svrnty-vision/.env.example
Svrnty 2a90c3f884 feat: initial scaffold — FastAPI shell + stub vision routers
Phase 4a of the BTE refactor (audit 2026-05-24 §3 V). svrnty-vision is a
sovereign HTTP gateway in front of four vision capabilities — VLM (Spark 2
Qwen3-VL), FLUX image gen (Spark 1 ComfyUI), palette extraction, and
background removal. This commit lays only the scaffold: FastAPI app,
/healthz, four 501-stub routers, pydantic-settings config, pytest smoke.

Real implementations land in Phase 4b. BTE code is untouched in 4a.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 13:25:57 -04:00

19 lines
525 B
Plaintext

# svrnty-vision configuration
#
# svrnty-vision is an HTTP gateway. It does NOT run ML models in-process.
# It calls existing Spark services (FLUX, Qwen3-VL) over HTTP.
# Server
SVRNTY_VISION_HOST=0.0.0.0
SVRNTY_VISION_PORT=8090
# Spark 1 — FLUX image generation (ComfyUI HTTP endpoint)
SPARK1_FLUX_URL=http://spark1.lan:8188
# Spark 2 — Qwen3-VL via vLLM (OpenAI-compatible HTTP endpoint)
SPARK2_VLM_URL=http://spark2.lan:8000
SPARK2_VLM_MODEL=Qwen/Qwen3-VL-7B-Instruct
# Defaults
VISION_REQUEST_TIMEOUT_SECONDS=120