Compare commits
1 Commits
3353c6fba1
...
feat/llama
| Author | SHA1 | Date | |
|---|---|---|---|
| 79cc530cce |
478
ai/compose.yml
478
ai/compose.yml
@@ -1,90 +1,113 @@
|
|||||||
services:
|
services:
|
||||||
|
|
||||||
hermes:
|
hermes:
|
||||||
build:
|
build:
|
||||||
context: ./hermes
|
context: ./hermes
|
||||||
|
ssh:
|
||||||
|
- default
|
||||||
container_name: hermes
|
container_name: hermes
|
||||||
|
entrypoint: ["/bin/bash", "-c",
|
||||||
|
"bash /usr/local/bin/run-multi-gateways.sh && exec /usr/bin/tini -g -- /opt/hermes/docker/entrypoint.sh \"$@\"",
|
||||||
|
"hermes-entrypoint"]
|
||||||
restart: always
|
restart: always
|
||||||
|
# Gateway run enables the internal API server on port 8642
|
||||||
command: gateway run
|
command: gateway run
|
||||||
environment:
|
environment:
|
||||||
- HERMES_UID=10000
|
- HERMES_UID=10000
|
||||||
- HERMES_GID=10000
|
- HERMES_GID=10000
|
||||||
- OLLAMA_HOST=http://ollama-cpu:11434
|
- OLLAMA_HOST=http://ollama-cpu:11434
|
||||||
- HERMES_DASHBOARD=1
|
- HERMES_DASHBOARD=1
|
||||||
- API_SERVER_ENABLED=true
|
# Multi-profile: comma-separated list of profiles to run as gateways.
|
||||||
- API_SERVER_PORT=8642
|
# The entrypoint reads this and starts one gateway per profile.
|
||||||
- API_SERVER_HOST=0.0.0.0
|
# Add profiles here when they exist on disk (e.g. default,researcher,writer)
|
||||||
- API_SERVER_KEY=hermes_local_key
|
- HERMES_PROFILES=ashley,claire,finn,matt,paul
|
||||||
- GATEWAY_ALLOW_ALL_USERS=true
|
- API_SERVER_ENABLED=true
|
||||||
- OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
|
- API_SERVER_PORT=8642
|
||||||
- OPENCODE_API_KEY=${OPENCODE_API_KEY}
|
- API_SERVER_HOST=0.0.0.0
|
||||||
- HSA_OVERRIDE_GFX_VERSION=9.0.6
|
- API_SERVER_KEY=hermes_local_key
|
||||||
- HCC_AMDGPU_TARGET=gfx906
|
- GATEWAY_ALLOW_ALL_USERS=true
|
||||||
- HIP_VISIBLE_DEVICES=0,1
|
- OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
|
||||||
- ROCR_VISIBLE_DEVICES=0,1
|
- OPENCODE_API_KEY=${OPENCODE_API_KEY}
|
||||||
- HSA_ENABLE_SDMA=0
|
# ROCm for GPU-accelerated faster-whisper STT
|
||||||
- TZ=America/Montreal
|
- HSA_OVERRIDE_GFX_VERSION=9.0.6
|
||||||
|
- HCC_AMDGPU_TARGET=gfx906
|
||||||
|
- HIP_VISIBLE_DEVICES=0,1
|
||||||
|
- ROCR_VISIBLE_DEVICES=0,1
|
||||||
|
- HSA_ENABLE_SDMA=0
|
||||||
|
- TZ=America/Montreal
|
||||||
volumes:
|
volumes:
|
||||||
- /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
|
- /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
|
||||||
- /mnt/HoardingCow_docker_data/Hermes/Syncthing/ExoKortex:/opt/data/ExoKortex
|
- /mnt/HoardingCow_docker_data/Hermes/Syncthing/ExoKortex:/opt/data/ExoKortex
|
||||||
devices:
|
devices:
|
||||||
- /dev/kfd:/dev/kfd
|
- /dev/kfd:/dev/kfd
|
||||||
- /dev/dri:/dev/dri
|
- /dev/dri:/dev/dri
|
||||||
group_add:
|
group_add:
|
||||||
- '303'
|
- "303"
|
||||||
- '26'
|
- "26"
|
||||||
networks:
|
networks:
|
||||||
ai_backend: null
|
- ai_backend
|
||||||
ai_net: null
|
- ai_net
|
||||||
vpn_net:
|
|
||||||
ipv4_address: 172.24.0.5
|
|
||||||
depends_on:
|
depends_on:
|
||||||
- honcho
|
- honcho
|
||||||
labels:
|
labels:
|
||||||
- traefik.enable=true
|
- "traefik.enable=true"
|
||||||
- traefik.docker.network=ai_net
|
- "traefik.docker.network=ai_net"
|
||||||
- traefik.http.routers.hermes-web-http.rule=Host(`hermes.lazyworkhorse.net`)
|
|
||||||
- traefik.http.routers.hermes-web-http.entrypoints=web
|
# Router for HTTP + redirection to HTTPS
|
||||||
- traefik.http.routers.hermes-web-http.middlewares=redirect-to-https
|
- "traefik.http.routers.hermes-web-http.rule=Host(`hermes.lazyworkhorse.net`)"
|
||||||
- traefik.http.routers.hermes-web-https.rule=Host(`hermes.lazyworkhorse.net`)
|
- "traefik.http.routers.hermes-web-http.entrypoints=web"
|
||||||
- traefik.http.routers.hermes-web-https.entrypoints=websecure
|
- "traefik.http.routers.hermes-web-http.middlewares=redirect-to-https"
|
||||||
- traefik.http.routers.hermes-web-https.tls=true
|
|
||||||
- traefik.http.routers.hermes-web-https.tls.certresolver=njalla
|
# Router for HTTPS with TLS — protected by Authelia
|
||||||
