mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2026-04-01 03:46:47 +00:00
Compare commits
9 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
61d6fbd344 | ||
|
|
7b3b5b9858 | ||
|
|
a22789d548 | ||
|
|
e3cc646cf5 | ||
|
|
778ff6268c | ||
|
|
d164e486cc | ||
|
|
12bf0c2d77 | ||
|
|
bfaf4f403b | ||
|
|
0258754a4c |
5
.gitignore
vendored
5
.gitignore
vendored
@@ -24,5 +24,10 @@ www/.env.production
|
||||
.secrets
|
||||
opencode.json
|
||||
|
||||
certs/
|
||||
docker-compose.ca.yml
|
||||
docker-compose.gpu-ca.yml
|
||||
Caddyfile.gpu-host
|
||||
.env.gpu-host
|
||||
vibedocs/
|
||||
server/tests/integration/logs/
|
||||
|
||||
14
CHANGELOG.md
14
CHANGELOG.md
@@ -1,5 +1,19 @@
|
||||
# Changelog
|
||||
|
||||
## [0.42.0](https://github.com/GreyhavenHQ/reflector/compare/v0.41.0...v0.42.0) (2026-03-30)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* custom ca for caddy ([#931](https://github.com/GreyhavenHQ/reflector/issues/931)) ([12bf0c2](https://github.com/GreyhavenHQ/reflector/commit/12bf0c2d77f9915b79b1eb1decd77ed2dadbb31d))
|
||||
* mixdown modal services + processor pattern ([#936](https://github.com/GreyhavenHQ/reflector/issues/936)) ([d164e48](https://github.com/GreyhavenHQ/reflector/commit/d164e486cc33ff8babf6cff6c163893cfc56fd76))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* grpc tls for local hatchet ([#937](https://github.com/GreyhavenHQ/reflector/issues/937)) ([a22789d](https://github.com/GreyhavenHQ/reflector/commit/a22789d5486bf8b83e33ab2fb5eb3ee9799c6d47))
|
||||
* remove share public from integration tests ([#938](https://github.com/GreyhavenHQ/reflector/issues/938)) ([7b3b5b9](https://github.com/GreyhavenHQ/reflector/commit/7b3b5b98586449afd0b6996ba9fd7aec8308bbc6))
|
||||
|
||||
## [0.41.0](https://github.com/GreyhavenHQ/reflector/compare/v0.40.0...v0.41.0) (2026-03-25)
|
||||
|
||||
|
||||
|
||||
@@ -193,6 +193,11 @@ Modal.com integration for scalable ML processing:
|
||||
|
||||
If you need to do any worker/pipeline related work, search for "Pipeline" classes and their "create" or "build" methods to find the main processor sequence. Look for task orchestration patterns (like "chord", "group", or "chain") to identify the post-processing flow with parallel execution chains. This will give you abstract vision on how processing pipeling is organized.
|
||||
|
||||
## Documentation
|
||||
|
||||
- New documentation files go in `docsv2/`, not in `docs/docs/`.
|
||||
- Existing `docs/` directory contains legacy Docusaurus docs.
|
||||
|
||||
## Code Style
|
||||
|
||||
- Always put imports at the top of the file. Let ruff/pre-commit handle sorting and formatting of imports.
|
||||
|
||||
106
docker-compose.gpu-host.yml
Normal file
106
docker-compose.gpu-host.yml
Normal file
@@ -0,0 +1,106 @@
|
||||
# Standalone GPU host for Reflector — transcription, diarization, translation.
|
||||
#
|
||||
# Usage: ./scripts/setup-gpu-host.sh [--domain DOMAIN] [--custom-ca PATH] [--api-key KEY] [--cpu]
|
||||
# or: docker compose -f docker-compose.gpu-host.yml --profile gpu [--profile caddy] up -d
|
||||
#
|
||||
# Processing mode (pick ONE — mutually exclusive, both bind port 8000):
|
||||
# --profile gpu NVIDIA GPU container (requires nvidia-container-toolkit)
|
||||
# --profile cpu CPU-only container (no GPU required, slower)
|
||||
#
|
||||
# Optional:
|
||||
# --profile caddy Caddy reverse proxy with HTTPS
|
||||
#
|
||||
# This file is checked into the repo. The setup script generates:
|
||||
# - .env.gpu-host (HF_TOKEN, API key, port config)
|
||||
# - Caddyfile.gpu-host (Caddy config, only with --domain)
|
||||
# - docker-compose.gpu-ca.yml (CA cert mounts, only with --custom-ca)
|
||||
|
||||
services:
|
||||
# ===========================================================
|
||||
# GPU service — NVIDIA GPU accelerated
|
||||
# Activated with: --profile gpu
|
||||
# ===========================================================
|
||||
|
||||
gpu:
|
||||
build:
|
||||
context: ./gpu/self_hosted
|
||||
dockerfile: Dockerfile
|
||||
profiles: [gpu]
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "${GPU_HOST_PORT:-8000}:8000"
|
||||
environment:
|
||||
HF_TOKEN: ${HF_TOKEN:-}
|
||||
REFLECTOR_GPU_APIKEY: ${REFLECTOR_GPU_APIKEY:-}
|
||||
volumes:
|
||||
- gpu_cache:/root/.cache
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: all
|
||||
capabilities: [gpu]
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
|
||||
interval: 15s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
start_period: 120s
|
||||
networks:
|
||||
default:
|
||||
aliases:
|
||||
- transcription
|
||||
|
||||
# ===========================================================
|
||||
# CPU service — no GPU required, uses Dockerfile.cpu
|
||||
# Activated with: --profile cpu
|
||||
# Mutually exclusive with gpu (both bind port 8000)
|
||||
# ===========================================================
|
||||
|
||||
cpu:
|
||||
build:
|
||||
context: ./gpu/self_hosted
|
||||
dockerfile: Dockerfile.cpu
|
||||
profiles: [cpu]
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "${GPU_HOST_PORT:-8000}:8000"
|
||||
environment:
|
||||
HF_TOKEN: ${HF_TOKEN:-}
|
||||
REFLECTOR_GPU_APIKEY: ${REFLECTOR_GPU_APIKEY:-}
|
||||
volumes:
|
||||
- gpu_cache:/root/.cache
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-f", "http://localhost:8000/docs"]
|
||||
interval: 15s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
start_period: 120s
|
||||
networks:
|
||||
default:
|
||||
aliases:
|
||||
- transcription
|
||||
|
||||
# ===========================================================
|
||||
# Caddy — reverse proxy with HTTPS (optional)
|
||||
# Activated with: --profile caddy
|
||||
# Proxies to "transcription" network alias (works for both gpu and cpu)
|
||||
# ===========================================================
|
||||
|
||||
caddy:
|
||||
image: caddy:2-alpine
|
||||
profiles: [caddy]
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "80:80"
|
||||
- "${CADDY_HTTPS_PORT:-443}:443"
|
||||
volumes:
|
||||
- ./Caddyfile.gpu-host:/etc/caddy/Caddyfile:ro
|
||||
- caddy_data:/data
|
||||
- caddy_config:/config
|
||||
|
||||
volumes:
|
||||
gpu_cache:
|
||||
caddy_data:
|
||||
caddy_config:
|
||||
76
docs/pnpm-lock.yaml
generated
76
docs/pnpm-lock.yaml
generated
@@ -701,6 +701,10 @@ packages:
|
||||
resolution: {integrity: sha512-05WQkdpL9COIMz4LjTxGpPNCdlpyimKppYNoJ5Di5EUObifl8t4tuLuUBBZEpoLYOmfvIWrsp9fCl0HoPRVTdA==}
|
||||
engines: {node: '>=6.9.0'}
|
||||
|
||||
'@babel/runtime@7.29.2':
|
||||
resolution: {integrity: sha512-JiDShH45zKHWyGe4ZNVRrCjBz8Nh9TMmZG1kh4QTK8hCBTWBi8Da+i7s1fJw7/lYpM4ccepSNfqzZ/QvABBi5g==}
|
||||
engines: {node: '>=6.9.0'}
|
||||
|
||||
'@babel/template@7.28.6':
|
||||
resolution: {integrity: sha512-YA6Ma2KsCdGb+WC6UpBVFJGXL58MDA6oyONbjyF/+5sBgxY/dwkhLogbMT2GXXyU84/IhRw/2D1Os1B/giz+BQ==}
|
||||
engines: {node: '>=6.9.0'}
|
||||
@@ -1490,42 +1494,36 @@ packages:
|
||||
engines: {node: '>= 10.0.0'}
|
||||
cpu: [arm]
|
||||
os: [linux]
|
||||
libc: [glibc]
|
||||
|
||||
'@parcel/watcher-linux-arm-musl@2.5.6':
|
||||
resolution: {integrity: sha512-Ve3gUCG57nuUUSyjBq/MAM0CzArtuIOxsBdQ+ftz6ho8n7s1i9E1Nmk/xmP323r2YL0SONs1EuwqBp2u1k5fxg==}
|
||||
engines: {node: '>= 10.0.0'}
|
||||
cpu: [arm]
|
||||
os: [linux]
|
||||
libc: [musl]
|
||||
|
||||
'@parcel/watcher-linux-arm64-glibc@2.5.6':
|
||||
resolution: {integrity: sha512-f2g/DT3NhGPdBmMWYoxixqYr3v/UXcmLOYy16Bx0TM20Tchduwr4EaCbmxh1321TABqPGDpS8D/ggOTaljijOA==}
|
||||
engines: {node: '>= 10.0.0'}
|
||||
cpu: [arm64]
|
||||
os: [linux]
|
||||
libc: [glibc]
|
||||
|
||||
'@parcel/watcher-linux-arm64-musl@2.5.6':
|
||||
resolution: {integrity: sha512-qb6naMDGlbCwdhLj6hgoVKJl2odL34z2sqkC7Z6kzir8b5W65WYDpLB6R06KabvZdgoHI/zxke4b3zR0wAbDTA==}
|
||||
engines: {node: '>= 10.0.0'}
|
||||
cpu: [arm64]
|
||||
os: [linux]
|
||||
libc: [musl]
|
||||
|
||||
'@parcel/watcher-linux-x64-glibc@2.5.6':
|
||||
resolution: {integrity: sha512-kbT5wvNQlx7NaGjzPFu8nVIW1rWqV780O7ZtkjuWaPUgpv2NMFpjYERVi0UYj1msZNyCzGlaCWEtzc+exjMGbQ==}
|
||||
engines: {node: '>= 10.0.0'}
|
||||
cpu: [x64]
|
||||
os: [linux]
|
||||
libc: [glibc]
|
||||
|
||||
'@parcel/watcher-linux-x64-musl@2.5.6':
|
||||
resolution: {integrity: sha512-1JRFeC+h7RdXwldHzTsmdtYR/Ku8SylLgTU/reMuqdVD7CtLwf0VR1FqeprZ0eHQkO0vqsbvFLXUmYm/uNKJBg==}
|
||||
engines: {node: '>= 10.0.0'}
|
||||
cpu: [x64]
|
||||
os: [linux]
|
||||
libc: [musl]
|
||||
|
||||
'@parcel/watcher-win32-arm64@2.5.6':
|
||||
resolution: {integrity: sha512-3ukyebjc6eGlw9yRt678DxVF7rjXatWiHvTXqphZLvo7aC5NdEgFufVwjFfY51ijYEWpXbqF5jtrK275z52D4Q==}
|
||||
@@ -2254,11 +2252,11 @@ packages:
|
||||
resolution: {integrity: sha512-2hCgjEmP8YLWQ130n2FerGv7rYpfBmnmp9Uy2Le1vge6X3gZIfSmEzP5QTDElFxcvVcXlEn8Aq6MU/PZygIOog==}
|
||||
engines: {node: '>=14.16'}
|
||||
|
||||
brace-expansion@1.1.12:
|
||||
resolution: {integrity: sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==}
|
||||
brace-expansion@1.1.13:
|
||||
resolution: {integrity: sha512-9ZLprWS6EENmhEOpjCYW2c8VkmOvckIJZfkr7rBW6dObmfgJ/L1GpSYW5Hpo9lDz4D1+n0Ckz8rU7FwHDQiG/w==}
|
||||
|
||||
brace-expansion@2.0.2:
|
||||
resolution: {integrity: sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==}
|
||||
brace-expansion@2.0.3:
|
||||
resolution: {integrity: sha512-MCV/fYJEbqx68aE58kv2cA/kiky1G8vux3OR6/jbS+jIMe/6fJWa0DTzJU7dqijOWYwHi1t29FlfYI9uytqlpA==}
|
||||
|
||||
braces@3.0.3:
|
||||
resolution: {integrity: sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==}
|
||||
@@ -3410,8 +3408,8 @@ packages:
|
||||
graphlib@2.1.8:
|
||||
resolution: {integrity: sha512-jcLLfkpoVGmH7/InMC/1hIvOPSUh38oJtGhvrOFGzioE1DZ+0YW16RgmOJhHiuWTvGiJQ9Z1Ik43JvkRPRvE+A==}
|
||||
|
||||
gray-matter@https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e317c87fe031e9368ffabde9c9149ce3ec:
|
||||
resolution: {tarball: https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e317c87fe031e9368ffabde9c9149ce3ec}
|
||||
gray-matter@https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e:
|
||||
resolution: {tarball: https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e}
|
||||
version: 4.0.3
|
||||
engines: {node: '>=6.0'}
|
||||
|
||||
@@ -4533,8 +4531,8 @@ packages:
|
||||
path-parse@1.0.7:
|
||||
resolution: {integrity: sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==}
|
||||
|
||||
path-to-regexp@0.1.12:
|
||||
resolution: {integrity: sha512-RA1GjUVMnvYFxuqovrEqZoxxW5NUZqbwKtYz/Tt7nXerk0LbLblQmrsgdeOxV5SFHf0UDggjS/bSeOZwt1pmEQ==}
|
||||
path-to-regexp@0.1.13:
|
||||
resolution: {integrity: sha512-A/AGNMFN3c8bOlvV9RreMdrv7jsmF9XIfDeCd87+I8RNg6s78BhJxMu69NEMHBSJFxKidViTEdruRwEk/WIKqA==}
|
||||
|
||||
path-to-regexp@1.9.0:
|
||||
resolution: {integrity: sha512-xIp7/apCFJuUHdDLWe8O1HIkb0kQrOMb/0u6FXQjemHn/ii5LrIzU6bdECnsiTF/GjZkMEKg1xdiZwNqDYlZ6g==}
|
||||
@@ -4555,12 +4553,12 @@ packages:
|
||||
picocolors@1.1.1:
|
||||
resolution: {integrity: sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==}
|
||||
|
||||
picomatch@2.3.1:
|
||||
resolution: {integrity: sha512-JU3teHTNjmE2VCGFzuY8EXzCDVwEqB2a8fsIvwaStHhAWJEeVd1o1QD80CU6+ZdEXXSLbSsuLwJjkCBWqRQUVA==}
|
||||
picomatch@2.3.2:
|
||||
resolution: {integrity: sha512-V7+vQEJ06Z+c5tSye8S+nHUfI51xoXIXjHQ99cQtKUkQqqO1kO/KCJUfZXuB47h/YBlDhah2H3hdUGXn8ie0oA==}
|
||||
engines: {node: '>=8.6'}
|
||||
|
||||
picomatch@4.0.3:
|
||||
resolution: {integrity: sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==}
|
||||
picomatch@4.0.4:
|
||||
resolution: {integrity: sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A==}
|
||||
engines: {node: '>=12'}
|
||||
|
||||
pirates@4.0.7:
|
||||
@@ -7024,6 +7022,8 @@ snapshots:
|
||||
|
||||
'@babel/runtime@7.28.6': {}
|
||||
|
||||
'@babel/runtime@7.29.2': {}
|
||||
|
||||
'@babel/template@7.28.6':
|
||||
dependencies:
|
||||
'@babel/code-frame': 7.29.0
|
||||
@@ -8162,7 +8162,7 @@ snapshots:
|
||||
fs-extra: 11.3.3
|
||||
github-slugger: 1.5.0
|
||||
globby: 11.1.0
|
||||
gray-matter: https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e317c87fe031e9368ffabde9c9149ce3ec
|
||||
gray-matter: https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e
|
||||
jiti: 1.21.7
|
||||
js-yaml: 4.1.1
|
||||
lodash: 4.17.23
|
||||
@@ -8473,7 +8473,7 @@ snapshots:
|
||||
detect-libc: 2.1.2
|
||||
is-glob: 4.0.3
|
||||
node-addon-api: 7.1.1
|
||||
picomatch: 4.0.3
|
||||
picomatch: 4.0.4
|
||||
optionalDependencies:
|
||||
'@parcel/watcher-android-arm64': 2.5.6
|
||||
'@parcel/watcher-darwin-arm64': 2.5.6
|
||||
@@ -8645,7 +8645,7 @@ snapshots:
|
||||
|
||||
'@slorber/react-helmet-async@1.3.0(react-dom@19.2.4(react@19.2.4))(react@19.2.4)':
|
||||
dependencies:
|
||||
'@babel/runtime': 7.28.6
|
||||
'@babel/runtime': 7.29.2
|
||||
invariant: 2.2.4
|
||||
prop-types: 15.8.1
|
||||
react: 19.2.4
|
||||
@@ -9244,7 +9244,7 @@ snapshots:
|
||||
anymatch@3.1.3:
|
||||
dependencies:
|
||||
normalize-path: 3.0.0
|
||||
picomatch: 2.3.1
|
||||
picomatch: 2.3.2
|
||||
|
||||
arg@5.0.2: {}
|
||||
|
||||
@@ -9378,12 +9378,12 @@ snapshots:
|
||||
widest-line: 4.0.1
|
||||
wrap-ansi: 8.1.0
|
||||
|
||||
brace-expansion@1.1.12:
|
||||
brace-expansion@1.1.13:
|
||||
dependencies:
|
||||
balanced-match: 1.0.2
|
||||
concat-map: 0.0.1
|
||||
|
||||
brace-expansion@2.0.2:
|
||||
brace-expansion@2.0.3:
|
||||
dependencies:
|
||||
balanced-match: 1.0.2
|
||||
|
||||
@@ -10436,7 +10436,7 @@ snapshots:
|
||||
methods: 1.1.2
|
||||
on-finished: 2.4.1
|
||||
parseurl: 1.3.3
|
||||
path-to-regexp: 0.1.12
|
||||
path-to-regexp: 0.1.13
|
||||
proxy-addr: 2.0.7
|
||||
qs: 6.14.2
|
||||
range-parser: 1.2.1
|
||||
@@ -10485,9 +10485,9 @@ snapshots:
|
||||
dependencies:
|
||||
websocket-driver: 0.7.4
|
||||
|
||||
fdir@6.5.0(picomatch@4.0.3):
|
||||
fdir@6.5.0(picomatch@4.0.4):
|
||||
optionalDependencies:
|
||||
picomatch: 4.0.3
|
||||
picomatch: 4.0.4
|
||||
|
||||
feed@4.2.2:
|
||||
dependencies:
|
||||
@@ -10658,7 +10658,7 @@ snapshots:
|
||||
dependencies:
|
||||
lodash: 4.17.23
|
||||
|
||||
gray-matter@https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e317c87fe031e9368ffabde9c9149ce3ec:
|
||||
gray-matter@https://codeload.github.com/jonschlinkert/gray-matter/tar.gz/234163e:
|
||||
dependencies:
|
||||
js-yaml: 4.1.1
|
||||
kind-of: 6.0.3
|
||||
@@ -11080,7 +11080,7 @@ snapshots:
|
||||
chalk: 4.1.2
|
||||
ci-info: 3.9.0
|
||||
graceful-fs: 4.2.11
|
||||
picomatch: 2.3.1
|
||||
picomatch: 2.3.2
|
||||
|
||||
jest-worker@27.5.1:
|
||||
dependencies:
|
||||
@@ -11780,7 +11780,7 @@ snapshots:
|
||||
micromatch@4.0.8:
|
||||
dependencies:
|
||||
braces: 3.0.3
|
||||
picomatch: 2.3.1
|
||||
picomatch: 2.3.2
|
||||
|
||||
mime-db@1.33.0: {}
|
||||
|
||||
@@ -11824,11 +11824,11 @@ snapshots:
|
||||
|
||||
minimatch@3.1.5:
|
||||
dependencies:
|
||||
brace-expansion: 1.1.12
|
||||
brace-expansion: 1.1.13
|
||||
|
||||
minimatch@5.1.8:
|
||||
dependencies:
|
||||
brace-expansion: 2.0.2
|
||||
brace-expansion: 2.0.3
|
||||
|
||||
minimist@1.2.8: {}
|
||||
|
||||
@@ -12127,7 +12127,7 @@ snapshots:
|
||||
|
||||
path-parse@1.0.7: {}
|
||||
|
||||
path-to-regexp@0.1.12: {}
|
||||
path-to-regexp@0.1.13: {}
|
||||
|
||||
path-to-regexp@1.9.0:
|
||||
dependencies:
|
||||
@@ -12146,9 +12146,9 @@ snapshots:
|
||||
|
||||
picocolors@1.1.1: {}
|
||||
|
||||
picomatch@2.3.1: {}
|
||||
picomatch@2.3.2: {}
|
||||
|
||||
picomatch@4.0.3: {}
|
||||
picomatch@4.0.4: {}
|
||||
|
||||
pirates@4.0.7: {}
|
||||
|
||||
@@ -12852,7 +12852,7 @@ snapshots:
|
||||
|
||||
readdirp@3.6.0:
|
||||
dependencies:
|
||||
picomatch: 2.3.1
|
||||
picomatch: 2.3.2
|
||||
|
||||
readdirp@4.1.2: {}
|
||||
|
||||
@@ -13510,8 +13510,8 @@ snapshots:
|
||||
|
||||
tinyglobby@0.2.15:
|
||||
dependencies:
|
||||
fdir: 6.5.0(picomatch@4.0.3)
|
||||
picomatch: 4.0.3
|
||||
fdir: 6.5.0(picomatch@4.0.4)
|
||||
picomatch: 4.0.4
|
||||
|
||||
tinypool@1.1.1: {}
|
||||
|
||||
|
||||
338
docsv2/custom-ca-setup.md
Normal file
338
docsv2/custom-ca-setup.md
Normal file
@@ -0,0 +1,338 @@
|
||||
# Custom CA Certificate Setup
|
||||
|
||||
Use a private Certificate Authority (CA) with Reflector self-hosted deployments. This covers two scenarios:
|
||||
|
||||
1. **Custom local domain** — Serve Reflector over HTTPS on an internal domain (e.g., `reflector.local`) using certs signed by your own CA
|
||||
2. **Backend CA trust** — Let Reflector's backend services (server, workers, GPU) make HTTPS calls to GPU, LLM, or other internal services behind your private CA
|
||||
|
||||
Both can be used independently or together.
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Generate test certificates
|
||||
|
||||
```bash
|
||||
./scripts/generate-certs.sh reflector.local
|
||||
```
|
||||
|
||||
This creates `certs/` with:
|
||||
- `ca.key` + `ca.crt` — Root CA (10-year validity)
|
||||
- `server-key.pem` + `server.pem` — Server certificate (1-year, SAN: domain + localhost + 127.0.0.1)
|
||||
|
||||
### Deploy with custom CA + domain
|
||||
|
||||
```bash
|
||||
# Add domain to /etc/hosts on the server (use 127.0.0.1 for local, or server LAN IP for network access)
|
||||
echo "127.0.0.1 reflector.local" | sudo tee -a /etc/hosts
|
||||
|
||||
# Run setup — pass the certs directory
|
||||
./scripts/setup-selfhosted.sh --gpu --caddy --domain reflector.local --custom-ca certs/
|
||||
|
||||
# Trust the CA on your machine (see "Trust the CA" section below)
|
||||
```
|
||||
|
||||
### Deploy with CA trust only (GPU/LLM behind private CA)
|
||||
|
||||
```bash
|
||||
# Only need the CA cert file — no Caddy TLS certs needed
|
||||
./scripts/setup-selfhosted.sh --hosted --custom-ca /path/to/corporate-ca.crt
|
||||
```
|
||||
|
||||
## How `--custom-ca` Works
|
||||
|
||||
The flag accepts a **directory** or a **single file**:
|
||||
|
||||
### Directory mode
|
||||
|
||||
```bash
|
||||
--custom-ca certs/
|
||||
```
|
||||
|
||||
Looks for these files by convention:
|
||||
- `ca.crt` (required) — CA certificate to trust
|
||||
- `server.pem` + `server-key.pem` (optional) — TLS certificate/key for Caddy
|
||||
|
||||
If `server.pem` + `server-key.pem` are found AND `--domain` is provided:
|
||||
- Caddy serves HTTPS using those certs
|
||||
- Backend containers trust the CA for outbound calls
|
||||
|
||||
If only `ca.crt` is found:
|
||||
- Backend containers trust the CA for outbound calls
|
||||
- Caddy is unaffected (uses Let's Encrypt, self-signed, or no Caddy)
|
||||
|
||||
### Single file mode
|
||||
|
||||
```bash
|
||||
--custom-ca /path/to/corporate-ca.crt
|
||||
```
|
||||
|
||||
Only injects CA trust into backend containers. No Caddy TLS changes.
|
||||
|
||||
## Scenarios
|
||||
|
||||
### Scenario 1: Custom local domain
|
||||
|
||||
Your Reflector instance runs on an internal network. You want `https://reflector.local` with proper TLS (no browser warnings).
|
||||
|
||||
```bash
|
||||
# 1. Generate certs
|
||||
./scripts/generate-certs.sh reflector.local
|
||||
|
||||
# 2. Add to /etc/hosts on the server
|
||||
echo "127.0.0.1 reflector.local" | sudo tee -a /etc/hosts
|
||||
|
||||
# 3. Deploy
|
||||
./scripts/setup-selfhosted.sh --gpu --garage --caddy --domain reflector.local --custom-ca certs/
|
||||
|
||||
# 4. Trust the CA on your machine (see "Trust the CA" section below)
|
||||
```
|
||||
|
||||
If other machines on the network need to access it, add the server's LAN IP to `/etc/hosts` on those machines instead:
|
||||
```bash
|
||||
echo "192.168.1.100 reflector.local" | sudo tee -a /etc/hosts
|
||||
```
|
||||
|
||||
And include that IP as an extra SAN when generating certs:
|
||||
```bash
|
||||
./scripts/generate-certs.sh reflector.local "IP:192.168.1.100"
|
||||
```
|
||||
|
||||
### Scenario 2: GPU/LLM behind corporate CA
|
||||
|
||||
Your GPU or LLM server (e.g., `https://gpu.internal.corp`) uses certificates signed by your corporate CA. Reflector's backend needs to trust that CA for outbound HTTPS calls.
|
||||
|
||||
```bash
|
||||
# Get the CA certificate from your IT team (PEM format)
|
||||
# Then deploy — Caddy can still use Let's Encrypt or self-signed
|
||||
./scripts/setup-selfhosted.sh --hosted --garage --caddy --custom-ca /path/to/corporate-ca.crt
|
||||
```
|
||||
|
||||
This works because:
|
||||
- **TLS cert/key** = "this is my identity" — for Caddy to serve HTTPS to browsers
|
||||
- **CA cert** = "I trust this authority" — for backend containers to verify outbound connections
|
||||
|
||||
Your Reflector frontend can use Let's Encrypt (public domain) or self-signed certs, while the backend trusts a completely different CA for GPU/LLM calls.
