Anas Khan b4996ae3c4 fix: divide DocumentMAPEvaluator average precision by all relevant documents (#12255) ...

Signed-off-by: Anas Khan <83116240+anxkhn@users.noreply.github.com>
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-08-10 11:29:00 +00:00

..

__init__.py

…

answer_exact_match.py

…

context_relevance.py

fix: add missing output sockes to LLM evaluators (#12049)

2026-07-17 15:43:00 +02:00

document_map.py

fix: divide DocumentMAPEvaluator average precision by all relevant documents (#12255)

2026-08-10 11:29:00 +00:00

document_mrr.py

…

document_ndcg.py

fix: cap DocumentNDCGEvaluator score at 1.0 for duplicate retrievals (#11959)

2026-07-27 07:49:28 +00:00

document_recall.py

fix: DocumentRecallEvaluator single_hit reports false 1.0 recall on missing comparison values (#11951)

2026-07-17 08:11:16 +00:00

faithfulness.py

fix: add missing output sockes to LLM evaluators (#12049)

2026-07-17 15:43:00 +02:00

llm_evaluator.py

feat: add internal tracing to components that use chat generators (#12075)

2026-07-21 09:10:35 +00:00

sas_evaluator.py

test: running docstrings code snippets which generate API docs (#10993)

2026-04-01 11:39:35 +00:00