FastAPI service in infra/media-worker implementing every MediaInferenceProvider operation behind HTTP API v1, plus capabilities. Bearer auth, MEDIA_ROOT realpath enforcement, strict request schemas, cancellation on disconnect, GPU/CPU gates with 503 overflow, input size/duration limits, lazy SHA256-pinned model downloads, fail-closed redaction with atomic output, offline pytest suite with fake backends, CPU/CUDA/ROCm Dockerfile and a license review of every model. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0138YqDj3ttfayRwuMKKrqVj
11 lines
330 B
Plaintext
11 lines
330 B
Plaintext
# Core: HTTP API, ffmpeg-driven operations, OpenCV, scene detection, audio features.
|
|
# Accelerator-specific ML wheels live in requirements-ml-<accelerator>.txt.
|
|
fastapi==0.142.2
|
|
uvicorn[standard]==0.54.0
|
|
pydantic==2.13.5
|
|
numpy==2.4.6
|
|
opencv-python-headless==4.13.0.92
|
|
scenedetect-headless==0.7.1
|
|
librosa==0.11.0
|
|
soundfile==0.14.0
|