|
||||
|
||||
### Scenario 3: Both combined (same CA)
|
||||
|
||||
Custom domain + GPU/LLM all behind the same CA:
|
||||
|
||||
```bash
|
||||
./scripts/generate-certs.sh reflector.local "DNS:gpu.local"
|
||||
./scripts/setup-selfhosted.sh --gpu --garage --caddy --domain reflector.local --custom-ca certs/
|
||||
```
|
||||
|
||||
### Scenario 4: Multiple CAs (local domain + remote GPU on different CA)
|
||||
|
||||
Your Reflector uses one CA for `reflector.local`, but the GPU host uses a different CA:
|
||||
|
||||
```bash
|
||||
# Your local domain setup
|
||||
./scripts/generate-certs.sh reflector.local
|
||||
|
||||
# Deploy with your CA + trust the GPU host's CA too
|
||||
./scripts/setup-selfhosted.sh --hosted --garage --caddy \
|
||||
--domain reflector.local \
|
||||
--custom-ca certs/ \
|
||||
--extra-ca /path/to/gpu-machine-ca.crt
|
||||
```
|
||||
|
||||
`--extra-ca` appends additional CA certs to the trust bundle. Backend containers trust ALL CAs — your local domain AND the GPU host's certs both work.
|
||||
|
||||
You can repeat `--extra-ca` for multiple remote services:
|
||||
```bash
|
||||
--extra-ca /path/to/gpu-ca.crt --extra-ca /path/to/llm-ca.crt
|
||||
```
|
||||
|
||||
For setting up a dedicated GPU host, see [Standalone GPU Host Setup](gpu-host-setup.md).
|
||||
|
||||
## Trust the CA on Client Machines
|
||||
|
||||
After deploying, clients need to trust the CA to avoid browser warnings.
|
||||
|
||||
### macOS
|
||||
|
||||
```bash
|
||||
sudo security add-trusted-cert -d -r trustRoot \
|
||||
-k /Library/Keychains/System.keychain certs/ca.crt
|
||||
```
|
||||
|
||||
### Linux (Ubuntu/Debian)
|
||||
|
||||
```bash
|
||||
sudo cp certs/ca.crt /usr/local/share/ca-certificates/reflector-ca.crt
|
||||
sudo update-ca-certificates
|
||||
```
|
||||
|
||||
### Linux (RHEL/Fedora)
|
||||
|
||||
```bash
|
||||
sudo cp certs/ca.crt /etc/pki/ca-trust/source/anchors/reflector-ca.crt
|
||||
sudo update-ca-trust
|
||||
```
|
||||
|
||||
### Windows (PowerShell as admin)
|
||||
|
||||
```powershell
|
||||
Import-Certificate -FilePath .\certs\ca.crt -CertStoreLocation Cert:\LocalMachine\Root
|
||||
```
|
||||
|
||||
### Firefox (all platforms)
|
||||
|
||||
Firefox uses its own certificate store:
|
||||
1. Settings > Privacy & Security > View Certificates
|
||||
2. Authorities tab > Import
|
||||
3. Select `ca.crt` and check "Trust this CA to identify websites"
|
||||
|
||||
## How It Works Internally
|
||||
|
||||
### Docker entrypoint CA injection
|
||||
|
||||
Each backend container (server, worker, beat, hatchet workers, GPU) has an entrypoint script (`docker-entrypoint.sh`) that:
|
||||
|
||||
1. Checks if a CA cert is mounted at `/usr/local/share/ca-certificates/custom-ca.crt`
|
||||
2. If present, runs `update-ca-certificates` to create a **combined bundle** (system CAs + custom CA)
|
||||
3. Sets environment variables so all Python/gRPC libraries use the combined bundle:
|
||||
|
||||
| Env var | Covers |
|
||||
|---------|--------|
|
||||
| `SSL_CERT_FILE` | httpx, OpenAI SDK, llama-index, Python ssl module |
|
||||
| `REQUESTS_CA_BUNDLE` | requests library (transitive dependencies) |
|
||||
| `CURL_CA_BUNDLE` | curl CLI (container healthchecks) |
|
||||
|
||||
Note: `GRPC_DEFAULT_SSL_ROOTS_FILE_PATH` is intentionally NOT set. Setting it causes grpcio to attempt TLS on internal Hatchet gRPC connections that run without TLS, resulting in handshake failures. The internal Hatchet connection uses `HATCHET_CLIENT_TLS_STRATEGY=none` (plaintext).
|
||||
|
||||
When no CA cert is mounted, the entrypoint is a no-op — containers behave exactly as before.
|
||||
|
||||
### Why this replaces manual certifi patching
|
||||
|
||||
Previously, the workaround for trusting a private CA in Python was to patch certifi's bundle directly:
|
||||
|
||||
```bash
|
||||
# OLD approach — fragile, do NOT use
|
||||
cat custom-ca.crt >> $(python -c "import certifi; print(certifi.where())")
|
||||
```
|
||||
|
||||
This breaks whenever certifi is updated (any `pip install`/`uv sync` overwrites the bundle and the CA is lost).
|
||||
|
||||
Our entrypoint approach is permanent because:
|
||||
|
||||
1. `SSL_CERT_FILE` is checked by Python's `ssl.create_default_context()` **before** falling back to `certifi.where()`. When set, certifi's bundle is never read.
|
||||
2. `REQUESTS_CA_BUNDLE` similarly overrides certifi for the `requests` library.
|
||||
3. The CA is injected at container startup (runtime), not baked into the Python environment. It survives image rebuilds, dependency updates, and `uv sync`.
|
||||
|
||||
```
|
||||
Python SSL lookup chain:
|
||||
ssl.create_default_context()
|
||||
→ SSL_CERT_FILE env var? → YES → use combined bundle (system + custom CA) ✓
|
||||
→ (certifi.where() is never reached)
|
||||
```
|
||||
|
||||
This covers all outbound HTTPS calls: httpx (transcription, diarization, translation, webhooks), OpenAI SDK (transcription), llama-index (LLM/summarization), and requests (transitive dependencies).
|
||||
|
||||
### Compose override
|
||||
|
||||
The setup script generates `docker-compose.ca.yml` which mounts the CA cert into every backend container as a read-only bind mount. This file is:
|
||||
- Only generated when `--custom-ca` is passed
|
||||
- Deleted on re-runs without `--custom-ca` (prevents stale overrides)
|
||||
- Added to `.gitignore`
|
||||
|
||||
### Node.js (frontend)
|
||||
|
||||
The web container uses `NODE_EXTRA_CA_CERTS` which **adds** to Node's trust store (unlike Python's `SSL_CERT_FILE` which replaces it). This is set via the compose override.
|
||||
|
||||
## Generate Your Own CA (Manual)
|
||||
|
||||
If you prefer not to use `generate-certs.sh`:
|
||||
|
||||
```bash
|
||||
# 1. Create CA
|
||||
openssl genrsa -out ca.key 4096
|
||||
openssl req -x509 -new -nodes -key ca.key -sha256 -days 3650 \
|
||||
-out ca.crt -subj "/CN=My CA/O=My Organization"
|
||||
|
||||
# 2. Create server key
|
||||
openssl genrsa -out server-key.pem 2048
|
||||
|
||||
# 3. Create CSR with SANs
|
||||
openssl req -new -key server-key.pem -out server.csr \
|
||||
-subj "/CN=reflector.local" \
|
||||
-addext "subjectAltName=DNS:reflector.local,DNS:localhost,IP:127.0.0.1"
|
||||
|
||||
# 4. Sign with CA
|
||||
openssl x509 -req -in server.csr -CA ca.crt -CAkey ca.key \
|
||||
-CAcreateserial -out server.pem -days 365 -sha256 \
|
||||
-copy_extensions copyall
|
||||
|
||||
# 5. Clean up
|
||||
rm server.csr ca.srl
|
||||
```
|
||||
|
||||
## Using Existing Corporate Certificates
|
||||
|
||||
If your organization already has a CA:
|
||||
|
||||
1. Get the CA certificate in PEM format from your IT team
|
||||
2. If you have a PKCS#12 (.p12/.pfx) bundle, extract the CA cert:
|
||||
```bash
|
||||
openssl pkcs12 -in bundle.p12 -cacerts -nokeys -out ca.crt
|
||||
```
|
||||
3. If you have multiple intermediate CAs, concatenate them into one PEM file:
|
||||
```bash
|
||||
cat intermediate-ca.crt root-ca.crt > ca.crt
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Browser: "Your connection is not private"
|
||||
|
||||
The CA is not trusted on the client machine. See "Trust the CA" section above.
|
||||
|
||||
Check certificate expiry:
|
||||
```bash
|
||||
openssl x509 -noout -dates -in certs/server.pem
|
||||
```
|
||||
|
||||
### Backend: `SSL: CERTIFICATE_VERIFY_FAILED`
|
||||
|
||||
CA cert not mounted or not loaded. Check inside the container:
|
||||
```bash
|
||||
docker compose exec server env | grep SSL_CERT_FILE
|
||||
docker compose exec server python -c "
|
||||
import ssl, os
|
||||
print('SSL_CERT_FILE:', os.environ.get('SSL_CERT_FILE', 'not set'))
|
||||
ctx = ssl.create_default_context()
|
||||
print('CA certs loaded:', ctx.cert_store_stats())
|
||||
"
|
||||
```
|
||||
|
||||
### Caddy: "certificate is not valid for any names"
|
||||
|
||||
Domain in Caddyfile doesn't match the certificate's SAN/CN. Check:
|
||||
```bash
|
||||
openssl x509 -noout -text -in certs/server.pem | grep -A1 "Subject Alternative Name"
|
||||
```
|
||||
|
||||
### Certificate chain issues
|
||||
|
||||
If you have intermediate CAs, concatenate them into `server.pem`:
|
||||
```bash
|
||||
cat server-cert.pem intermediate-ca.pem > certs/server.pem
|
||||
```
|
||||
|
||||
Verify the chain:
|
||||
```bash
|
||||
openssl verify -CAfile certs/ca.crt certs/server.pem
|
||||
```
|
||||
|
||||
### Certificate renewal
|
||||
|
||||
Custom CA certs are NOT auto-renewed (unlike Let's Encrypt). Replace cert files and restart:
|
||||
```bash
|
||||
# Replace certs
|
||||
cp new-server.pem certs/server.pem
|
||||
cp new-server-key.pem certs/server-key.pem
|
||||
|
||||
# Restart Caddy to pick up new certs
|
||||
docker compose restart caddy
|
||||
```
|
||||
294
docsv2/gpu-host-setup.md
Normal file
294
docsv2/gpu-host-setup.md
Normal file
@@ -0,0 +1,294 @@
|
||||
# Standalone GPU Host Setup
|
||||
|
||||
Deploy Reflector's GPU transcription/diarization/translation service on a dedicated machine, separate from the main Reflector instance. Useful when:
|
||||
|
||||
- Your GPU machine is on a different network than the Reflector server
|
||||
- You want to share one GPU service across multiple Reflector instances
|
||||
- The GPU machine has special hardware/drivers that can't run the full stack
|
||||
- You need to scale GPU processing independently
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
┌─────────────────────┐ HTTPS ┌────────────────────┐
|
||||
│ Reflector Server │ ────────────────────── │ GPU Host │
|
||||
│ (server, worker, │ TRANSCRIPT_URL │ (transcription, │
|
||||
│ web, postgres, │ DIARIZATION_URL │ diarization, │
|
||||
│ redis, hatchet) │ TRANSLATE_URL │ translation) │
|
||||
│ │ │ │
|
||||
│ setup-selfhosted.sh │ │ setup-gpu-host.sh │
|
||||
│ --hosted │ │ │
|
||||
└─────────────────────┘ └────────────────────┘
|
||||
```
|
||||
|
||||
The GPU service is a standalone FastAPI app that exposes transcription, diarization, translation, and audio padding endpoints. It has **no dependencies** on PostgreSQL, Redis, Hatchet, or any other Reflector service.
|
||||
|
||||
## Quick Start
|
||||
|
||||
### On the GPU machine
|
||||
|
||||
```bash
|
||||
git clone <reflector-repo>
|
||||
cd reflector
|
||||
|
||||
# Set HuggingFace token (required for diarization models)
|
||||
export HF_TOKEN=your-huggingface-token
|
||||
|
||||
# Deploy with HTTPS (Let's Encrypt)
|
||||
./scripts/setup-gpu-host.sh --domain gpu.example.com --api-key my-secret-key
|
||||
|
||||
# Or deploy with custom CA
|
||||
./scripts/generate-certs.sh gpu.local
|
||||
./scripts/setup-gpu-host.sh --domain gpu.local --custom-ca certs/ --api-key my-secret-key
|
||||
```
|
||||
|
||||
### On the Reflector machine
|
||||
|
||||
```bash
|
||||
# If the GPU host uses a custom CA, trust it
|
||||
./scripts/setup-selfhosted.sh --hosted --garage --caddy \
|
||||
--extra-ca /path/to/gpu-machine-ca.crt
|
||||
|
||||
# Or if you already have --custom-ca for your local domain
|
||||
./scripts/setup-selfhosted.sh --hosted --garage --caddy \
|
||||
--domain reflector.local --custom-ca certs/ \
|
||||
--extra-ca /path/to/gpu-machine-ca.crt
|
||||
```
|
||||
|
||||
Then configure `server/.env` to point to the GPU host:
|
||||
|
||||
```bash
|
||||
TRANSCRIPT_BACKEND=modal
|
||||
TRANSCRIPT_URL=https://gpu.example.com
|
||||
TRANSCRIPT_MODAL_API_KEY=my-secret-key
|
||||
|
||||
DIARIZATION_BACKEND=modal
|
||||
DIARIZATION_URL=https://gpu.example.com
|
||||
DIARIZATION_MODAL_API_KEY=my-secret-key
|
||||
|
||||
TRANSLATION_BACKEND=modal
|
||||
TRANSLATE_URL=https://gpu.example.com
|
||||
TRANSLATION_MODAL_API_KEY=my-secret-key
|
||||
```
|
||||
|
||||
## Script Options
|
||||
|
||||
```
|
||||
./scripts/setup-gpu-host.sh [OPTIONS]
|
||||
|
||||
Options:
|
||||
--domain DOMAIN Domain name for HTTPS (Let's Encrypt or custom cert)
|
||||
--custom-ca PATH Custom CA (directory or single PEM file)
|
||||
--extra-ca FILE Additional CA cert to trust (repeatable)
|
||||
--api-key KEY API key to protect the service (strongly recommended)
|
||||
--cpu CPU-only mode (no NVIDIA GPU required)
|
||||
--port PORT Host port (default: 443 with Caddy, 8000 without)
|
||||
```
|
||||
|
||||
## Deployment Scenarios
|
||||
|
||||
### Public internet with Let's Encrypt
|
||||
|
||||
GPU machine has a public IP and domain:
|
||||
|
||||
```bash
|
||||
./scripts/setup-gpu-host.sh --domain gpu.example.com --api-key my-secret-key
|
||||
```
|
||||
|
||||
Requirements:
|
||||
- DNS A record: `gpu.example.com` → GPU machine's public IP
|
||||
- Ports 80 and 443 open
|
||||
- Caddy auto-provisions Let's Encrypt certificate
|
||||
|
||||
### Internal network with custom CA
|
||||
|
||||
GPU machine on a private network:
|
||||
|
||||
```bash
|
||||
# Generate certs on the GPU machine
|
||||
./scripts/generate-certs.sh gpu.internal "IP:192.168.1.200"
|
||||
|
||||
# Deploy
|
||||
./scripts/setup-gpu-host.sh --domain gpu.internal --custom-ca certs/ --api-key my-secret-key
|
||||
```
|
||||
|
||||
On each machine that connects (including the Reflector server), add DNS:
|
||||
```bash
|
||||
echo "192.168.1.200 gpu.internal" | sudo tee -a /etc/hosts
|
||||
```
|
||||
|
||||
### IP-only (no domain)
|
||||
|
||||
No domain needed — just use the machine's IP:
|
||||
|
||||
```bash
|
||||
./scripts/setup-gpu-host.sh --api-key my-secret-key
|
||||
```
|
||||
|
||||
Caddy is not used; the GPU service runs directly on port 8000 (HTTP). For HTTPS without a domain, the Reflector machine connects via `http://<GPU_IP>:8000`.
|
||||
|
||||
### CPU-only (no NVIDIA GPU)
|
||||
|
||||
Works on any machine — transcription will be slower:
|
||||
|
||||
```bash
|
||||
./scripts/setup-gpu-host.sh --cpu --domain gpu.example.com --api-key my-secret-key
|
||||
```
|
||||
|
||||
## DNS Resolution
|
||||
|
||||
The Reflector server must be able to reach the GPU host by name or IP.
|
||||
|
||||
| Setup | DNS Method | TRANSCRIPT_URL example |
|
||||
|-------|------------|----------------------|
|
||||
| Public domain | DNS A record | `https://gpu.example.com` |
|
||||
| Internal domain | `/etc/hosts` on both machines | `https://gpu.internal` |
|
||||
| IP only | No DNS needed | `http://192.168.1.200:8000` |
|
||||
|
||||
For internal domains, add the GPU machine's IP to `/etc/hosts` on the Reflector machine:
|
||||
```bash
|
||||
echo "192.168.1.200 gpu.internal" | sudo tee -a /etc/hosts
|
||||
```
|
||||
|
||||
If the Reflector server runs in Docker, the containers resolve DNS from the host (Docker's default DNS behavior). So adding to the host's `/etc/hosts` is sufficient.
|
||||
|
||||
## Multi-CA Setup
|
||||
|
||||
When your Reflector instance has its own CA (for `reflector.local`) and the GPU host has a different CA:
|
||||
|
||||
**On the GPU machine:**
|
||||
```bash
|
||||
./scripts/generate-certs.sh gpu.local
|
||||
./scripts/setup-gpu-host.sh --domain gpu.local --custom-ca certs/ --api-key my-key
|
||||
```
|
||||
|
||||
**On the Reflector machine:**
|
||||
```bash
|
||||
# Your local CA for reflector.local + the GPU host's CA
|
||||
./scripts/setup-selfhosted.sh --hosted --garage --caddy \
|
||||
--domain reflector.local \
|
||||
--custom-ca certs/ \
|
||||
--extra-ca /path/to/gpu-machine-ca.crt
|
||||
```
|
||||
|
||||
The `--extra-ca` flag appends the GPU host's CA to the trust bundle. Backend containers trust both CAs — your local domain works AND outbound calls to the GPU host succeed.
|
||||
|
||||
You can repeat `--extra-ca` for multiple remote services:
|
||||
```bash
|
||||
--extra-ca /path/to/gpu-ca.crt --extra-ca /path/to/llm-ca.crt
|
||||
```
|
||||
|
||||
## API Key Authentication
|
||||
|
||||
The GPU service uses Bearer token authentication via `REFLECTOR_GPU_APIKEY`:
|
||||
|
||||
```bash
|
||||
# Test from the Reflector machine
|
||||
curl -s https://gpu.example.com/docs # No auth needed for docs
|
||||
curl -s -X POST https://gpu.example.com/v1/audio/transcriptions \
|
||||
-H "Authorization: Bearer <my-secret-key>" \ #gitleaks:allow
|
||||
-F "file=@audio.wav"
|
||||
```
|
||||
|
||||
If `REFLECTOR_GPU_APIKEY` is not set, the service accepts all requests (open access). Always use `--api-key` for internet-facing deployments.
|
||||
|
||||
The same key goes in Reflector's `server/.env` as `TRANSCRIPT_MODAL_API_KEY` and `DIARIZATION_MODAL_API_KEY`.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Checked in? | Purpose |
|
||||
|------|-------------|---------|
|
||||
| `docker-compose.gpu-host.yml` | Yes | Static compose file with profiles (`gpu`, `cpu`, `caddy`) |
|
||||
| `.env.gpu-host` | No (generated) | Environment variables (HF_TOKEN, API key, ports) |
|
||||
| `Caddyfile.gpu-host` | No (generated) | Caddy config (only when using HTTPS) |
|
||||
| `docker-compose.gpu-ca.yml` | No (generated) | CA cert mounts override (only with --custom-ca) |
|
||||
| `certs/` | No (generated) | Staged certificates (when using --custom-ca) |
|
||||
|
||||
The compose file is checked into the repo — you can read it to understand exactly what runs. The script only generates env vars, Caddyfile, and CA overrides. Profiles control which service starts:
|
||||
|
||||
```bash
|
||||
# What the script does under the hood:
|
||||
docker compose -f docker-compose.gpu-host.yml --profile gpu --profile caddy \
|
||||
--env-file .env.gpu-host up -d
|
||||
|
||||
# CPU mode:
|
||||
docker compose -f docker-compose.gpu-host.yml --profile cpu --profile caddy \
|
||||
--env-file .env.gpu-host up -d
|
||||
```
|
||||
|
||||
Both `gpu` and `cpu` services get the network alias `transcription`, so Caddy's config works with either.
|
||||
|
||||
## Management
|
||||
|
||||
```bash
|
||||
# View logs
|
||||
docker compose -f docker-compose.gpu-host.yml --profile gpu logs -f gpu
|
||||
|
||||
# Restart
|
||||
docker compose -f docker-compose.gpu-host.yml --profile gpu restart gpu
|
||||
|
||||
# Stop
|
||||
docker compose -f docker-compose.gpu-host.yml --profile gpu --profile caddy down
|
||||
|
||||
# Re-run setup
|
||||
./scripts/setup-gpu-host.sh [same flags]
|
||||
|
||||
# Rebuild after code changes
|
||||
docker compose -f docker-compose.gpu-host.yml --profile gpu build gpu
|
||||
docker compose -f docker-compose.gpu-host.yml --profile gpu up -d gpu
|
||||
```
|
||||
|
||||
If you deployed with `--custom-ca`, include the CA override in manual commands:
|
||||
```bash
|
||||
docker compose -f docker-compose.gpu-host.yml -f docker-compose.gpu-ca.yml \
|
||||
--profile gpu logs -f gpu
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### GPU service won't start
|
||||
|
||||
Check logs:
|
||||
```bash
|
||||
docker compose -f docker-compose.gpu-host.yml logs gpu
|
||||
```
|
||||
|
||||
Common causes:
|
||||
- NVIDIA driver not installed or `nvidia-container-toolkit` missing
|
||||
- `HF_TOKEN` not set (diarization model download fails)
|
||||
- Port already in use
|
||||
|
||||
### Reflector can't connect to GPU host
|
||||
|
||||
From the Reflector machine:
|
||||
```bash
|
||||
# Test HTTPS connectivity
|
||||
curl -v https://gpu.example.com/docs
|
||||
|
||||
# If using custom CA, test with explicit CA
|
||||
curl --cacert /path/to/gpu-ca.crt https://gpu.internal/docs
|
||||
```
|
||||
|
||||
From inside the Reflector container:
|
||||
```bash
|
||||
docker compose exec server python -c "
|
||||
import httpx
|
||||
r = httpx.get('https://gpu.internal/docs')
|
||||
print(r.status_code)
|
||||
"
|
||||
```
|
||||
|
||||
### SSL: CERTIFICATE_VERIFY_FAILED
|
||||
|
||||
The Reflector backend doesn't trust the GPU host's CA. Fix:
|
||||
```bash
|
||||
# Re-run Reflector setup with the GPU host's CA
|
||||
./scripts/setup-selfhosted.sh --hosted --extra-ca /path/to/gpu-ca.crt
|
||||
```
|
||||
|
||||
### Diarization returns errors
|
||||
|
||||
- Accept pyannote model licenses on HuggingFace:
|
||||
- https://huggingface.co/pyannote/speaker-diarization-3.1
|
||||
- https://huggingface.co/pyannote/segmentation-3.0
|
||||
- Verify `HF_TOKEN` is set in `.env.gpu-host`
|
||||
@@ -24,6 +24,8 @@ This document explains the internals of the self-hosted deployment: how the setu
|
||||
The self-hosted deployment runs the entire Reflector platform on a single server using Docker Compose. A single bash script (`scripts/setup-selfhosted.sh`) handles all configuration and orchestration. The key design principles are:
|
||||
|
||||
- **One command to deploy** — flags select which features to enable
|
||||
- **Config memory** — CLI args are saved to `data/.selfhosted-last-args`; re-run with no flags to replay
|
||||
- **Per-service overrides** — individual ML backends (transcript, diarization, translation, padding, mixdown) can be overridden independently from the base mode
|
||||
- **Idempotent** — safe to re-run without losing existing configuration
|
||||
- **Profile-based composition** — Docker Compose profiles activate optional services
|
||||
- **No external dependencies required** — with `--garage` and `--ollama-*`, everything runs locally
|
||||
@@ -61,8 +63,9 @@ Creates or updates the backend environment file from `server/.env.selfhosted.exa
|
||||
- **Infrastructure** — PostgreSQL URL, Redis host, Celery broker (all pointing to Docker-internal hostnames)
|
||||
- **Public URLs** — `BASE_URL` and `CORS_ORIGIN` computed from the domain (if `--domain`), IP (if detected on Linux), or `localhost`
|
||||
- **WebRTC** — `WEBRTC_HOST` set to the server's LAN IP so browsers can reach UDP ICE candidates
|
||||
- **Specialized models** — always points to `http://transcription:8000` (the Docker network alias shared by GPU and CPU containers)
|
||||
- **HuggingFace token** — prompts interactively for pyannote model access; writes to root `.env` so Docker Compose can inject it into GPU/CPU containers
|
||||
- **ML backends (per-service)** — Each ML service (transcript, diarization, translation, padding, mixdown) is configured independently using "effective backends" (`EFF_TRANSCRIPT`, `EFF_DIARIZATION`, `EFF_TRANSLATION`, `EFF_PADDING`, `EFF_MIXDOWN`). These are resolved from the base mode default + any `--transcript`/`--diarization`/`--translation`/`--padding`/`--mixdown` overrides. For `modal` backends, the URL is `http://transcription:8000` (GPU mode), user-provided (hosted mode), or read from existing env (CPU mode with override). For CPU backends, no URL is needed (in-process). If a service is overridden to `modal` in CPU mode without a URL configured, the script warns the user to set `TRANSCRIPT_URL` in `server/.env`
|
||||
- **CPU timeouts** — `TRANSCRIPT_FILE_TIMEOUT` and `DIARIZATION_FILE_TIMEOUT` are increased to 3600s only for services actually using CPU backends (whisper/pyannote), not blanket for the whole mode
|
||||
- **HuggingFace token** — prompted when diarization uses `pyannote` (in-process) or when GPU mode is active (GPU container needs it). Writes to root `.env` so Docker Compose can inject it into GPU/CPU containers
|
||||
- **LLM** — if `--ollama-*` is used, configures `LLM_URL` pointing to the Ollama container. Otherwise, warns that the user needs to configure an external LLM
|
||||
- **Public mode** — sets `PUBLIC_MODE=true` so the app is accessible without authentication by default
|
||||
- **Password auth** — if `--password` is passed, sets `AUTH_BACKEND=password`, `PUBLIC_MODE=false`, `ADMIN_EMAIL=admin@localhost`, and `ADMIN_PASSWORD_HASH` (the hash generated in Step 1). The admin user is provisioned in the database on container startup via `runserver.sh`
|
||||
@@ -228,11 +231,19 @@ Both the `gpu` and `cpu` services define a Docker network alias of `transcriptio
|
||||
Environment variables flow through multiple layers. Understanding this prevents confusion when debugging:
|
||||
|
||||
```
|
||||
Flags (--gpu, --garage, etc.)
|
||||
CLI args (--gpu, --garage, --padding modal, --mixdown modal, etc.)
