mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2026-03-21 22:56:47 +00:00
Igor Monadical
adc4c20bf4
* feat: add local pyannote file diarization processor Enables file diarization without Modal by using pyannote.audio locally. Downloads model bundle from S3 on first use, caches locally, patches config to use local paths. Set DIARIZATION_BACKEND=pyannote to enable. * fix: standalone setup enables pyannote diarization and public mode Replace DIARIZATION_ENABLED=false with DIARIZATION_BACKEND=pyannote so file uploads get speaker diarization out of the box. Add PUBLIC_MODE=true so unauthenticated users can list/browse transcripts. * fix: touch env files before first compose_cmd in standalone setup docker-compose.yml references www/.env.local as env_file, but the setup script only creates it in step 4. compose_cmd calls in step 3 (Garage) fail on a fresh clone when the file doesn't exist yet. * feat: standalone uses self-hosted GPU service for transcription+diarization Replace in-process pyannote approach with self-hosted gpu/self_hosted/ service. Same HTTP API as Modal — just TRANSCRIPT_URL/DIARIZATION_URL point to local container. - Add gpu/self_hosted/Dockerfile.cpu (GPU Dockerfile minus NVIDIA CUDA) - Add S3 model bundle fallback in diarizer.py when HF_TOKEN not set - Add gpu service to docker-compose.standalone.yml with compose env overrides - Fix /browse empty in PUBLIC_MODE (search+list queries filtered out roomless transcripts) - Remove audio_diarization_pyannote.py, file_diarization_pyannote.py and tests - Remove pyannote-audio from server local deps * fix: allow unauthenticated GPU requests when no API key configured OAuth2PasswordBearer with auto_error=True rejects requests without Authorization header before apikey_auth can check if auth is needed. * fix: rename standalone gpu service to cpu to match Dockerfile.cpu usage * docs: add programmatic testing section and fix gpu->cpu naming in setup script/docs - Add "Testing programmatically" section to standalone docs with curl commands for creating transcript, uploading audio, polling status, checking result - Fix setup-standalone.sh to reference `cpu` service (was still `gpu` after rename) - Update all docs references from gpu to cpu service naming --------- Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>
117 lines
2.9 KiB
YAML
117 lines
2.9 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://cpu:8000
|
|
DIARIZATION_BACKEND: modal
|
|
DIARIZATION_URL: http://cpu:8000
|
|
|
|
worker:
|
|
environment:
|
|
TRANSCRIPT_BACKEND: modal
|
|
TRANSCRIPT_URL: http://cpu:8000
|
|
DIARIZATION_BACKEND: modal
|
|
DIARIZATION_URL: http://cpu:8000
|
|
|
|
cpu:
|
|
build:
|
|
context: ./gpu/self_hosted
|
|
dockerfile: Dockerfile.cpu
|
|
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:
|