mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2026-03-22 07:06:47 +00:00
f6a23cfddd
Server runs with network_mode: host and can't resolve Docker service names. Publish cpu port as 8100 on host, point server at localhost:8100. Worker stays on bridge network using cpu:8000. Add dummy TRANSCRIPT_MODAL_API_KEY since OpenAI SDK requires it even for local endpoints.
121 lines
3.1 KiB
YAML
121 lines
3.1 KiB
YAML
# Standalone services for fully local deployment (no external dependencies).
|
|
# Usage: docker compose -f docker-compose.yml -f docker-compose.standalone.yml up -d
|
|
#
|
|
# On Linux with NVIDIA GPU, also pass: --profile ollama-gpu
|
|
# On Linux without GPU: --profile ollama-cpu
|
|
# On Mac: Ollama runs natively (Metal GPU) — no profile needed, services here unused.
|
|
|
|
services:
|
|
garage:
|
|
image: dxflrs/garage:v1.1.0
|
|
ports:
|
|
- "3900:3900" # S3 API
|
|
- "3903:3903" # Admin API
|
|
volumes:
|
|
- garage_data:/var/lib/garage/data
|
|
- garage_meta:/var/lib/garage/meta
|
|
- ./data/garage.toml:/etc/garage.toml:ro
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "/garage", "stats"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 5s
|
|
|
|
ollama:
|
|
image: ollama/ollama:latest
|
|
profiles: ["ollama-gpu"]
|
|
ports:
|
|
- "11434:11434"
|
|
volumes:
|
|
- ollama_data:/root/.ollama
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
ollama-cpu:
|
|
image: ollama/ollama:latest
|
|
profiles: ["ollama-cpu"]
|
|
ports:
|
|
- "11434:11434"
|
|
volumes:
|
|
- ollama_data:/root/.ollama
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
|
|
# Override server/worker/beat to use self-hosted GPU service for transcription+diarization.
|
|
# compose `environment:` overrides values from `env_file:` — no need to edit server/.env.
|
|
server:
|
|
environment:
|
|
TRANSCRIPT_BACKEND: modal
|
|
TRANSCRIPT_URL: http://localhost:8100
|
|
TRANSCRIPT_MODAL_API_KEY: local
|
|
DIARIZATION_BACKEND: modal
|
|
DIARIZATION_URL: http://localhost:8100
|
|
|
|
worker:
|
|
environment:
|
|
TRANSCRIPT_BACKEND: modal
|
|
TRANSCRIPT_URL: http://cpu:8000
|
|
TRANSCRIPT_MODAL_API_KEY: local
|
|
DIARIZATION_BACKEND: modal
|
|
DIARIZATION_URL: http://cpu:8000
|
|
|
|
cpu:
|
|
build:
|
|
context: ./gpu/self_hosted
|
|
dockerfile: Dockerfile.cpu
|
|
ports:
|
|
- "8100:8000"
|
|
volumes:
|
|
- gpu_cache:/root/.cache
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 10
|
|
start_period: 120s
|
|
|
|
gpu-nvidia:
|
|
build:
|
|
context: ./gpu/self_hosted
|
|
profiles: ["gpu-nvidia"]
|
|
volumes:
|
|
- gpu_cache:/root/.cache
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 10
|
|
start_period: 120s
|
|
|
|
volumes:
|
|
garage_data:
|
|
garage_meta:
|
|
ollama_data:
|
|
gpu_cache:
|