|
||||
│
|
||||
├── setup-selfhosted.sh interprets flags
|
||||
├── Config memory: saved to data/.selfhosted-last-args
|
||||
│ (replayed on next run if no args provided)
|
||||
│
|
||||
├── setup-selfhosted.sh resolves effective backends:
|
||||
│ EFF_TRANSCRIPT = override or base mode default
|
||||
│ EFF_DIARIZATION = override or base mode default
|
||||
│ EFF_TRANSLATION = override or base mode default
|
||||
│ EFF_PADDING = override or base mode default
|
||||
│ EFF_MIXDOWN = override or base mode default
|
||||
│ │
|
||||
│ ├── Writes server/.env (backend config)
|
||||
│ ├── Writes server/.env (backend config, per-service backends)
|
||||
│ ├── Writes www/.env (frontend config)
|
||||
│ ├── Writes .env (HF_TOKEN for compose interpolation)
|
||||
│ └── Writes Caddyfile (proxy routes)
|
||||
|
||||
@@ -70,7 +70,7 @@ That's it. The script generates env files, secrets, starts all containers, waits
|
||||
|
||||
## ML Processing Modes (Required)
|
||||
|
||||
Pick `--gpu`, `--cpu`, or `--hosted`. This determines how **transcription, diarization, translation, and audio padding** run:
|
||||
Pick `--gpu`, `--cpu`, or `--hosted`. This determines how **transcription, diarization, translation, audio padding, and audio mixdown** run:
|
||||
|
||||
| Flag | What it does | Requires |
|
||||
|------|-------------|----------|
|
||||
@@ -158,6 +158,56 @@ Without `--caddy` or `--domain`, no ports are exposed. Point your own reverse pr
|
||||
|
||||
**Without a domain:** `--caddy` alone uses a self-signed certificate. Browsers will show a security warning that must be accepted.
|
||||
|
||||
## Per-Service Backend Overrides
|
||||
|
||||
Override individual ML services without changing the base mode. Useful when you want most services on one backend but need specific services on another.
|
||||
|
||||
| Flag | Valid backends | Default (`--gpu`/`--hosted`) | Default (`--cpu`) |
|
||||
|------|---------------|------------------------------|-------------------|
|
||||
| `--transcript BACKEND` | `whisper`, `modal` | `modal` | `whisper` |
|
||||
| `--diarization BACKEND` | `pyannote`, `modal` | `modal` | `pyannote` |
|
||||
| `--translation BACKEND` | `marian`, `modal`, `passthrough` | `modal` | `marian` |
|
||||
| `--padding BACKEND` | `pyav`, `modal` | `modal` | `pyav` |
|
||||
| `--mixdown BACKEND` | `pyav`, `modal` | `modal` | `pyav` |
|
||||
|
||||
**Examples:**
|
||||
|
||||
```bash
|
||||
# CPU base, but use a remote modal service for padding only
|
||||
./scripts/setup-selfhosted.sh --cpu --padding modal --garage --caddy
|
||||
|
||||
# GPU base, but skip translation entirely (passthrough)
|
||||
./scripts/setup-selfhosted.sh --gpu --translation passthrough --garage --caddy
|
||||
|
||||
# CPU base with remote modal diarization and translation
|
||||
./scripts/setup-selfhosted.sh --cpu --diarization modal --translation modal --garage
|
||||
```
|
||||
|
||||
When overriding a service to `modal` in `--cpu` mode, the script will warn you to configure the service URL (`TRANSCRIPT_URL` etc.) in `server/.env` to point to your GPU service, then re-run.
|
||||
|
||||
When overriding a service to a CPU backend (e.g., `--transcript whisper`) in `--gpu` mode, that service runs in-process on the server/worker containers while the GPU container still serves the remaining `modal` services.
|
||||
|
||||
## Config Memory (No-Flag Re-run)
|
||||
|
||||
After a successful run, the script saves your CLI arguments to `data/.selfhosted-last-args`. On subsequent runs with no arguments, the saved configuration is automatically replayed:
|
||||
|
||||
```bash
|
||||
# First run — saves the config
|
||||
./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy
|
||||
|
||||
# Later re-runs — same config, no flags needed
|
||||
./scripts/setup-selfhosted.sh
|
||||
# => "No flags provided — replaying saved configuration:"
|
||||
# => " --gpu --ollama-gpu --garage --caddy"
|
||||
```
|
||||
|
||||
To change the configuration, pass new flags — they override and replace the saved config:
|
||||
|
||||
```bash
|
||||
# Switch to CPU mode with overrides — this becomes the new saved config
|
||||
./scripts/setup-selfhosted.sh --cpu --padding modal --garage --caddy
|
||||
```
|
||||
|
||||
## What the Script Does
|
||||
|
||||
1. **Prerequisites check** — Docker, NVIDIA GPU (if needed), compose file exists
|
||||
@@ -189,6 +239,8 @@ Without `--caddy` or `--domain`, no ports are exposed. Point your own reverse pr
|
||||
| `TRANSCRIPT_URL` | Specialized model endpoint | `http://transcription:8000` |
|
||||
| `PADDING_BACKEND` | Audio padding backend (`pyav` or `modal`) | `modal` (selfhosted), `pyav` (default) |
|
||||
| `PADDING_URL` | Audio padding endpoint (when `PADDING_BACKEND=modal`) | `http://transcription:8000` |
|
||||
| `MIXDOWN_BACKEND` | Audio mixdown backend (`pyav` or `modal`) | `modal` (selfhosted), `pyav` (default) |
|
||||
| `MIXDOWN_URL` | Audio mixdown endpoint (when `MIXDOWN_BACKEND=modal`) | `http://transcription:8000` |
|
||||
| `LLM_URL` | OpenAI-compatible LLM endpoint | Auto-set for Ollama modes |
|
||||
| `LLM_API_KEY` | LLM API key | `not-needed` for Ollama |
|
||||
| `LLM_MODEL` | LLM model name | `qwen2.5:14b` for Ollama (override with `--llm-model`) |
|
||||
@@ -576,9 +628,9 @@ docker compose -f docker-compose.selfhosted.yml exec gpu curl http://localhost:8
|
||||
## Updating
|
||||
|
||||
```bash
|
||||
# Option A: Pull latest prebuilt images and restart
|
||||
# Option A: Pull latest prebuilt images and restart (replays saved config automatically)
|
||||
docker compose -f docker-compose.selfhosted.yml down
|
||||
./scripts/setup-selfhosted.sh <same-flags-as-before>
|
||||
./scripts/setup-selfhosted.sh
|
||||
|
||||
# Option B: Build from source (after git pull) and restart
|
||||
git pull
|
||||
@@ -589,6 +641,8 @@ docker compose -f docker-compose.selfhosted.yml down
|
||||
docker compose -f docker-compose.selfhosted.yml build gpu # or cpu
|
||||
```
|
||||
|
||||
> **Note on config memory:** Running with no flags replays the saved config from your last run. Running with *any* flags replaces the saved config entirely — the script always saves the complete set of flags you provide. See [Config Memory](#config-memory-no-flag-re-run).
|
||||
|
||||
The setup script is idempotent — it won't overwrite existing secrets or env vars that are already set.
|
||||
|
||||
## Architecture Overview
|
||||
|
||||
@@ -132,13 +132,22 @@ fi
|
||||
echo " -> $DIARIZER_URL"
|
||||
|
||||
echo ""
|
||||
echo "Deploying padding (CPU audio processing via Modal SDK)..."
|
||||
modal deploy reflector_padding.py
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Deploying padding (CPU audio processing)..."
|
||||
PADDING_URL=$(modal deploy reflector_padding.py 2>&1 | grep -o 'https://[^ ]*web.modal.run' | head -1)
|
||||
if [ -z "$PADDING_URL" ]; then
|
||||
echo "Error: Failed to deploy padding. Check Modal dashboard for details."
|
||||
exit 1
|
||||
fi
|
||||
echo " -> reflector-padding.pad_track (Modal SDK function)"
|
||||
echo " -> $PADDING_URL"
|
||||
|
||||
echo ""
|
||||
echo "Deploying mixdown (CPU multi-track audio mixing)..."
|
||||
MIXDOWN_URL=$(modal deploy reflector_mixdown.py 2>&1 | grep -o 'https://[^ ]*web.modal.run' | head -1)
|
||||
if [ -z "$MIXDOWN_URL" ]; then
|
||||
echo "Error: Failed to deploy mixdown. Check Modal dashboard for details."
|
||||
exit 1
|
||||
fi
|
||||
echo " -> $MIXDOWN_URL"
|
||||
|
||||
# --- Output Configuration ---
|
||||
echo ""
|
||||
@@ -157,5 +166,11 @@ echo "DIARIZATION_BACKEND=modal"
|
||||
echo "DIARIZATION_URL=$DIARIZER_URL"
|
||||
echo "DIARIZATION_MODAL_API_KEY=$API_KEY"
|
||||
echo ""
|
||||
echo "# Padding uses Modal SDK (requires MODAL_TOKEN_ID/SECRET in worker containers)"
|
||||
echo "PADDING_BACKEND=modal"
|
||||
echo "PADDING_URL=$PADDING_URL"
|
||||
echo "PADDING_MODAL_API_KEY=$API_KEY"
|
||||
echo ""
|
||||
echo "MIXDOWN_BACKEND=modal"
|
||||
echo "MIXDOWN_URL=$MIXDOWN_URL"
|
||||
echo "MIXDOWN_MODAL_API_KEY=$API_KEY"
|
||||
echo "# --- End Modal Configuration ---"
|
||||
|
||||
385
gpu/modal_deployments/reflector_mixdown.py
Normal file
385
gpu/modal_deployments/reflector_mixdown.py
Normal file
@@ -0,0 +1,385 @@
|
||||
"""
|
||||
Reflector GPU backend - audio mixdown
|
||||
=====================================
|
||||
|
||||
CPU-intensive multi-track audio mixdown service.
|
||||
Mixes N audio tracks into a single MP3 using PyAV amix filter graph.
|
||||
|
||||
IMPORTANT: This mixdown logic is duplicated from server/reflector/utils/audio_mixdown.py
|
||||
for Modal deployment isolation (Modal can't import from server/reflector/). If you modify
|
||||
the PyAV filter graph or mixdown algorithm, you MUST update both:
|
||||
- gpu/modal_deployments/reflector_mixdown.py (this file)
|
||||
- server/reflector/utils/audio_mixdown.py
|
||||
|
||||
Constants duplicated from server/reflector/utils/audio_constants.py for same reason.
|
||||
"""
|
||||
|
||||
import os
|
||||
import tempfile
|
||||
from fractions import Fraction
|
||||
import asyncio
|
||||
|
||||
import modal
|
||||
|
||||
S3_TIMEOUT = 120 # Higher than padding (60s) — multiple track downloads
|
||||
MIXDOWN_TIMEOUT = 1200 + (S3_TIMEOUT * 2) # 1440s total
|
||||
SCALEDOWN_WINDOW = 60
|
||||
DISCONNECT_CHECK_INTERVAL = 2
|
||||
|
||||
app = modal.App("reflector-mixdown")
|
||||
|
||||
# CPU-based image (mixdown is CPU-bound, no GPU needed)
|
||||
image = (
|
||||
modal.Image.debian_slim(python_version="3.12")
|
||||
.apt_install("ffmpeg") # Required by PyAV
|
||||
.pip_install(
|
||||
"av==13.1.0", # PyAV for audio processing
|
||||
"requests==2.32.3", # HTTP for presigned URL downloads/uploads
|
||||
"fastapi==0.115.12", # API framework
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@app.function(
|
||||
cpu=4.0, # Higher than padding (2.0) for multi-track mixing
|
||||
timeout=MIXDOWN_TIMEOUT,
|
||||
scaledown_window=SCALEDOWN_WINDOW,
|
||||
image=image,
|
||||
secrets=[modal.Secret.from_name("reflector-gpu")],
|
||||
)
|
||||
@modal.asgi_app()
|
||||
def web():
|
||||
from fastapi import Depends, FastAPI, HTTPException, Request, status
|
||||
from fastapi.security import OAuth2PasswordBearer
|
||||
from pydantic import BaseModel
|
||||
|
||||
class MixdownRequest(BaseModel):
|
||||
track_urls: list[str]
|
||||
output_url: str
|
||||
target_sample_rate: int | None = None
|
||||
offsets_seconds: list[float] | None = None
|
||||
|
||||
class MixdownResponse(BaseModel):
|
||||
size: int
|
||||
duration_ms: float = 0.0
|
||||
cancelled: bool = False
|
||||
|
||||
web_app = FastAPI()
|
||||
|
||||
oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
|
||||
|
||||
def apikey_auth(apikey: str = Depends(oauth2_scheme)):
|
||||
if apikey == os.environ["REFLECTOR_GPU_APIKEY"]:
|
||||
return
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_401_UNAUTHORIZED,
|
||||
detail="Invalid API key",
|
||||
headers={"WWW-Authenticate": "Bearer"},
|
||||
)
|
||||
|
||||
@web_app.post("/mixdown", dependencies=[Depends(apikey_auth)])
|
||||
async def mixdown_endpoint(request: Request, req: MixdownRequest) -> MixdownResponse:
|
||||
"""Modal web endpoint for mixing audio tracks with disconnect detection."""
|
||||
import logging
|
||||
import threading
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
valid_urls = [u for u in req.track_urls if u]
|
||||
if not valid_urls:
|
||||
raise HTTPException(status_code=400, detail="No valid track URLs provided")
|
||||
if req.offsets_seconds is not None:
|
||||
if len(req.offsets_seconds) != len(req.track_urls):
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"offsets_seconds length ({len(req.offsets_seconds)}) "
|
||||
f"must match track_urls ({len(req.track_urls)})",
|
||||
)
|
||||
if any(o > 18000 for o in req.offsets_seconds):
|
||||
raise HTTPException(status_code=400, detail="offsets_seconds exceeds maximum 18000s (5 hours)")
|
||||
if not req.output_url:
|
||||
raise HTTPException(status_code=400, detail="output_url cannot be empty")
|
||||
|
||||
logger.info(f"Mixdown request: {len(valid_urls)} tracks")
|
||||
|
||||
# Thread-safe cancellation flag
|
||||
cancelled = threading.Event()
|
||||
|
||||
async def check_disconnect():
|
||||
"""Background task to check for client disconnect."""
|
||||
while not cancelled.is_set():
|
||||
await asyncio.sleep(DISCONNECT_CHECK_INTERVAL)
|
||||
if await request.is_disconnected():
|
||||
logger.warning("Client disconnected, setting cancellation flag")
|
||||
cancelled.set()
|
||||
break
|
||||
|
||||
disconnect_task = asyncio.create_task(check_disconnect())
|
||||
|
||||
try:
|
||||
result = await asyncio.get_event_loop().run_in_executor(
|
||||
None, _mixdown_tracks_blocking, req, cancelled, logger
|
||||
)
|
||||
return MixdownResponse(**result)
|
||||
finally:
|
||||
cancelled.set()
|
||||
disconnect_task.cancel()
|
||||
try:
|
||||
await disconnect_task
|
||||
except asyncio.CancelledError:
|
||||
pass
|
||||
|
||||
def _mixdown_tracks_blocking(req, cancelled, logger) -> dict:
|
||||
"""Blocking CPU-bound mixdown work with periodic cancellation checks.
|
||||
|
||||
Downloads all tracks, builds PyAV amix filter graph, encodes to MP3,
|
||||
and uploads the result to the presigned output URL.
|
||||
"""
|
||||
import av
|
||||
import requests
|
||||
from av.audio.resampler import AudioResampler
|
||||
import time
|
||||
|
||||
temp_dir = tempfile.mkdtemp()
|
||||
track_paths = []
|
||||
output_path = None
|
||||
last_check = time.time()
|
||||
|
||||
try:
|
||||
# --- Download all tracks ---
|
||||
valid_urls = [u for u in req.track_urls if u]
|
||||
for i, url in enumerate(valid_urls):
|
||||
if cancelled.is_set():
|
||||
logger.info("Cancelled during download phase")
|
||||
return {"size": 0, "duration_ms": 0.0, "cancelled": True}
|
||||
|
||||
logger.info(f"Downloading track {i}")
|
||||
response = requests.get(url, stream=True, timeout=S3_TIMEOUT)
|
||||
response.raise_for_status()
|
||||
|
||||
track_path = os.path.join(temp_dir, f"track_{i}.webm")
|
||||
total_bytes = 0
|
||||
chunk_count = 0
|
||||
with open(track_path, "wb") as f:
|
||||
for chunk in response.iter_content(chunk_size=8192):
|
||||
if chunk:
|
||||
f.write(chunk)
|
||||
total_bytes += len(chunk)
|
||||
chunk_count += 1
|
||||
if chunk_count % 12 == 0:
|
||||
now = time.time()
|
||||
if now - last_check >= DISCONNECT_CHECK_INTERVAL:
|
||||
if cancelled.is_set():
|
||||
logger.info(f"Cancelled during track {i} download")
|
||||
return {"size": 0, "duration_ms": 0.0, "cancelled": True}
|
||||
last_check = now
|
||||
|
||||
track_paths.append(track_path)
|
||||
logger.info(f"Track {i} downloaded: {total_bytes} bytes")
|
||||
|
||||
if not track_paths:
|
||||
raise ValueError("No tracks downloaded")
|
||||
|
||||
# --- Detect sample rate ---
|
||||
target_sample_rate = req.target_sample_rate
|
||||
if target_sample_rate is None:
|
||||
for path in track_paths:
|
||||
try:
|
||||
container = av.open(path)
|
||||
for frame in container.decode(audio=0):
|
||||
target_sample_rate = frame.sample_rate
|
||||
container.close()
|
||||
break
|
||||
else:
|
||||
container.close()
|
||||
continue
|
||||
break
|
||||
except Exception:
|
||||
continue
|
||||
if target_sample_rate is None:
|
||||
raise ValueError("Could not detect sample rate from any track")
|
||||
|
||||
logger.info(f"Target sample rate: {target_sample_rate}")
|
||||
|
||||
# --- Calculate per-input delays ---
|
||||
input_offsets_seconds = None
|
||||
if req.offsets_seconds is not None:
|
||||
input_offsets_seconds = [
|
||||
req.offsets_seconds[i] for i, url in enumerate(req.track_urls) if url
|
||||
]
|
||||
|
||||
delays_ms = []
|
||||
if input_offsets_seconds is not None:
|
||||
base = min(input_offsets_seconds) if input_offsets_seconds else 0.0
|
||||
delays_ms = [max(0, int(round((o - base) * 1000))) for o in input_offsets_seconds]
|
||||
else:
|
||||
delays_ms = [0 for _ in track_paths]
|
||||
|
||||
# --- Build filter graph ---
|
||||
# N abuffer -> optional adelay -> amix -> aformat -> abuffersink
|
||||
graph = av.filter.Graph()
|
||||
inputs = []
|
||||
|
||||
for idx in range(len(track_paths)):
|
||||
args = (
|
||||
f"time_base=1/{target_sample_rate}:"
|
||||
f"sample_rate={target_sample_rate}:"
|
||||
f"sample_fmt=s32:"
|
||||
f"channel_layout=stereo"
|
||||
)
|
||||
in_ctx = graph.add("abuffer", args=args, name=f"in{idx}")
|
||||
inputs.append(in_ctx)
|
||||
|
||||
mixer = graph.add("amix", args=f"inputs={len(inputs)}:normalize=0", name="mix")
|
||||
fmt = graph.add(
|
||||
"aformat",
|
||||
args=f"sample_fmts=s32:channel_layouts=stereo:sample_rates={target_sample_rate}",
|
||||
name="fmt",
|
||||
)
|
||||
sink = graph.add("abuffersink", name="out")
|
||||
|
||||
for idx, in_ctx in enumerate(inputs):
|
||||
delay_ms = delays_ms[idx] if idx < len(delays_ms) else 0
|
||||
if delay_ms > 0:
|
||||
adelay = graph.add(
|
||||
"adelay",
|
||||
args=f"delays={delay_ms}|{delay_ms}:all=1",
|
||||
name=f"delay{idx}",
|
||||
)
|
||||
in_ctx.link_to(adelay)
|
||||
adelay.link_to(mixer, 0, idx)
|
||||
else:
|
||||
in_ctx.link_to(mixer, 0, idx)
|
||||
|
||||
mixer.link_to(fmt)
|
||||
fmt.link_to(sink)
|
||||
graph.configure()
|
||||
|
||||
# --- Open all containers and decode ---
|
||||
containers = []
|
||||
output_path = os.path.join(temp_dir, "mixed.mp3")
|
||||
|
||||
try:
|
||||
for path in track_paths:
|
||||
containers.append(av.open(path))
|
||||
|
||||
decoders = [c.decode(audio=0) for c in containers]
|
||||
active = [True] * len(decoders)
|
||||
resamplers = [
|
||||
AudioResampler(format="s32", layout="stereo", rate=target_sample_rate)
|
||||
for _ in decoders
|
||||
]
|
||||
|
||||
# Open output MP3
|
||||
out_container = av.open(output_path, "w", format="mp3")
|
||||
out_stream = out_container.add_stream("libmp3lame", rate=target_sample_rate)
|
||||
total_duration = 0
|
||||
|
||||
while any(active):
|
||||
# Check cancellation periodically
|
||||
now = time.time()
|
||||
if now - last_check >= DISCONNECT_CHECK_INTERVAL:
|
||||
if cancelled.is_set():
|
||||
logger.info("Cancelled during mixing")
|
||||
out_container.close()
|
||||
return {"size": 0, "duration_ms": 0.0, "cancelled": True}
|
||||
last_check = now
|
||||
|
||||
for i, (dec, is_active) in enumerate(zip(decoders, active)):
|
||||
if not is_active:
|
||||
continue
|
||||
try:
|
||||
frame = next(dec)
|
||||
except StopIteration:
|
||||
active[i] = False
|
||||
inputs[i].push(None)
|
||||
continue
|
||||
|
||||
if frame.sample_rate != target_sample_rate:
|
||||
continue
|
||||
|
||||
out_frames = resamplers[i].resample(frame) or []
|
||||
for rf in out_frames:
|
||||
rf.sample_rate = target_sample_rate
|
||||
rf.time_base = Fraction(1, target_sample_rate)
|
||||
inputs[i].push(rf)
|
||||
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
for packet in out_stream.encode(mixed):
|
||||
out_container.mux(packet)
|
||||
total_duration += packet.duration
|
||||
|
||||
# Flush filter graph
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
for packet in out_stream.encode(mixed):
|
||||
out_container.mux(packet)
|
||||
total_duration += packet.duration
|
||||
|
||||
# Flush encoder
|
||||
for packet in out_stream.encode(None):
|
||||
out_container.mux(packet)
|
||||
total_duration += packet.duration
|
||||
|
||||
# Calculate duration in ms
|
||||
last_tb = out_stream.time_base
|
||||
duration_ms = 0.0
|
||||
if last_tb and total_duration > 0:
|
||||
duration_ms = round(float(total_duration * last_tb * 1000), 2)
|
||||
|
||||
out_container.close()
|
||||
|
||||
finally:
|
||||
for c in containers:
|
||||
try:
|
||||
c.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
file_size = os.path.getsize(output_path)
|
||||
logger.info(f"Mixdown complete: {file_size} bytes, {duration_ms}ms")
|
||||
|
||||
if cancelled.is_set():
|
||||
logger.info("Cancelled after mixing, before upload")
|
||||
return {"size": 0, "duration_ms": 0.0, "cancelled": True}
|
||||
|
||||
# --- Upload result ---
|
||||
logger.info("Uploading mixed audio to S3")
|
||||
with open(output_path, "rb") as f:
|
||||
upload_response = requests.put(req.output_url, data=f, timeout=S3_TIMEOUT)
|
||||
upload_response.raise_for_status()
|
||||
logger.info(f"Upload complete: {file_size} bytes")
|
||||
|
||||
return {"size": file_size, "duration_ms": duration_ms}
|
||||
|
||||
finally:
|
||||
# Cleanup all temp files
|
||||
for path in track_paths:
|
||||
if os.path.exists(path):
|
||||
try:
|
||||
os.unlink(path)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to cleanup track file: {e}")
|
||||
if output_path and os.path.exists(output_path):
|
||||
try:
|
||||
os.unlink(output_path)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to cleanup output file: {e}")
|
||||
try:
|
||||
os.rmdir(temp_dir)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to cleanup temp directory: {e}")
|
||||
|
||||
return web_app
|
||||
@@ -52,10 +52,12 @@ OPUS_DEFAULT_BIT_RATE = 128000
|
||||
timeout=PADDING_TIMEOUT,
|
||||
scaledown_window=SCALEDOWN_WINDOW,
|
||||
image=image,
|
||||
secrets=[modal.Secret.from_name("reflector-gpu")],
|
||||
)
|
||||
@modal.asgi_app()
|
||||
def web():
|
||||
from fastapi import FastAPI, Request, HTTPException
|
||||
from fastapi import Depends, FastAPI, HTTPException, Request, status
|
||||
from fastapi.security import OAuth2PasswordBearer
|
||||
from pydantic import BaseModel
|
||||
|
||||
class PaddingRequest(BaseModel):
|
||||
@@ -70,7 +72,18 @@ def web():
|
||||
|
||||
web_app = FastAPI()
|
||||
|
||||
@web_app.post("/pad")
|
||||
oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
|
||||
|
||||
def apikey_auth(apikey: str = Depends(oauth2_scheme)):
|
||||
if apikey == os.environ["REFLECTOR_GPU_APIKEY"]:
|
||||
return
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_401_UNAUTHORIZED,
|
||||
detail="Invalid API key",
|
||||
headers={"WWW-Authenticate": "Bearer"},
|
||||
)
|
||||
|
||||
@web_app.post("/pad", dependencies=[Depends(apikey_auth)])
|
||||
async def pad_track_endpoint(request: Request, req: PaddingRequest) -> PaddingResponse:
|
||||
"""Modal web endpoint for padding audio tracks with disconnect detection.
|
||||
"""
|
||||
|
||||
@@ -42,6 +42,7 @@ COPY pyproject.toml uv.lock /app/
|
||||
COPY ./app /app/app
|
||||
COPY ./main.py /app/
|
||||
COPY ./runserver.sh /app/
|
||||
COPY ./docker-entrypoint.sh /app/
|
||||
|
||||
# prevent uv failing with too many open files on big cpus
|
||||
ENV UV_CONCURRENT_INSTALLS=16
|
||||
@@ -52,6 +53,8 @@ RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
CMD ["sh", "/app/runserver.sh"]
|
||||
RUN chmod +x /app/docker-entrypoint.sh
|
||||
|
||||
CMD ["sh", "/app/docker-entrypoint.sh"]
|
||||
|
||||
|
||||
|
||||
@@ -26,6 +26,7 @@ COPY pyproject.toml uv.lock /app/
|
||||
COPY ./app /app/app
|
||||
COPY ./main.py /app/
|
||||
COPY ./runserver.sh /app/
|
||||
COPY ./docker-entrypoint.sh /app/
|
||||
|
||||
# prevent uv failing with too many open files on big cpus
|
||||
ENV UV_CONCURRENT_INSTALLS=16
|
||||
@@ -36,4 +37,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
|
||||
EXPOSE 8000
|
||||
|
||||
CMD ["sh", "/app/runserver.sh"]
|
||||
RUN chmod +x /app/docker-entrypoint.sh
|
||||
|
||||
CMD ["sh", "/app/docker-entrypoint.sh"]
|
||||
|
||||
@@ -3,6 +3,7 @@ from contextlib import asynccontextmanager
|
||||
from fastapi import FastAPI
|
||||
|
||||
from .routers.diarization import router as diarization_router
|
||||
from .routers.mixdown import router as mixdown_router
|
||||
from .routers.padding import router as padding_router
|
||||
from .routers.transcription import router as transcription_router
|
||||
from .routers.translation import router as translation_router
|
||||
@@ -29,4 +30,5 @@ def create_app() -> FastAPI:
|
||||
app.include_router(translation_router)
|
||||
app.include_router(diarization_router)
|
||||
app.include_router(padding_router)
|
||||
app.include_router(mixdown_router)
|
||||
return app
|
||||
|
||||
288
gpu/self_hosted/app/routers/mixdown.py
Normal file
288
gpu/self_hosted/app/routers/mixdown.py
Normal file
@@ -0,0 +1,288 @@
|
||||
"""
|
||||
Audio mixdown endpoint for selfhosted GPU service.
