oval
df8d0d6b74
- docker-compose.yml: default TORCH_DEVICE=cpu, PORT=8001, named volumes for model cache (marker-cache) and results (marker-results) with :Z flag - convert_both.py: API_URL defaults to port 8001, overridable via env - TODO.md: reflect final decisions (iGPU 30x slower than CPU, --privileged required for GPU, CPU mode is default)
43 lines
1.3 KiB
YAML
43 lines
1.3 KiB
YAML
# ==================================================
|
|
# docker-compose.yml -- local testing (Podman or Docker)
|
|
# ==================================================
|
|
services:
|
|
marker-api:
|
|
build:
|
|
context: .
|
|
dockerfile: Containerfile
|
|
image: marker-api:latest
|
|
env_file:
|
|
- .env
|
|
environment:
|
|
- TORCH_DEVICE=${TORCH_DEVICE:-cpu}
|
|
- MODEL_DTYPE=${MODEL_DTYPE:-float32}
|
|
- OLLAMA_HOST=${OLLAMA_HOST:-http://localhost:11435}
|
|
- DEESEEK_OCR_MODEL=${DEESEEK_OCR_MODEL:-}
|
|
- LLM_SERVICE=marker.services.openai.OpenAIService
|
|
- USE_LLM=${USE_LLM:-false}
|
|
- OPENAI_BASE_URL=http://localhost:11435/v1
|
|
- OPENAI_API_KEY=not-needed
|
|
- OPENAI_MODEL=
|
|
- PORT=${PORT:-8001}
|
|
- HOST=0.0.0.0
|
|
- GUNICORN_WORKERS=${GUNICORN_WORKERS:-1}
|
|
- GUNICORN_THREADS=${GUNICORN_THREADS:-2}
|
|
- GUNICORN_TIMEOUT=${GUNICORN_TIMEOUT:-600}
|
|
ports:
|
|
- "${PORT:-8001}:${PORT:-8001}"
|
|
volumes:
|
|
- marker-results:/app/conversion_results:rw,Z
|
|
- marker-cache:/app/.cache:rw,Z
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:${PORT:-8001}/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 120s
|
|
|
|
volumes:
|
|
marker-results:
|
|
marker-cache:
|