Skip to content

Releases: quotient-ai/judges

v0.1.1 - Fix prompt for RaftCorrectness

25 Jun 21:59
89e6f48
Compare
Choose a tag to compare

What's Changed

  • Update RaftCorrectness judge to use f-string for user_prompt by @fjlanasawhoop in #28

New Contributors

Full Changelog: v0.1.0...v0.1.1

v0.1.0 - Updated LLM client and docs

04 Jun 20:16
Compare
Choose a tag to compare

What's Changed

NOTE: this is a breaking change in that you must pass the provider along with the model name, whereas previously you could pass just the model name for some providers.

Full Changelog: v0.0.12...v0.1.0

v0.0.12 - Add `judges` CLI

23 May 03:21
74b8c56
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.0.11...v0.0.12

v0.0.11 - Fix formatting in `ZeroShotClassifier` and add `HypoEval`

21 May 14:09
ca82967
Compare
Choose a tag to compare

What's Changed

  • Fix erroneous format string in ZeroShotClassifier by @alewarne in #23
  • Add HypoEval evaluators to judges.graders by @itea1001 in #24

New Contributors

Full Changelog: v0.0.10...v0.0.11

v0.0.10

14 May 16:55
77a4457
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.0.9...v0.0.10

v0.0.9 - Fix broken imports

14 May 16:41
e599247
Compare
Choose a tag to compare

What's Changed

New Contributors

Full Changelog: v0.0.8...v0.0.9

v0.0.8 - Loosen dependencies and add examples

20 Mar 00:11
65b04f3
Compare
Choose a tag to compare

What's Changed

  • Loosen Version Restrictions by @njbrake in #15
  • enhancements: examples directory with example files to try out, and minor fixups by @pk-lit in #16

New Contributors

Full Changelog: v0.0.7...v0.0.8

v0.0.7 — ReliableCIRelevance prompt fix

11 Mar 15:45
5a9404d
Compare
Choose a tag to compare

Fixes a bug in the ReliableCIRelevance judge prompt #14 by @jimthompson5802

Bug fix for integer conversions

07 Feb 21:05
e584114
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.0.5...v0.0.6

v0.0.5 - Addition of `AutoJudge`

20 Dec 19:56
bd1261a
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.0.4...v0.0.5