|
||||
|
||||
CPU-intensive multi-track audio mixing service for combining N audio tracks
|
||||
into a single MP3 using PyAV amix filter graph.
|
||||
|
||||
IMPORTANT: This mixdown logic is duplicated from server/reflector/utils/audio_mixdown.py
|
||||
for deployment isolation (self_hosted can't import from server/reflector/). If you modify
|
||||
the PyAV filter graph or mixdown algorithm, you MUST update both:
|
||||
- gpu/self_hosted/app/routers/mixdown.py (this file)
|
||||
- server/reflector/utils/audio_mixdown.py
|
||||
|
||||
Constants duplicated from server/reflector/utils/audio_constants.py for same reason.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import tempfile
|
||||
from fractions import Fraction
|
||||
|
||||
import av
|
||||
import requests
|
||||
from av.audio.resampler import AudioResampler
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from pydantic import BaseModel
|
||||
|
||||
from ..auth import apikey_auth
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(tags=["mixdown"])
|
||||
|
||||
S3_TIMEOUT = 120
|
||||
|
||||
|
||||
class MixdownRequest(BaseModel):
|
||||
track_urls: list[str]
|
||||
output_url: str
|
||||
target_sample_rate: int | None = None
|
||||
offsets_seconds: list[float] | None = None
|
||||
|
||||
|
||||
class MixdownResponse(BaseModel):
|
||||
size: int
|
||||
duration_ms: float = 0.0
|
||||
cancelled: bool = False
|
||||
|
||||
|
||||
@router.post("/mixdown", dependencies=[Depends(apikey_auth)], response_model=MixdownResponse)
|
||||
def mixdown_tracks(req: MixdownRequest):
|
||||
"""Mix multiple audio tracks into single MP3 using PyAV amix filter graph."""
|
||||
valid_urls = [u for u in req.track_urls if u]
|
||||
if not valid_urls:
|
||||
raise HTTPException(status_code=400, detail="No valid track URLs provided")
|
||||
if req.offsets_seconds is not None:
|
||||
if len(req.offsets_seconds) != len(req.track_urls):
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"offsets_seconds length ({len(req.offsets_seconds)}) "
|
||||
f"must match track_urls ({len(req.track_urls)})",
|
||||
)
|
||||
if any(o > 18000 for o in req.offsets_seconds):
|
||||
raise HTTPException(
|
||||
status_code=400, detail="offsets_seconds exceeds maximum 18000s (5 hours)"
|
||||
)
|
||||
if not req.output_url:
|
||||
raise HTTPException(status_code=400, detail="output_url cannot be empty")
|
||||
|
||||
logger.info("Mixdown request: %d tracks", len(valid_urls))
|
||||
|
||||
temp_dir = tempfile.mkdtemp()
|
||||
track_paths = []
|
||||
output_path = None
|
||||
|
||||
try:
|
||||
# --- Download all tracks ---
|
||||
for i, url in enumerate(valid_urls):
|
||||
logger.info("Downloading track %d", i)
|
||||
response = requests.get(url, stream=True, timeout=S3_TIMEOUT)
|
||||
response.raise_for_status()
|
||||
|
||||
track_path = os.path.join(temp_dir, f"track_{i}.webm")
|
||||
total_bytes = 0
|
||||
with open(track_path, "wb") as f:
|
||||
for chunk in response.iter_content(chunk_size=8192):
|
||||
if chunk:
|
||||
f.write(chunk)
|
||||
total_bytes += len(chunk)
|
||||
|
||||
track_paths.append(track_path)
|
||||
logger.info("Track %d downloaded: %d bytes", i, total_bytes)
|
||||
|
||||
if not track_paths:
|
||||
raise HTTPException(status_code=400, detail="No tracks could be downloaded")
|
||||
|
||||
# --- Detect sample rate ---
|
||||
target_sample_rate = req.target_sample_rate
|
||||
if target_sample_rate is None:
|
||||
for path in track_paths:
|
||||
try:
|
||||
container = av.open(path)
|
||||
for frame in container.decode(audio=0):
|
||||
target_sample_rate = frame.sample_rate
|
||||
container.close()
|
||||
break
|
||||
else:
|
||||
container.close()
|
||||
continue
|
||||
break
|
||||
except Exception:
|
||||
continue
|
||||
if target_sample_rate is None:
|
||||
raise HTTPException(
|
||||
status_code=400, detail="Could not detect sample rate from any track"
|
||||
)
|
||||
|
||||
logger.info("Target sample rate: %d", target_sample_rate)
|
||||
|
||||
# --- Calculate per-input delays ---
|
||||
input_offsets_seconds = None
|
||||
if req.offsets_seconds is not None:
|
||||
input_offsets_seconds = [
|
||||
req.offsets_seconds[i] for i, url in enumerate(req.track_urls) if url
|
||||
]
|
||||
|
||||
delays_ms = []
|
||||
if input_offsets_seconds is not None:
|
||||
base = min(input_offsets_seconds) if input_offsets_seconds else 0.0
|
||||
delays_ms = [max(0, int(round((o - base) * 1000))) for o in input_offsets_seconds]
|
||||
else:
|
||||
delays_ms = [0 for _ in track_paths]
|
||||
|
||||
# --- Build filter graph ---
|
||||
# N abuffer -> optional adelay -> amix -> aformat -> abuffersink
|
||||
graph = av.filter.Graph()
|
||||
inputs = []
|
||||
|
||||
for idx in range(len(track_paths)):
|
||||
args = (
|
||||
f"time_base=1/{target_sample_rate}:"
|
||||
f"sample_rate={target_sample_rate}:"
|
||||
f"sample_fmt=s32:"
|
||||
f"channel_layout=stereo"
|
||||
)
|
||||
in_ctx = graph.add("abuffer", args=args, name=f"in{idx}")
|
||||
inputs.append(in_ctx)
|
||||
|
||||
mixer = graph.add("amix", args=f"inputs={len(inputs)}:normalize=0", name="mix")
|
||||
fmt = graph.add(
|
||||
"aformat",
|
||||
args=f"sample_fmts=s32:channel_layouts=stereo:sample_rates={target_sample_rate}",
|
||||
name="fmt",
|
||||
)
|
||||
sink = graph.add("abuffersink", name="out")
|
||||
|
||||
for idx, in_ctx in enumerate(inputs):
|
||||
delay_ms = delays_ms[idx] if idx < len(delays_ms) else 0
|
||||
if delay_ms > 0:
|
||||
adelay = graph.add(
|
||||
"adelay",
|
||||
args=f"delays={delay_ms}|{delay_ms}:all=1",
|
||||
name=f"delay{idx}",
|
||||
)
|
||||
in_ctx.link_to(adelay)
|
||||
adelay.link_to(mixer, 0, idx)
|
||||
else:
|
||||
in_ctx.link_to(mixer, 0, idx)
|
||||
|
||||
mixer.link_to(fmt)
|
||||
fmt.link_to(sink)
|
||||
graph.configure()
|
||||
|
||||
# --- Open all containers and decode ---
|
||||
containers = []
|
||||
output_path = os.path.join(temp_dir, "mixed.mp3")
|
||||
|
||||
try:
|
||||
for path in track_paths:
|
||||
containers.append(av.open(path))
|
||||
|
||||
decoders = [c.decode(audio=0) for c in containers]
|
||||
active = [True] * len(decoders)
|
||||
resamplers = [
|
||||
AudioResampler(format="s32", layout="stereo", rate=target_sample_rate)
|
||||
for _ in decoders
|
||||
]
|
||||
|
||||
# Open output MP3
|
||||
out_container = av.open(output_path, "w", format="mp3")
|
||||
out_stream = out_container.add_stream("libmp3lame", rate=target_sample_rate)
|
||||
total_duration = 0
|
||||
|
||||
while any(active):
|
||||
for i, (dec, is_active) in enumerate(zip(decoders, active)):
|
||||
if not is_active:
|
||||
continue
|
||||
try:
|
||||
frame = next(dec)
|
||||
except StopIteration:
|
||||
active[i] = False
|
||||
inputs[i].push(None)
|
||||
continue
|
||||
|
||||
if frame.sample_rate != target_sample_rate:
|
||||
continue
|
||||
|
||||
out_frames = resamplers[i].resample(frame) or []
|
||||
for rf in out_frames:
|
||||
rf.sample_rate = target_sample_rate
|
||||
rf.time_base = Fraction(1, target_sample_rate)
|
||||
inputs[i].push(rf)
|
||||
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
for packet in out_stream.encode(mixed):
|
||||
out_container.mux(packet)
|
||||
total_duration += packet.duration
|
||||
|
||||
# Flush filter graph
|
||||
while True:
|
||||
try:
|
||||
mixed = sink.pull()
|
||||
except Exception:
|
||||
break
|
||||
mixed.sample_rate = target_sample_rate
|
||||
mixed.time_base = Fraction(1, target_sample_rate)
|
||||
for packet in out_stream.encode(mixed):
|
||||
out_container.mux(packet)
|
||||
total_duration += packet.duration
|
||||
|
||||
# Flush encoder
|
||||
for packet in out_stream.encode(None):
|
||||
out_container.mux(packet)
|
||||
total_duration += packet.duration
|
||||
|
||||
# Calculate duration in ms
|
||||
last_tb = out_stream.time_base
|
||||
duration_ms = 0.0
|
||||
if last_tb and total_duration > 0:
|
||||
duration_ms = round(float(total_duration * last_tb * 1000), 2)
|
||||
|
||||
out_container.close()
|
||||
|
||||
finally:
|
||||
for c in containers:
|
||||
try:
|
||||
c.close()
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
file_size = os.path.getsize(output_path)
|
||||
logger.info("Mixdown complete: %d bytes, %.2fms", file_size, duration_ms)
|
||||
|
||||
# --- Upload result ---
|
||||
logger.info("Uploading mixed audio to S3")
|
||||
with open(output_path, "rb") as f:
|
||||
upload_response = requests.put(req.output_url, data=f, timeout=S3_TIMEOUT)
|
||||
upload_response.raise_for_status()
|
||||
logger.info("Upload complete: %d bytes", file_size)
|
||||
|
||||
return MixdownResponse(size=file_size, duration_ms=duration_ms)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error("Mixdown failed: %s", e, exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=f"Mixdown failed: {e}") from e
|
||||
finally:
|
||||
for path in track_paths:
|
||||
if os.path.exists(path):
|
||||
try:
|
||||
os.unlink(path)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to cleanup track file: %s", e)
|
||||
if output_path and os.path.exists(output_path):
|
||||
try:
|
||||
os.unlink(output_path)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to cleanup output file: %s", e)
|
||||
try:
|
||||
os.rmdir(temp_dir)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to cleanup temp directory: %s", e)
|
||||
23
gpu/self_hosted/docker-entrypoint.sh
Normal file
23
gpu/self_hosted/docker-entrypoint.sh
Normal file
@@ -0,0 +1,23 @@
|
||||
#!/bin/sh
|
||||
set -e
|
||||
|
||||
# Custom CA certificate injection
|
||||
# If a CA cert is mounted at this path (via docker-compose.ca.yml),
|
||||
# add it to the system trust store and configure all Python SSL libraries.
|
||||
CUSTOM_CA_PATH="/usr/local/share/ca-certificates/custom-ca.crt"
|
||||
|
||||
if [ -s "$CUSTOM_CA_PATH" ]; then
|
||||
echo "[entrypoint] Custom CA certificate detected, updating trust store..."
|
||||
update-ca-certificates 2>/dev/null
|
||||
|
||||
# update-ca-certificates creates a combined bundle (system + custom CAs)
|
||||
COMBINED_BUNDLE="/etc/ssl/certs/ca-certificates.crt"
|
||||
export SSL_CERT_FILE="$COMBINED_BUNDLE"
|
||||
export REQUESTS_CA_BUNDLE="$COMBINED_BUNDLE"
|
||||
export CURL_CA_BUNDLE="$COMBINED_BUNDLE"
|
||||
# Note: GRPC_DEFAULT_SSL_ROOTS_FILE_PATH is intentionally NOT set here.
|
||||
# Setting it causes grpcio to attempt TLS on connections that may be plaintext.
|
||||
echo "[entrypoint] CA trust store updated (SSL_CERT_FILE=$COMBINED_BUNDLE)"
|
||||
fi
|
||||
|
||||
exec sh /app/runserver.sh
|
||||
6
gpu/self_hosted/uv.lock
generated
6
gpu/self_hosted/uv.lock
generated
@@ -2153,7 +2153,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "requests"
|
||||
version = "2.32.5"
|
||||
version = "2.33.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "certifi" },
|
||||
@@ -2161,9 +2161,9 @@ dependencies = [
|
||||
{ name = "idna" },
|
||||
{ name = "urllib3" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/c9/74/b3ff8e6c8446842c3f5c837e9c3dfcfe2018ea6ecef224c710c85ef728f4/requests-2.32.5.tar.gz", hash = "sha256:dbba0bac56e100853db0ea71b82b4dfd5fe2bf6d3754a8893c3af500cec7d7cf", size = 134517, upload-time = "2025-08-18T20:46:02.573Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/34/64/8860370b167a9721e8956ae116825caff829224fbca0ca6e7bf8ddef8430/requests-2.33.0.tar.gz", hash = "sha256:c7ebc5e8b0f21837386ad0e1c8fe8b829fa5f544d8df3b2253bff14ef29d7652", size = 134232, upload-time = "2026-03-25T15:10:41.586Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/1e/db/4254e3eabe8020b458f1a747140d32277ec7a271daf1d235b70dc0b4e6e3/requests-2.32.5-py3-none-any.whl", hash = "sha256:2462f94637a34fd532264295e186976db0f5d453d1cdd31473c85a6a161affb6", size = 64738, upload-time = "2025-08-18T20:46:00.542Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/56/5d/c814546c2333ceea4ba42262d8c4d55763003e767fa169adc693bd524478/requests-2.33.0-py3-none-any.whl", hash = "sha256:3324635456fa185245e24865e810cecec7b4caf933d7eb133dcde67d48cee69b", size = 65017, upload-time = "2026-03-25T15:10:40.382Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
130
scripts/generate-certs.sh
Executable file
130
scripts/generate-certs.sh
Executable file
@@ -0,0 +1,130 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Generate a local CA and server certificate for Reflector self-hosted deployments.
|
||||
#
|
||||
# Usage:
|
||||
# ./scripts/generate-certs.sh DOMAIN [EXTRA_SANS...]
|
||||
#
|
||||
# Examples:
|
||||
# ./scripts/generate-certs.sh reflector.local
|
||||
# ./scripts/generate-certs.sh reflector.local "DNS:gpu.local,IP:192.168.1.100"
|
||||
#
|
||||
# Generates in certs/:
|
||||
# ca.key — CA private key (keep secret)
|
||||
# ca.crt — CA certificate (distribute to clients)
|
||||
# server-key.pem — Server private key
|
||||
# server.pem — Server certificate (signed by CA)
|
||||
#
|
||||
# Then use with setup-selfhosted.sh:
|
||||
# ./scripts/setup-selfhosted.sh --gpu --caddy --domain DOMAIN --custom-ca certs/
|
||||
#
|
||||
set -euo pipefail
|
||||
|
||||
DOMAIN="${1:?Usage: $0 DOMAIN [EXTRA_SANS...]}"
|
||||
EXTRA_SANS="${2:-}"
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
CERTS_DIR="$(cd "$SCRIPT_DIR/.." && pwd)/certs"
|
||||
|
||||
# Colors
|
||||
GREEN='\033[0;32m'
|
||||
CYAN='\033[0;36m'
|
||||
NC='\033[0m'
|
||||
info() { echo -e "${CYAN}==>${NC} $*"; }
|
||||
ok() { echo -e "${GREEN} ✓${NC} $*"; }
|
||||
|
||||
# Check for openssl
|
||||
if ! command -v openssl &>/dev/null; then
|
||||
echo "Error: openssl is required but not found. Install it first." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
mkdir -p "$CERTS_DIR"
|
||||
|
||||
# Build SAN list
|
||||
SAN_LIST="DNS:$DOMAIN,DNS:localhost,IP:127.0.0.1"
|
||||
if [[ -n "$EXTRA_SANS" ]]; then
|
||||
SAN_LIST="$SAN_LIST,$EXTRA_SANS"
|
||||
fi
|
||||
|
||||
info "Generating CA and server certificate for: $DOMAIN"
|
||||
echo " SANs: $SAN_LIST"
|
||||
echo ""
|
||||
|
||||
# --- Step 1: Generate CA ---
|
||||
if [[ -f "$CERTS_DIR/ca.key" ]] && [[ -f "$CERTS_DIR/ca.crt" ]]; then
|
||||
ok "CA already exists at certs/ca.key + certs/ca.crt — reusing"
|
||||
else
|
||||
info "Generating CA key and certificate..."
|
||||
openssl genrsa -out "$CERTS_DIR/ca.key" 4096 2>/dev/null
|
||||
openssl req -x509 -new -nodes \
|
||||
-key "$CERTS_DIR/ca.key" \
|
||||
-sha256 -days 3650 \
|
||||
-out "$CERTS_DIR/ca.crt" \
|
||||
-subj "/CN=Reflector Local CA/O=Reflector Self-Hosted"
|
||||
ok "CA certificate generated (valid for 10 years)"
|
||||
fi
|
||||
|
||||
# --- Step 2: Generate server key ---
|
||||
info "Generating server key..."
|
||||
openssl genrsa -out "$CERTS_DIR/server-key.pem" 2048 2>/dev/null
|
||||
ok "Server key generated"
|
||||
|
||||
# --- Step 3: Create CSR with SANs ---
|
||||
info "Creating certificate signing request..."
|
||||
openssl req -new \
|
||||
-key "$CERTS_DIR/server-key.pem" \
|
||||
-out "$CERTS_DIR/server.csr" \
|
||||
-subj "/CN=$DOMAIN" \
|
||||
-addext "subjectAltName=$SAN_LIST"
|
||||
ok "CSR created"
|
||||
|
||||
# --- Step 4: Sign with CA ---
|
||||
info "Signing server certificate with CA..."
|
||||
openssl x509 -req \
|
||||
-in "$CERTS_DIR/server.csr" \
|
||||
-CA "$CERTS_DIR/ca.crt" \
|
||||
-CAkey "$CERTS_DIR/ca.key" \
|
||||
-CAcreateserial \
|
||||
-out "$CERTS_DIR/server.pem" \
|
||||
-days 365 -sha256 \
|
||||
-copy_extensions copyall \
|
||||
2>/dev/null
|
||||
ok "Server certificate signed (valid for 1 year)"
|
||||
|
||||
# --- Cleanup ---
|
||||
rm -f "$CERTS_DIR/server.csr" "$CERTS_DIR/ca.srl"
|
||||
|
||||
# --- Set permissions ---
|
||||
chmod 644 "$CERTS_DIR/ca.crt" "$CERTS_DIR/server.pem"
|
||||
chmod 600 "$CERTS_DIR/ca.key" "$CERTS_DIR/server-key.pem"
|
||||
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo -e " ${GREEN}Certificates generated in certs/${NC}"
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
echo " certs/ca.key CA private key (keep secret)"
|
||||
echo " certs/ca.crt CA certificate (distribute to clients)"
|
||||
echo " certs/server-key.pem Server private key"
|
||||
echo " certs/server.pem Server certificate for $DOMAIN"
|
||||
echo ""
|
||||
echo " SANs: $SAN_LIST"
|
||||
echo ""
|
||||
echo "Use with setup-selfhosted.sh:"
|
||||
echo " ./scripts/setup-selfhosted.sh --gpu --caddy --domain $DOMAIN --custom-ca certs/"
|
||||
echo ""
|
||||
echo "Trust the CA on your machine:"
|
||||
case "$(uname -s)" in
|
||||
Darwin)
|
||||
echo " sudo security add-trusted-cert -d -r trustRoot -k /Library/Keychains/System.keychain certs/ca.crt"
|
||||
;;
|
||||
Linux)
|
||||
echo " sudo cp certs/ca.crt /usr/local/share/ca-certificates/reflector-ca.crt"
|
||||
echo " sudo update-ca-certificates"
|
||||
;;
|
||||
*)
|
||||
echo " See docsv2/custom-ca-setup.md for your platform"
|
||||
;;
|
||||
esac
|
||||
echo ""
|
||||
496
scripts/setup-gpu-host.sh
Executable file
496
scripts/setup-gpu-host.sh
Executable file
@@ -0,0 +1,496 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Standalone GPU service setup for Reflector.
|
||||
# Deploys ONLY the GPU transcription/diarization/translation service on a dedicated machine.
|
||||
# The main Reflector instance connects to this machine over HTTPS.
|
||||
#
|
||||
# Usage:
|
||||
# ./scripts/setup-gpu-host.sh [--domain DOMAIN] [--custom-ca PATH] [--extra-ca FILE] [--api-key KEY] [--cpu] [--build]
|
||||
#
|
||||
# Options:
|
||||
# --domain DOMAIN Domain name for this GPU host (e.g., gpu.example.com)
|
||||
# With --custom-ca: uses custom TLS cert. Without: uses Let's Encrypt.
|
||||
# --custom-ca PATH Custom CA certificate (dir with ca.crt + server.pem + server-key.pem, or single PEM file)
|
||||
# --extra-ca FILE Additional CA cert to trust (repeatable)
|
||||
# --api-key KEY API key to protect the GPU service (recommended for internet-facing deployments)
|
||||
# --cpu Use CPU-only Dockerfile (no NVIDIA GPU required)
|
||||
# --build Build image from source (default: build, since no pre-built GPU image is published)
|
||||
# --port PORT Host port to expose (default: 443 with Caddy, 8000 without)
|
||||
#
|
||||
# Examples:
|
||||
# # GPU on LAN with custom CA
|
||||
# ./scripts/generate-certs.sh gpu.local
|
||||
# ./scripts/setup-gpu-host.sh --domain gpu.local --custom-ca certs/ --api-key my-secret-key
|
||||
#
|
||||
# # GPU on public internet with Let's Encrypt
|
||||
# ./scripts/setup-gpu-host.sh --domain gpu.example.com --api-key my-secret-key
|
||||
#
|
||||
# # GPU on LAN, IP access only (self-signed cert)
|
||||
# ./scripts/setup-gpu-host.sh --api-key my-secret-key
|
||||
#
|
||||
# # CPU-only mode (no NVIDIA GPU)
|
||||
# ./scripts/setup-gpu-host.sh --cpu --api-key my-secret-key
|
||||
#
|
||||
# After setup, configure the main Reflector instance to use this GPU:
|
||||
# In server/.env on the Reflector machine:
|
||||
# TRANSCRIPT_BACKEND=modal
|
||||
# TRANSCRIPT_URL=https://gpu.example.com
|
||||
# TRANSCRIPT_MODAL_API_KEY=my-secret-key
|
||||
# DIARIZATION_BACKEND=modal
|
||||
# DIARIZATION_URL=https://gpu.example.com
|
||||
# DIARIZATION_MODAL_API_KEY=my-secret-key
|
||||
# TRANSLATION_BACKEND=modal
|
||||
# TRANSLATE_URL=https://gpu.example.com
|
||||
# TRANSLATION_MODAL_API_KEY=my-secret-key
|
||||
#
|
||||
# DNS Resolution:
|
||||
# - Public domain: Create a DNS A record pointing to this machine's public IP.
|
||||
# - Internal domain (e.g., gpu.local): Add to /etc/hosts on both machines:
|
||||
# <GPU_MACHINE_IP> gpu.local
|
||||
# - IP-only: Use the machine's IP directly in TRANSCRIPT_URL/DIARIZATION_URL.
|
||||
# The Reflector backend must trust the CA or accept self-signed certs.
|
||||
#
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||
|
||||
GPU_DIR="$ROOT_DIR/gpu/self_hosted"
|
||||
OS="$(uname -s)"
|
||||
|
||||
# --- Colors ---
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
YELLOW='\033[1;33m'
|
||||
CYAN='\033[0;36m'
|
||||
NC='\033[0m'
|
||||
|
||||
info() { echo -e "${CYAN}==>${NC} $*"; }
|
||||
ok() { echo -e "${GREEN} ✓${NC} $*"; }
|
||||
warn() { echo -e "${YELLOW} !${NC} $*"; }
|
||||
err() { echo -e "${RED} ✗${NC} $*" >&2; }
|
||||
|
||||
# --- Parse arguments ---
|
||||
CUSTOM_DOMAIN=""
|
||||
CUSTOM_CA=""
|
||||
EXTRA_CA_FILES=()
|
||||
API_KEY=""
|
||||
USE_CPU=false
|
||||
HOST_PORT=""
|
||||
|
||||
SKIP_NEXT=false
|
||||
ARGS=("$@")
|
||||
for i in "${!ARGS[@]}"; do
|
||||
if [[ "$SKIP_NEXT" == "true" ]]; then
|
||||
SKIP_NEXT=false
|
||||
continue
|
||||
fi
|
||||
arg="${ARGS[$i]}"
|
||||
case "$arg" in
|
||||
--domain)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--domain requires a domain name"
|
||||
exit 1
|
||||
fi
|
||||
CUSTOM_DOMAIN="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--custom-ca)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--custom-ca requires a path to a directory or PEM certificate file"
|
||||
exit 1
|
||||
fi
|
||||
CUSTOM_CA="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--extra-ca)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--extra-ca requires a path to a PEM certificate file"
|
||||
exit 1
|
||||
fi
|
||||
if [[ ! -f "${ARGS[$next_i]}" ]]; then
|
||||
err "--extra-ca file not found: ${ARGS[$next_i]}"
|
||||
exit 1
|
||||
fi
|
||||
EXTRA_CA_FILES+=("${ARGS[$next_i]}")
|
||||
SKIP_NEXT=true ;;
|
||||
--api-key)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--api-key requires a key value"
|
||||
exit 1
|
||||
fi
|
||||
API_KEY="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--cpu)
|
||||
USE_CPU=true ;;
|
||||
--port)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--port requires a port number"
|
||||
exit 1
|
||||
fi
|
||||
HOST_PORT="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--build)
|
||||
;; # Always build from source for GPU, flag accepted for compatibility
|
||||
*)
|
||||
err "Unknown argument: $arg"
|
||||
err "Usage: $0 [--domain DOMAIN] [--custom-ca PATH] [--extra-ca FILE] [--api-key KEY] [--cpu] [--port PORT]"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
# --- Resolve CA paths ---
|
||||
CA_CERT_PATH=""
|
||||
TLS_CERT_PATH=""
|
||||
TLS_KEY_PATH=""
|
||||
USE_CUSTOM_CA=false
|
||||
USE_CADDY=false
|
||||
|
||||
if [[ -n "$CUSTOM_CA" ]] || [[ -n "${EXTRA_CA_FILES[0]+x}" ]]; then
|
||||
USE_CUSTOM_CA=true
|
||||
fi
|
||||
|
||||
if [[ -n "$CUSTOM_CA" ]]; then
|
||||
CUSTOM_CA="${CUSTOM_CA%/}"
|
||||
if [[ -d "$CUSTOM_CA" ]]; then
|
||||
[[ -f "$CUSTOM_CA/ca.crt" ]] || { err "$CUSTOM_CA/ca.crt not found"; exit 1; }
|
||||
CA_CERT_PATH="$CUSTOM_CA/ca.crt"
|
||||
if [[ -f "$CUSTOM_CA/server.pem" ]] && [[ -f "$CUSTOM_CA/server-key.pem" ]]; then
|
||||
TLS_CERT_PATH="$CUSTOM_CA/server.pem"
|
||||
TLS_KEY_PATH="$CUSTOM_CA/server-key.pem"
|
||||
elif [[ -f "$CUSTOM_CA/server.pem" ]] || [[ -f "$CUSTOM_CA/server-key.pem" ]]; then
|
||||
warn "Found only one of server.pem/server-key.pem — both needed for TLS. Skipping."
