* trying out a fix
* add ability to manually run model tests
* add log dump
* check status code, not text?
* just the model server
* add port mapping to host
* pass through more api keys
* add azure tests
* fix litellm env vars
* fix env vars in github workflow
* temp disable litellm test
---------
Co-authored-by: Richard Kuo (Danswer) <rkuo@onyx.app>
* wip checkpointing/continue on failure
more stuff for checkpointing
Basic implementation
FE stuff
More checkpointing/failure handling
rebase
rebase
initial scaffolding for IT
IT to test checkpointing
Cleanup
cleanup
Fix it
Rebase
Add todo
Fix actions IT
Test more
Pagination + fixes + cleanup
Fix IT networking
fix it
* rebase
* Address misc comments
* Address comments
* Remove unused router
* rebase
* Fix mypy
* Fixes
* fix it
* Fix tests
* Add drop index
* Add retries
* reset lock timeout
* Try hard drop of schema
* Add timeout/retries to downgrade
* rebase
* test
* test
* test
* Close all connections
* test closing idle only
* Fix it
* fix
* try using null pool
* Test
* fix
* rebase
* log
* Fix
* apply null pool
* Fix other test
* Fix quality checks
* Test not using the fixture
* Fix ordering
* fix test
* Change pooling behavior
* initial commit for helm chart refactoring
* Continue refactoring helm. I was able to use helm to deploy all of the apps to a cluster in aws. The bottleneck was setting up PVC dynamic provisioning.
* use default storage class
* Fix linter errors
* Fix broken helm test
---------
Co-authored-by: jpb80 <jordan.buttkevitz@gmail.com>
* shared admin level test dependency
* change to on - push (recommended by chromatic)
* change playwright reporter to list, name test jobs
* use test tags ... much cleaner
* test vs prod
* try copying templates
* run with localhost?
* revert to dev
* new tests and a bit of refactoring
* add additional checks so that page snapshots reflect loaded state
* more admin tests
* User Management tests
* remaining admin pages
* test search and chat
* await fix and exclude UI that changes with dates.
* test overlapping connectors (but using a source that is way too big and slow, fix that next)
* pass thru secrets
* rename
* rename again
* now we are fixing it
---------
Co-authored-by: Richard Kuo <rkuo@rkuo.com>
* initial PoC
* preliminary working config
* first cut at chromatic tests
* first cut at chromatic tests
* fix yaml
* fix yaml again
* use workingDir
* adapt playwright example
* remove env
* fix working directory
* fix more paths
* fix dir
* add playwright setup
* accidentally deleted a step
* update test
* think we don't need home.png right now
* remove unused home.png
---------
Co-authored-by: Richard Kuo <rkuo@rkuo.com>
* doc_sync is refactored
* maybe this works
* tested to work!
* mypy fixes
* enabled integration tests
* fixed the test
* added external group sync
* testing should work now
* mypy
* confluence doc id fix
* got group sync working
* addressed feedback
* renamed some vars and fixed mypy
* conf fix?
* added wiki handling to confluence connector
* test fixes
* revert google drive connector
* fixed groups
* hotfix
* re-enable helm
* allow manual triggering
* change vespa host
* change vespa chart location
* update Chart.lock
* update ct.yaml with new vespa chart repo
* bump vespa to 0.2.5
* update Chart.lock
* update to vespa 0.2.6
* bump vespa to 0.2.7
* bump to 0.2.8
* bump version
* try appending the ordinal
* try new configmap
* bump vespa
* bump vespa
* add debug to see if we can figure out what ct install thinks is failing
* add debug flag to helm
* try disabling nginx because of KinD
* use helm-extra-set-args
* try command line
* try pointing test connection to the correct service name
* bump vespa to 0.2.12
* update chart.lock
* bump vespa to 0.2.13
* bump vespa to 0.2.14
* bump vespa
* bump vespa
* re-enable chart testing only on changes
* name the check more specifically than "lint-test"
* add some debugging
* try setting remote
* might have to specify chart dirs directly
* add comments
---------
Co-authored-by: Richard Kuo <rkuo@rkuo.com>