- traefik.http.routers.hermes-web-https.middlewares=hermes-auth
|
- "traefik.http.routers.hermes-web-https.rule=Host(`hermes.lazyworkhorse.net`)"
|
||||||
- traefik.http.middlewares.hermes-auth.forwardauth.address=http://authelia:9091/api/verify?rd=https://auth.lazyworkhorse.net/
|
- "traefik.http.routers.hermes-web-https.entrypoints=websecure"
|
||||||
- traefik.http.middlewares.hermes-auth.forwardauth.trustforwardheader=true
|
- "traefik.http.routers.hermes-web-https.tls=true"
|
||||||
- traefik.http.middlewares.hermes-auth.forwardauth.authresponseheaders=X-Forwarded-User,X-Forwarded-Groups
|
- "traefik.http.routers.hermes-web-https.tls.certresolver=njalla"
|
||||||
- traefik.http.services.hermes-web.loadbalancer.server.port=9119
|
- "traefik.http.routers.hermes-web-https.middlewares=hermes-auth"
|
||||||
|
|
||||||
|
# Authelia forwardAuth
|
||||||
|
- "traefik.http.middlewares.hermes-auth.forwardauth.address=http://authelia:9091/api/verify?rd=https://auth.lazyworkhorse.net/"
|
||||||
|
- "traefik.http.middlewares.hermes-auth.forwardauth.trustforwardheader=true"
|
||||||
|
- "traefik.http.middlewares.hermes-auth.forwardauth.authresponseheaders=X-Forwarded-User,X-Forwarded-Groups"
|
||||||
|
|
||||||
|
# Service Loadbalancer (dashboard port 9119)
|
||||||
|
- "traefik.http.services.hermes-web.loadbalancer.server.port=9119"
|
||||||
|
|
||||||
syncthing:
|
syncthing:
|
||||||
image: syncthing/syncthing:latest
|
image: syncthing/syncthing:latest
|
||||||
container_name: syncthing
|
container_name: syncthing
|
||||||
hostname: syncthing
|
hostname: syncthing
|
||||||
restart: always
|
restart: always
|
||||||
ports:
|
ports:
|
||||||
- 8384:8384
|
- "8384:8384"
|
||||||
- 22000:22000
|
- "22000:22000"
|
||||||
- 21027:21027/udp
|
- "21027:21027/udp"
|
||||||
environment:
|
environment:
|
||||||
- TZ=America/Montreal
|
- TZ=America/Montreal
|
||||||
- PUID=10000
|
- PUID=10000
|
||||||
- PGID=10000
|
- PGID=10000
|
||||||
volumes:
|
volumes:
|
||||||
- /mnt/HoardingCow_docker_data/Hermes/Syncthing/config:/var/syncthing/config
|
- /mnt/HoardingCow_docker_data/Hermes/Syncthing/config:/var/syncthing/config
|
||||||
- /mnt/HoardingCow_docker_data/Hermes/Syncthing/ExoKortex:/ExoKortex
|
- /mnt/HoardingCow_docker_data/Hermes/Syncthing/ExoKortex:/ExoKortex
|
||||||
networks:
|
networks:
|
||||||
- ai_backend
|
- ai_backend
|
||||||
- ai_net
|
- ai_net
|
||||||
labels:
|
labels:
|
||||||
- traefik.enable=true
|
- "traefik.enable=true"
|
||||||
- traefik.docker.network=ai_net
|
- "traefik.docker.network=ai_net"
|
||||||
- traefik.http.routers.syncthing-http.rule=Host(`syncthing.lazyworkhorse.net`)
|
|
||||||
- traefik.http.routers.syncthing-http.entrypoints=web
|
- "traefik.http.routers.syncthing-http.rule=Host(`syncthing.lazyworkhorse.net`)"
|
||||||
- traefik.http.routers.syncthing-http.middlewares=redirect-to-https
|
- "traefik.http.routers.syncthing-http.entrypoints=web"
|
||||||
- traefik.http.routers.syncthing-https.rule=Host(`syncthing.lazyworkhorse.net`)
|
- "traefik.http.routers.syncthing-http.middlewares=redirect-to-https"
|
||||||
- traefik.http.routers.syncthing-https.entrypoints=websecure
|
|
||||||
- traefik.http.routers.syncthing-https.tls=true
|
- "traefik.http.routers.syncthing-https.rule=Host(`syncthing.lazyworkhorse.net`)"
|
||||||
- traefik.http.routers.syncthing-https.tls.certresolver=njalla
|
- "traefik.http.routers.syncthing-https.entrypoints=websecure"
|
||||||
- traefik.http.routers.syncthing-https.middlewares=hermes-auth
|
- "traefik.http.routers.syncthing-https.tls=true"
|
||||||
- traefik.http.services.syncthing.loadbalancer.server.port=8384
|
- "traefik.http.routers.syncthing-https.tls.certresolver=njalla"
|
||||||
|
- "traefik.http.routers.syncthing-https.middlewares=hermes-auth"
|
||||||
|
|
||||||
|
- "traefik.http.services.syncthing.loadbalancer.server.port=8384"
|
||||||
|
|
||||||
ollama-cpu:
|
ollama-cpu:
|
||||||
build:
|
build:
|
||||||
context: ./ollama
|
context: ./ollama
|
||||||
@@ -92,110 +115,126 @@ services:
|
|||||||
image: ollama/ollama:rocm-gfx906
|
image: ollama/ollama:rocm-gfx906
