48 lines
4.0 KiB
Python
48 lines
4.0 KiB
Python
"""Suchraum fürs Training (make train): welche config-Parameter der Trainer bewegen darf.
|
|
|
|
Je Parameter: default (muss config spiegeln — Test prüft das), min/max (harte Ränder,
|
|
flow-sicher), step (Schrittweite der Koordinaten-Suche), kategorie (welches Ziel er
|
|
primär bewegt: qualitaet/auswahl/laufzeit/tokens). QA-/Detektor-Konstanten stehen
|
|
bewusst NICHT hier — die Messlatte darf nie Teil des Suchraums sein.
|
|
"""
|
|
|
|
PARAMS: dict[str, dict] = {
|
|
# Recherche / Inventar
|
|
"RESEARCH_THEMA_AGENTS": {"default": 5, "min": 2, "max": 8, "step": 1, "kategorie": "qualitaet", "fidelity": "voll"},
|
|
"RESEARCH_READERS": {"default": 2, "min": 1, "max": 3, "step": 1, "kategorie": "qualitaet", "fidelity": "voll"},
|
|
"RESEARCH_SECTION_CHARS": {"default": 12000, "min": 6000, "max": 24000, "step": 3000, "kategorie": "tokens", "fidelity": "voll"},
|
|
"DEDUP_PAIR_FLOOR": {"default": 0.6, "min": 0.45, "max": 0.8, "step": 0.05, "kategorie": "auswahl", "fidelity": "voll"},
|
|
"DEDUP_TITLE_AUTO": {"default": 0.95, "min": 0.9, "max": 0.99, "step": 0.01, "kategorie": "auswahl", "fidelity": "voll"},
|
|
"DEDUP_GLOBAL_FLOOR": {"default": 0.65, "min": 0.5, "max": 0.8, "step": 0.05, "kategorie": "auswahl", "fidelity": "voll"},
|
|
"DEDUP_PAIRS_CHUNK": {"default": 40, "min": 15, "max": 80, "step": 10, "kategorie": "laufzeit", "fidelity": "voll"},
|
|
"FILTER_CHUNK": {"default": 35, "min": 15, "max": 60, "step": 10, "kategorie": "laufzeit", "fidelity": "voll"},
|
|
"FILTER_RECHECK_PANEL": {"default": 3, "min": 1, "max": 5, "step": 1, "kategorie": "qualitaet", "fidelity": "voll"},
|
|
"CONSOLIDATION_PANEL": {"default": 3, "min": 1, "max": 5, "step": 1, "kategorie": "qualitaet", "fidelity": "voll"},
|
|
# Board 2, verschmolzene Calls (block_calls.py)
|
|
"GEN_PANEL": {"default": 2, "min": 1, "max": 3, "step": 1, "kategorie": "qualitaet", "fidelity": "board2"},
|
|
"VERIFY_PANEL": {"default": 2, "min": 1, "max": 3, "step": 1, "kategorie": "qualitaet", "fidelity": "board2"},
|
|
"ART_SPLIT_SUBS": {"default": 20, "min": 10, "max": 40, "step": 5, "kategorie": "laufzeit", "fidelity": "board2"},
|
|
# Embedding-Schwellen (Auswahl-Kern)
|
|
"SUB_VARIANT_COS": {"default": 0.90, "min": 0.85, "max": 0.96, "step": 0.01, "kategorie": "auswahl", "fidelity": "board2"},
|
|
"SEED_COVER_COS": {"default": 0.80, "min": 0.7, "max": 0.9, "step": 0.02, "kategorie": "auswahl", "fidelity": "board2"},
|
|
"SUB_DUP_KANDIDAT_COS": {"default": 0.75, "min": 0.65, "max": 0.85, "step": 0.02, "kategorie": "auswahl", "fidelity": "board2"},
|
|
"EMBEDDING_BLOCK_FLOOR": {"default": 0.5, "min": 0.35, "max": 0.65, "step": 0.05, "kategorie": "auswahl", "fidelity": "voll"},
|
|
"CROSS_CHUNK_PAARE": {"default": 40, "min": 15, "max": 80, "step": 10, "kategorie": "laufzeit", "fidelity": "board2"},
|
|
# Guide
|
|
"GATE_FIX_MIN": {"default": 3, "min": 1, "max": 6, "step": 1, "kategorie": "qualitaet", "fidelity": "board2"},
|
|
"WRITER_SPLIT_SUBS": {"default": 30, "min": 15, "max": 45, "step": 5, "kategorie": "qualitaet", "fidelity": "board2"},
|
|
# Engine / Kosten
|
|
"CONSENSUS_GRACE": {"default": 300, "min": 0, "max": 600, "step": 60, "kategorie": "laufzeit", "fidelity": "board2"},
|
|
"MAX_RESTARTS": {"default": 2, "min": 1, "max": 3, "step": 1, "kategorie": "laufzeit", "fidelity": "board2"},
|
|
"EVIDENCE_BUDGET_CHARS": {"default": 48000, "min": 16000, "max": 64000, "step": 8000, "kategorie": "tokens", "fidelity": "board2"},
|
|
"QUELLE_RELEVANZ_CHUNK": {"default": 12, "min": 6, "max": 24, "step": 3, "kategorie": "laufzeit", "fidelity": "voll"},
|
|
}
|
|
|
|
|
|
def schritte(name: str) -> tuple[float, float]:
|
|
"""(wert_runter, wert_hoch) je einen step von default, an die Ränder geklemmt."""
|
|
p = PARAMS[name]
|
|
lo = max(p["min"], round(p["default"] - p["step"], 4))
|
|
hi = min(p["max"], round(p["default"] + p["step"], 4))
|
|
return lo, hi
|