-
Notifications
You must be signed in to change notification settings - Fork 1.2k
Pull requests: confident-ai/deepeval
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix: compare winner against contestant.name instead of contestant object
#2485
opened Feb 10, 2026 by
themavik
Loading…
4 tasks done
refactor: use subprocess.run for robust path handling on Windows
#2484
opened Feb 10, 2026 by
RinZ27
Loading…
fix: support separate sync/async HTTP clients in GPTModel (#2351)
#2483
opened Feb 9, 2026 by
themavik
Loading…
fix: guard against None verdicts in turn relevancy metric (#2327)
#2482
opened Feb 9, 2026 by
themavik
Loading…
fix: guard against None verdicts in conversation completeness metric (#2327)
#2481
opened Feb 9, 2026 by
themavik
Loading…
Fix AccessDeniedException when using AmazonBedrockModel in async evaluations
#2471
opened Feb 3, 2026 by
Fizza-Mukhtar
Loading…
[Bugfix]
collection.count() returns the number of chunks, not tokens.
#2468
opened Feb 2, 2026 by
phungpx
Loading…
Fix AzureOpenAI keyless auth by deferring credential validation to SDK
#2464
opened Jan 31, 2026 by
ppon1086
Loading…
Fix variable name from 'golden' to 'goldens'
awaiting docs fix
#2454
opened Jan 22, 2026 by
himanshutech4purpose
Loading…
tests(docs): add component-level eval tracing and dataset IO tests
#2433
opened Jan 14, 2026 by
BloggerBust
Loading…
feat: add DeepEval + E2B sandbox SWE evaluation pipeline example
#2430
opened Jan 12, 2026 by
Ayush7614
Loading…
docs: add migration note for ConversationRelevancyMetric → TurnRelevancyMetric
#2428
opened Jan 11, 2026 by
YassinNouh21
Loading…
docs: fix incorrect import path for MMLUTask in benchmarks docs
#2427
opened Jan 11, 2026 by
YassinNouh21
Loading…
fix: map MIPROv2 trial history to AcceptedIteration schema to prevent…
#2425
opened Jan 9, 2026 by
Redtius
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.