|
||||||
container_name: ollama-cpu
|
container_name: ollama-cpu
|
||||||
tty: true
|
tty: true
|
||||||
restart: always
|
restart: always
|
||||||
ports:
|
ports:
|
||||||
- 127.0.0.1:11434:11434
|
- "127.0.0.1:11434:11434"
|
||||||
networks:
|
networks:
|
||||||
- ai_backend
|
- ai_backend
|
||||||
volumes:
|
volumes:
|
||||||
- /mnt/HoardingCow_docker_data/Ollama/ollama:/root/.ollama
|
- /mnt/HoardingCow_docker_data/Ollama/ollama:/root/.ollama
|
||||||
environment:
|
environment:
|
||||||
- OLLAMA_VULKAN=0
|
- OLLAMA_VULKAN=0
|
||||||
- OLLAMA_HOST=0.0.0.0
|
- OLLAMA_HOST=0.0.0.0
|
||||||
|
|
||||||
llama-cpp-hermes:
|
llama-cpp-hermes:
|
||||||
image: llama-cpp:rocm-gfx906
|
image: llama-cpp:rocm-gfx906
|
||||||
container_name: llama-cpp-hermes
|
container_name: llama-cpp-hermes
|
||||||
restart: unless-stopped
|
restart: unless-stopped
|
||||||
networks:
|
networks:
|
||||||
- ai_backend
|
- ai_backend
|
||||||
ports:
|
ports:
|
||||||
- 127.0.0.1:8300:8080
|
- "127.0.0.1:8300:8080"
|
||||||
ipc: host
|
ipc: host
|
||||||
devices:
|
devices:
|
||||||
- /dev/kfd:/dev/kfd
|
- /dev/kfd:/dev/kfd
|
||||||
- /dev/dri:/dev/dri
|
- /dev/dri:/dev/dri
|
||||||
group_add:
|
group_add:
|
||||||
- '303'
|
- "303"
|
||||||
- '26'
|
- "26"
|
||||||
environment:
|
environment:
|
||||||
- HSA_OVERRIDE_GFX_VERSION=9.0.6
|
- HSA_OVERRIDE_GFX_VERSION=9.0.6
|
||||||
- HSA_ENABLE_SDMA=0
|
- HSA_ENABLE_SDMA=0
|
||||||
- HIP_VISIBLE_DEVICES=0,1
|
- HIP_VISIBLE_DEVICES=0,1
|
||||||
- LLAMA_CACHE=/models
|
- LLAMA_CACHE=/models
|
||||||
volumes:
|
volumes:
|
||||||
- /mnt/HoardingCow_docker_data/Llama_cpp/models:/models
|
- /mnt/HoardingCow_docker_data/Llama_cpp/models:/models
|
||||||
- /mnt/HoardingCow_docker_data/Ollama/ollama/models/blobs/sha256-17823599694fa3503ef54bf748d5078c6ce881f4d01616cafa255dc05d215a08:/model.gguf:ro
|
- /mnt/HoardingCow_docker_data/Ollama/ollama/models/blobs/sha256-17823599694fa3503ef54bf748d5078c6ce881f4d01616cafa255dc05d215a08:/model.gguf:ro
|
||||||
command: '-m /model.gguf --host 0.0.0.0 --port 8080 --gpu-layers 99 --ctx-size
|
command: >
|
||||||
163840 -ctk f16 -ctv f16 --flash-attn on --split-mode layer --no-mmap --n-predict
|
-m /model.gguf
|
||||||
-1
|
--host 0.0.0.0
|
||||||
|
--port 8080
|
||||||
|
--gpu-layers 99
|
||||||
|
--ctx-size 163840
|
||||||
|
-ctk f16 -ctv f16
|
||||||
|
--flash-attn on
|
||||||
|
--split-mode layer
|
||||||
|
--no-mmap
|
||||||
|
--n-predict -1
|
||||||
|
|
||||||
'
|
# --- Honcho + OpenConcho combiné: API + Web UI nginx/FastAPI ---
|
||||||
honcho:
|
honcho:
|
||||||
build:
|
build:
|
||||||
context: ./honcho
|
context: ./honcho
|
||||||
ssh:
|
ssh:
|
||||||
- default
|
- default
|
||||||
container_name: honcho
|
container_name: honcho
|
||||||
restart: unless-stopped
|
restart: unless-stopped
|
||||||
environment:
|
environment:
|
||||||
- DB_CONNECTION_URI=postgresql+psycopg://honcho:honcho_pass@honcho-db:5432/honcho
|
- DB_CONNECTION_URI=postgresql+psycopg://honcho:honcho_pass@honcho-db:5432/honcho
|
||||||
- CACHE_URL=redis://honcho-redis:6379/0
|
- CACHE_URL=redis://honcho-redis:6379/0
|
||||||
- CACHE_ENABLED=true
|
- CACHE_ENABLED=true
|
||||||
- EMBEDDING_VECTOR_DIMENSIONS=1024
|
- EMBEDDING_VECTOR_DIMENSIONS=1024
|
||||||
- AUTH_USE_AUTH=true
|
- AUTH_USE_AUTH=true
|
||||||
- AUTH_JWT_SECRET=${HONCHO_AUTH_JWT_SECRET}
|
- AUTH_JWT_SECRET=${HONCHO_AUTH_JWT_SECRET}
|
||||||
- HONCHO_OPENAI_API_KEY=${HONCHO_OPENAI_API_KEY}
|
# Needed by deriver/dream to make LLM calls (api_key_env = "HONCHO_OPENAI_API_KEY" in config.toml)
|
||||||
|
- HONCHO_OPENAI_API_KEY=${HONCHO_OPENAI_API_KEY}
|
||||||
volumes:
|
volumes:
|
||||||
- /mnt/HoardingCow_docker_data/Honcho/data:/app/data
|
- /mnt/HoardingCow_docker_data/Honcho/data:/app/data
|
||||||
- /mnt/HoardingCow_docker_data/Honcho/config.toml:/app/config.toml:ro
|
- /mnt/HoardingCow_docker_data/Honcho/config.toml:/app/config.toml:ro
|
||||||
networks:
|
networks:
|
||||||
- ai_backend
|
- ai_backend
|
||||||
- ai_net
|
- ai_net
|
||||||
labels:
|
labels:
|
||||||
- traefik.enable=true
|
- "traefik.enable=true"
