hyungi
5cb8d04b50
P1 of family-adaptive-bengio (Mac mini 4-lever bundle). AIModelConfig: temperature/top_p Optional fields (None = server default). _request OpenAI/MLX branch payload 조건부 sampling 인자 삽입. config.yaml ai.models.triage.temperature=0.0 (deterministic) / primary temperature=0.3 top_p=0.9 (summary creativity). fallback (Anthropic) branch 미적용 — 별 plan 범위. caller 코드 무변경. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
261 lines
10 KiB
Python
261 lines
10 KiB
Python
"""설정 로딩 — config.yaml + credentials.env"""
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
import yaml
|
|
from pydantic import BaseModel
|
|
|
|
|
|
class UploadConfig(BaseModel):
|
|
max_bytes: int = 100_000_000
|
|
content_length_slack_ratio: float = 1.05
|
|
stream_chunk_bytes: int = 1_048_576
|
|
# orphan cleanup (`*.uploading` — 크래시/abort 후 잔존물)
|
|
orphan_max_age_sec: int = 3600
|
|
cleanup_warn_threshold: int = 10
|
|
|
|
|
|
class AIModelConfig(BaseModel):
|
|
endpoint: str
|
|
model: str
|
|
max_tokens: int = 4096
|
|
timeout: int = 60
|
|
daily_budget_usd: float | None = None
|
|
require_explicit_trigger: bool = False
|
|
# B-0: 4B/26B 에 부여한 실사용 컨텍스트 상한 (char). triage=120k, primary=260k.
|
|
# classify_worker 가 에스컬레이션 판정 시 참고. 0/None 이면 상한 무시.
|
|
context_char_limit: int | None = None
|
|
# P1 of family-adaptive-bengio (2026-05-23): config-driven sampling profile.
|
|
# None = MLX/OpenAI server default. Anthropic branch 는 미적용 (별 plan 범위).
|
|
temperature: float | None = None
|
|
top_p: float | None = None
|
|
|
|
|
|
class DeepSummaryBacklogConfig(BaseModel):
|
|
"""B-1 R2 — deep_summary enqueue 폭발 억제 임계치."""
|
|
ratio_threshold: float = 0.3 # 지난 window 의 deep_n/classify_n
|
|
pending_threshold: int = 5 # deep_summary pending+processing
|
|
window_minutes: int = 30
|
|
|
|
|
|
class SearchAskBackendConfig(BaseModel):
|
|
"""PR-MacBook-RAG-Backend-1: /api/search/ask backend dispatcher.
|
|
|
|
backend 미지정 = Gemma Mac mini (settings.ai.primary 경로 그대로).
|
|
backend="qwen-macbook" 명시 opt-in = MacBook M5 Max mlx-vlm.server.
|
|
MacBook unavailable 시 503 + error_reason=macbook_unavailable (자동 fallback 없음).
|
|
"""
|
|
|
|
macmini_url: str = "http://100.76.254.116:8801"
|
|
macbook_url: str = "http://100.118.112.84:8810"
|
|
macbook_model: str = "mlx-community/Qwen3.6-27B-8bit"
|
|
timeout_connect_s: int = 1
|
|
timeout_read_s: int = 30
|
|
|
|
|
|
class SearchAskReactConfig(BaseModel):
|
|
"""PR-DocSrv-Ask-ToolCalling-ReAct-1: /api/search/ask/react ReAct loop.
|
|
|
|
qwen-macbook only (endpoint 자체가 implicit opt-in). G0-2 counter semantics:
|
|
max_tool_rounds=2 → LLM 호출 최대 3회 (tool round 2 + final 1), search 실행 최대 2회.
|
|
"""
|
|
|
|
enabled: bool = True
|
|
max_tool_rounds: int = 2
|
|
search_tool_limit: int = 5
|
|
search_tool_mode: str = "hybrid"
|
|
|
|
|
|
class SearchAskConfig(BaseModel):
|
|
backend: SearchAskBackendConfig = SearchAskBackendConfig()
|
|
react: SearchAskReactConfig = SearchAskReactConfig()
|
|
|
|
|
|
class SearchConfig(BaseModel):
|
|
ask: SearchAskConfig = SearchAskConfig()
|
|
|
|
|
|
class AIConfig(BaseModel):
|
|
gateway_endpoint: str
|
|
# B-0: 3-tier routing. triage/primary = Mac mini 26B MLX (PR #20 endpoint 통합). fallback = Claude Sonnet 4 API.
|
|
triage: AIModelConfig
|
|
primary: AIModelConfig
|
|
fallback: AIModelConfig
|
|
premium: AIModelConfig
|
|
embedding: AIModelConfig
|
|
rerank: AIModelConfig
|
|
# Phase 3.5a: answerability classifier (optional — 없으면 score-only gate). PR #20 이후 Mac mini 26B MLX endpoint (initial = exaone3.5).
