Degraded Reranking on Queries due to Capacity issues
major- Started
- Nov 3, 4:50 PM EST
- Resolved
- Nov 3, 7:09 PM EST
- Duration
- 2h 18m
Vectara's updates (3)
- identified · Nov 3, 4:50 PM EST
Queries with default Multilingual Rerankers have increased error rates on some. Cloud provider GPU availability is causing scheduling issues, we are working on resolving capacity.
- monitoring · Nov 3, 5:39 PM EST
We are monitoring the fix, error rates are back to normal.
- resolved · Nov 3, 7:09 PM EST
This incident has been resolved.
What our checks recorded
We checked Vectara 27 times from Vectara's start time to its resolution, once every five minutes. Every one of them reached Vectara's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 428 ms, against 430 ms over the 24 hours before. Vectara posted the incident at Nov 3, 4:50 PM EST.
Updates are Vectara's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