|
||||||
- traefik.docker.network=ai_net
|
- "traefik.docker.network=ai_net"
|
||||||
- traefik.http.routers.honcho-http.rule=Host(`honcho.lazyworkhorse.net`)
|
|
||||||
- traefik.http.routers.honcho-http.entrypoints=web
|
# Router for HTTP + redirect to HTTPS
|
||||||
- traefik.http.routers.honcho-http.middlewares=redirect-to-https
|
- "traefik.http.routers.honcho-http.rule=Host(`honcho.lazyworkhorse.net`)"
|
||||||
- traefik.http.routers.honcho-https.rule=Host(`honcho.lazyworkhorse.net`)
|
- "traefik.http.routers.honcho-http.entrypoints=web"
|
||||||
- traefik.http.routers.honcho-https.entrypoints=websecure
|
- "traefik.http.routers.honcho-http.middlewares=redirect-to-https"
|
||||||
- traefik.http.routers.honcho-https.tls=true
|
|
||||||
- traefik.http.routers.honcho-https.tls.certresolver=njalla
|
# Router for HTTPS with TLS — protected by Authelia
|
||||||
- traefik.http.routers.honcho-https.middlewares=hermes-auth
|
- "traefik.http.routers.honcho-https.rule=Host(`honcho.lazyworkhorse.net`)"
|
||||||
- traefik.http.services.honcho.loadbalancer.server.port=80
|
- "traefik.http.routers.honcho-https.entrypoints=websecure"
|
||||||
|
- "traefik.http.routers.honcho-https.tls=true"
|
||||||
|
- "traefik.http.routers.honcho-https.tls.certresolver=njalla"
|
||||||
|
- "traefik.http.routers.honcho-https.middlewares=hermes-auth"
|
||||||
|
|
||||||
|
# Service Loadbalancer (nginx port)
|
||||||
|
- "traefik.http.services.honcho.loadbalancer.server.port=80"
|
||||||
depends_on:
|
depends_on:
|
||||||
- honcho-db
|
- honcho-db
|
||||||
- honcho-redis
|
- honcho-redis
|
||||||
|
|
||||||
honcho-db:
|
honcho-db:
|
||||||
image: pgvector/pgvector:pg15
|
image: pgvector/pgvector:pg15
|
||||||
container_name: honcho-db
|
container_name: honcho-db
|
||||||
restart: unless-stopped
|
restart: unless-stopped
|
||||||
ports:
|
ports:
|
||||||
- 127.0.0.1:5432:5432
|
- "127.0.0.1:5432:5432"
|
||||||
command:
|
command: ["postgres", "-c", "max_connections=200"]
|
||||||
- postgres
|
|
||||||
- -c
|
|
||||||
- max_connections=200
|
|
||||||
environment:
|
environment:
|
||||||
- POSTGRES_DB=honcho
|
- POSTGRES_DB=honcho
|
||||||
- POSTGRES_USER=honcho
|
- POSTGRES_USER=honcho
|
||||||
- POSTGRES_PASSWORD=honcho_pass
|
- POSTGRES_PASSWORD=honcho_pass
|
||||||
- PGDATA=/var/lib/postgresql/data/pgdata
|
- PGDATA=/var/lib/postgresql/data/pgdata
|
||||||
volumes:
|
volumes:
|
||||||
- /mnt/HoardingCow_docker_data/Honcho/postgres:/var/lib/postgresql/data
|
- /mnt/HoardingCow_docker_data/Honcho/postgres:/var/lib/postgresql/data
|
||||||
- ./honcho/init-db.sql:/docker-entrypoint-initdb.d/init.sql:ro
|
- ./honcho/init-db.sql:/docker-entrypoint-initdb.d/init.sql:ro
|
||||||
networks:
|
networks:
|
||||||
- ai_backend
|
- ai_backend
|
||||||
|
|
||||||
honcho-redis:
|
honcho-redis:
|
||||||
image: redis:8
|
image: redis:8
|
||||||
container_name: honcho-redis
|
container_name: honcho-redis
|
||||||
restart: unless-stopped
|
restart: unless-stopped
|
||||||
ports:
|
ports:
|
||||||
- 127.0.0.1:6379:6379
|
- "127.0.0.1:6379:6379"
|
||||||
volumes:
|
volumes:
|
||||||
- /mnt/HoardingCow_docker_data/Honcho/redis:/data
|
- /mnt/HoardingCow_docker_data/Honcho/redis:/data
|
||||||
networks:
|
networks:
|
||||||
- ai_backend
|
- ai_backend
|
||||||
|
|
||||||
networks:
|
networks:
|
||||||
ai_net:
|
ai_net:
|
||||||
driver: bridge
|
driver: bridge
|
||||||
@@ -203,10 +242,193 @@ networks:
|
|||||||
ai_backend:
|
ai_backend:
|
||||||
driver: bridge
|
driver: bridge
|
||||||
name: ai_backend
|
name: ai_backend
|
||||||
vpn_net:
|
|
||||||
external: true
|
|
||||||
name: vpn_net
|
|
||||||
volumes:
|
volumes:
|
||||||
honcho_data:
|
honcho_data:
|
||||||
driver: bridge
|
driver: bridge
|
||||||
name: honcho_data
|
name: honcho_data
|
||||||
|
|
||||||
|
# vllm:
|
||||||
|
# image: nalanzeyu/vllm-gfx906:v0.9.0-rocm6.3
|
||||||
|
# container_name: vllm
|
||||||
|
# # Required for multi-GPU communication (NCCL)
|
||||||
|
# ipc: host
|
||||||
|
# init: true
|
||||||
|
# shm_size: '2g'
|
||||||
|
# networks:
|
||||||
|
# - ai_backend
|
||||||
|
# ports:
|
||||||