|
|
classifier: AIModelConfig | None = None
|
|
# Phase 3.5b: semantic verifier (optional — 없으면 grounding-only). PR #20 이후 Mac mini 26B MLX endpoint (initial = exaone3.5).
|
|
verifier: AIModelConfig | None = None
|
|
# Legacy: vision 슬롯 (현재 사용처 0 — Document Server 는 OCR/STT 별도 서비스).
|
|
# 제거 진행 중이므로 optional 로 관대한 로딩 유지.
|
|
vision: AIModelConfig | None = None
|
|
# B-1 R2: backlog guard 임계치
|
|
deep_summary_backlog: DeepSummaryBacklogConfig = DeepSummaryBacklogConfig()
|
|
|
|
|
|
class Settings(BaseModel):
|
|
# DB
|
|
database_url: str = ""
|
|
|
|
# AI
|
|
ai: AIConfig | None = None
|
|
|
|
# PR-MacBook-RAG-Backend-1: /api/search/ask backend dispatcher
|
|
search: SearchConfig = SearchConfig()
|
|
|
|
# NAS
|
|
nas_mount_path: str = "/documents"
|
|
nas_pkm_root: str = "/documents/PKM"
|
|
|
|
# 인증
|
|
jwt_secret: str = ""
|
|
totp_secret: str = ""
|
|
|
|
# Phase 3.5: eval runner shared secret — X-Source=eval / X-Eval-Case-Id 헤더 신뢰 검증.
|
|
# 비어있으면 모든 eval 헤더 거부 (부재 = 비활성).
|
|
eval_runner_token: str = ""
|
|
|
|
# kordoc
|
|
kordoc_endpoint: str = "http://kordoc-service:3100"
|
|
|
|
# OCR (Surya)
|
|
ocr_endpoint: str = "http://ocr-service:3200"
|
|
|
|
# STT (faster-whisper, §3)
|
|
stt_endpoint: str = "http://stt-service:3300"
|
|
|
|
# §3 file_watcher: Roon 음원 경로 (prefix match 로 skip).
|
|
# 빈 문자열이면 skip 없음. 예: "/documents/PKM/../Music/roon-library" 또는
|
|
# NFS 경유 별도 마운트된 Roon 라이브러리.
|
|
roon_library_path: str = ""
|
|
|
|
# KGS Code 등 외부 작성 마크다운 자료 추가 스캔 경로 (PKM 상대 경로, 쉼표 구분).
|
|
# env: ADDITIONAL_WATCH_TARGETS=Knowledge/Industrial_Safety/가스기사/KGS_Code,...
|
|
# 모두 expected_category="library" 로 처리 (md/pdf/docx 등 문서 확장자만 수락).
|
|
# Inbox/Recordings/Videos 기본 스캔 외에 추가만 허용.
|
|
additional_watch_targets: list[str] = []
|
|
|
|
# 분류 체계
|
|
taxonomy: dict = {}
|
|
document_types: list[str] = []
|
|
|
|
# 업로드 한도 (authoritative policy)
|
|
upload: UploadConfig = UploadConfig()
