Skip to content

Pull requests: vibrantlabsai/ragas

New pull request New
95 Open 1,342 Closed
95 Open 1,342 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat: add evidence triplet score metric
#2728 opened May 17, 2026 by SeCuReDmE-main-dev Loading…
2 tasks done
3
security: fix shell injection vulnerability in claude-docs-check workflow
#2726 opened May 16, 2026 by sgwrld-999 Loading…
fix: support dotted and multi-digit model versions in is_reasoning_mo…
#2725 opened May 16, 2026 by Siddhart-Yadav Loading…
1
1
fix: AnswerCorrectness delegates factuality to FactualCorrectness (#1958)
#2724 opened May 14, 2026 by munnasuprathik Loading…
1
1
fix: clip ResponseRelevancy/AnswerRelevancy score to [0, 1] (#2088)
#2723 opened May 14, 2026 by munnasuprathik Loading…
1
1
fix: respect underlying LLM's temperature when caller doesn't set one (#1976)
#2722 opened May 14, 2026 by munnasuprathik Loading…
1
1
fix: route SimpleCriteriaScore/AspectCritic init through definition setter (#1944)
#2721 opened May 14, 2026 by munnasuprathik Loading…
1
1
fix(examples): guard against IndexError on empty LLM choices list
#2720 opened May 14, 2026 by qizwiz Loading…
2
Add bounded async batch execution controls needs-doc-update PR may need documentation updates
#2719 opened May 13, 2026 by islam731 Loading…
2
fix(metrics): use recall TP (reference claims supported by response) in FactualCorrectness recall mode
#2718 opened May 13, 2026 by xodn348 Loading…
2 tasks done
1
1
token optimisation
#2717 opened May 12, 2026 by apurrrva Loading…
2 tasks
token optimisation
#2716 opened May 12, 2026 by apurrrva Loading…
2 tasks
token optimisation
#2715 opened May 12, 2026 by apurrrva Loading…
2 tasks
token optimisation
#2714 opened May 12, 2026 by apurrrva Loading…
2 tasks
token optimisation
#2713 opened May 12, 2026 by apurrrva Loading…
2 tasks
token optimisation
#2712 opened May 12, 2026 by apurrrva Loading…
2 tasks
token optimisation
#2711 opened May 12, 2026 by apurrrva Loading…
2 tasks
token optimisation
#2710 opened May 12, 2026 by apurrrva Loading…
2 tasks
fix: unsupported parameters mapping for latest OpenAI model variants in InstructorLLM
#2709 opened May 11, 2026 by Samia35-2973 Loading…
1
1
fix: use chunk summary when filtering prechunked nodes
#2707 opened May 10, 2026 by Raditya0902 Loading…
2 tasks done
1
1
fix: omit default top_p for Anthropic instructor LLM
#2706 opened May 10, 2026 by Raditya0902 Loading…
2 tasks done
1
1
feat: add exact-match financial grounding metricCreate financial_grounding.py
#2705 opened May 10, 2026 by Vivek76760 Loading…
2
fix: compute factual correctness recall from reference coverage
#2704 opened May 10, 2026 by Raditya0902 Loading…
1
fix: update Langfuse trace field names
#2703 opened May 10, 2026 by Raditya0902 Loading…
1
fix(metrics/summarization): return NaN instead of dividing by zero on empty answers
#2702 opened May 9, 2026 by Spectual Loading…
1
ProTip! Follow long discussions with comments:>50.