feat: setup dataset enrichment app codebase and scripts

backend/main.py

@@ -0,0 +1,75 @@
+"""FastAPI server for the dataset enrichment platform.
+
+Run it with:  .venv/bin/uvicorn backend.main:app --port 8000
+or:           docker compose up
+
+Routes live in `backend/api/`, one module per domain; this file only wires them
+together and owns startup.
+"""
+
+import os
+import shutil
+from contextlib import asynccontextmanager
+
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+from backend import config, db, jobs
+from backend.api import batches, jobs as job_routes, models, projects, review
+
+
+@asynccontextmanager
+async def lifespan(_app: FastAPI):
+    config.ensure_dirs()
+    db.migrate()
+    from backend import projects as project_store
+    project_store.ensure_seed_project()
+    interrupted = jobs.recover()
+    if interrupted:
+        print(f"[startup] closed {interrupted} job(s) interrupted by the last restart")
+    yield
+
+
+app = FastAPI(title="Dataset Enrichment", lifespan=lifespan)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=config.CORS_ORIGINS,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.include_router(projects.router)
+app.include_router(batches.router)
+app.include_router(review.router)
+app.include_router(models.router)
+app.include_router(job_routes.router)
+
+
+@app.get("/api/health")
+def health() -> dict:
+    import torch
+    from backend import hardware
+
+    free_vram = hardware.free_vram_gb()
+    needed = hardware.SAM3_RESIDENT_GB + hardware.SAM3_HEADROOM_GB
+
+    return {
+        "device": "cuda" if torch.cuda.is_available() else "cpu",
+        "gpu": torch.cuda.get_device_name(0) if torch.cuda.is_available() else None,
+        "vram_free_gb": free_vram,
+        "sam3_ready": free_vram >= needed or _engine_loaded(),
+        "ffmpeg": shutil.which("ffmpeg") is not None,
+        "ffprobe": shutil.which("ffprobe") is not None,
+        "hf_token": bool(os.environ.get("HUGGING_FACE_HUB_TOKEN")),
+        "db": db.healthy(),
+        "data_dir": config.DATA_DIR,
+        "video_root": config.VIDEO_ROOT,
+        "model_loaded": _engine_loaded(),
+    }
+
+
+
+def _engine_loaded() -> bool:
+    from backend.sam3_engine import engine_is_loaded
+
+    return engine_is_loaded()