|
||||
fi
|
||||
elif [[ -f "$CUSTOM_CA" ]]; then
|
||||
CA_CERT_PATH="$CUSTOM_CA"
|
||||
else
|
||||
err "--custom-ca path not found: $CUSTOM_CA"
|
||||
exit 1
|
||||
fi
|
||||
elif [[ -n "${EXTRA_CA_FILES[0]+x}" ]]; then
|
||||
CA_CERT_PATH="${EXTRA_CA_FILES[0]}"
|
||||
unset 'EXTRA_CA_FILES[0]'
|
||||
EXTRA_CA_FILES=("${EXTRA_CA_FILES[@]+"${EXTRA_CA_FILES[@]}"}")
|
||||
fi
|
||||
|
||||
# Caddy if we have a domain or TLS certs
|
||||
if [[ -n "$CUSTOM_DOMAIN" ]] || [[ -n "$TLS_CERT_PATH" ]]; then
|
||||
USE_CADDY=true
|
||||
fi
|
||||
|
||||
# Default port
|
||||
if [[ -z "$HOST_PORT" ]]; then
|
||||
if [[ "$USE_CADDY" == "true" ]]; then
|
||||
HOST_PORT="443"
|
||||
else
|
||||
HOST_PORT="8000"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Detect primary IP
|
||||
PRIMARY_IP=""
|
||||
if [[ "$OS" == "Linux" ]]; then
|
||||
PRIMARY_IP=$(hostname -I 2>/dev/null | awk '{print $1}' || true)
|
||||
if [[ "$PRIMARY_IP" == "127."* ]] || [[ -z "$PRIMARY_IP" ]]; then
|
||||
PRIMARY_IP=$(ip -4 route get 1 2>/dev/null | sed -n 's/.*src \([0-9.]*\).*/\1/p' || true)
|
||||
fi
|
||||
fi
|
||||
|
||||
# --- Display config ---
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo " Reflector — Standalone GPU Host Setup"
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
echo " Mode: $(if [[ "$USE_CPU" == "true" ]]; then echo "CPU-only"; else echo "NVIDIA GPU"; fi)"
|
||||
echo " Caddy: $USE_CADDY"
|
||||
[[ -n "$CUSTOM_DOMAIN" ]] && echo " Domain: $CUSTOM_DOMAIN"
|
||||
[[ "$USE_CUSTOM_CA" == "true" ]] && echo " CA: Custom"
|
||||
[[ -n "$TLS_CERT_PATH" ]] && echo " TLS: Custom cert"
|
||||
[[ -n "$API_KEY" ]] && echo " Auth: API key protected"
|
||||
[[ -z "$API_KEY" ]] && echo " Auth: NONE (open access — use --api-key for production!)"
|
||||
echo " Port: $HOST_PORT"
|
||||
echo ""
|
||||
|
||||
# --- Prerequisites ---
|
||||
info "Checking prerequisites"
|
||||
|
||||
if ! command -v docker &>/dev/null; then
|
||||
err "Docker not found. Install Docker first."
|
||||
exit 1
|
||||
fi
|
||||
ok "Docker available"
|
||||
|
||||
if ! docker compose version &>/dev/null; then
|
||||
err "Docker Compose V2 not found."
|
||||
exit 1
|
||||
fi
|
||||
ok "Docker Compose V2 available"
|
||||
|
||||
if [[ "$USE_CPU" != "true" ]]; then
|
||||
if ! docker info 2>/dev/null | grep -qi nvidia; then
|
||||
warn "NVIDIA runtime not detected in Docker. GPU mode may fail."
|
||||
warn "Install nvidia-container-toolkit if you have an NVIDIA GPU."
|
||||
else
|
||||
ok "NVIDIA Docker runtime available"
|
||||
fi
|
||||
fi
|
||||
|
||||
# --- Stage certificates ---
|
||||
CERTS_DIR="$ROOT_DIR/certs"
|
||||
if [[ "$USE_CUSTOM_CA" == "true" ]]; then
|
||||
info "Staging certificates"
|
||||
mkdir -p "$CERTS_DIR"
|
||||
|
||||
if [[ -n "$CA_CERT_PATH" ]]; then
|
||||
local_ca_dest="$CERTS_DIR/ca.crt"
|
||||
src_id=$(ls -i "$CA_CERT_PATH" 2>/dev/null | awk '{print $1}')
|
||||
dst_id=$(ls -i "$local_ca_dest" 2>/dev/null | awk '{print $1}')
|
||||
if [[ "$src_id" != "$dst_id" ]] || [[ -z "$dst_id" ]]; then
|
||||
cp "$CA_CERT_PATH" "$local_ca_dest"
|
||||
fi
|
||||
chmod 644 "$local_ca_dest"
|
||||
ok "CA certificate staged"
|
||||
|
||||
# Append extra CAs
|
||||
for extra_ca in "${EXTRA_CA_FILES[@]+"${EXTRA_CA_FILES[@]}"}"; do
|
||||
echo "" >> "$local_ca_dest"
|
||||
cat "$extra_ca" >> "$local_ca_dest"
|
||||
ok "Appended extra CA: $extra_ca"
|
||||
done
|
||||
fi
|
||||
|
||||
if [[ -n "$TLS_CERT_PATH" ]]; then
|
||||
cert_dest="$CERTS_DIR/server.pem"
|
||||
key_dest="$CERTS_DIR/server-key.pem"
|
||||
src_id=$(ls -i "$TLS_CERT_PATH" 2>/dev/null | awk '{print $1}')
|
||||
dst_id=$(ls -i "$cert_dest" 2>/dev/null | awk '{print $1}')
|
||||
if [[ "$src_id" != "$dst_id" ]] || [[ -z "$dst_id" ]]; then
|
||||
cp "$TLS_CERT_PATH" "$cert_dest"
|
||||
cp "$TLS_KEY_PATH" "$key_dest"
|
||||
fi
|
||||
chmod 644 "$cert_dest"
|
||||
chmod 600 "$key_dest"
|
||||
ok "TLS cert/key staged"
|
||||
fi
|
||||
fi
|
||||
|
||||
# --- Build profiles and compose command ---
|
||||
COMPOSE_FILE="$ROOT_DIR/docker-compose.gpu-host.yml"
|
||||
COMPOSE_PROFILES=()
|
||||
GPU_SERVICE="gpu"
|
||||
|
||||
if [[ "$USE_CPU" == "true" ]]; then
|
||||
COMPOSE_PROFILES+=("cpu")
|
||||
GPU_SERVICE="cpu"
|
||||
else
|
||||
COMPOSE_PROFILES+=("gpu")
|
||||
fi
|
||||
if [[ "$USE_CADDY" == "true" ]]; then
|
||||
COMPOSE_PROFILES+=("caddy")
|
||||
fi
|
||||
|
||||
# Compose command helper
|
||||
compose_cmd() {
|
||||
local profiles="" files="-f $COMPOSE_FILE"
|
||||
if [[ "$USE_CUSTOM_CA" == "true" ]] && [[ -f "$ROOT_DIR/docker-compose.gpu-ca.yml" ]]; then
|
||||
files="$files -f $ROOT_DIR/docker-compose.gpu-ca.yml"
|
||||
fi
|
||||
for p in "${COMPOSE_PROFILES[@]}"; do
|
||||
profiles="$profiles --profile $p"
|
||||
done
|
||||
docker compose $files $profiles "$@"
|
||||
}
|
||||
|
||||
# Generate CA compose override if needed (mounts certs into containers)
|
||||
if [[ "$USE_CUSTOM_CA" == "true" ]]; then
|
||||
info "Generating docker-compose.gpu-ca.yml override"
|
||||
ca_override="$ROOT_DIR/docker-compose.gpu-ca.yml"
|
||||
cat > "$ca_override" << 'CAEOF'
|
||||
# Generated by setup-gpu-host.sh — custom CA trust.
|
||||
# Do not edit manually; re-run setup-gpu-host.sh with --custom-ca to regenerate.
|
||||
services:
|
||||
gpu:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
cpu:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
CAEOF
|
||||
|
||||
if [[ -n "$TLS_CERT_PATH" ]]; then
|
||||
cat >> "$ca_override" << 'CADDYCAEOF'
|
||||
caddy:
|
||||
volumes:
|
||||
- ./certs:/etc/caddy/certs:ro
|
||||
CADDYCAEOF
|
||||
fi
|
||||
ok "Generated docker-compose.gpu-ca.yml"
|
||||
else
|
||||
rm -f "$ROOT_DIR/docker-compose.gpu-ca.yml"
|
||||
fi
|
||||
|
||||
# --- Generate Caddyfile ---
|
||||
if [[ "$USE_CADDY" == "true" ]]; then
|
||||
info "Generating Caddyfile.gpu-host"
|
||||
|
||||
CADDYFILE="$ROOT_DIR/Caddyfile.gpu-host"
|
||||
|
||||
if [[ -n "$TLS_CERT_PATH" ]] && [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
cat > "$CADDYFILE" << CADDYEOF
|
||||
# Generated by setup-gpu-host.sh — Custom TLS cert for $CUSTOM_DOMAIN
|
||||
$CUSTOM_DOMAIN {
|
||||
tls /etc/caddy/certs/server.pem /etc/caddy/certs/server-key.pem
|
||||
reverse_proxy transcription:8000
|
||||
}
|
||||
CADDYEOF
|
||||
ok "Caddyfile: custom TLS for $CUSTOM_DOMAIN"
|
||||
elif [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
cat > "$CADDYFILE" << CADDYEOF
|
||||
# Generated by setup-gpu-host.sh — Let's Encrypt for $CUSTOM_DOMAIN
|
||||
$CUSTOM_DOMAIN {
|
||||
reverse_proxy transcription:8000
|
||||
}
|
||||
CADDYEOF
|
||||
ok "Caddyfile: Let's Encrypt for $CUSTOM_DOMAIN"
|
||||
else
|
||||
cat > "$CADDYFILE" << 'CADDYEOF'
|
||||
# Generated by setup-gpu-host.sh — self-signed cert for IP access
|
||||
:443 {
|
||||
tls internal
|
||||
reverse_proxy transcription:8000
|
||||
}
|
||||
CADDYEOF
|
||||
ok "Caddyfile: self-signed cert for IP access"
|
||||
fi
|
||||
fi
|
||||
|
||||
# --- Generate .env ---
|
||||
info "Generating GPU service .env"
|
||||
|
||||
GPU_ENV="$ROOT_DIR/.env.gpu-host"
|
||||
cat > "$GPU_ENV" << EOF
|
||||
# Generated by setup-gpu-host.sh
|
||||
# HuggingFace token for pyannote diarization models
|
||||
HF_TOKEN=${HF_TOKEN:-}
|
||||
# API key to protect the GPU service (set via --api-key)
|
||||
REFLECTOR_GPU_APIKEY=${API_KEY:-}
|
||||
# Port configuration
|
||||
GPU_HOST_PORT=${HOST_PORT}
|
||||
CADDY_HTTPS_PORT=${HOST_PORT}
|
||||
EOF
|
||||
|
||||
if [[ -z "${HF_TOKEN:-}" ]]; then
|
||||
warn "HF_TOKEN not set. Diarization requires a HuggingFace token."
|
||||
warn "Set it: export HF_TOKEN=your-token-here and re-run, or edit .env.gpu-host"
|
||||
fi
|
||||
|
||||
ok "Generated .env.gpu-host"
|
||||
|
||||
# --- Build and start ---
|
||||
info "Building $GPU_SERVICE image (first build downloads ML models — may take a while)..."
|
||||
compose_cmd --env-file "$GPU_ENV" build "$GPU_SERVICE"
|
||||
ok "$GPU_SERVICE image built"
|
||||
|
||||
info "Starting services..."
|
||||
compose_cmd --env-file "$GPU_ENV" up -d
|
||||
ok "Services started"
|
||||
|
||||
# --- Wait for health ---
|
||||
info "Waiting for GPU service to be healthy (model loading takes 1-2 minutes)..."
|
||||
local_url="http://localhost:8000"
|
||||
for i in $(seq 1 40); do
|
||||
if curl -sf "$local_url/docs" >/dev/null 2>&1; then
|
||||
ok "GPU service is healthy!"
|
||||
break
|
||||
fi
|
||||
if [[ $i -eq 40 ]]; then
|
||||
err "GPU service did not become healthy after 5 minutes."
|
||||
err "Check logs: docker compose -f docker-compose.gpu-host.yml logs gpu"
|
||||
exit 1
|
||||
fi
|
||||
sleep 8
|
||||
done
|
||||
|
||||
# --- Summary ---
|
||||
echo ""
|
||||
echo "=========================================="
|
||||
echo -e " ${GREEN}GPU service is running!${NC}"
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
|
||||
if [[ "$USE_CADDY" == "true" ]]; then
|
||||
if [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
echo " URL: https://$CUSTOM_DOMAIN"
|
||||
elif [[ -n "$PRIMARY_IP" ]]; then
|
||||
echo " URL: https://$PRIMARY_IP"
|
||||
else
|
||||
echo " URL: https://localhost"
|
||||
fi
|
||||
else
|
||||
if [[ -n "$PRIMARY_IP" ]]; then
|
||||
echo " URL: http://$PRIMARY_IP:$HOST_PORT"
|
||||
else
|
||||
echo " URL: http://localhost:$HOST_PORT"
|
||||
fi
|
||||
fi
|
||||
|
||||
echo " Health: curl \$(URL)/docs"
|
||||
[[ -n "$API_KEY" ]] && echo " API key: $API_KEY"
|
||||
echo ""
|
||||
echo " Configure the main Reflector instance (in server/.env):"
|
||||
echo ""
|
||||
|
||||
local_gpu_url=""
|
||||
if [[ "$USE_CADDY" == "true" ]]; then
|
||||
if [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
local_gpu_url="https://$CUSTOM_DOMAIN"
|
||||
elif [[ -n "$PRIMARY_IP" ]]; then
|
||||
local_gpu_url="https://$PRIMARY_IP"
|
||||
else
|
||||
local_gpu_url="https://localhost"
|
||||
fi
|
||||
else
|
||||
if [[ -n "$PRIMARY_IP" ]]; then
|
||||
local_gpu_url="http://$PRIMARY_IP:$HOST_PORT"
|
||||
else
|
||||
local_gpu_url="http://localhost:$HOST_PORT"
|
||||
fi
|
||||
fi
|
||||
|
||||
echo " TRANSCRIPT_BACKEND=modal"
|
||||
echo " TRANSCRIPT_URL=$local_gpu_url"
|
||||
[[ -n "$API_KEY" ]] && echo " TRANSCRIPT_MODAL_API_KEY=$API_KEY"
|
||||
echo " DIARIZATION_BACKEND=modal"
|
||||
echo " DIARIZATION_URL=$local_gpu_url"
|
||||
[[ -n "$API_KEY" ]] && echo " DIARIZATION_MODAL_API_KEY=$API_KEY"
|
||||
echo " TRANSLATION_BACKEND=modal"
|
||||
echo " TRANSLATE_URL=$local_gpu_url"
|
||||
[[ -n "$API_KEY" ]] && echo " TRANSLATION_MODAL_API_KEY=$API_KEY"
|
||||
echo ""
|
||||
|
||||
if [[ "$USE_CUSTOM_CA" == "true" ]]; then
|
||||
echo " The Reflector instance must also trust this CA."
|
||||
echo " On the Reflector machine, run setup-selfhosted.sh with:"
|
||||
echo " --extra-ca /path/to/this-machines-ca.crt"
|
||||
echo ""
|
||||
fi
|
||||
|
||||
echo " DNS Resolution:"
|
||||
if [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
echo " Ensure '$CUSTOM_DOMAIN' resolves to this machine's IP."
|
||||
echo " Public: Create a DNS A record."
|
||||
echo " Internal: Add to /etc/hosts on the Reflector machine:"
|
||||
echo " ${PRIMARY_IP:-<GPU_IP>} $CUSTOM_DOMAIN"
|
||||
else
|
||||
echo " Use this machine's IP directly in TRANSCRIPT_URL/DIARIZATION_URL."
|
||||
fi
|
||||
echo ""
|
||||
echo " To stop: docker compose -f docker-compose.gpu-host.yml down"
|
||||
echo " To re-run: ./scripts/setup-gpu-host.sh $*"
|
||||
echo " Logs: docker compose -f docker-compose.gpu-host.yml logs -f gpu"
|
||||
echo ""
|
||||
@@ -4,13 +4,21 @@
|
||||
# Single script to configure and launch everything on one server.
|
||||
#
|
||||
# Usage:
|
||||
# ./scripts/setup-selfhosted.sh <--gpu|--cpu|--hosted> [--ollama-gpu|--ollama-cpu] [--llm-model MODEL] [--garage] [--caddy] [--domain DOMAIN] [--password PASSWORD] [--build]
|
||||
# ./scripts/setup-selfhosted.sh <--gpu|--cpu|--hosted> [options] [--transcript BACKEND] [--diarization BACKEND] [--translation BACKEND] [--padding BACKEND] [--mixdown BACKEND]
|
||||
# ./scripts/setup-selfhosted.sh (re-run with saved config from last run)
|
||||
#
|
||||
# ML processing modes (pick ONE — required):
|
||||
# ML processing modes (pick ONE — required on first run):
|
||||
# --gpu NVIDIA GPU container for transcription/diarization/translation
|
||||
# --cpu In-process CPU processing (no ML container, slower)
|
||||
# --hosted Remote GPU service URL (no ML container)
|
||||
#
|
||||
# Per-service backend overrides (optional — override individual services from the base mode):
|
||||
# --transcript BACKEND whisper | modal (default: whisper for --cpu, modal for --gpu/--hosted)
|
||||
# --diarization BACKEND pyannote | modal (default: pyannote for --cpu, modal for --gpu/--hosted)
|
||||
# --translation BACKEND marian | modal | passthrough (default: marian for --cpu, modal for --gpu/--hosted)
|
||||
# --padding BACKEND pyav | modal (default: pyav for --cpu, modal for --gpu/--hosted)
|
||||
# --mixdown BACKEND pyav | modal (default: pyav for --cpu, modal for --gpu/--hosted)
|
||||
#
|
||||
# Local LLM (optional — for summarization & topic detection):
|
||||
# --ollama-gpu Local Ollama with NVIDIA GPU acceleration
|
||||
# --ollama-cpu Local Ollama on CPU only
|
||||
@@ -23,6 +31,13 @@
|
||||
# --domain DOMAIN Use a real domain for Caddy (enables Let's Encrypt auto-HTTPS)
|
||||
# Requires: DNS pointing to this server + ports 80/443 open
|
||||
# Without --domain: Caddy uses self-signed cert for IP access
|
||||
# --custom-ca PATH Custom CA certificate for private HTTPS services
|
||||
# PATH can be a directory (containing ca.crt, optionally server.pem + server-key.pem)
|
||||
# or a single PEM file (CA trust only, no Caddy TLS)
|
||||
# With server.pem+server-key.pem: Caddy serves HTTPS using those certs (requires --domain)
|
||||
# Without: only injects CA trust into backend containers for outbound calls
|
||||
# --extra-ca FILE Additional CA cert to trust (can be repeated for multiple CAs)
|
||||
# Appended to the CA bundle so backends trust multiple authorities
|
||||
# --password PASS Enable password auth with admin@localhost user
|
||||
# --build Build backend and frontend images from source instead of pulling
|
||||
#
|
||||
@@ -31,10 +46,17 @@
|
||||
# ./scripts/setup-selfhosted.sh --gpu --ollama-gpu --garage --caddy --domain reflector.example.com
|
||||
# ./scripts/setup-selfhosted.sh --cpu --ollama-cpu --garage --caddy
|
||||
# ./scripts/setup-selfhosted.sh --hosted --garage --caddy
|
||||
# ./scripts/setup-selfhosted.sh --cpu --padding modal --garage --caddy
|
||||
# ./scripts/setup-selfhosted.sh --gpu --translation passthrough --garage --caddy
|
||||
# ./scripts/setup-selfhosted.sh --cpu --diarization modal --translation modal --garage
|
||||
# ./scripts/setup-selfhosted.sh --gpu --ollama-gpu --llm-model mistral --garage --caddy
|
||||
# ./scripts/setup-selfhosted.sh --gpu --garage --caddy --password mysecretpass
|
||||
# ./scripts/setup-selfhosted.sh --gpu --garage --caddy
|
||||
# ./scripts/setup-selfhosted.sh --cpu
|
||||
# ./scripts/setup-selfhosted.sh --gpu --caddy --domain reflector.local --custom-ca certs/
|
||||
# ./scripts/setup-selfhosted.sh --hosted --custom-ca /path/to/corporate-ca.crt
|
||||
# ./scripts/setup-selfhosted.sh # re-run with saved config
|
||||
#
|
||||
# Config memory: after a successful run, flags are saved to data/.selfhosted-last-args.
|
||||
# Re-running with no arguments replays the saved configuration automatically.
|
||||
#
|
||||
# The script auto-detects Daily.co (DAILY_API_KEY) and Whereby (WHEREBY_API_KEY)
|
||||
# from server/.env. If Daily.co is configured, Hatchet workflow services are
|
||||
@@ -50,6 +72,7 @@ ROOT_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||
COMPOSE_FILE="$ROOT_DIR/docker-compose.selfhosted.yml"
|
||||
SERVER_ENV="$ROOT_DIR/server/.env"
|
||||
WWW_ENV="$ROOT_DIR/www/.env"
|
||||
LAST_ARGS_FILE="$ROOT_DIR/data/.selfhosted-last-args"
|
||||
|
||||
OLLAMA_MODEL="qwen2.5:14b"
|
||||
OS="$(uname -s)"
|
||||
@@ -154,18 +177,32 @@ env_set() {
|
||||
}
|
||||
|
||||
compose_cmd() {
|
||||
local profiles=""
|
||||
local profiles="" files="-f $COMPOSE_FILE"
|
||||
[[ "$USE_CUSTOM_CA" == "true" ]] && files="$files -f $ROOT_DIR/docker-compose.ca.yml"
|
||||
for p in "${COMPOSE_PROFILES[@]}"; do
|
||||
profiles="$profiles --profile $p"
|
||||
done
|
||||
docker compose -f "$COMPOSE_FILE" $profiles "$@"
|
||||
docker compose $files $profiles "$@"
|
||||
}
|
||||
|
||||
# Compose command with only garage profile (for garage-only operations before full stack start)
|
||||
compose_garage_cmd() {
|
||||
docker compose -f "$COMPOSE_FILE" --profile garage "$@"
|
||||
local files="-f $COMPOSE_FILE"
|
||||
[[ "$USE_CUSTOM_CA" == "true" ]] && files="$files -f $ROOT_DIR/docker-compose.ca.yml"
|
||||
docker compose $files --profile garage "$@"
|
||||
}
|
||||
|
||||
# --- Config memory: replay last args if none provided ---
|
||||
if [[ $# -eq 0 ]] && [[ -f "$LAST_ARGS_FILE" ]]; then
|
||||
SAVED_ARGS="$(cat "$LAST_ARGS_FILE")"
|
||||
if [[ -n "$SAVED_ARGS" ]]; then
|
||||
info "No flags provided — replaying saved configuration:"
|
||||
info " $SAVED_ARGS"
|
||||
echo ""
|
||||
eval "set -- $SAVED_ARGS"
|
||||
fi
|
||||
fi
|
||||
|
||||
# --- Parse arguments ---
|
||||
MODEL_MODE="" # gpu or cpu (required, mutually exclusive)
|
||||
OLLAMA_MODE="" # ollama-gpu or ollama-cpu (optional)
|
||||
@@ -174,6 +211,22 @@ USE_CADDY=false
|
||||
CUSTOM_DOMAIN="" # optional domain for Let's Encrypt HTTPS
|
||||
BUILD_IMAGES=false # build backend/frontend from source
|
||||
ADMIN_PASSWORD="" # optional admin password for password auth
|
||||
CUSTOM_CA="" # --custom-ca: path to dir or CA cert file
|
||||
USE_CUSTOM_CA=false # derived flag: true when --custom-ca is provided
|
||||
EXTRA_CA_FILES=() # --extra-ca: additional CA certs to trust (can be repeated)
|
||||
OVERRIDE_TRANSCRIPT="" # per-service override: whisper | modal
|
||||
OVERRIDE_DIARIZATION="" # per-service override: pyannote | modal
|
||||
OVERRIDE_TRANSLATION="" # per-service override: marian | modal | passthrough
|
||||
OVERRIDE_PADDING="" # per-service override: pyav | modal
|
||||
OVERRIDE_MIXDOWN="" # per-service override: pyav | modal
|
||||
|
||||
# Validate per-service backend override values
|
||||
validate_backend() {
|
||||
local service="$1" value="$2"; shift 2; local valid=("$@")
|
||||
for v in "${valid[@]}"; do [[ "$value" == "$v" ]] && return 0; done
|
||||
err "--$service value '$value' is not valid. Choose one of: ${valid[*]}"
|
||||
exit 1
|
||||
}
|
||||
|
||||
SKIP_NEXT=false
|
||||
ARGS=("$@")
|
||||
@@ -227,24 +280,159 @@ for i in "${!ARGS[@]}"; do
|
||||
CUSTOM_DOMAIN="${ARGS[$next_i]}"
|
||||
USE_CADDY=true # --domain implies --caddy
|
||||
SKIP_NEXT=true ;;
|
||||
--custom-ca)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--custom-ca requires a path to a directory or PEM certificate file"
|
||||
exit 1
|
||||
fi
|
||||
CUSTOM_CA="${ARGS[$next_i]}"
|
||||
USE_CUSTOM_CA=true
|
||||
SKIP_NEXT=true ;;
|
||||
--extra-ca)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--extra-ca requires a path to a PEM certificate file"
|
||||
exit 1
|
||||
fi
|
||||
extra_ca_file="${ARGS[$next_i]}"
|
||||
if [[ ! -f "$extra_ca_file" ]]; then
|
||||
err "--extra-ca file not found: $extra_ca_file"
|
||||
exit 1
|
||||
fi
|
||||
EXTRA_CA_FILES+=("$extra_ca_file")
|
||||
USE_CUSTOM_CA=true
|
||||
SKIP_NEXT=true ;;
|
||||
--transcript)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--transcript requires a backend (whisper | modal)"
|
||||
exit 1
|
||||
fi
|
||||
validate_backend "transcript" "${ARGS[$next_i]}" whisper modal
|
||||
OVERRIDE_TRANSCRIPT="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--diarization)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--diarization requires a backend (pyannote | modal)"
|
||||
exit 1
|
||||
fi
|
||||
validate_backend "diarization" "${ARGS[$next_i]}" pyannote modal
|
||||
OVERRIDE_DIARIZATION="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--translation)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--translation requires a backend (marian | modal | passthrough)"
|
||||
exit 1
|
||||
fi
|
||||
validate_backend "translation" "${ARGS[$next_i]}" marian modal passthrough
|
||||
OVERRIDE_TRANSLATION="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--padding)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--padding requires a backend (pyav | modal)"
|
||||
exit 1
|
||||
fi
|
||||
validate_backend "padding" "${ARGS[$next_i]}" pyav modal
|
||||
OVERRIDE_PADDING="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
--mixdown)
|
||||
next_i=$((i + 1))
|
||||
if [[ $next_i -ge ${#ARGS[@]} ]] || [[ "${ARGS[$next_i]}" == --* ]]; then
|
||||
err "--mixdown requires a backend (pyav | modal)"
|
||||
exit 1
|
||||
fi
|
||||
validate_backend "mixdown" "${ARGS[$next_i]}" pyav modal
|
||||
OVERRIDE_MIXDOWN="${ARGS[$next_i]}"
|
||||
SKIP_NEXT=true ;;
|
||||
*)
|
||||
err "Unknown argument: $arg"
|
||||
err "Usage: $0 <--gpu|--cpu|--hosted> [--ollama-gpu|--ollama-cpu] [--llm-model MODEL] [--garage] [--caddy] [--domain DOMAIN] [--password PASS] [--build]"
|
||||
err "Usage: $0 <--gpu|--cpu|--hosted> [options] [--transcript BACKEND] [--diarization BACKEND] [--translation BACKEND] [--padding BACKEND] [--mixdown BACKEND]"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
# --- Save CLI args for config memory (re-run without flags) ---
|
||||
if [[ $# -gt 0 ]]; then
|
||||
mkdir -p "$ROOT_DIR/data"
|
||||
printf '%q ' "$@" > "$LAST_ARGS_FILE"
|
||||
fi
|
||||
|
||||
# --- Resolve --custom-ca flag ---
|
||||
CA_CERT_PATH="" # resolved path to CA certificate
|
||||
TLS_CERT_PATH="" # resolved path to server cert (optional, for Caddy TLS)
|
||||
TLS_KEY_PATH="" # resolved path to server key (optional, for Caddy TLS)
|
||||
|
||||
if [[ "$USE_CUSTOM_CA" == "true" ]]; then
|
||||
# Strip trailing slashes to avoid double-slash paths
|
||||
CUSTOM_CA="${CUSTOM_CA%/}"
|
||||
|
||||
if [[ -z "$CUSTOM_CA" ]] && [[ -n "${EXTRA_CA_FILES[0]+x}" ]]; then
|
||||
# --extra-ca only (no --custom-ca): use first extra CA as the base
|
||||
CA_CERT_PATH="${EXTRA_CA_FILES[0]}"
|
||||
unset 'EXTRA_CA_FILES[0]'
|
||||
EXTRA_CA_FILES=("${EXTRA_CA_FILES[@]+"${EXTRA_CA_FILES[@]}"}")
|
||||
elif [[ -d "$CUSTOM_CA" ]]; then
|
||||
# Directory mode: look for convention files
|
||||
if [[ ! -f "$CUSTOM_CA/ca.crt" ]]; then
|
||||
err "CA certificate not found: $CUSTOM_CA/ca.crt"
|
||||
err "Directory must contain ca.crt (and optionally server.pem + server-key.pem)"
|
||||
exit 1
|
||||
fi
|
||||
CA_CERT_PATH="$CUSTOM_CA/ca.crt"
|
||||
# Server cert/key are optional — if both present, use for Caddy TLS
|
||||
if [[ -f "$CUSTOM_CA/server.pem" ]] && [[ -f "$CUSTOM_CA/server-key.pem" ]]; then
|
||||
TLS_CERT_PATH="$CUSTOM_CA/server.pem"
|
||||
TLS_KEY_PATH="$CUSTOM_CA/server-key.pem"
|
||||
elif [[ -f "$CUSTOM_CA/server.pem" ]] || [[ -f "$CUSTOM_CA/server-key.pem" ]]; then
|
||||
warn "Found only one of server.pem/server-key.pem in $CUSTOM_CA — both are needed for Caddy TLS. Skipping."