|
# - "8300:8000"
|
||||||
|
# devices:
|
||||||
|
# - "/dev/kfd:/dev/kfd"
|
||||||
|
# - "/dev/dri:/dev/dri"
|
||||||
|
# group_add:
|
||||||
|
# - "303"
|
||||||
|
# - "26"
|
||||||
|
# environment:
|
||||||
|
# HSA_OVERRIDE_GFX_VERSION: 9.0.6
|
||||||
|
# HSA_ENABLE_SDMA: 0
|
||||||
|
# HIP_VISIBLE_DEVICES: 0,1
|
||||||
|
# NCCL_P2P_DISABLE: 1
|
||||||
|
# VLLM_WORKER_MULTIPROC_METHOD: spawn
|
||||||
|
# VLLM_USE_TRITON_FLASH_ATTN: 0
|
||||||
|
# VLLM_USE_ROCM_CUSTOM_PAGED_ATTN: 0
|
||||||
|
# VLLM_ATTENTION_BACKEND: ROPE_NAIVE
|
||||||
|
# VLLM_SKIP_WARMUP: 1
|
||||||
|
# VLLM_USE_V1: 0
|
||||||
|
# HF_TOKEN: ${HF_TOKEN}
|
||||||
|
# command: >
|
||||||
|
# vllm serve "mistralai/Devstral-Small-2-24B-Instruct-2512"
|
||||||
|
# --tensor-parallel-size 2
|
||||||
|
# --max-model-len 8192
|
||||||
|
# --gpu-memory-utilization 0.90
|
||||||
|
# --tokenizer_mode mistral
|
||||||
|
# --config_format auto
|
||||||
|
# --load-format auto
|
||||||
|
# --enforce-eager
|
||||||
|
# --disable-custom-all-reduce
|
||||||
|
# --trust-remote-code
|
||||||
|
# --task generate
|
||||||
|
# --block-size 16
|
||||||
|
# volumes:
|
||||||
|
# - /mnt/HoardingCow_docker_data/vllm/models:/root/.cache/huggingface
|
||||||
|
# restart: unless-stopped
|
||||||
|
|
||||||
|
# webui:
|
||||||
|
# image: ghcr.io/open-webui/open-webui:main
|
||||||
|
# volumes:
|
||||||
|
# - /mnt/HoardingCow_docker_data/Ollama/open-webui:/app/backend/data
|
||||||
|
# restart: always
|
||||||
|
# environment:
|
||||||
|
# - OLLAMA_API_BASE_URL=http://ollama:11434/api
|
||||||
|
# networks:
|
||||||
|
# - ai_net
|
||||||
|
# - ai_backend
|
||||||
|
# labels:
|
||||||
|
# - "traefik.enable=true"
|
||||||
|
|
||||||
|
# # Router for HTTP + redirection to HTTPS
|
||||||
|
# - "traefik.http.routers.webui-http.rule=Host(`ai.lazyworkhorse.net`)"
|
||||||
|
# - "traefik.http.routers.webui-http.entrypoints=web"
|
||||||
|
# - "traefik.http.routers.webui-http.middlewares=redirect-to-https"
|
||||||
|
|
||||||
|
# # Router for HTTPS with TLS
|
||||||
|
# - "traefik.http.routers.webui-https.rule=Host(`ai.lazyworkhorse.net`)"
|
||||||
|
# - "traefik.http.routers.webui-https.entrypoints=websecure"
|
||||||
|
# - "traefik.http.routers.webui-https.tls=true"
|
||||||
|
# - "traefik.http.routers.webui-https.tls.certresolver=njalla"
|
||||||
|
|
||||||
|
# n8n:
|
||||||
|
# image: n8nio/n8n:latest
|
||||||
|
# container_name: n8n
|
||||||
|
# restart: unless-stopped
|
||||||
|
# networks:
|
||||||
|
# - ai_net
|
||||||
|
# environment:
|
||||||
|
# - N8N_HOST=n8n.lazyworkhorse.net
|
||||||
|
# - N8N_PORT=5678
|
||||||
|
# - N8N_PROTOCOL=https
|
||||||
|
# - NODE_ENV=production
|
||||||
|
# - N8N_ENCRYPTION_KEY=${N8N_ENCRYPTION_KEY}
|
||||||
|
# - WEBHOOK_URL=https://n8n.lazyworkhorse.net/
|
||||||
|
# - GENERIC_TIMEZONE=America/New_York # Adjust to your timezone
|
||||||
|
# - N8N_BLOCK_EXTERNAL_STORAGE_ACCESS=false
|
||||||
|
# - N8N_NODES_PYTHON_CAN_IMPORT_MODULES=true
|
||||||
|
# - N8N_NATIVE_PYTHON_RUNNER=true
|
||||||
|
# - N8N_PYTHON_ALLOW_STDLIB=uuid,re,os,json
|
||||||
|
# - N8N_PYTHON_ALLOW_EXTERNAL=requests,pandas
|
||||||
|
# - NODE_FUNCTION_ALLOW_EXTERNAL=uuid,requests
|
||||||
|
# volumes:
|
||||||
|
# - /mnt/HoardingCow_docker_data/n8n:/home/node/.n8n
|
||||||
|
# labels:
|
||||||
|
# - "traefik.enable=true"
|
||||||
|
|
||||||
|
# # Router for HTTP + redirection to HTTPS
|
||||||
|
# - "traefik.http.routers.n8n-http.rule=Host(`n8n.lazyworkhorse.net`)"
|
||||||
|
# - "traefik.http.routers.n8n-http.entrypoints=web"
|
||||||
|
# - "traefik.http.routers.n8n-http.middlewares=redirect-to-https"
|
||||||
|
|
||||||
|
# # Router for HTTPS with TLS
|
||||||
|
# - "traefik.http.routers.n8n-https.rule=Host(`n8n.lazyworkhorse.net`)"
|
||||||
|
# - "traefik.http.routers.n8n-https.entrypoints=websecure"
|
||||||
|
# - "traefik.http.routers.n8n-https.tls=true"
|
||||||
|
# - "traefik.http.routers.n8n-https.tls.certresolver=njalla"
|
||||||
|
|
||||||
|
# # Service Loadbalancer (n8n default port)
|
||||||
|
# - "traefik.http.services.n8n.loadbalancer.server.port=5678"
|
