly resulted in the LangSmith API being briefly unavailable.

During this time, any already-submitted runs would have been processed but net-new runs would have been rejected with a 500 error and, by default, not retried by the LangSmith SDK.

This issue is no longer occurring and we are taking long-term measures to prevent a recurrence outside of a scheduled maintenance window.
May 11, 16:23 UTC
May 10, 2024

No incidents reported.

May 9, 2024

No incidents reported.

May 8, 2024

No incidents reported.

May 7, 2024

No incidents reported.

May 6, 2024

No incidents reported.

May 5, 2024

No incidents reported.

May 4, 2024

No incidents reported.

May 3, 2024

No incidents reported.

May 2, 2024
Inability to retrieve feedback on runs
Resolved - This incident has been resolved.
May 2, 17:07 UTC
Monitoring - We have applied a workaround that has addressed the issue and are monitoring for any recurrence. Feedback should now be fetched as expected.
May 2, 14:13 UTC
Investigating - An issue with our database provider has resulted in an inability to fetch feedback from runs in the LangSmith via the UI and SDK. We are investigating workarounds until the database issue can be corrected. New feedback continues to be processed successfully.
May 2, 13:59 UTC
LangSmith Authentication Database Maintenance
Completed - The scheduled maintenance has been completed. Login access has now been restored.
May 2, 05:34 UTC
In progress - Scheduled maintenance is currently in progress. We will provide updates as necessary.
May 2, 05:25 UTC
Scheduled - We will be performing upgrades on our infrastructure. We expect to see a small amount of downtime (less than 15 min) impacting access to the LangSmith UI. Application tracing via the LangSmith API and SDK should not be affected.
Apr 27, 16:29 UTC
Run Ingest Delays in LangSmith
Resolved - A spike in the number of incoming complex trace payloads between May 1 at 2350 UTC and May 2 at 0030 UTC caused some of our ingest workers to be become CPU starved temporarily which resulted in periods of high latency for some LangSmith tenants. We have adjusted our scaling parameters to reduce the duration of latency in the future and will be implementing optimizations to relieve the CPU starvation in an upcoming release.
May 2, 02:56 UTC
Identified - A spike in the number of incoming complex trace payloads caused some of our ingest workers to be become CPU starved temporarily which resulted in some periods of high latency. This effect was temporary and we are adjusting our scaling parameters to prevent a recurrence.
May 2, 01:37 UTC
Investigating - We are investigating latency in run ingests with delays of more than 2 minutes for a subset of runs to appear in the LangSmith UI.
May 2, 00:03 UTC
← Incident History Powered by Atlassian Statuspage