|
||||
fi
|
||||
elif [[ -f "$CUSTOM_CA" ]]; then
|
||||
# Single file mode: CA trust only (no Caddy TLS certs)
|
||||
CA_CERT_PATH="$CUSTOM_CA"
|
||||
else
|
||||
err "--custom-ca path not found: $CUSTOM_CA"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate PEM format
|
||||
if ! head -1 "$CA_CERT_PATH" | grep -q "BEGIN"; then
|
||||
err "CA certificate does not appear to be PEM format: $CA_CERT_PATH"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# If server cert/key found, require --domain and imply --caddy
|
||||
if [[ -n "$TLS_CERT_PATH" ]]; then
|
||||
if [[ -z "$CUSTOM_DOMAIN" ]]; then
|
||||
err "Server cert/key found in $CUSTOM_CA but --domain not set."
|
||||
err "Provide --domain to specify the domain name matching the certificate."
|
||||
exit 1
|
||||
fi
|
||||
USE_CADDY=true # custom TLS certs imply --caddy
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ -z "$MODEL_MODE" ]]; then
|
||||
err "No model mode specified. You must choose --gpu, --cpu, or --hosted."
|
||||
err ""
|
||||
err "Usage: $0 <--gpu|--cpu|--hosted> [--ollama-gpu|--ollama-cpu] [--llm-model MODEL] [--garage] [--caddy] [--domain DOMAIN] [--password PASS] [--build]"
|
||||
err "Usage: $0 <--gpu|--cpu|--hosted> [options] [--transcript BACKEND] [--diarization BACKEND] [--translation BACKEND] [--padding BACKEND] [--mixdown BACKEND]"
|
||||
err ""
|
||||
err "ML processing modes (required):"
|
||||
err " --gpu NVIDIA GPU container for transcription/diarization/translation"
|
||||
err " --cpu In-process CPU processing (no ML container, slower)"
|
||||
err " --hosted Remote GPU service URL (no ML container)"
|
||||
err ""
|
||||
err "Per-service backend overrides (optional — override individual services):"
|
||||
err " --transcript BACKEND whisper | modal (default: whisper for --cpu, modal for --gpu/--hosted)"
|
||||
err " --diarization BACKEND pyannote | modal (default: pyannote for --cpu, modal for --gpu/--hosted)"
|
||||
err " --translation BACKEND marian | modal | passthrough (default: marian for --cpu, modal for --gpu/--hosted)"
|
||||
err " --padding BACKEND pyav | modal (default: pyav for --cpu, modal for --gpu/--hosted)"
|
||||
err " --mixdown BACKEND pyav | modal (default: pyav for --cpu, modal for --gpu/--hosted)"
|
||||
err ""
|
||||
err "Local LLM (optional):"
|
||||
err " --ollama-gpu Local Ollama with GPU (for summarization/topics)"
|
||||
err " --ollama-cpu Local Ollama on CPU (for summarization/topics)"
|
||||
@@ -255,8 +443,12 @@ if [[ -z "$MODEL_MODE" ]]; then
|
||||
err " --garage Local S3-compatible storage (Garage)"
|
||||
err " --caddy Caddy reverse proxy with self-signed cert"
|
||||
err " --domain DOMAIN Use a real domain with Let's Encrypt HTTPS (implies --caddy)"
|
||||
err " --custom-ca PATH Custom CA cert (dir with ca.crt[+server.pem+server-key.pem] or single PEM file)"
|
||||
err " --extra-ca FILE Additional CA cert to trust (repeatable for multiple CAs)"
|
||||
err " --password PASS Enable password auth (admin@localhost) instead of public mode"
|
||||
err " --build Build backend/frontend images from source instead of pulling"
|
||||
err ""
|
||||
err "Tip: After your first run, re-run with no flags to reuse the same configuration."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
@@ -280,9 +472,38 @@ OLLAMA_SVC=""
|
||||
[[ "$OLLAMA_MODE" == "ollama-gpu" ]] && USES_OLLAMA=true && OLLAMA_SVC="ollama"
|
||||
[[ "$OLLAMA_MODE" == "ollama-cpu" ]] && USES_OLLAMA=true && OLLAMA_SVC="ollama-cpu"
|
||||
|
||||
# Resolve effective backend per service (override wins over base mode default)
|
||||
case "$MODEL_MODE" in
|
||||
gpu|hosted)
|
||||
EFF_TRANSCRIPT="${OVERRIDE_TRANSCRIPT:-modal}"
|
||||
EFF_DIARIZATION="${OVERRIDE_DIARIZATION:-modal}"
|
||||
EFF_TRANSLATION="${OVERRIDE_TRANSLATION:-modal}"
|
||||
EFF_PADDING="${OVERRIDE_PADDING:-modal}"
|
||||
EFF_MIXDOWN="${OVERRIDE_MIXDOWN:-modal}"
|
||||
;;
|
||||
cpu)
|
||||
EFF_TRANSCRIPT="${OVERRIDE_TRANSCRIPT:-whisper}"
|
||||
EFF_DIARIZATION="${OVERRIDE_DIARIZATION:-pyannote}"
|
||||
EFF_TRANSLATION="${OVERRIDE_TRANSLATION:-marian}"
|
||||
EFF_PADDING="${OVERRIDE_PADDING:-pyav}"
|
||||
EFF_MIXDOWN="${OVERRIDE_MIXDOWN:-pyav}"
|
||||
;;
|
||||
esac
|
||||
|
||||
# Check if any per-service overrides were provided
|
||||
HAS_OVERRIDES=false
|
||||
[[ -n "$OVERRIDE_TRANSCRIPT" ]] && HAS_OVERRIDES=true
|
||||
[[ -n "$OVERRIDE_DIARIZATION" ]] && HAS_OVERRIDES=true
|
||||
[[ -n "$OVERRIDE_TRANSLATION" ]] && HAS_OVERRIDES=true
|
||||
[[ -n "$OVERRIDE_PADDING" ]] && HAS_OVERRIDES=true
|
||||
[[ -n "$OVERRIDE_MIXDOWN" ]] && HAS_OVERRIDES=true
|
||||
|
||||
# Human-readable mode string for display
|
||||
MODE_DISPLAY="$MODEL_MODE"
|
||||
[[ -n "$OLLAMA_MODE" ]] && MODE_DISPLAY="$MODEL_MODE + $OLLAMA_MODE"
|
||||
if [[ "$HAS_OVERRIDES" == "true" ]]; then
|
||||
MODE_DISPLAY="$MODE_DISPLAY (overrides: transcript=$EFF_TRANSCRIPT, diarization=$EFF_DIARIZATION, translation=$EFF_TRANSLATION, padding=$EFF_PADDING, mixdown=$EFF_MIXDOWN)"
|
||||
fi
|
||||
|
||||
# =========================================================
|
||||
# Step 0: Prerequisites
|
||||
@@ -366,6 +587,103 @@ print(f'pbkdf2:sha256:100000\$\$' + salt + '\$\$' + dk.hex())
|
||||
ok "Secrets ready"
|
||||
}
|
||||
|
||||
# =========================================================
|
||||
# Step 1b: Custom CA certificate setup
|
||||
# =========================================================
|
||||
step_custom_ca() {
|
||||
if [[ "$USE_CUSTOM_CA" != "true" ]]; then
|
||||
# Clean up stale override from previous runs
|
||||
rm -f "$ROOT_DIR/docker-compose.ca.yml"
|
||||
return
|
||||
fi
|
||||
|
||||
info "Configuring custom CA certificate"
|
||||
local certs_dir="$ROOT_DIR/certs"
|
||||
mkdir -p "$certs_dir"
|
||||
|
||||
# Stage CA certificate (skip copy if source and dest are the same file)
|
||||
local ca_dest="$certs_dir/ca.crt"
|
||||
local src_id dst_id
|
||||
src_id=$(ls -i "$CA_CERT_PATH" 2>/dev/null | awk '{print $1}')
|
||||
dst_id=$(ls -i "$ca_dest" 2>/dev/null | awk '{print $1}')
|
||||
if [[ "$src_id" != "$dst_id" ]] || [[ -z "$dst_id" ]]; then
|
||||
cp "$CA_CERT_PATH" "$ca_dest"
|
||||
fi
|
||||
chmod 644 "$ca_dest"
|
||||
ok "CA certificate staged at certs/ca.crt"
|
||||
|
||||
# Append extra CA certs (--extra-ca flags)
|
||||
for extra_ca in "${EXTRA_CA_FILES[@]+"${EXTRA_CA_FILES[@]}"}"; do
|
||||
if ! head -1 "$extra_ca" | grep -q "BEGIN"; then
|
||||
warn "Skipping $extra_ca — does not appear to be PEM format"
|
||||
continue
|
||||
fi
|
||||
echo "" >> "$ca_dest"
|
||||
cat "$extra_ca" >> "$ca_dest"
|
||||
ok "Appended extra CA: $extra_ca"
|
||||
done
|
||||
|
||||
# Stage TLS cert/key if present (for Caddy)
|
||||
if [[ -n "$TLS_CERT_PATH" ]]; then
|
||||
local cert_dest="$certs_dir/server.pem"
|
||||
local key_dest="$certs_dir/server-key.pem"
|
||||
src_id=$(ls -i "$TLS_CERT_PATH" 2>/dev/null | awk '{print $1}')
|
||||
dst_id=$(ls -i "$cert_dest" 2>/dev/null | awk '{print $1}')
|
||||
if [[ "$src_id" != "$dst_id" ]] || [[ -z "$dst_id" ]]; then
|
||||
cp "$TLS_CERT_PATH" "$cert_dest"
|
||||
cp "$TLS_KEY_PATH" "$key_dest"
|
||||
fi
|
||||
chmod 644 "$cert_dest"
|
||||
chmod 600 "$key_dest"
|
||||
ok "TLS cert/key staged at certs/server.pem, certs/server-key.pem"
|
||||
fi
|
||||
|
||||
# Generate docker-compose.ca.yml override
|
||||
local ca_override="$ROOT_DIR/docker-compose.ca.yml"
|
||||
cat > "$ca_override" << 'CAEOF'
|
||||
# Generated by setup-selfhosted.sh — custom CA trust for backend services.
|
||||
# Do not edit manually; re-run setup-selfhosted.sh with --custom-ca to regenerate.
|
||||
services:
|
||||
server:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
worker:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
beat:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
hatchet-worker-llm:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
hatchet-worker-cpu:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
gpu:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
cpu:
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
web:
|
||||
environment:
|
||||
NODE_EXTRA_CA_CERTS: /usr/local/share/ca-certificates/custom-ca.crt
|
||||
volumes:
|
||||
- ./certs/ca.crt:/usr/local/share/ca-certificates/custom-ca.crt:ro
|
||||
CAEOF
|
||||
|
||||
# If TLS cert/key present, also mount certs dir into Caddy
|
||||
if [[ -n "$TLS_CERT_PATH" ]]; then
|
||||
cat >> "$ca_override" << 'CADDYCAEOF'
|
||||
caddy:
|
||||
volumes:
|
||||
- ./certs:/etc/caddy/certs:ro
|
||||
CADDYCAEOF
|
||||
fi
|
||||
|
||||
ok "Generated docker-compose.ca.yml override"
|
||||
}
|
||||
|
||||
# =========================================================
|
||||
# Step 2: Generate server/.env
|
||||
# =========================================================
|
||||
@@ -432,54 +750,30 @@ step_server_env() {
|
||||
env_set "$SERVER_ENV" "WEBRTC_HOST" "$PRIMARY_IP"
|
||||
fi
|
||||
|
||||
# Specialized models — backend configuration per mode
|
||||
# Specialized models — backend configuration per service
|
||||
env_set "$SERVER_ENV" "DIARIZATION_ENABLED" "true"
|
||||
|
||||
# Resolve the URL for modal backends
|
||||
local modal_url=""
|
||||
case "$MODEL_MODE" in
|
||||
gpu)
|
||||
# GPU container aliased as "transcription" on docker network
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_URL" "http://transcription:8000"
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_MODAL_API_KEY" "selfhosted"
|
||||
env_set "$SERVER_ENV" "DIARIZATION_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "DIARIZATION_URL" "http://transcription:8000"
|
||||
env_set "$SERVER_ENV" "TRANSLATION_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "TRANSLATE_URL" "http://transcription:8000"
|
||||
env_set "$SERVER_ENV" "PADDING_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "PADDING_URL" "http://transcription:8000"
|
||||
ok "ML backends: GPU container (modal)"
|
||||
;;
|
||||
cpu)
|
||||
# In-process backends — no ML service container needed
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_BACKEND" "whisper"
|
||||
env_set "$SERVER_ENV" "DIARIZATION_BACKEND" "pyannote"
|
||||
env_set "$SERVER_ENV" "TRANSLATION_BACKEND" "marian"
|
||||
env_set "$SERVER_ENV" "PADDING_BACKEND" "pyav"
|
||||
ok "ML backends: in-process CPU (whisper/pyannote/marian/pyav)"
|
||||
modal_url="http://transcription:8000"
|
||||
;;
|
||||
hosted)
|
||||
# Remote GPU service — user provides URL
|
||||
local gpu_url=""
|
||||
if env_has_key "$SERVER_ENV" "TRANSCRIPT_URL"; then
|
||||
gpu_url=$(env_get "$SERVER_ENV" "TRANSCRIPT_URL")
|
||||
modal_url=$(env_get "$SERVER_ENV" "TRANSCRIPT_URL")
|
||||
fi
|
||||
if [[ -z "$gpu_url" ]] && [[ -t 0 ]]; then
|
||||
if [[ -z "$modal_url" ]] && [[ -t 0 ]]; then
|
||||
echo ""
|
||||
info "Enter the URL of your remote GPU service (e.g. https://gpu.example.com)"
|
||||
read -rp " GPU service URL: " gpu_url
|
||||
read -rp " GPU service URL: " modal_url
|
||||
fi
|
||||
if [[ -z "$gpu_url" ]]; then
|
||||
if [[ -z "$modal_url" ]]; then
|
||||
err "GPU service URL required for --hosted mode."
|
||||
err "Set TRANSCRIPT_URL in server/.env or provide it interactively."
|
||||
exit 1
|
||||
fi
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_URL" "$gpu_url"
|
||||
env_set "$SERVER_ENV" "DIARIZATION_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "DIARIZATION_URL" "$gpu_url"
|
||||
env_set "$SERVER_ENV" "TRANSLATION_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "TRANSLATE_URL" "$gpu_url"
|
||||
env_set "$SERVER_ENV" "PADDING_BACKEND" "modal"
|
||||
env_set "$SERVER_ENV" "PADDING_URL" "$gpu_url"
|
||||
# API key for remote service
|
||||
local gpu_api_key=""
|
||||
if env_has_key "$SERVER_ENV" "TRANSCRIPT_MODAL_API_KEY"; then
|
||||
@@ -491,15 +785,106 @@ step_server_env() {
|
||||
if [[ -n "$gpu_api_key" ]]; then
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_MODAL_API_KEY" "$gpu_api_key"
|
||||
fi
|
||||
ok "ML backends: remote hosted ($gpu_url)"
|
||||
;;
|
||||
cpu)
|
||||
# CPU mode: modal_url stays empty. If services are overridden to modal,
|
||||
# the user must configure the URL (TRANSCRIPT_URL etc.) in server/.env manually.
|
||||
# We intentionally do NOT read from existing env here to avoid overwriting
|
||||
# per-service URLs with a stale TRANSCRIPT_URL from a previous --gpu run.
|
||||
;;
|
||||
esac
|
||||
|
||||
# Set each service backend independently using effective backends
|
||||
# Transcript
|
||||
case "$EFF_TRANSCRIPT" in
|
||||
modal)
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_BACKEND" "modal"
|
||||
if [[ -n "$modal_url" ]]; then
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_URL" "$modal_url"
|
||||
fi
|
||||
[[ "$MODEL_MODE" == "gpu" ]] && env_set "$SERVER_ENV" "TRANSCRIPT_MODAL_API_KEY" "selfhosted"
|
||||
;;
|
||||
whisper)
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_BACKEND" "whisper"
|
||||
;;
|
||||
esac
|
||||
|
||||
# Diarization
|
||||
case "$EFF_DIARIZATION" in
|
||||
modal)
|
||||
env_set "$SERVER_ENV" "DIARIZATION_BACKEND" "modal"
|
||||
if [[ -n "$modal_url" ]]; then
|
||||
env_set "$SERVER_ENV" "DIARIZATION_URL" "$modal_url"
|
||||
fi
|
||||
;;
|
||||
pyannote)
|
||||
env_set "$SERVER_ENV" "DIARIZATION_BACKEND" "pyannote"
|
||||
;;
|
||||
esac
|
||||
|
||||
# Translation
|
||||
case "$EFF_TRANSLATION" in
|
||||
modal)
|
||||
env_set "$SERVER_ENV" "TRANSLATION_BACKEND" "modal"
|
||||
if [[ -n "$modal_url" ]]; then
|
||||
env_set "$SERVER_ENV" "TRANSLATE_URL" "$modal_url"
|
||||
fi
|
||||
;;
|
||||
marian)
|
||||
env_set "$SERVER_ENV" "TRANSLATION_BACKEND" "marian"
|
||||
;;
|
||||
passthrough)
|
||||
env_set "$SERVER_ENV" "TRANSLATION_BACKEND" "passthrough"
|
||||
;;
|
||||
esac
|
||||
|
||||
# Padding
|
||||
case "$EFF_PADDING" in
|
||||
modal)
|
||||
env_set "$SERVER_ENV" "PADDING_BACKEND" "modal"
|
||||
if [[ -n "$modal_url" ]]; then
|
||||
env_set "$SERVER_ENV" "PADDING_URL" "$modal_url"
|
||||
fi
|
||||
;;
|
||||
pyav)
|
||||
env_set "$SERVER_ENV" "PADDING_BACKEND" "pyav"
|
||||
;;
|
||||
esac
|
||||
|
||||
# Mixdown
|
||||
case "$EFF_MIXDOWN" in
|
||||
modal)
|
||||
env_set "$SERVER_ENV" "MIXDOWN_BACKEND" "modal"
|
||||
if [[ -n "$modal_url" ]]; then
|
||||
env_set "$SERVER_ENV" "MIXDOWN_URL" "$modal_url"
|
||||
fi
|
||||
;;
|
||||
pyav)
|
||||
env_set "$SERVER_ENV" "MIXDOWN_BACKEND" "pyav"
|
||||
;;
|
||||
esac
|
||||
|
||||
# Warn about modal overrides in CPU mode that need URL configuration
|
||||
if [[ "$MODEL_MODE" == "cpu" ]] && [[ -z "$modal_url" ]]; then
|
||||
local needs_url=false
|
||||
[[ "$EFF_TRANSCRIPT" == "modal" ]] && needs_url=true
|
||||
[[ "$EFF_DIARIZATION" == "modal" ]] && needs_url=true
|
||||
[[ "$EFF_TRANSLATION" == "modal" ]] && needs_url=true
|
||||
[[ "$EFF_PADDING" == "modal" ]] && needs_url=true
|
||||
[[ "$EFF_MIXDOWN" == "modal" ]] && needs_url=true
|
||||
if [[ "$needs_url" == "true" ]]; then
|
||||
warn "One or more services are set to 'modal' but no service URL is configured."
|
||||
warn "Set TRANSCRIPT_URL (and optionally TRANSCRIPT_MODAL_API_KEY) in server/.env"
|
||||
warn "to point to your GPU service, then re-run this script."
