2 Commits

Include renames

Author	SHA1	Message	Date
Chris CoutinhoandClaude Opus 4.8	b134b2c539	docs(adr): correct stale statuses for shipped ADRs ... Audit of all ADR status fields found several marked Proposed/Draft that are in fact implemented. Correct them with an evidence pointer; also fix the ADR-025 title that read "ADR-024". - ADR-007 background vector sync: Proposed -> Accepted/implemented - ADR-008 MCP sampling: Proposed -> Accepted/implemented - ADR-009 semantic.read scope: Proposed -> Accepted/implemented - ADR-010 webhook-based vector sync: Proposed -> Accepted/implemented - ADR-012 unified multi-algorithm search: Proposed -> Accepted/implemented - ADR-013 RAG evaluation: Proposed -> Partially implemented - ADR-018 Nextcloud settings-UI app: Proposed -> Accepted/implemented - ADR-025 dynaconf: Proposed -> Accepted/implemented; fix title typo (ADR-024 -> ADR-025) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-06-14 12:00:54 +02:00
Chris CoutinhoandClaude	c272ddd82d	feat: implement RAG evaluation framework with CLI tooling ... - Add ADR-013 documenting RAG evaluation architecture - Implement two-part evaluation: Context Recall (retrieval) + Answer Correctness (generation) - Create Click CLI for ground truth generation and corpus upload - Add pytest fixtures and tests for retrieval/generation quality - Use BeIR/nfcorpus dataset with 5 selected test queries - Support Ollama and Anthropic LLM providers - Generate synthetic ground truth answers offline - Add comprehensive documentation in tests/rag_evaluation/README.md The framework separates one-time setup (generate/upload) from test execution, making tests much faster (~6-12 min vs ~15-25 min per run). Tests are manual only (not in CI) and require external LLM access. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-15 23:11:21 +01:00