||||||
|
|
||||||
|
# openclaw:
|
||||||
|
# image: coollabsio/openclaw:latest
|
||||||
|
# container_name: openclaw
|
||||||
|
# restart: unless-stopped
|
||||||
|
# expose:
|
||||||
|
# - "8080" # WebUI
|
||||||
|
# - "18789" # Gateway/WebSocket
|
||||||
|
# - "8788" # Nextcloud Webhook
|
||||||
|
# networks:
|
||||||
|
# - ai_net
|
||||||
|
# - ai_backend
|
||||||
|
# volumes:
|
||||||
|
# - /mnt/HoardingCow_docker_data/openclaw/data:/data
|
||||||
|
# - /home/gortium/infra:/data/workspace/infra
|
||||||
|
# environment:
|
||||||
|
# - TZ=America/Toronto
|
||||||
|
# - OPENCLAW_GATEWAY_TOKEN=${OPENCLAW_GATEWAY_TOKEN}
|
||||||
|
# - OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
|
||||||
|
# # Point to the sidecar browser
|
||||||
|
# - BROWSER_CDP_URL=http://openclaw-browser:9222
|
||||||
|
# - BROWSER_EVALUATE_ENABLED=true
|
||||||
|
# - OPENCLAW_GATEWAY_HOST=0.0.0.0
|
||||||
|
# - OPENCLAW_ALLOWED_ORIGINS=https://claw.lazyworkhorse.net
|
||||||
|
# labels:
|
||||||
|
# - "traefik.enable=true"
|
||||||
|
|
||||||
|
# - "traefik.http.routers.openclaw-http.rule=Host(`claw.lazyworkhorse.net`)"
|
||||||
|
# - "traefik.http.routers.openclaw-http.entrypoints=web"
|
||||||
|
# - "traefik.http.routers.openclaw-http.middlewares=redirect-to-https"
|
||||||
|
|
||||||
|
# - "traefik.http.routers.openclaw-https.rule=Host(`claw.lazyworkhorse.net`)"
|
||||||
|
# - "traefik.http.routers.openclaw-https.priority=50"
|
||||||
|
# - "traefik.http.routers.openclaw-https.entrypoints=websecure"
|
||||||
|
# - "traefik.http.routers.openclaw-https.tls=true"
|
||||||
|
# - "traefik.http.routers.openclaw-https.tls.certresolver=njalla"
|
||||||
|
# - "traefik.http.services.openclaw.loadbalancer.server.port=8080"
|
||||||
|
# depends_on:
|
||||||
|
# - openclaw-browser
|
||||||
|
|
||||||
|
# openclaw-browser:
|
||||||
|
# image: ghcr.io/browserless/chromium:latest
|
||||||
|
# restart: always
|
||||||
|
# expose:
|
||||||
|
# - "3000"
|
||||||
|
# environment:
|
||||||
|
# - MAX_CONCURRENT_SESSIONS=10
|
||||||
|
# - CONNECTION_TIMEOUT=300000
|
||||||
|
# - PREBOOT_CHROME=true
|
||||||
|
# - DEMO_MODE=false
|
||||||
|
# networks:
|
||||||
|
# ai_backend:
|
||||||
|
# aliases:
|
||||||
|
# - browser
|
||||||
|
|
||||||
|
# openclaw-ssh:
|
||||||
|
# image: linuxserver/openssh-server:latest
|
||||||
|
# container_name: openclaw-ssh
|
||||||
|
# environment:
|
||||||
|
# - PUID=1000
|
||||||
|
# - PGID=1000
|
||||||
|
# - PUBLIC_KEY_FILE=/config/ssh/authorized_keys
|
||||||
|
# - SUDO_ACCESS=false
|
||||||
|
# - PASSWORD_ACCESS=false
|
||||||
|
# volumes:
|
||||||
|
# - /mnt/HoardingCow_docker_data/openclaw/ssh-config:/config
|
||||||
|
# - /home/gortium/infra:/data/workspace/infra:ro
|
||||||
|
# restart: unless-stopped
|
||||||
|
# networks:
|
||||||
|
# - ai_backend
|
||||||
|
# labels:
|
||||||
|
# - "traefik.enable=true"
|
||||||
|
# - "traefik.tcp.routers.openclaw-ssh.rule=HostSNI(*)"
|
||||||
|
# - "traefik.tcp.routers.openclaw-ssh.entrypoints=sshnode"
|
||||||
|
# - "traefik.tcp.routers.openclaw-ssh.tls.passthrough=false"
|
||||||
|
# - "traefik.tcp.services.openclaw-ssh.loadbalancer.server.port=2222"
|
||||||
|
|||||||
@@ -59,6 +59,10 @@ os.remove(tgz)
|
|||||||
print('himalaya v1.2.0 installed')
|
print('himalaya v1.2.0 installed')
|
||||||
PYEOF
|
PYEOF
|
||||||
|
|
||||||
|
# ---------- Install multi-gateway launcher ----------
|
||||||
|
# Launches one gateway process per profile (HERMES_PROFILES env var)
|
||||||
|
COPY --chmod=0755 run-multi-gateways.sh /usr/local/bin/run-multi-gateways.sh
|
||||||
|
|
||||||
# ---------- Runtime ----------
|
# ---------- Runtime ----------
|
||||||
USER hermes
|
USER hermes
|
||||||
ENV HERMES_HOME=/opt/data
|
ENV HERMES_HOME=/opt/data
|
||||||
|
|||||||
181
ai/hermes/patch_tts_tool.py
Normal file
181
ai/hermes/patch_tts_tool.py
Normal file
@@ -0,0 +1,181 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Patch Hermes TTS tool: add Piper TTS provider, remove Edge TTS as default.
|
||||||
|
|
||||||
|
Patches ALL copies of tts_tool.py found (venv site-packages + /opt/hermes/tools/).