|
||||
fi
|
||||
fi
|
||||
|
||||
ok "ML backends: transcript=$EFF_TRANSCRIPT, diarization=$EFF_DIARIZATION, translation=$EFF_TRANSLATION, padding=$EFF_PADDING, mixdown=$EFF_MIXDOWN"
|
||||
|
||||
# HuggingFace token for gated models (pyannote diarization)
|
||||
# --gpu: written to root .env (docker compose passes to GPU container)
|
||||
# --cpu: written to both root .env and server/.env (in-process pyannote needs it)
|
||||
# --hosted: not needed (remote service handles its own auth)
|
||||
if [[ "$MODEL_MODE" != "hosted" ]]; then
|
||||
# Needed when: GPU container is running (MODEL_MODE=gpu), or diarization uses pyannote in-process
|
||||
# Not needed when: all modal services point to a remote hosted URL with its own auth
|
||||
if [[ "$MODEL_MODE" == "gpu" ]] || [[ "$EFF_DIARIZATION" == "pyannote" ]]; then
|
||||
local root_env="$ROOT_DIR/.env"
|
||||
local current_hf_token="${HF_TOKEN:-}"
|
||||
if [[ -f "$root_env" ]] && env_has_key "$root_env" "HF_TOKEN"; then
|
||||
@@ -518,8 +903,8 @@ step_server_env() {
|
||||
touch "$root_env"
|
||||
env_set "$root_env" "HF_TOKEN" "$current_hf_token"
|
||||
export HF_TOKEN="$current_hf_token"
|
||||
# In CPU mode, server process needs HF_TOKEN directly
|
||||
if [[ "$MODEL_MODE" == "cpu" ]]; then
|
||||
# When diarization runs in-process (pyannote), server process needs HF_TOKEN directly
|
||||
if [[ "$EFF_DIARIZATION" == "pyannote" ]]; then
|
||||
env_set "$SERVER_ENV" "HF_TOKEN" "$current_hf_token"
|
||||
fi
|
||||
ok "HF_TOKEN configured"
|
||||
@@ -552,11 +937,15 @@ step_server_env() {
|
||||
fi
|
||||
fi
|
||||
|
||||
# CPU mode: increase file processing timeouts (default 600s is too short for long audio on CPU)
|
||||
if [[ "$MODEL_MODE" == "cpu" ]]; then
|
||||
# Increase file processing timeouts for CPU backends (default 600s is too short for long audio on CPU)
|
||||
if [[ "$EFF_TRANSCRIPT" == "whisper" ]]; then
|
||||
env_set "$SERVER_ENV" "TRANSCRIPT_FILE_TIMEOUT" "3600"
|
||||
fi
|
||||
if [[ "$EFF_DIARIZATION" == "pyannote" ]]; then
|
||||
env_set "$SERVER_ENV" "DIARIZATION_FILE_TIMEOUT" "3600"
|
||||
ok "CPU mode — file processing timeouts set to 3600s (1 hour)"
|
||||
fi
|
||||
if [[ "$EFF_TRANSCRIPT" == "whisper" ]] || [[ "$EFF_DIARIZATION" == "pyannote" ]]; then
|
||||
ok "CPU backend(s) detected — file processing timeouts set to 3600s (1 hour)"
|
||||
fi
|
||||
|
||||
# Hatchet is always required (file, live, and multitrack pipelines all use it)
|
||||
@@ -799,7 +1188,25 @@ step_caddyfile() {
|
||||
rm -rf "$caddyfile"
|
||||
fi
|
||||
|
||||
if [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
if [[ -n "$TLS_CERT_PATH" ]] && [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
# Custom domain with user-provided TLS certificate (from --custom-ca directory)
|
||||
cat > "$caddyfile" << CADDYEOF
|
||||
# Generated by setup-selfhosted.sh — Custom TLS cert for $CUSTOM_DOMAIN
|
||||
$CUSTOM_DOMAIN {
|
||||
tls /etc/caddy/certs/server.pem /etc/caddy/certs/server-key.pem
|
||||
handle /v1/* {
|
||||
reverse_proxy server:1250
|
||||
}
|
||||
handle /health {
|
||||
reverse_proxy server:1250
|
||||
}
|
||||
handle {
|
||||
reverse_proxy web:3000
|
||||
}
|
||||
}
|
||||
CADDYEOF
|
||||
ok "Created Caddyfile for $CUSTOM_DOMAIN (custom TLS certificate)"
|
||||
elif [[ -n "$CUSTOM_DOMAIN" ]]; then
|
||||
# Real domain: Caddy auto-provisions Let's Encrypt certificate
|
||||
cat > "$caddyfile" << CADDYEOF
|
||||
# Generated by setup-selfhosted.sh — Let's Encrypt HTTPS for $CUSTOM_DOMAIN
|
||||
@@ -966,9 +1373,9 @@ step_health() {
|
||||
warn "Check with: docker compose -f docker-compose.selfhosted.yml logs gpu"
|
||||
fi
|
||||
elif [[ "$MODEL_MODE" == "cpu" ]]; then
|
||||
ok "CPU mode — ML processing runs in-process on server/worker (no separate service)"
|
||||
ok "CPU mode — in-process backends run on server/worker (transcript=$EFF_TRANSCRIPT, diarization=$EFF_DIARIZATION, translation=$EFF_TRANSLATION, padding=$EFF_PADDING, mixdown=$EFF_MIXDOWN)"
|
||||
elif [[ "$MODEL_MODE" == "hosted" ]]; then
|
||||
ok "Hosted mode — ML processing via remote GPU service (no local health check)"
|
||||
ok "Hosted mode — ML processing via remote GPU service (transcript=$EFF_TRANSCRIPT, diarization=$EFF_DIARIZATION, translation=$EFF_TRANSLATION, padding=$EFF_PADDING, mixdown=$EFF_MIXDOWN)"
|
||||
fi
|
||||
|
||||
# Ollama (if applicable)
|
||||
@@ -1166,10 +1573,16 @@ main() {
|
||||
echo "=========================================="
|
||||
echo ""
|
||||
echo " Models: $MODEL_MODE"
|
||||
if [[ "$HAS_OVERRIDES" == "true" ]]; then
|
||||
echo " transcript=$EFF_TRANSCRIPT, diarization=$EFF_DIARIZATION"
|
||||
echo " translation=$EFF_TRANSLATION, padding=$EFF_PADDING, mixdown=$EFF_MIXDOWN"
|
||||
fi
|
||||
echo " LLM: ${OLLAMA_MODE:-external}"
|
||||
echo " Garage: $USE_GARAGE"
|
||||
echo " Caddy: $USE_CADDY"
|
||||
[[ -n "$CUSTOM_DOMAIN" ]] && echo " Domain: $CUSTOM_DOMAIN"
|
||||
[[ "$USE_CUSTOM_CA" == "true" ]] && echo " CA: Custom ($CUSTOM_CA)"
|
||||
[[ -n "$TLS_CERT_PATH" ]] && echo " TLS: Custom cert (from $CUSTOM_CA)"
|
||||
[[ "$BUILD_IMAGES" == "true" ]] && echo " Build: from source"
|
||||
echo ""
|
||||
|
||||
@@ -1200,6 +1613,8 @@ main() {
|
||||
echo ""
|
||||
step_secrets
|
||||
echo ""
|
||||
step_custom_ca
|
||||
echo ""
|
||||
step_server_env
|
||||
echo ""
|
||||
|
||||
@@ -1274,7 +1689,13 @@ EOF
|
||||
echo " API: server:1250 (or localhost:1250 from host)"
|
||||
fi
|
||||
echo ""
|
||||
echo " Models: $MODEL_MODE (transcription/diarization/translation)"
|
||||
if [[ "$HAS_OVERRIDES" == "true" ]]; then
|
||||
echo " Models: $MODEL_MODE base + overrides"
|
||||
echo " transcript=$EFF_TRANSCRIPT, diarization=$EFF_DIARIZATION"
|
||||
echo " translation=$EFF_TRANSLATION, padding=$EFF_PADDING, mixdown=$EFF_MIXDOWN"
|
||||
else
|
||||
echo " Models: $MODEL_MODE (transcription/diarization/translation/padding)"
|
||||
fi
|
||||
[[ "$USE_GARAGE" == "true" ]] && echo " Storage: Garage (local S3)"
|
||||
[[ "$USE_GARAGE" != "true" ]] && echo " Storage: External S3"
|
||||
[[ "$USES_OLLAMA" == "true" ]] && echo " LLM: Ollama ($OLLAMA_MODEL) for summarization/topics"
|
||||
@@ -1282,9 +1703,20 @@ EOF
|
||||
[[ "$DAILY_DETECTED" == "true" ]] && echo " Video: Daily.co (live rooms + multitrack processing via Hatchet)"
|
||||
[[ "$WHEREBY_DETECTED" == "true" ]] && echo " Video: Whereby (live rooms)"
|
||||
[[ "$ANY_PLATFORM_DETECTED" != "true" ]] && echo " Video: None (rooms disabled)"
|
||||
if [[ "$USE_CUSTOM_CA" == "true" ]]; then
|
||||
echo " CA: Custom (certs/ca.crt)"
|
||||
[[ -n "$TLS_CERT_PATH" ]] && echo " TLS: Custom cert (certs/server.pem)"
|
||||
fi
|
||||
echo ""
|
||||
if [[ "$USE_CUSTOM_CA" == "true" ]]; then
|
||||
echo " NOTE: Clients must trust the CA certificate to avoid browser warnings."
|
||||
echo " CA cert location: certs/ca.crt"
|
||||
echo " See docsv2/custom-ca-setup.md for instructions."
|
||||
echo ""
|
||||
fi
|
||||
echo " To stop: docker compose -f docker-compose.selfhosted.yml down"
|
||||
echo " To re-run: ./scripts/setup-selfhosted.sh $*"
|
||||
echo " To re-run: ./scripts/setup-selfhosted.sh (replays saved config)"
|
||||
echo " Last args: $*"
|
||||
echo ""
|
||||
}
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ ENV PYTHONUNBUFFERED=1 \
|
||||
|
||||
# builder install base dependencies
|
||||
WORKDIR /tmp
|
||||
RUN apt-get update && apt-get install -y curl ffmpeg && apt-get clean
|
||||
RUN apt-get update && apt-get install -y curl ffmpeg ca-certificates && apt-get clean
|
||||
ADD https://astral.sh/uv/install.sh /uv-installer.sh
|
||||
RUN sh /uv-installer.sh && rm /uv-installer.sh
|
||||
ENV PATH="/root/.local/bin/:$PATH"
|
||||
@@ -18,7 +18,7 @@ COPY pyproject.toml uv.lock README.md /app/
|
||||
RUN uv sync --compile-bytecode --locked
|
||||
|
||||
# bootstrap
|
||||
COPY alembic.ini runserver.sh /app/
|
||||
COPY alembic.ini docker-entrypoint.sh runserver.sh /app/
|
||||
COPY images /app/images
|
||||
COPY migrations /app/migrations
|
||||
COPY reflector /app/reflector
|
||||
@@ -35,4 +35,6 @@ RUN if [ "$(uname -m)" = "aarch64" ] && [ ! -f /usr/lib/libgomp.so.1 ]; then \
|
||||
# Pre-check just to make sure the image will not fail
|
||||
RUN uv run python -c "import silero_vad.model"
|
||||
|
||||
CMD ["./runserver.sh"]
|
||||
RUN chmod +x /app/docker-entrypoint.sh
|
||||
|
||||
CMD ["./docker-entrypoint.sh"]
|
||||
|
||||
25
server/docker-entrypoint.sh
Normal file
25
server/docker-entrypoint.sh
Normal file
@@ -0,0 +1,25 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Custom CA certificate injection
|
||||
# If a CA cert is mounted at this path (via docker-compose.ca.yml),
|
||||
# add it to the system trust store and configure all Python SSL libraries.
|
||||
CUSTOM_CA_PATH="/usr/local/share/ca-certificates/custom-ca.crt"
|
||||
|
||||
if [ -s "$CUSTOM_CA_PATH" ]; then
|
||||
echo "[entrypoint] Custom CA certificate detected, updating trust store..."
|
||||
update-ca-certificates 2>/dev/null
|
||||
|
||||
# update-ca-certificates creates a combined bundle (system + custom CAs)
|
||||
COMBINED_BUNDLE="/etc/ssl/certs/ca-certificates.crt"
|
||||
export SSL_CERT_FILE="$COMBINED_BUNDLE"
|
||||
export REQUESTS_CA_BUNDLE="$COMBINED_BUNDLE"
|
||||
export CURL_CA_BUNDLE="$COMBINED_BUNDLE"
|
||||
# Note: GRPC_DEFAULT_SSL_ROOTS_FILE_PATH is intentionally NOT set here.
|
||||
# Setting it causes grpcio to attempt TLS on internal Hatchet connections
|
||||
# that run without TLS (SERVER_GRPC_INSECURE=t), resulting in handshake failures.
|
||||
# If you need gRPC with custom CA, set GRPC_DEFAULT_SSL_ROOTS_FILE_PATH explicitly.
|
||||
echo "[entrypoint] CA trust store updated (SSL_CERT_FILE=$COMBINED_BUNDLE)"
|
||||
fi
|
||||
|
||||
exec ./runserver.sh
|
||||
@@ -84,7 +84,7 @@ from reflector.hatchet.workflows.topic_chunk_processing import (
|
||||
from reflector.hatchet.workflows.track_processing import TrackInput, track_workflow
|
||||
from reflector.logger import logger
|
||||
from reflector.pipelines import topic_processing
|
||||
from reflector.processors import AudioFileWriterProcessor
|
||||
from reflector.processors.audio_mixdown_auto import AudioMixdownAutoProcessor
|
||||
from reflector.processors.summary.models import ActionItemsResponse
|
||||
from reflector.processors.summary.prompts import (
|
||||
RECAP_PROMPT,
|
||||
@@ -99,10 +99,6 @@ from reflector.utils.audio_constants import (
|
||||
PRESIGNED_URL_EXPIRATION_SECONDS,
|
||||
WAVEFORM_SEGMENTS,
|
||||
)
|
||||
from reflector.utils.audio_mixdown import (
|
||||
detect_sample_rate_from_tracks,
|
||||
mixdown_tracks_pyav,
|
||||
)
|
||||
from reflector.utils.audio_waveform import get_audio_waveform
|
||||
from reflector.utils.daily import (
|
||||
filter_cam_audio_tracks,
|
||||
@@ -539,7 +535,7 @@ async def process_tracks(input: PipelineInput, ctx: Context) -> ProcessTracksRes
|
||||
)
|
||||
@with_error_handling(TaskName.MIXDOWN_TRACKS)
|
||||
async def mixdown_tracks(input: PipelineInput, ctx: Context) -> MixdownResult:
|
||||
"""Mix all padded tracks into single audio file using PyAV (same as Celery)."""
|
||||
"""Mix all padded tracks into single audio file via configured backend."""
|
||||
ctx.log("mixdown_tracks: mixing padded tracks into single audio file")
|
||||
|
||||
track_result = ctx.task_output(process_tracks)
|
||||
@@ -579,37 +575,33 @@ async def mixdown_tracks(input: PipelineInput, ctx: Context) -> MixdownResult:
|
||||
if not valid_urls:
|
||||
raise ValueError("No valid padded tracks to mixdown")
|
||||
|
||||
target_sample_rate = detect_sample_rate_from_tracks(valid_urls, logger=logger)
|
||||
if not target_sample_rate:
|
||||
logger.error("Mixdown failed - no decodable audio frames found")
|
||||
raise ValueError("No decodable audio frames in any track")
|
||||
|
||||
output_path = tempfile.mktemp(suffix=".mp3")
|
||||
duration_ms_callback_capture_container = [0.0]
|
||||
|
||||
async def capture_duration(d):
|
||||
duration_ms_callback_capture_container[0] = d
|
||||
|
||||
writer = AudioFileWriterProcessor(path=output_path, on_duration=capture_duration)
|
||||
|
||||
await mixdown_tracks_pyav(
|
||||
valid_urls,
|
||||
writer,
|
||||
target_sample_rate,
|
||||
offsets_seconds=None,
|
||||
logger=logger,
|
||||
progress_callback=make_audio_progress_logger(ctx, TaskName.MIXDOWN_TRACKS),
|
||||
expected_duration_sec=recording_duration if recording_duration > 0 else None,
|
||||
)
|
||||
await writer.flush()
|
||||
|
||||
file_size = Path(output_path).stat().st_size
|
||||
storage_path = f"{input.transcript_id}/audio.mp3"
|
||||
|
||||
with open(output_path, "rb") as mixed_file:
|
||||
await storage.put_file(storage_path, mixed_file)
|
||||
# Generate presigned PUT URL for the output (used by modal backend;
|
||||
# pyav backend ignores it and writes locally instead)
|
||||
output_url = await storage.get_file_url(
|
||||
storage_path,
|
||||
operation="put_object",
|
||||
expires_in=PRESIGNED_URL_EXPIRATION_SECONDS,
|
||||
)
|
||||
|
||||
Path(output_path).unlink(missing_ok=True)
|
||||
processor = AudioMixdownAutoProcessor()
|
||||
result = await processor.mixdown_tracks(
|
||||
valid_urls, output_url, offsets_seconds=None
|
||||
)
|
||||
|
||||
if result.output_path:
|
||||
# Pyav backend wrote locally — upload to storage ourselves
|
||||
output_file = Path(result.output_path)
|
||||
with open(output_file, "rb") as mixed_file:
|
||||
await storage.put_file(storage_path, mixed_file)
|
||||
output_file.unlink(missing_ok=True)
|
||||
# Clean up the temp directory the pyav processor created
|
||||
try:
|
||||
output_file.parent.rmdir()
|
||||
except OSError:
|
||||
pass
|
||||
# else: modal backend already uploaded to output_url
|
||||
|
||||
async with fresh_db_connection():
|
||||
from reflector.db.transcripts import transcripts_controller # noqa: PLC0415
|
||||
@@ -620,11 +612,11 @@ async def mixdown_tracks(input: PipelineInput, ctx: Context) -> MixdownResult:
|
||||
transcript, {"audio_location": "storage"}
|
||||
)
|
||||
|
||||
ctx.log(f"mixdown_tracks complete: uploaded {file_size} bytes to {storage_path}")
|
||||
ctx.log(f"mixdown_tracks complete: {result.size} bytes to {storage_path}")
|
||||
|
||||
return MixdownResult(
|
||||
audio_key=storage_path,
|
||||
duration=duration_ms_callback_capture_container[0],
|
||||
duration=result.duration_ms,
|
||||
tracks_mixed=len(valid_urls),
|
||||
)
|
||||
|
||||
|
||||
@@ -4,6 +4,8 @@ from .audio_diarization_auto import AudioDiarizationAutoProcessor # noqa: F401
|
||||
from .audio_downscale import AudioDownscaleProcessor # noqa: F401
|
||||
from .audio_file_writer import AudioFileWriterProcessor # noqa: F401
|
||||
from .audio_merge import AudioMergeProcessor # noqa: F401
|
||||
from .audio_mixdown import AudioMixdownProcessor # noqa: F401
|
||||
from .audio_mixdown_auto import AudioMixdownAutoProcessor # noqa: F401
|
||||
from .audio_padding import AudioPaddingProcessor # noqa: F401
|
||||
from .audio_padding_auto import AudioPaddingAutoProcessor # noqa: F401
|
||||
from .audio_transcript import AudioTranscriptProcessor # noqa: F401
|
||||
|
||||
27
server/reflector/processors/audio_mixdown.py
Normal file
27
server/reflector/processors/audio_mixdown.py
Normal file
@@ -0,0 +1,27 @@
|
||||
"""
|
||||
Base class for audio mixdown processors.
|
||||
"""
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class MixdownResponse(BaseModel):
|
||||
size: int
|
||||
duration_ms: float = 0.0
|
||||
cancelled: bool = False
|
||||
output_path: str | None = (
|
||||
None # Local file path (pyav sets this; modal leaves None)
|
||||
)
|
||||
|
||||
|
||||
class AudioMixdownProcessor:
|
||||
"""Base class for audio mixdown processors."""
|
||||
|
||||
async def mixdown_tracks(
|
||||
self,
|
||||
track_urls: list[str],
|
||||
output_url: str,
|
||||
target_sample_rate: int | None = None,
|
||||
offsets_seconds: list[float] | None = None,
|
||||
) -> MixdownResponse:
|
||||
raise NotImplementedError
|
||||
32
server/reflector/processors/audio_mixdown_auto.py
Normal file
32
server/reflector/processors/audio_mixdown_auto.py
Normal file
@@ -0,0 +1,32 @@
|
||||
import importlib
|
||||
|
||||
from reflector.processors.audio_mixdown import AudioMixdownProcessor
|
||||
from reflector.settings import settings
|
||||
|
||||
|
||||
class AudioMixdownAutoProcessor(AudioMixdownProcessor):
|
||||
_registry = {}
|
||||
|
||||
@classmethod
|
||||
def register(cls, name, kclass):
|
||||
cls._registry[name] = kclass
|
||||
|
||||
def __new__(cls, name: str | None = None, **kwargs):
|
||||
if name is None:
|
||||
name = settings.MIXDOWN_BACKEND
|
||||
if name not in cls._registry:
|
||||
module_name = f"reflector.processors.audio_mixdown_{name}"
|
||||
importlib.import_module(module_name)
|
||||
|
||||
# gather specific configuration for the processor
|
||||
# search `MIXDOWN_XXX_YYY`, push to constructor as `xxx_yyy`
|
||||
config = {}
|
||||
name_upper = name.upper()
|
||||
settings_prefix = "MIXDOWN_"
|
||||
config_prefix = f"{settings_prefix}{name_upper}_"
|
||||
for key, value in settings:
|
||||
if key.startswith(config_prefix):
|
||||
config_name = key[len(settings_prefix) :].lower()
|
||||
config[config_name] = value
|
||||
|
||||
return cls._registry[name](**config | kwargs)
|
||||
110
server/reflector/processors/audio_mixdown_modal.py
Normal file
110
server/reflector/processors/audio_mixdown_modal.py
Normal file
@@ -0,0 +1,110 @@
|
||||
"""
|
||||
Modal.com backend for audio mixdown.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
import httpx
|
||||
|
||||
from reflector.hatchet.constants import TIMEOUT_HEAVY_HTTP
|
||||
from reflector.logger import logger
|
||||
from reflector.processors.audio_mixdown import AudioMixdownProcessor, MixdownResponse
|
||||
from reflector.processors.audio_mixdown_auto import AudioMixdownAutoProcessor
|
||||
|
||||
|
||||
class AudioMixdownModalProcessor(AudioMixdownProcessor):
|
||||
"""Audio mixdown processor using Modal.com/self-hosted backend via HTTP."""
|
||||
|
||||
def __init__(
|
||||
self, mixdown_url: str | None = None, modal_api_key: str | None = None
|
||||
):
|
||||
self.mixdown_url = mixdown_url or os.getenv("MIXDOWN_URL")
|
||||
if not self.mixdown_url:
|
||||
raise ValueError(
|
||||
"MIXDOWN_URL required to use AudioMixdownModalProcessor. "
|
||||
"Set MIXDOWN_URL environment variable or pass mixdown_url parameter."
|
||||
)
|
||||
|
||||
self.modal_api_key = modal_api_key or os.getenv("MODAL_API_KEY")
|
||||
|
||||
async def mixdown_tracks(
|
||||
self,
|
||||
track_urls: list[str],
|
||||
output_url: str,
|
||||
target_sample_rate: int | None = None,
|
||||
offsets_seconds: list[float] | None = None,
|
||||
) -> MixdownResponse:
|
||||
"""Mix audio tracks via remote Modal/self-hosted backend.
|
||||
|
||||
Args:
|
||||
track_urls: Presigned GET URLs for source audio tracks
|
||||
output_url: Presigned PUT URL for output MP3
|
||||
target_sample_rate: Sample rate for output (Hz), auto-detected if None
|
||||
offsets_seconds: Optional per-track delays in seconds for alignment
|
||||
"""
|
||||
valid_count = len([u for u in track_urls if u])
|
||||
log = logger.bind(track_count=valid_count)
|
||||
log.info("Sending Modal mixdown HTTP request")
|
||||
|
||||
url = f"{self.mixdown_url}/mixdown"
|
||||
|
||||
headers = {}
|
||||
if self.modal_api_key:
|
||||
headers["Authorization"] = f"Bearer {self.modal_api_key}"
|
||||
|
||||
# Scale timeout with track count: base TIMEOUT_HEAVY_HTTP + 60s per track beyond 2
|
||||
extra_timeout = max(0, (valid_count - 2)) * 60
|
||||
timeout = TIMEOUT_HEAVY_HTTP + extra_timeout
|
||||
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=timeout) as client:
|
||||
response = await client.post(
|
||||
url,
|
||||
headers=headers,
|
||||
json={
|
||||
"track_urls": track_urls,
|
||||
"output_url": output_url,
|
||||
"target_sample_rate": target_sample_rate,
|
||||
"offsets_seconds": offsets_seconds,
|
||||
},
|
||||
follow_redirects=True,
|
||||
)
|
||||
|
||||
if response.status_code != 200:
|
||||
error_body = response.text
|
||||
log.error(
|
||||
"Modal mixdown API error",
|
||||
status_code=response.status_code,
|
||||
error_body=error_body,
|
||||
)
|
||||
|
||||
response.raise_for_status()
|
||||
result = response.json()
|
||||
|
||||
# Check if work was cancelled
|
||||
if result.get("cancelled"):
|
||||
log.warning("Modal mixdown was cancelled by disconnect detection")
|
||||
raise asyncio.CancelledError(
|
||||
"Mixdown cancelled due to client disconnect"
|
||||
)
|
||||
|
||||
log.info("Modal mixdown complete", size=result["size"])
|
||||
return MixdownResponse(**result)
|
||||
except asyncio.CancelledError:
|
||||
log.warning(
|
||||
"Modal mixdown cancelled (Hatchet timeout, disconnect detected on Modal side)"
|
||||
)
|
||||
raise
|
||||
except httpx.TimeoutException as e:
|
||||
log.error("Modal mixdown timeout", error=str(e), exc_info=True)
|
||||
raise Exception(f"Modal mixdown timeout: {e}") from e
|
||||
except httpx.HTTPStatusError as e:
|
||||
log.error("Modal mixdown HTTP error", error=str(e), exc_info=True)
|
||||
raise Exception(f"Modal mixdown HTTP error: {e}") from e
|
||||
except Exception as e:
|
||||
log.error("Modal mixdown unexpected error", error=str(e), exc_info=True)
|
||||
raise
|
||||
|
||||
|
||||
AudioMixdownAutoProcessor.register("modal", AudioMixdownModalProcessor)
|
||||
101
server/reflector/processors/audio_mixdown_pyav.py
Normal file
101
server/reflector/processors/audio_mixdown_pyav.py
Normal file
@@ -0,0 +1,101 @@
|
||||
"""
|
||||
PyAV audio mixdown processor.
|
||||
|
||||
Mixes N tracks in-process using the existing utility from reflector.utils.audio_mixdown.
|
||||
Writes to a local temp file (does NOT upload to S3 — the pipeline handles upload).
|
||||
"""
|
||||
|
||||
import os
|
||||
import tempfile
|
||||
|
||||
from reflector.logger import logger
|
||||
from reflector.processors.audio_file_writer import AudioFileWriterProcessor
|
||||
from reflector.processors.audio_mixdown import AudioMixdownProcessor, MixdownResponse
|
||||
from reflector.processors.audio_mixdown_auto import AudioMixdownAutoProcessor
|
||||
from reflector.utils.audio_mixdown import (
|
||||
detect_sample_rate_from_tracks,
|
||||
mixdown_tracks_pyav,
|
||||
)
|
||||
|
||||
|
||||
class AudioMixdownPyavProcessor(AudioMixdownProcessor):
|
||||
"""Audio mixdown processor using PyAV (no HTTP backend).
|
||||
|
||||
Writes the mixed output to a local temp file and returns its path
|
||||
in MixdownResponse.output_path. The caller is responsible for
|
||||
uploading the file and cleaning it up.
