Skip to content

Allow setting embedding model in AnswerCorrectness#162

Merged
Stephen Belanger (Qard) merged 1 commit into
mainfrom
configurable-answer-correctness-embedding-model
Jan 14, 2026
Merged

Allow setting embedding model in AnswerCorrectness#162
Stephen Belanger (Qard) merged 1 commit into
mainfrom
configurable-answer-correctness-embedding-model

Conversation

@Qard
Copy link
Copy Markdown
Contributor

Fixes #140

@github-actions
Copy link
Copy Markdown

github-actions Bot commented Jan 13, 2026

Braintrust eval report

Autoevals (configurable-answer-correctness-embedding-model-1768353136)

Score Average Improvements Regressions
NumericDiff 71.5% (-1pp) 2 🟢 4 🔴
Time_to_first_token 1.37tok (+0.06tok) 40 🟢 79 🔴
Llm_calls 1.55 (+0) - -
Tool_calls 0 (+0) - -
Errors 0 (+0) - -
Llm_errors 0 (+0) - -
Tool_errors 0 (+0) - -
Prompt_tokens 279.25tok (+0tok) - -
Prompt_cached_tokens 0tok (+0tok) - -
Prompt_cache_creation_tokens 0tok (+0tok) - -
Completion_tokens 19.3tok (+0tok) - -
Completion_reasoning_tokens 0tok (+0tok) - -
Total_tokens 298.54tok (+0tok) - -
Estimated_cost 0$ (+0$) - -
Duration 3.02s (-0.01s) 139 🟢 80 🔴
Llm_duration 2.62s (-0.07s) 91 🟢 28 🔴

Comment thread js/ragas.ts
Comment thread js/ragas.test.ts Outdated
@Qard Stephen Belanger (Qard) force-pushed the configurable-answer-correctness-embedding-model branch 2 times, most recently from 374cba4 to c5c2ac7 Compare January 13, 2026 21:20
@Qard Stephen Belanger (Qard) force-pushed the configurable-answer-correctness-embedding-model branch 2 times, most recently from 40898ef to 5b4e619 Compare January 14, 2026 01:11
@Qard Stephen Belanger (Qard) merged commit 71a3cf4 into main Jan 14, 2026
14 checks passed
@Qard Stephen Belanger (Qard) deleted the configurable-answer-correctness-embedding-model branch January 14, 2026 03:37
@github-actions
Copy link
Copy Markdown

github-actions Bot commented Jan 14, 2026

Braintrust eval report

Autoevals (main-1768361867)

Score Average Improvements Regressions
NumericDiff 71.5% (-1pp) 2 🟢 4 🔴
Time_to_first_token 1.37tok (+0.05tok) 42 🟢 74 🔴
Llm_calls 1.55 (+0) - -
Tool_calls 0 (+0) - -
Errors 0 (+0) - -
Llm_errors 0 (+0) - -
Tool_errors 0 (+0) - -
Prompt_tokens 279.25tok (+0tok) - -
Prompt_cached_tokens 0tok (+0tok) - -
Prompt_cache_creation_tokens 0tok (+0tok) - -
Completion_tokens 19.3tok (+0tok) - -
Completion_reasoning_tokens 0tok (+0tok) - -
Total_tokens 298.54tok (+0tok) - -
Estimated_cost 0$ (+0$) - -
Duration 2.73s (+0.27s) 86 🟢 132 🔴
Llm_duration 2.8s (+0.06s) 46 🟢 72 🔴

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Set embedding model in AnswerCorrectness scorer

2 participants