|
|
|
|
# PR-MacMini-Derived-Worker-1: study explanation owner = Mac mini
|
|
# GPU 측은 false 로 설정 (.env), explanation 분기 skip guard 트리거.
|
|
study_explanation_enabled: bool = True
|
|
|
|
# internal endpoint Bearer token (Mac mini derived-worker 호출용)
|
|
internal_worker_token: str = ""
|
|
|
|
|
|
def load_settings() -> Settings:
|
|
"""config.yaml + 환경변수에서 설정 로딩"""
|
|
# 환경변수 (docker-compose에서 주입)
|
|
database_url = os.getenv("DATABASE_URL", "")
|
|
study_explanation_enabled = os.getenv("STUDY_EXPLANATION_ENABLED", "true").lower() in ("1", "true", "yes")
|
|
internal_worker_token = os.getenv("INTERNAL_WORKER_TOKEN", "")
|
|
jwt_secret = os.getenv("JWT_SECRET", "")
|
|
totp_secret = os.getenv("TOTP_SECRET", "")
|
|
eval_runner_token = os.getenv("EVAL_RUNNER_TOKEN", "")
|
|
kordoc_endpoint = os.getenv("KORDOC_ENDPOINT", "http://kordoc-service:3100")
|
|
ocr_endpoint = os.getenv("OCR_ENDPOINT", "http://ocr-service:3200")
|
|
stt_endpoint = os.getenv("STT_ENDPOINT", "http://stt-service:3300")
|
|
roon_library_path = os.getenv("ROON_LIBRARY_PATH", "")
|
|
|
|
# ADDITIONAL_WATCH_TARGETS — 쉼표 구분 (공백 제거)
|
|
awt_raw = os.getenv("ADDITIONAL_WATCH_TARGETS", "")
|
|
additional_watch_targets = [p.strip() for p in awt_raw.split(",") if p.strip()]
|
|
|
|
# config.yaml — Docker 컨테이너 내부(/app/config.yaml) 또는 프로젝트 루트
|
|
config_path = Path("/app/config.yaml")
|
|
if not config_path.exists():
|
|
config_path = Path(__file__).parent.parent.parent / "config.yaml"
|
|
ai_config = None
|
|
nas_mount = "/documents"
|
|
nas_pkm = "/documents/PKM"
|
|
|
|
if config_path.exists():
|
|
with open(config_path) as f:
|
|
raw = yaml.safe_load(f)
|
|
|
|
if "ai" in raw:
|
|
ai_raw = raw["ai"]
|
|
models = ai_raw.get("models", {})
|
|
# B-0: triage 는 config.yaml 에 없을 수도 있는 신규 슬롯. 구버전 호환을 위해
|
|
# 없으면 fallback 를 triage 로 대체 (동일 모델 재사용).
|
|
triage_raw = models.get("triage") or models.get("fallback")
|
|
if triage_raw is None:
|
|
raise ValueError("config.yaml: ai.models.triage (or fallback) required")
|
|
ai_config = AIConfig(
|
|
gateway_endpoint=ai_raw.get("gateway", {}).get("endpoint", ""),
|
|
triage=AIModelConfig(**triage_raw),
|
|
primary=AIModelConfig(**models["primary"]),
|
|
fallback=AIModelConfig(**models["fallback"]),
|
|
premium=AIModelConfig(**models["premium"]),
|
|
embedding=AIModelConfig(**models["embedding"]),
|
|
rerank=AIModelConfig(**models["rerank"]),
|
|
vision=(AIModelConfig(**models["vision"]) if "vision" in models else None),
|
|
classifier=(
|
|
AIModelConfig(**models["classifier"]) if "classifier" in models else None
|
|
),
|
|
verifier=(
|
|
AIModelConfig(**models["verifier"]) if "verifier" in models else None
|
|
),
|
|
deep_summary_backlog=DeepSummaryBacklogConfig(
|
|
**ai_raw.get("deep_summary_backlog", {})
|
|
),
|
|
)
|
|
|
|
if "nas" in raw:
|
|
nas_mount = raw["nas"].get("mount_path", nas_mount)
|
|
nas_pkm = raw["nas"].get("pkm_root", nas_pkm)
|
|
|
|
search_cfg = SearchConfig()
|
|
if config_path.exists() and raw and "search" in raw:
|
|
ask_raw = (raw.get("search") or {}).get("ask", {}) or {}
|
|
sb = ask_raw.get("backend", {}) or {}
|
|
sr = ask_raw.get("react", {}) or {}
|
|
search_cfg = SearchConfig(
|
|
ask=SearchAskConfig(
|
|
backend=SearchAskBackendConfig(**sb),
|
|
react=SearchAskReactConfig(**sr),
|
|
)
|
|
)
|
|
|
|
taxonomy = raw.get("taxonomy", {}) if config_path.exists() and raw else {}
|
|
document_types = raw.get("document_types", []) if config_path.exists() and raw else []
|
|
upload_cfg = (
|
|
UploadConfig(**raw["upload"])
|
|
if config_path.exists() and raw and "upload" in raw
|
|
else UploadConfig()
|
|
)
|
|
|
|
return Settings(
|
|
database_url=database_url,
|
|
ai=ai_config,
|
|
search=search_cfg,
|
|
nas_mount_path=nas_mount,
|
|
nas_pkm_root=nas_pkm,
|
|
jwt_secret=jwt_secret,
|
|
totp_secret=totp_secret,
|
|
eval_runner_token=eval_runner_token,
|
|
kordoc_endpoint=kordoc_endpoint,
|
|
ocr_endpoint=ocr_endpoint,
|
|
stt_endpoint=stt_endpoint,
|
|
roon_library_path=roon_library_path,
|
|
additional_watch_targets=additional_watch_targets,
|
|
taxonomy=taxonomy,
|
|
document_types=document_types,
|
|
upload=upload_cfg,
|
|
study_explanation_enabled=study_explanation_enabled,
|
|
internal_worker_token=internal_worker_token,
|
|
)
|
|
|
|
|
|
settings = load_settings()
|