|
||||
"""
|
||||
|
||||
async def mixdown_tracks(
|
||||
self,
|
||||
track_urls: list[str],
|
||||
output_url: str,
|
||||
target_sample_rate: int | None = None,
|
||||
offsets_seconds: list[float] | None = None,
|
||||
) -> MixdownResponse:
|
||||
log = logger.bind(track_count=len(track_urls))
|
||||
log.info("Starting local PyAV mixdown")
|
||||
|
||||
valid_urls = [url for url in track_urls if url]
|
||||
if not valid_urls:
|
||||
raise ValueError("No valid track URLs provided")
|
||||
|
||||
# Auto-detect sample rate if not provided
|
||||
if target_sample_rate is None:
|
||||
target_sample_rate = detect_sample_rate_from_tracks(
|
||||
valid_urls, logger=logger
|
||||
)
|
||||
if not target_sample_rate:
|
||||
raise ValueError("No decodable audio frames in any track")
|
||||
|
||||
# Write to temp MP3 file
|
||||
temp_dir = tempfile.mkdtemp()
|
||||
output_path = os.path.join(temp_dir, "mixed.mp3")
|
||||
duration_ms_container = [0.0]
|
||||
|
||||
async def capture_duration(d):
|
||||
duration_ms_container[0] = d
|
||||
|
||||
writer = AudioFileWriterProcessor(
|
||||
path=output_path, on_duration=capture_duration
|
||||
)
|
||||
|
||||
try:
|
||||
await mixdown_tracks_pyav(
|
||||
valid_urls,
|
||||
writer,
|
||||
target_sample_rate,
|
||||
offsets_seconds=offsets_seconds,
|
||||
logger=logger,
|
||||
)
|
||||
await writer.flush()
|
||||
|
||||
file_size = os.path.getsize(output_path)
|
||||
log.info(
|
||||
"Local mixdown complete",
|
||||
size=file_size,
|
||||
duration_ms=duration_ms_container[0],
|
||||
)
|
||||
|
||||
return MixdownResponse(
|
||||
size=file_size,
|
||||
duration_ms=duration_ms_container[0],
|
||||
output_path=output_path,
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
# Cleanup on failure
|
||||
if os.path.exists(output_path):
|
||||
try:
|
||||
os.unlink(output_path)
|
||||
except Exception:
|
||||
pass
|
||||
try:
|
||||
os.rmdir(temp_dir)
|
||||
except Exception:
|
||||
pass
|
||||
log.error("Local mixdown failed", error=str(e), exc_info=True)
|
||||
raise
|
||||
|
||||
|
||||
AudioMixdownAutoProcessor.register("pyav", AudioMixdownPyavProcessor)
|
||||
@@ -127,6 +127,14 @@ class Settings(BaseSettings):
|
||||
PADDING_URL: str | None = None
|
||||
PADDING_MODAL_API_KEY: str | None = None
|
||||
|
||||
# Audio Mixdown
|
||||
# backends:
|
||||
# - pyav: in-process PyAV mixdown (no HTTP, runs in same process)
|
||||
# - modal: HTTP API client (works with Modal.com OR self-hosted gpu/self_hosted/)
|
||||
MIXDOWN_BACKEND: str = "pyav"
|
||||
MIXDOWN_URL: str | None = None
|
||||
MIXDOWN_MODAL_API_KEY: str | None = None
|
||||
|
||||
# Sentry
|
||||
SENTRY_DSN: str | None = None
|
||||
|
||||
|
||||
@@ -700,8 +700,6 @@ async def transcript_post_to_zulip(
|
||||
)
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=404, detail="Transcript not found")
|
||||
if not transcripts_controller.user_can_mutate(transcript, user_id):
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
content = get_zulip_message(transcript, include_topics)
|
||||
|
||||
message_updated = False
|
||||
@@ -733,17 +731,15 @@ class SendEmailResponse(BaseModel):
|
||||
async def transcript_send_email(
|
||||
transcript_id: str,
|
||||
request: SendEmailRequest,
|
||||
user: Annotated[auth.UserInfo, Depends(auth.current_user)],
|
||||
user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
|
||||
):
|
||||
if not is_email_configured():
|
||||
raise HTTPException(status_code=400, detail="Email not configured")
|
||||
user_id = user["sub"]
|
||||
user_id = user["sub"] if user else None
|
||||
transcript = await transcripts_controller.get_by_id_for_http(
|
||||
transcript_id, user_id=user_id
|
||||
)
|
||||
if not transcript:
|
||||
raise HTTPException(status_code=404, detail="Transcript not found")
|
||||
if not transcripts_controller.user_can_mutate(transcript, user_id):
|
||||
raise HTTPException(status_code=403, detail="Not authorized")
|
||||
sent = await send_transcript_email([request.email], transcript)
|
||||
return SendEmailResponse(sent=sent)
|
||||
|
||||
@@ -162,15 +162,9 @@ async def test_multitrack_pipeline_end_to_end(
|
||||
), f"Expected at least 2 speakers for multitrack, got {len(participants)}"
|
||||
|
||||
# 7. Verify email transcript notification
|
||||
# The send_email pipeline task should have:
|
||||
# a) Set the transcript to public share_mode
|
||||
# b) Sent an email to TEST_EMAIL via Mailpit
|
||||
transcript_resp = await api_client.get(f"/transcripts/{transcript_id}")
|
||||
transcript_resp.raise_for_status()
|
||||
transcript_data = transcript_resp.json()
|
||||
assert (
|
||||
transcript_data.get("share_mode") == "public"
|
||||
), "Transcript should be set to public when email recipients exist"
|
||||
# The send_email pipeline task should have sent an email to TEST_EMAIL via Mailpit.
|
||||
# Note: share_mode is only set to "public" when meeting has email_recipients;
|
||||
# room-level emails do NOT change share_mode.
|
||||
|
||||
# Poll Mailpit for the delivered email (send_email task runs async after finalize)
|
||||
messages = await poll_mailpit_messages(mailpit_client, TEST_EMAIL, max_wait=30)
|
||||
|
||||
78
server/uv.lock
generated
78
server/uv.lock
generated
@@ -776,47 +776,47 @@ toml = [
|
||||
|
||||
[[package]]
|
||||
name = "cryptography"
|
||||
version = "46.0.5"
|
||||
version = "46.0.6"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "cffi", version = "2.0.0", source = { registry = "https://pypi.org/simple" }, marker = "platform_python_implementation != 'PyPy'" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/60/04/ee2a9e8542e4fa2773b81771ff8349ff19cdd56b7258a0cc442639052edb/cryptography-46.0.5.tar.gz", hash = "sha256:abace499247268e3757271b2f1e244b36b06f8515cf27c4d49468fc9eb16e93d", size = 750064, upload-time = "2026-02-10T19:18:38.255Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/a4/ba/04b1bd4218cbc58dc90ce967106d51582371b898690f3ae0402876cc4f34/cryptography-46.0.6.tar.gz", hash = "sha256:27550628a518c5c6c903d84f637fbecf287f6cb9ced3804838a1295dc1fd0759", size = 750542, upload-time = "2026-03-25T23:34:53.396Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/f7/81/b0bb27f2ba931a65409c6b8a8b358a7f03c0e46eceacddff55f7c84b1f3b/cryptography-46.0.5-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:351695ada9ea9618b3500b490ad54c739860883df6c1f555e088eaf25b1bbaad", size = 7176289, upload-time = "2026-02-10T19:17:08.274Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ff/9e/6b4397a3e3d15123de3b1806ef342522393d50736c13b20ec4c9ea6693a6/cryptography-46.0.5-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:c18ff11e86df2e28854939acde2d003f7984f721eba450b56a200ad90eeb0e6b", size = 4275637, upload-time = "2026-02-10T19:17:10.53Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/63/e7/471ab61099a3920b0c77852ea3f0ea611c9702f651600397ac567848b897/cryptography-46.0.5-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4d7e3d356b8cd4ea5aff04f129d5f66ebdc7b6f8eae802b93739ed520c47c79b", size = 4424742, upload-time = "2026-02-10T19:17:12.388Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/37/53/a18500f270342d66bf7e4d9f091114e31e5ee9e7375a5aba2e85a91e0044/cryptography-46.0.5-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:50bfb6925eff619c9c023b967d5b77a54e04256c4281b0e21336a130cd7fc263", size = 4277528, upload-time = "2026-02-10T19:17:13.853Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/22/29/c2e812ebc38c57b40e7c583895e73c8c5adb4d1e4a0cc4c5a4fdab2b1acc/cryptography-46.0.5-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:803812e111e75d1aa73690d2facc295eaefd4439be1023fefc4995eaea2af90d", size = 4947993, upload-time = "2026-02-10T19:17:15.618Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6b/e7/237155ae19a9023de7e30ec64e5d99a9431a567407ac21170a046d22a5a3/cryptography-46.0.5-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3ee190460e2fbe447175cda91b88b84ae8322a104fc27766ad09428754a618ed", size = 4456855, upload-time = "2026-02-10T19:17:17.221Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2d/87/fc628a7ad85b81206738abbd213b07702bcbdada1dd43f72236ef3cffbb5/cryptography-46.0.5-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:f145bba11b878005c496e93e257c1e88f154d278d2638e6450d17e0f31e558d2", size = 3984635, upload-time = "2026-02-10T19:17:18.792Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/84/29/65b55622bde135aedf4565dc509d99b560ee4095e56989e815f8fd2aa910/cryptography-46.0.5-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:e9251e3be159d1020c4030bd2e5f84d6a43fe54b6c19c12f51cde9542a2817b2", size = 4277038, upload-time = "2026-02-10T19:17:20.256Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bc/36/45e76c68d7311432741faf1fbf7fac8a196a0a735ca21f504c75d37e2558/cryptography-46.0.5-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:47fb8a66058b80e509c47118ef8a75d14c455e81ac369050f20ba0d23e77fee0", size = 4912181, upload-time = "2026-02-10T19:17:21.825Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/6d/1a/c1ba8fead184d6e3d5afcf03d569acac5ad063f3ac9fb7258af158f7e378/cryptography-46.0.5-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:4c3341037c136030cb46e4b1e17b7418ea4cbd9dd207e4a6f3b2b24e0d4ac731", size = 4456482, upload-time = "2026-02-10T19:17:25.133Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f9/e5/3fb22e37f66827ced3b902cf895e6a6bc1d095b5b26be26bd13c441fdf19/cryptography-46.0.5-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:890bcb4abd5a2d3f852196437129eb3667d62630333aacc13dfd470fad3aaa82", size = 4405497, upload-time = "2026-02-10T19:17:26.66Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1a/df/9d58bb32b1121a8a2f27383fabae4d63080c7ca60b9b5c88be742be04ee7/cryptography-46.0.5-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:80a8d7bfdf38f87ca30a5391c0c9ce4ed2926918e017c29ddf643d0ed2778ea1", size = 4667819, upload-time = "2026-02-10T19:17:28.569Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ea/ed/325d2a490c5e94038cdb0117da9397ece1f11201f425c4e9c57fe5b9f08b/cryptography-46.0.5-cp311-abi3-win32.whl", hash = "sha256:60ee7e19e95104d4c03871d7d7dfb3d22ef8a9b9c6778c94e1c8fcc8365afd48", size = 3028230, upload-time = "2026-02-10T19:17:30.518Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e9/5a/ac0f49e48063ab4255d9e3b79f5def51697fce1a95ea1370f03dc9db76f6/cryptography-46.0.5-cp311-abi3-win_amd64.whl", hash = "sha256:38946c54b16c885c72c4f59846be9743d699eee2b69b6988e0a00a01f46a61a4", size = 3480909, upload-time = "2026-02-10T19:17:32.083Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e2/fa/a66aa722105ad6a458bebd64086ca2b72cdd361fed31763d20390f6f1389/cryptography-46.0.5-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:4108d4c09fbbf2789d0c926eb4152ae1760d5a2d97612b92d508d96c861e4d31", size = 7170514, upload-time = "2026-02-10T19:17:56.267Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0f/04/c85bdeab78c8bc77b701bf0d9bdcf514c044e18a46dcff330df5448631b0/cryptography-46.0.5-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7d1f30a86d2757199cb2d56e48cce14deddf1f9c95f1ef1b64ee91ea43fe2e18", size = 4275349, upload-time = "2026-02-10T19:17:58.419Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5c/32/9b87132a2f91ee7f5223b091dc963055503e9b442c98fc0b8a5ca765fab0/cryptography-46.0.5-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:039917b0dc418bb9f6edce8a906572d69e74bd330b0b3fea4f79dab7f8ddd235", size = 4420667, upload-time = "2026-02-10T19:18:00.619Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/a1/a6/a7cb7010bec4b7c5692ca6f024150371b295ee1c108bdc1c400e4c44562b/cryptography-46.0.5-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:ba2a27ff02f48193fc4daeadf8ad2590516fa3d0adeeb34336b96f7fa64c1e3a", size = 4276980, upload-time = "2026-02-10T19:18:02.379Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8e/7c/c4f45e0eeff9b91e3f12dbd0e165fcf2a38847288fcfd889deea99fb7b6d/cryptography-46.0.5-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:61aa400dce22cb001a98014f647dc21cda08f7915ceb95df0c9eaf84b4b6af76", size = 4939143, upload-time = "2026-02-10T19:18:03.964Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/37/19/e1b8f964a834eddb44fa1b9a9976f4e414cbb7aa62809b6760c8803d22d1/cryptography-46.0.5-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3ce58ba46e1bc2aac4f7d9290223cead56743fa6ab94a5d53292ffaac6a91614", size = 4453674, upload-time = "2026-02-10T19:18:05.588Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/db/ed/db15d3956f65264ca204625597c410d420e26530c4e2943e05a0d2f24d51/cryptography-46.0.5-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:420d0e909050490d04359e7fdb5ed7e667ca5c3c402b809ae2563d7e66a92229", size = 3978801, upload-time = "2026-02-10T19:18:07.167Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/41/e2/df40a31d82df0a70a0daf69791f91dbb70e47644c58581d654879b382d11/cryptography-46.0.5-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:582f5fcd2afa31622f317f80426a027f30dc792e9c80ffee87b993200ea115f1", size = 4276755, upload-time = "2026-02-10T19:18:09.813Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/33/45/726809d1176959f4a896b86907b98ff4391a8aa29c0aaaf9450a8a10630e/cryptography-46.0.5-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:bfd56bb4b37ed4f330b82402f6f435845a5f5648edf1ad497da51a8452d5d62d", size = 4901539, upload-time = "2026-02-10T19:18:11.263Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/99/0f/a3076874e9c88ecb2ecc31382f6e7c21b428ede6f55aafa1aa272613e3cd/cryptography-46.0.5-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:a3d507bb6a513ca96ba84443226af944b0f7f47dcc9a399d110cd6146481d24c", size = 4452794, upload-time = "2026-02-10T19:18:12.914Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/02/ef/ffeb542d3683d24194a38f66ca17c0a4b8bf10631feef44a7ef64e631b1a/cryptography-46.0.5-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9f16fbdf4da055efb21c22d81b89f155f02ba420558db21288b3d0035bafd5f4", size = 4404160, upload-time = "2026-02-10T19:18:14.375Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/96/93/682d2b43c1d5f1406ed048f377c0fc9fc8f7b0447a478d5c65ab3d3a66eb/cryptography-46.0.5-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:ced80795227d70549a411a4ab66e8ce307899fad2220ce5ab2f296e687eacde9", size = 4667123, upload-time = "2026-02-10T19:18:15.886Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/45/2d/9c5f2926cb5300a8eefc3f4f0b3f3df39db7f7ce40c8365444c49363cbda/cryptography-46.0.5-cp38-abi3-win32.whl", hash = "sha256:02f547fce831f5096c9a567fd41bc12ca8f11df260959ecc7c3202555cc47a72", size = 3010220, upload-time = "2026-02-10T19:18:17.361Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/48/ef/0c2f4a8e31018a986949d34a01115dd057bf536905dca38897bacd21fac3/cryptography-46.0.5-cp38-abi3-win_amd64.whl", hash = "sha256:556e106ee01aa13484ce9b0239bca667be5004efb0aabbed28d353df86445595", size = 3467050, upload-time = "2026-02-10T19:18:18.899Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/eb/dd/2d9fdb07cebdf3d51179730afb7d5e576153c6744c3ff8fded23030c204e/cryptography-46.0.5-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:3b4995dc971c9fb83c25aa44cf45f02ba86f71ee600d81091c2f0cbae116b06c", size = 3476964, upload-time = "2026-02-10T19:18:20.687Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e9/6f/6cc6cc9955caa6eaf83660b0da2b077c7fe8ff9950a3c5e45d605038d439/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:bc84e875994c3b445871ea7181d424588171efec3e185dced958dad9e001950a", size = 4218321, upload-time = "2026-02-10T19:18:22.349Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/3e/5d/c4da701939eeee699566a6c1367427ab91a8b7088cc2328c09dbee940415/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:2ae6971afd6246710480e3f15824ed3029a60fc16991db250034efd0b9fb4356", size = 4381786, upload-time = "2026-02-10T19:18:24.529Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ac/97/a538654732974a94ff96c1db621fa464f455c02d4bb7d2652f4edc21d600/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:d861ee9e76ace6cf36a6a89b959ec08e7bc2493ee39d07ffe5acb23ef46d27da", size = 4217990, upload-time = "2026-02-10T19:18:25.957Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ae/11/7e500d2dd3ba891197b9efd2da5454b74336d64a7cc419aa7327ab74e5f6/cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:2b7a67c9cd56372f3249b39699f2ad479f6991e62ea15800973b956f4b73e257", size = 4381252, upload-time = "2026-02-10T19:18:27.496Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bc/58/6b3d24e6b9bc474a2dcdee65dfd1f008867015408a271562e4b690561a4d/cryptography-46.0.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:8456928655f856c6e1533ff59d5be76578a7157224dbd9ce6872f25055ab9ab7", size = 3407605, upload-time = "2026-02-10T19:18:29.233Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/47/23/9285e15e3bc57325b0a72e592921983a701efc1ee8f91c06c5f0235d86d9/cryptography-46.0.6-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:64235194bad039a10bb6d2d930ab3323baaec67e2ce36215fd0952fad0930ca8", size = 7176401, upload-time = "2026-03-25T23:33:22.096Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/60/f8/e61f8f13950ab6195b31913b42d39f0f9afc7d93f76710f299b5ec286ae6/cryptography-46.0.6-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:26031f1e5ca62fcb9d1fcb34b2b60b390d1aacaa15dc8b895a9ed00968b97b30", size = 4275275, upload-time = "2026-03-25T23:33:23.844Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/19/69/732a736d12c2631e140be2348b4ad3d226302df63ef64d30dfdb8db7ad1c/cryptography-46.0.6-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9a693028b9cbe51b5a1136232ee8f2bc242e4e19d456ded3fa7c86e43c713b4a", size = 4425320, upload-time = "2026-03-25T23:33:25.703Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d4/12/123be7292674abf76b21ac1fc0e1af50661f0e5b8f0ec8285faac18eb99e/cryptography-46.0.6-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:67177e8a9f421aa2d3a170c3e56eca4e0128883cf52a071a7cbf53297f18b175", size = 4278082, upload-time = "2026-03-25T23:33:27.423Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/5b/ba/d5e27f8d68c24951b0a484924a84c7cdaed7502bac9f18601cd357f8b1d2/cryptography-46.0.6-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:d9528b535a6c4f8ff37847144b8986a9a143585f0540fbcb1a98115b543aa463", size = 4926514, upload-time = "2026-03-25T23:33:29.206Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/34/71/1ea5a7352ae516d5512d17babe7e1b87d9db5150b21f794b1377eac1edc0/cryptography-46.0.6-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:22259338084d6ae497a19bae5d4c66b7ca1387d3264d1c2c0e72d9e9b6a77b97", size = 4457766, upload-time = "2026-03-25T23:33:30.834Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/01/59/562be1e653accee4fdad92c7a2e88fced26b3fdfce144047519bbebc299e/cryptography-46.0.6-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:760997a4b950ff00d418398ad73fbc91aa2894b5c1db7ccb45b4f68b42a63b3c", size = 3986535, upload-time = "2026-03-25T23:33:33.02Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d6/8b/b1ebfeb788bf4624d36e45ed2662b8bd43a05ff62157093c1539c1288a18/cryptography-46.0.6-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:3dfa6567f2e9e4c5dceb8ccb5a708158a2a871052fa75c8b78cb0977063f1507", size = 4277618, upload-time = "2026-03-25T23:33:34.567Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/dd/52/a005f8eabdb28df57c20f84c44d397a755782d6ff6d455f05baa2785bd91/cryptography-46.0.6-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:cdcd3edcbc5d55757e5f5f3d330dd00007ae463a7e7aa5bf132d1f22a4b62b19", size = 4890802, upload-time = "2026-03-25T23:33:37.034Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ec/4d/8e7d7245c79c617d08724e2efa397737715ca0ec830ecb3c91e547302555/cryptography-46.0.6-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:d4e4aadb7fc1f88687f47ca20bb7227981b03afaae69287029da08096853b738", size = 4457425, upload-time = "2026-03-25T23:33:38.904Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1d/5c/f6c3596a1430cec6f949085f0e1a970638d76f81c3ea56d93d564d04c340/cryptography-46.0.6-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:2b417edbe8877cda9022dde3a008e2deb50be9c407eef034aeeb3a8b11d9db3c", size = 4405530, upload-time = "2026-03-25T23:33:40.842Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/7e/c9/9f9cea13ee2dbde070424e0c4f621c091a91ffcc504ffea5e74f0e1daeff/cryptography-46.0.6-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:380343e0653b1c9d7e1f55b52aaa2dbb2fdf2730088d48c43ca1c7c0abb7cc2f", size = 4667896, upload-time = "2026-03-25T23:33:42.781Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ad/b5/1895bc0821226f129bc74d00eccfc6a5969e2028f8617c09790bf89c185e/cryptography-46.0.6-cp311-abi3-win32.whl", hash = "sha256:bcb87663e1f7b075e48c3be3ecb5f0b46c8fc50b50a97cf264e7f60242dca3f2", size = 3026348, upload-time = "2026-03-25T23:33:45.021Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c3/f8/c9bcbf0d3e6ad288b9d9aa0b1dee04b063d19e8c4f871855a03ab3a297ab/cryptography-46.0.6-cp311-abi3-win_amd64.whl", hash = "sha256:6739d56300662c468fddb0e5e291f9b4d084bead381667b9e654c7dd81705124", size = 3483896, upload-time = "2026-03-25T23:33:46.649Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c4/cc/f330e982852403da79008552de9906804568ae9230da8432f7496ce02b71/cryptography-46.0.6-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:12cae594e9473bca1a7aceb90536060643128bb274fcea0fc459ab90f7d1ae7a", size = 7162776, upload-time = "2026-03-25T23:34:13.308Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/49/b3/dc27efd8dcc4bff583b3f01d4a3943cd8b5821777a58b3a6a5f054d61b79/cryptography-46.0.6-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:639301950939d844a9e1c4464d7e07f902fe9a7f6b215bb0d4f28584729935d8", size = 4270529, upload-time = "2026-03-25T23:34:15.019Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e6/05/e8d0e6eb4f0d83365b3cb0e00eb3c484f7348db0266652ccd84632a3d58d/cryptography-46.0.6-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ed3775295fb91f70b4027aeba878d79b3e55c0b3e97eaa4de71f8f23a9f2eb77", size = 4414827, upload-time = "2026-03-25T23:34:16.604Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2f/97/daba0f5d2dc6d855e2dcb70733c812558a7977a55dd4a6722756628c44d1/cryptography-46.0.6-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:8927ccfbe967c7df312ade694f987e7e9e22b2425976ddbf28271d7e58845290", size = 4271265, upload-time = "2026-03-25T23:34:18.586Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/89/06/fe1fce39a37ac452e58d04b43b0855261dac320a2ebf8f5260dd55b201a9/cryptography-46.0.6-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:b12c6b1e1651e42ab5de8b1e00dc3b6354fdfd778e7fa60541ddacc27cd21410", size = 4916800, upload-time = "2026-03-25T23:34:20.561Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/ff/8a/b14f3101fe9c3592603339eb5d94046c3ce5f7fc76d6512a2d40efd9724e/cryptography-46.0.6-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:063b67749f338ca9c5a0b7fe438a52c25f9526b851e24e6c9310e7195aad3b4d", size = 4448771, upload-time = "2026-03-25T23:34:22.406Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/01/b3/0796998056a66d1973fd52ee89dc1bb3b6581960a91ad4ac705f182d398f/cryptography-46.0.6-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:02fad249cb0e090b574e30b276a3da6a149e04ee2f049725b1f69e7b8351ec70", size = 3978333, upload-time = "2026-03-25T23:34:24.281Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c5/3d/db200af5a4ffd08918cd55c08399dc6c9c50b0bc72c00a3246e099d3a849/cryptography-46.0.6-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:7e6142674f2a9291463e5e150090b95a8519b2fb6e6aaec8917dd8d094ce750d", size = 4271069, upload-time = "2026-03-25T23:34:25.895Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/d7/18/61acfd5b414309d74ee838be321c636fe71815436f53c9f0334bf19064fa/cryptography-46.0.6-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:456b3215172aeefb9284550b162801d62f5f264a081049a3e94307fe20792cfa", size = 4878358, upload-time = "2026-03-25T23:34:27.67Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/8b/65/5bf43286d566f8171917cae23ac6add941654ccf085d739195a4eacf1674/cryptography-46.0.6-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:341359d6c9e68834e204ceaf25936dffeafea3829ab80e9503860dcc4f4dac58", size = 4448061, upload-time = "2026-03-25T23:34:29.375Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/e0/25/7e49c0fa7205cf3597e525d156a6bce5b5c9de1fd7e8cb01120e459f205a/cryptography-46.0.6-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9a9c42a2723999a710445bc0d974e345c32adfd8d2fac6d8a251fa829ad31cfb", size = 4399103, upload-time = "2026-03-25T23:34:32.036Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/44/46/466269e833f1c4718d6cd496ffe20c56c9c8d013486ff66b4f69c302a68d/cryptography-46.0.6-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6617f67b1606dfd9fe4dbfa354a9508d4a6d37afe30306fe6c101b7ce3274b72", size = 4659255, upload-time = "2026-03-25T23:34:33.679Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/0a/09/ddc5f630cc32287d2c953fc5d32705e63ec73e37308e5120955316f53827/cryptography-46.0.6-cp38-abi3-win32.whl", hash = "sha256:7f6690b6c55e9c5332c0b59b9c8a3fb232ebf059094c17f9019a51e9827df91c", size = 3010660, upload-time = "2026-03-25T23:34:35.418Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1b/82/ca4893968aeb2709aacfb57a30dec6fa2ab25b10fa9f064b8882ce33f599/cryptography-46.0.6-cp38-abi3-win_amd64.whl", hash = "sha256:79e865c642cfc5c0b3eb12af83c35c5aeff4fa5c672dc28c43721c2c9fdd2f0f", size = 3471160, upload-time = "2026-03-25T23:34:37.191Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/2e/84/7ccff00ced5bac74b775ce0beb7d1be4e8637536b522b5df9b73ada42da2/cryptography-46.0.6-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:2ea0f37e9a9cf0df2952893ad145fd9627d326a59daec9b0802480fa3bcd2ead", size = 3475444, upload-time = "2026-03-25T23:34:38.944Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/bc/1f/4c926f50df7749f000f20eede0c896769509895e2648db5da0ed55db711d/cryptography-46.0.6-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:a3e84d5ec9ba01f8fd03802b2147ba77f0c8f2617b2aff254cedd551844209c8", size = 4218227, upload-time = "2026-03-25T23:34:40.871Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/c6/65/707be3ffbd5f786028665c3223e86e11c4cda86023adbc56bd72b1b6bab5/cryptography-46.0.6-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:12f0fa16cc247b13c43d56d7b35287ff1569b5b1f4c5e87e92cc4fcc00cd10c0", size = 4381399, upload-time = "2026-03-25T23:34:42.609Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/f3/6d/73557ed0ef7d73d04d9aba745d2c8e95218213687ee5e76b7d236a5030fc/cryptography-46.0.6-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:50575a76e2951fe7dbd1f56d181f8c5ceeeb075e9ff88e7ad997d2f42af06e7b", size = 4217595, upload-time = "2026-03-25T23:34:44.205Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/9e/c5/e1594c4eec66a567c3ac4400008108a415808be2ce13dcb9a9045c92f1a0/cryptography-46.0.6-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:90e5f0a7b3be5f40c3a0a0eafb32c681d8d2c181fc2a1bdabe9b3f611d9f6b1a", size = 4380912, upload-time = "2026-03-25T23:34:46.328Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/1a/89/843b53614b47f97fe1abc13f9a86efa5ec9e275292c457af1d4a60dc80e0/cryptography-46.0.6-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:6728c49e3b2c180ef26f8e9f0a883a2c585638db64cf265b49c9ba10652d430e", size = 3409955, upload-time = "2026-03-25T23:34:48.465Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3543,7 +3543,7 @@ wheels = [
|
||||
|
||||
[[package]]
|
||||
name = "requests"
|
||||
version = "2.32.4"
|
||||
version = "2.33.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "certifi" },
|
||||
@@ -3551,9 +3551,9 @@ dependencies = [
|
||||
{ name = "idna" },
|
||||
{ name = "urllib3" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e1/0a/929373653770d8a0d7ea76c37de6e41f11eb07559b103b1c02cafb3f7cf8/requests-2.32.4.tar.gz", hash = "sha256:27d0316682c8a29834d3264820024b62a36942083d52caf2f14c0591336d3422", size = 135258, upload-time = "2025-06-09T16:43:07.34Z" }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/34/64/8860370b167a9721e8956ae116825caff829224fbca0ca6e7bf8ddef8430/requests-2.33.0.tar.gz", hash = "sha256:c7ebc5e8b0f21837386ad0e1c8fe8b829fa5f544d8df3b2253bff14ef29d7652", size = 134232, upload-time = "2026-03-25T15:10:41.586Z" }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/7c/e4/56027c4a6b4ae70ca9de302488c5ca95ad4a39e190093d6c1a8ace08341b/requests-2.32.4-py3-none-any.whl", hash = "sha256:27babd3cda2a6d50b30443204ee89830707d396671944c998b5975b031ac2b2c", size = 64847, upload-time = "2025-06-09T16:43:05.728Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/56/5d/c814546c2333ceea4ba42262d8c4d55763003e767fa169adc693bd524478/requests-2.33.0-py3-none-any.whl", hash = "sha256:3324635456fa185245e24865e810cecec7b4caf933d7eb133dcde67d48cee69b", size = 65017, upload-time = "2026-03-25T15:10:40.382Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
@@ -178,14 +178,11 @@ export default function ShareAndPrivacy(props: ShareAndPrivacyProps) {
|
||||
<ShareZulip
|
||||
transcript={props.transcript}
|
||||
topics={props.topics}
|
||||
disabled={toShareMode(shareMode.value) === "private"}
|
||||
disabled={toShareMode(shareMode.value) === "public"}
|
||||
/>
|
||||
)}
|
||||
{emailEnabled && (
|
||||
<ShareEmail
|
||||
transcript={props.transcript}
|
||||
disabled={toShareMode(shareMode.value) === "private"}
|
||||
/>
|
||||
<ShareEmail transcript={props.transcript} disabled={false} />
|
||||
)}
|
||||
<ShareCopy
|
||||
finalSummaryElement={props.finalSummaryElement}
|
||||
|
||||
Reference in New Issue
Block a user