|
||||||
|
|
||||||
|
Searches multiple paths for tts_tool.py so it works both at build time
|
||||||
|
(in the image venv) and at runtime (on the mounted data volume).
|
||||||
|
|
||||||
|
Idempotent: if already patched, does nothing.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import sys
|
||||||
|
import os
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Search for all copies of tts_tool.py
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
CANDIDATE_PATHS = [
|
||||||
|
"/opt/hermes/.venv/lib/python3.13/site-packages/tools/tts_tool.py",
|
||||||
|
"/opt/hermes/tools/tts_tool.py",
|
||||||
|
]
|
||||||
|
|
||||||
|
found_paths = []
|
||||||
|
|
||||||
|
for p in CANDIDATE_PATHS:
|
||||||
|
if os.path.exists(p):
|
||||||
|
found_paths.append(p)
|
||||||
|
print(f"Found tts_tool.py at: {p}")
|
||||||
|
|
||||||
|
# Also try to find via Python import
|
||||||
|
import subprocess
|
||||||
|
try:
|
||||||
|
result = subprocess.run(
|
||||||
|
[sys.executable, "-c", "import tools.tts_tool; print(tools.tts_tool.__file__)"],
|
||||||
|
capture_output=True, text=True, timeout=5
|
||||||
|
)
|
||||||
|
if result.returncode == 0:
|
||||||
|
p = result.stdout.strip()
|
||||||
|
if os.path.exists(p) and p not in found_paths:
|
||||||
|
found_paths.append(p)
|
||||||
|
print(f"Found tts_tool.py via import at: {p}")
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
|
||||||
|
if not found_paths:
|
||||||
|
print("WARNING: tts_tool.py not found anywhere. Patching deferred to runtime.")
|
||||||
|
print(f"Searched: {CANDIDATE_PATHS}")
|
||||||
|
sys.exit(0)
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Old else block: the Edge TTS default fallback to replace
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
old_else = ''' else:
|
||||||
|
# Default: Edge TTS (free), with NeuTTS as local fallback
|
||||||
|
edge_available = True
|
||||||
|
try:
|
||||||
|
_import_edge_tts()
|
||||||
|
except ImportError:
|
||||||
|
edge_available = False
|
||||||
|
|
||||||
|
if edge_available:
|
||||||
|
logger.info("Generating speech with Edge TTS...")
|
||||||
|
try:
|
||||||
|
import concurrent.futures
|
||||||
|
with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
|
||||||
|
pool.submit(
|
||||||
|
lambda: asyncio.run(_generate_edge_tts(text, file_str, tts_config))
|
||||||
|
).result(timeout=60)
|
||||||
|
except RuntimeError:
|
||||||
|
asyncio.run(_generate_edge_tts(text, file_str, tts_config))
|
||||||
|
elif _check_neutts_available():
|
||||||
|
logger.info("Edge TTS not available, falling back to NeuTTS (local)...")
|
||||||
|
provider = "neutts"
|
||||||
|
_generate_neutts(text, file_str, tts_config)
|
||||||
|
else:
|
||||||
|
return json.dumps({
|
||||||
|
"success": False,
|
||||||
|
"error": "No TTS provider available. Install edge-tts (pip install edge-tts) "
|
||||||
|
"or set up NeuTTS for local synthesis."
|
||||||
|
}, ensure_ascii=False)'''
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# New block: elif provider == "piper" + else: fallback with Piper only
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
new_block = ''' elif provider == "piper":
|
||||||
|
# Piper TTS (local, CPU, no cloud, no Microsoft)
|
||||||
|
piper_binary = "/opt/hermes/.venv/bin/piper"
|
||||||
|
piper_config = tts_config.get("piper", {})
|
||||||
|
voice = piper_config.get("voice", "en_US-lessac-medium")
|
||||||
|
model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
|
||||||
|
model_path = os.path.join(model_dir, f"{voice}.onnx")
|
||||||
|
if not os.path.exists(model_path):
|
||||||
|
return json.dumps({
|
||||||
|
"success": False,
|
||||||
|
"error": "Piper TTS voice model not found. "
|
||||||
|
"Install Piper TTS and download a voice model."
|
||||||
|
}, ensure_ascii=False)
|
||||||
|
logger.info("Generating speech with Piper TTS (local, CPU)...")
|
||||||
|
import subprocess as _sp
|
||||||
|
cmd = [piper_binary, "--model", model_path, "--output-raw"]
|
||||||
|
try:
|
||||||
|
proc = _sp.Popen(cmd, stdin=_sp.PIPE, stdout=_sp.PIPE, stderr=_sp.PIPE)
|
||||||
|
raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
|
||||||
|
if proc.returncode != 0:
|
||||||
|
raise RuntimeError(f"Piper TTS failed: {stderr.decode()[:200]}")
|
||||||
|
ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
|
||||||
|
_sp.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
|
||||||
|
except Exception as e:
|
||||||
|
return json.dumps({
|
||||||
|
"success": False,
|
||||||
|
"error": f"Piper TTS failed: {e}"
|
||||||
|
}, ensure_ascii=False)
|
||||||
|
|
||||||
|
else:
|
||||||
|
# Default: Piper TTS (local, CPU, no cloud, no Microsoft)
|
||||||
|
piper_binary = "/opt/hermes/.venv/bin/piper"
|
||||||
|
piper_config = tts_config.get("piper", {})
|
||||||
|
voice = piper_config.get("voice", "en_US-lessac-medium")
|
||||||
|
model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
|
||||||
|
model_path = os.path.join(model_dir, f"{voice}.onnx")
|
||||||
|
if os.path.exists(model_path) and os.path.exists(piper_binary):
|
||||||
|
logger.info("Generating speech with Piper TTS (local, CPU)...")
