rock 853c78bbdb feat(O4): relevance judge with Prometheus metrics ...

- RelevanceJudge: threshold-based relevance evaluation
- evaluate(): single query-result pair scoring
- evaluate_batch(): batch eval with precision/recall/F1
- Tracks: evals total, relevant/irrelevant, score histogram
- Updates precision/recall/F1 gauges per batch
- 4 unit tests passing
- Metrics: R1-R9 (9 metrics instrumented)

2026-09-13 21:38:27 +09:00

..

mem-chunk

Implement M3.6.1: DocCorpusSource with heading-boundary chunking (196 tests)

2026-08-23 09:42:09 -07:00

mem-cli

feat(O4): relevance judge with Prometheus metrics

2026-09-13 21:38:27 +09:00

mem-core

feat: LLM entity + fact extraction pipeline (Zep paper alignment) (#48)

2026-09-11 01:11:15 +00:00

mem-ingest

feat: LLM entity + fact extraction pipeline (Zep paper alignment) (#48)

2026-09-11 01:11:15 +00:00

mem-llm

fix: log raw embedding response before parsing for debugging

2026-09-13 21:27:55 +09:00

mem-store

feat: LLM entity + fact extraction pipeline (Zep paper alignment) (#48)

2026-09-11 01:11:15 +00:00