Trade Safety Backend
K-pop 굿즈 거래 안전성 AI 분석 Python 패키지
주요 기능
- LLM 기반 거래글 분석
- 다국어 지원 (한국어 번역 및 뉘앙스 설명)
- 위험 신호 탐지 (결제, 판매자, 플랫폼, 가격, 콘텐츠)
- 시장가 대비 가격 분석
- Freemium 모델
설치
cd backend
poetry install
사용법
서비스 사용
from aioia_core.settings import OpenAIAPISettings
from trade_safety.service import TradeSafetyService
from trade_safety.settings import TradeSafetyModelSettings
openai_api = OpenAIAPISettings(api_key="sk-...")
model_settings = TradeSafetyModelSettings()
service = TradeSafetyService(
openai_api=openai_api,
model_settings=model_settings,
)
analysis = await service.analyze_trade("급처분 양도해요")
print(f"위험도: {analysis.risk_score}/100")
FastAPI 통합
from trade_safety.api.router import create_trade_safety_router
router = create_trade_safety_router(app_config)
app.include_router(router, prefix="/api/v2")
개발
poetry install
poetry run make test
poetry run make lint
poetry run make type-check
poetry run make format
환경 변수
| 변수명 | 필수 | 설명 |
|---|---|---|
OPENAI_API_KEY |
O | OpenAI API 키 |
TWITTER_BEARER_TOKEN |
X | Twitter/X URL 분석용 (미설정 시 URL 분석 불가) |
의존성
- aioia-core (공통 인프라)
- FastAPI, SQLAlchemy, Pydantic
- OpenAI API 키 필요
라이선스
Apache 2.0
Metadata
Release files for trade-safety 1.12.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| trade_safety-1.12.0.tar.gz | 21.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| trade_safety-1.12.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 49.1 kB
Release files / trade_safety-1.12.0.tar.gz
| Download URL | trade_safety-1.12.0.tar.gz |
|---|---|
| Size | 21.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d310e479efe33bc8d0ef63a2dbf277816df2601493735709e8bfe06db2cc4286
|
|
BLAKE2b-256 checksum How to use checksums |
279476e1e2e49a8f555cec7ca6ec5572b53a6975e898d138aa5309ee8813e6a7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 8, 2026.
Transparency logRelease files / trade_safety-1.12.0-py3-none-any.whl
| Download URL | trade_safety-1.12.0-py3-none-any.whl |
|---|---|
| Size | 27.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
923ccfc8e9604c51acf6fa07b91d120518166cf227175248df98ecb2d7d6cac7
|
|
BLAKE2b-256 checksum How to use checksums |
0a271af735dd704b9aa5d2d27c5b04e58f4005213c5917a5c6ce2f4f4c148603
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 8, 2026.
Transparency log