[04:24:03] 10Machine-Learning-Team, 10Add-Link, 10Growth-Team, 10Chinese-Sites, 10User-notice: Deploy "add a link" to 14th round of wikis - https://phabricator.wikimedia.org/T308139 (10kevinbazira) [04:25:38] 10Machine-Learning-Team, 10Add-Link, 10Growth-Team, 10Chinese-Sites, 10User-notice: Deploy "add a link" to 14th round of wikis - https://phabricator.wikimedia.org/T308139 (10kevinbazira) Model evaluation has been completed and below are the backtesting results: | | Precision@0.5 | Recall@0.5 |wawiki | 0.... [11:14:13] (03PS1) 10Elukey: events.py: prioritize the excp handling of ClientResponseError [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/902689 (https://phabricator.wikimedia.org/T328576) [11:15:35] aiko: o/ [11:15:56] \o [11:16:06] hello :) [11:16:09] Github changed their SSH host key https://github.blog/2023-03-23-we-updated-our-rsa-ssh-host-key/ [11:16:27] So you'll likely see scary errors if you fecth from repos using ssh URLs [11:20:22] ack [11:21:32] aiko: so I tried the new events code with changeprop/ml-staging and events generated fail to validate, but I noticed a weird thing and I opened the above code review to (hopefully) have better logging. [11:21:41] lemme know when you have a moment if you like the idea :) [11:21:48] going afk for lunch, ttl! [11:26:58] (03CR) 10AikoChou: [C: 03+1] "LGTM!" [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/902689 (https://phabricator.wikimedia.org/T328576) (owner: 10Elukey) [13:07:50] Good morning all [14:07:17] (03CR) 10Klausman: [C: 03+1] events.py: prioritize the excp handling of ClientResponseError [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/902689 (https://phabricator.wikimedia.org/T328576) (owner: 10Elukey) [14:15:49] (03CR) 10Elukey: [C: 03+2] events.py: prioritize the excp handling of ClientResponseError [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/902689 (https://phabricator.wikimedia.org/T328576) (owner: 10Elukey) [14:23:11] 10Machine-Learning-Team, 10artificial-intelligence, 10Bad-Words-Detection-System, 10revscoring, 10Thai-Sites: Add language support for Thai (th) - https://phabricator.wikimedia.org/T304045 (10PatsagornY) [14:32:36] (03Merged) 10jenkins-bot: events.py: prioritize the excp handling of ClientResponseError [machinelearning/liftwing/inference-services] - 10https://gerrit.wikimedia.org/r/902689 (https://phabricator.wikimedia.org/T328576) (owner: 10Elukey) [14:33:37] 10Lift-Wing, 10Machine-Learning-Team: Move Revert-risk language agnostic model from staging to production - https://phabricator.wikimedia.org/T332998 (10achou) [15:11:59] aiko: your fix works! I wasn't testing the right pod :) [15:12:14] but I found a possible good fix for the logging issue, sooo I am happy anyway [15:12:48] I sent some page_change events to the special staging kafka topic that we use with changeprop staging, and I see events in the revscoring-test topic now! [15:17:59] looks working very well [15:20:42] I sent thousands of events and everything went fine [15:21:51] 10Machine-Learning-Team, 10Platform Team Workboards (Platform Engineering Reliability): Implement new mediawiki.revision-score streams with Lift Wing - https://phabricator.wikimedia.org/T328576 (10elukey) Finally we have something working, I've just tested ~20k events in changeprop staging, hitting the ml-stag... [15:30:52] 10Machine-Learning-Team: Review and test the AMD GPU kubernetes plugin - https://phabricator.wikimedia.org/T333009 (10elukey) [15:32:37] 10Machine-Learning-Team, 10Analytics-Radar, 10Data-Engineering-Icebox, 10Patch-For-Review: Upgrade ROCm to 4.5 - https://phabricator.wikimedia.org/T295661 (10elukey) Hi @fkaelin, we'll definitely try to upgrade during the next quarter to the latest ROCm release :) [15:33:56] ok I'll re-try to add the drafttopic stream [15:33:59] fingers crossed [15:40:58] wow something is working [16:22:36] 10Machine-Learning-Team, 10Platform Team Workboards (Platform Engineering Reliability): Implement new mediawiki.revision-score streams with Lift Wing - https://phabricator.wikimedia.org/T328576 (10elukey) Stream deployed, I see traffic!! https://grafana.wikimedia.org/d/zsdYRV7Vk/istio-sidecar?orgId=1&var-clus... [16:30:53] yayyy that's great!!!! \o/ [16:33:31] aiko: for some weird reason changeprop is only pulling from the codfw page_change topic, not eqiad [16:33:41] I'll try to investigate on monday why, but so far all good! [16:36:15] elukey: good job Luca! congrats :D [16:36:55] aiko: you worked on it too! Milestone for the whole team :) [16:37:03] going afk folks! Have a good rest of the day and weekend :) [16:37:53] o/ have a nice weekend! [16:51:50] 10Machine-Learning-Team, 10API Platform, 10API-Portal, 10Platform Team Initiatives (API Gateway Roadmap): Add documentation about LiftWing to the API Portal - https://phabricator.wikimedia.org/T325759 (10apaskulin) > For example, revscoring could point to https://github.com/wikimedia/revscoring, and outlin... [23:41:24] 10Machine-Learning-Team, 10Add-Link, 10Growth-Team (Current Sprint), 10User-notice: Deploy "add a link" to 6th round of wikis - https://phabricator.wikimedia.org/T304550 (10Etonkovidova) Checked some wikis from the list - `ce.wp`, `it.wp`, `cy.wp`, `chy.wp`. Generally works as expected - no new issues; log...