DEPT·F3 — RESEARCH & RETRIEVAL2026
CodebaseRAG
Hexagonal RAG over your own codebase, with a deterministic, eval-first core: ingest, query, and CI-gated retrieval evals.
The brief
RAG demos are easy; trustworthy RAG is not. This one pins retrieval quality with a golden Q/A set (≥40 pairs) and fails CI if mean recall@5 drops below its committed baseline.
What was built
Eval baseline gate in CI: recall@5 0.409 · MRR 0.231 · nDCG@5 0.277 (committed baseline, ADR-gated overrides).
Ports & adapters: pgvector (default) or Qdrant; Ollama or Anthropic embeddings & LLM; Langfuse observability.
Python 3.13 · Pydantic v2 · typer · FastAPI · ruff · black · mypy --strict.
Metrics
Impact
The result is an eval gate that blocks retrieval regressions before merge: quality is a CI-checked claim with a committed floor, not a demo vibe.