Files
hyungi_document_server/app/core/config.py
T
Hyungi Ahn 088966bf78 feat(extract): OCR 트리거 규칙 + extract_meta JSONB
스캔 PDF/이미지 자동 OCR 트리거 + 결과 품질 검증 + 1회 제한.

- extract_meta JSONB 컬럼 추가 (migration 134)
  ocr_attempted, ocr_reason, ocr_skip_reason, ocr_terminal, ocr_chars
- PDF OCR 트리거: total_chars < 300 또는 avg < 80 && total < 3000
- 이미지 자동 OCR: jpg/png/tiff/webp 등
- 품질 차등: 이미지 50자, PDF 200자 또는 페이지당 30자
- 상한: pages > 200 또는 file_size > 150MB → 스킵
- OCR 1회 제한: extract_meta.ocr_attempted로 재시도 방지
- extractor_version은 도구명만 (surya_ocr/pymupdf/kordoc)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-15 15:04:13 +09:00

124 lines
3.8 KiB
Python

"""설정 로딩 — config.yaml + credentials.env"""
import os
from pathlib import Path
import yaml
from pydantic import BaseModel
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
class AIConfig(BaseModel):
gateway_endpoint: str
primary: AIModelConfig
fallback: AIModelConfig
premium: AIModelConfig
embedding: AIModelConfig
vision: AIModelConfig
rerank: AIModelConfig
# Phase 3.5a: exaone classifier (optional — 없으면 score-only gate)
classifier: AIModelConfig | None = None
# Phase 3.5b: exaone verifier (optional — 없으면 grounding-only)
verifier: AIModelConfig | None = None
class Settings(BaseModel):
# DB
database_url: str = ""
# AI
ai: AIConfig | None = None
# NAS
nas_mount_path: str = "/documents"
nas_pkm_root: str = "/documents/PKM"
# 인증
jwt_secret: str = ""
totp_secret: str = ""
# kordoc
kordoc_endpoint: str = "http://kordoc-service:3100"
# OCR (Surya)
ocr_endpoint: str = "http://ocr-service:3200"
# 분류 체계
taxonomy: dict = {}
document_types: list[str] = []
def load_settings() -> Settings:
"""config.yaml + 환경변수에서 설정 로딩"""
# 환경변수 (docker-compose에서 주입)
database_url = os.getenv("DATABASE_URL", "")
jwt_secret = os.getenv("JWT_SECRET", "")
totp_secret = os.getenv("TOTP_SECRET", "")
kordoc_endpoint = os.getenv("KORDOC_ENDPOINT", "http://kordoc-service:3100")
ocr_endpoint = os.getenv("OCR_ENDPOINT", "http://ocr-service:3200")
# 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"]
ai_config = AIConfig(
gateway_endpoint=ai_raw.get("gateway", {}).get("endpoint", ""),
primary=AIModelConfig(**ai_raw["models"]["primary"]),
fallback=AIModelConfig(**ai_raw["models"]["fallback"]),
premium=AIModelConfig(**ai_raw["models"]["premium"]),
embedding=AIModelConfig(**ai_raw["models"]["embedding"]),
vision=AIModelConfig(**ai_raw["models"]["vision"]),
rerank=AIModelConfig(**ai_raw["models"]["rerank"]),
classifier=(
AIModelConfig(**ai_raw["models"]["classifier"])
if "classifier" in ai_raw.get("models", {})
else None
),
verifier=(
AIModelConfig(**ai_raw["models"]["verifier"])
if "verifier" in ai_raw.get("models", {})
else None
),
)
if "nas" in raw:
nas_mount = raw["nas"].get("mount_path", nas_mount)
nas_pkm = raw["nas"].get("pkm_root", nas_pkm)
taxonomy = raw.get("taxonomy", {}) if config_path.exists() and raw else {}
document_types = raw.get("document_types", []) if config_path.exists() and raw else []
return Settings(
database_url=database_url,
ai=ai_config,
nas_mount_path=nas_mount,
nas_pkm_root=nas_pkm,
jwt_secret=jwt_secret,
totp_secret=totp_secret,
kordoc_endpoint=kordoc_endpoint,
ocr_endpoint=ocr_endpoint,
taxonomy=taxonomy,
document_types=document_types,
)
settings = load_settings()