feat(rag): hybrid FTS+vector retrieval and multi-format ingestion — name-your-tool questions find the right document

2026-08-22 01:27:02 -04:00
parent 2f738a7f19
commit 7e8d14702e
36 changed files with 2018 additions and 290 deletions
@@ -82,6 +82,12 @@ def app_server(mock_llm: int) -> Iterator[str]:
        if USE_REAL_LLM
        else f"http://127.0.0.1:{mock_llm}/v1"
    )
+    # The E2E mock's token-overlap embeddings have their own score
+    # distribution (phase 09) — the app under test gets the mock-calibrated
+    # threshold so every story suite keeps its deterministic gate behavior.
+    # The production default stays 0.62 (re-tuned against the real
+    # `embed` model's 0.41–0.84 cosine range, PLAN A8).
+    env["BOR_RELEVANCE_THRESHOLD"] = "0.30"
    env.setdefault("BOR_DATABASE_URL", "postgresql+psycopg://reese:reese@localhost:5432/brain_of_reese")
    proc = subprocess.Popen(
        [sys.executable, "-m", "uvicorn", "app.main:app",