EIS elevated 5xx error rates for model google-gemini-embedding-001
Apr 20, 06:37 UTCApr 20, 10:41 UTC
Duration
4h 5m
Impact
Major
Root cause
Not disclosed
Elastic, 90 days
27 incidents
Affected
Elastic Inference ServiceGlobal services - Elastic Inference Service
Final update
An incident with an upstream service provider has been resolved, and access to the model is now restored.
Timeline
- Resolved · Apr 20, 10:41 UTC
An incident with an upstream service provider has been resolved, and access to the model is now restored.
- Investigating · Apr 20, 09:50 UTC
Errors are coming from the provider API (Google). The incident has been escalated to them, and we are still waiting for a response.
- Investigating · Apr 20, 06:37 UTC
We're seeing elevated 5xx error rates for the Gemini Embedding v1 model in EIS. The following default inference endpoint is affected: - .google-gemini-embedding-001 We're investigating and will update again in 2 hours or if there's a change in status.
More from Elastic
Full history| Started | Incident | Impact | Duration |
|---|---|---|---|
| Sep 2314:04 UTC | Degraded Performance: Cloud Provisioning Delays | major | 1h 59m |
| Sep 1715:50 UTC | AutoOps node metrics temporarily unavailable in some regions | major | 41m |
| Sep 1613:17 UTC | Elastic Support Portal unavailable | major | 2h 21m |
| Sep 1223:21 UTC | Delayed Metrics in Cloud Console - GCP us-east4 | major | 8h 24m |
| Sep 1001:30 UTC | Kibana access restored for UI-assigned Organization Owners on Hosted deployments | major | 21h |
| Sep 920:44 UTC | Elastic Agent enrollment/check-in failures on 9.5.3 (and 9.4.6) with Fleet remote Elasticsearch output | major | 7d 13h |
From vendors' own status pages and disclosures. Times as reported. Logos via logo.dev; trademarks belong to their owners.