fix(video-render): Veo Vertex AI → Gemini API (T10 follow-up)

박재오 발견: Veo는 Gemini API key 단일로 충분 (ai.google.dev).
Vertex AI의 GCP project + service account JSON + GCS bucket 셋업 불필요.

변경:
- providers/veo.py: generativelanguage.googleapis.com/v1beta endpoint
  + x-goog-api-key 헤더 + response.generateVideoResponse.generatedSamples[0].video.uri
- .env.example: GOOGLE_PROJECT_ID/LOCATION/GCS_BUCKET/SA_JSON 4 변수 → GEMINI_API_KEY 1개
- docker-compose: GCP 4 env + SA JSON volume mount 제거, GEMINI_API_KEY 추가
- requirements.txt: google-cloud-storage 제거 (requests만 사용)

박재오 측 영향: /etc/webai/gcp-sa.json 더미 파일 + GCP_SA_JSON_HOST_PATH env 무관.
GEMINI_API_KEY 1개만 발급하여 .env에 추가하면 됨.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-20 02:32:11 +09:00
parent 4db0551d33
commit 8aa3f1c3b2
4 changed files with 54 additions and 101 deletions

View File

@@ -4,7 +4,6 @@ requests==2.32.3
redis>=5.0
httpx>=0.27
openai>=1.50.0
google-cloud-storage>=2.18.0
pytest>=8.0
pytest-asyncio>=0.24
respx>=0.21