|
||||||
|
import subprocess as _sp
|
||||||
|
cmd = [piper_binary, "--model", model_path, "--output-raw"]
|
||||||
|
try:
|
||||||
|
proc = _sp.Popen(cmd, stdin=_sp.PIPE, stdout=_sp.PIPE, stderr=_sp.PIPE)
|
||||||
|
raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
|
||||||
|
if proc.returncode != 0:
|
||||||
|
raise RuntimeError(stderr.decode()[:200])
|
||||||
|
ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
|
||||||
|
_sp.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
else:
|
||||||
|
return json.dumps({
|
||||||
|
"success": False,
|
||||||
|
"error": "Piper TTS not available. Install piper-tts and download a voice model."
|
||||||
|
}, ensure_ascii=False)'''
|
||||||
|
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
# Apply the patch to all copies found
|
||||||
|
# ---------------------------------------------------------------------------
|
||||||
|
patched_any = False
|
||||||
|
|
||||||
|
for tts_path in found_paths:
|
||||||
|
with open(tts_path) as f:
|
||||||
|
code = f.read()
|
||||||
|
|
||||||
|
if 'provider == "piper"' in code:
|
||||||
|
print(f"ALREADY PATCHED: {tts_path}")
|
||||||
|
continue
|
||||||
|
|
||||||
|
if old_else in code:
|
||||||
|
code = code.replace(old_else, new_block, 1)
|
||||||
|
with open(tts_path, 'w') as f:
|
||||||
|
f.write(code)
|
||||||
|
print(f"PATCHED: {tts_path}")
|
||||||
|
patched_any = True
|
||||||
|
else:
|
||||||
|
print(f"SKIP {tts_path}: Edge fallback pattern not found")
|
||||||
|
import re
|
||||||
|
for m in re.finditer(r' else:\n # Default:', code):
|
||||||
|
start = max(0, m.start() - 100)
|
||||||
|
end = min(len(code), m.end() + 300)
|
||||||
|
print(f" Found 'else:/# Default:' at position {m.start()}:")
|
||||||
|
print(f" {code[start:end]}")
|
||||||
|
print(" ---")
|
||||||
|
# Don't exit with error — if one copy isn't patchable, try the others
|
||||||
|
|
||||||
|
if not patched_any:
|
||||||
|
all_patched = all(
|
||||||
|
'provider == "piper"' in open(p).read()
|
||||||
|
for p in found_paths
|
||||||
|
)
|
||||||
|
if all_patched:
|
||||||
|
print("All copies already patched.")
|
||||||
|
sys.exit(0)
|
||||||
|
print("WARNING: Could not patch any copy of tts_tool.py")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
print("tts_tool.py patched successfully across all copies.")
|
||||||
32
ai/hermes/run-multi-gateways.sh
Executable file
32
ai/hermes/run-multi-gateways.sh
Executable file
@@ -0,0 +1,32 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
# Multi-gateway launcher for HERMES_PROFILES env var.
|
||||||
|
# Reads comma-separated profile names, spawns one gateway per profile.
|
||||||
|
# Designed to run before the main entrypoint — gateways run in background.
|
||||||
|
set -e
|
||||||
|
|
||||||
|
if [ -z "${HERMES_PROFILES}" ]; then
|
||||||
|
echo "HERMES_PROFILES not set — skipping multi-gateway launch"
|
||||||
|
exit 0
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Source venv to make 'hermes' available (entrypoint.sh sources it later,
|
||||||
|
# but we need it NOW for the background gateways)
|
||||||
|
HERMES_BIN="/opt/hermes/.venv/bin/hermes"
|
||||||
|
if [ ! -x "$HERMES_BIN" ]; then
|
||||||
|
echo "ERROR: hermes binary not found at $HERMES_BIN"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
mkdir -p /opt/data/logs
|
||||||
|
|
||||||
|
IFS=',' read -ra PROFILES <<< "${HERMES_PROFILES}"
|
||||||
|
for profile in "${PROFILES[@]}"; do
|
||||||
|
profile="$(echo "${profile}" | xargs)" # trim whitespace
|
||||||
|
[ -z "${profile}" ] && continue
|
||||||
|
|
||||||
|
echo "Starting gateway for profile: ${profile}"
|
||||||
|
nohup env API_SERVER_ENABLED=false API_SERVER_KEY= gosu hermes "$HERMES_BIN" --profile "${profile}" gateway run \
|
||||||
|
>> "/opt/data/logs/gateway-${profile}.log" 2>&1 &
|
||||||
|
done
|
||||||
|
|
||||||
|
echo "All gateways launched: ${HERMES_PROFILES}"
|
||||||
@@ -30,7 +30,7 @@ RUN corepack enable && corepack prepare pnpm@latest --activate
|
|||||||
WORKDIR /app
|
WORKDIR /app
|
||||||
RUN apt-get update && apt-get install -y git openssh-client && rm -rf /var/lib/apt/lists/**
|
RUN apt-get update && apt-get install -y git openssh-client && rm -rf /var/lib/apt/lists/**
|
||||||
|
|
||||||
ARG OPENCONCHO_SHA=148766312e6a5256f399c64171854f0ff6173b6d
|
ARG OPENCONCHO_SHA=3b5c3293fc18d768dbe85285264a8d66c896bd81
|
||||||
RUN mkdir -p -m 0700 ~/.ssh && ssh-keyscan -p 2222 code.lazyworkhorse.net >> ~/.ssh/known_hosts 2>/dev/null
|
RUN mkdir -p -m 0700 ~/.ssh && ssh-keyscan -p 2222 code.lazyworkhorse.net >> ~/.ssh/known_hosts 2>/dev/null
|
||||||
RUN --mount=type=ssh git clone --depth 1 ssh://git@code.lazyworkhorse.net:2222/gortium/openconcho.git /app && \
|
RUN --mount=type=ssh git clone --depth 1 ssh://git@code.lazyworkhorse.net:2222/gortium/openconcho.git /app && \
|
||||||
git -C /app fetch --depth 1 origin ${OPENCONCHO_SHA} && \
|
git -C /app fetch --depth 1 origin ${OPENCONCHO_SHA} && \
|
||||||
|
|||||||
Reference in New Issue
Block a user