deepset Outage History

13 incidents recorded over the last 365 days, 6 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.

Live deepset status100.00% uptime history

Every Recorded deepset Incident

deepset incidents, newest first, with date, duration and status.
DateIncidentDurationStatus
Oct 15, 2026Haystack Enterprise Platform scheduled maintenanceMaintenance has started1h 35mResolved
Aug 27, 2026Scheduled authentication system maintenance Maintenance has started17h 56mResolved
Aug 26, 2026Migration of the authentication system of the platformMaintenance still underway. Login functionality operational, minor issues with logout.21h 51mResolved
Aug 25, 2026Elevated error rate for pipeline invocationsIssue identified and resolved10 minResolved
Jul 23, 2026Haystack Enterprise Platform scheduled maintenanceThe scheduled maintenance has been completed.2h 0mScheduled
Jul 4, 2026Triton rerankers models error rateThe overall error rate was at 0.02% percent. This downtime was individual requests failing of misconfigured pipelines. No impact on production workloads1h 2mResolved
Jul 3, 2026Shared Reranker models degraded performanceAll models are healthy again4 minResolved
May 28, 2026Haystack Enterprise Platform scheduled maintenanceThe scheduled maintenance has been completed.1h 30mScheduled
May 21, 2026Haystack Enterprise Platform scheduled maintenanceThe scheduled maintenance has been completed.4h 0mScheduled
Apr 28, 2026Haystack Enterprise Platform scheduled maintenanceThe scheduled maintenance has been completed.12h 0mScheduled
Apr 1, 2026Haystack Enterprise Platform scheduled maintenanceThe scheduled maintenance has been completed.24h 0mScheduled
Feb 19, 2026deepset AI platform scheduled maintenanceThe scheduled maintenance has been completed.12h 0mScheduled
Dec 11, 2025deepset AI Platform Scheduled MaintenanceThe scheduled maintenance has been completed.4h 0mScheduled

Hear about the next one while it is open

Everything above is a record written after the fact. We can email you when the next deepset incident opens instead, at the point where knowing still changes what you do.

Free, no password, no card. Unsubscribe in one click.

How to Read This deepset Incident Log

Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before deepset acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.

Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.

The longest single deepset outage in this window ran 1d, against a mean recovery of 7h 51m. If you depend on deepset in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.