hermes
cf6ba1d32b
Sin cap, ollama crece sin freno (visto en docker stats: 3.94 GB y subiendo). Cap 6G suficiente para llama3.2:3b Q4 + ctx 16k: - compose (openwebui, wordpress): deploy.resources.limits.memory 6G - docker run (hermes, openclaw): --memory 6g
62 lines
1.5 KiB
YAML
62 lines
1.5 KiB
YAML
# d0a1 pack — Open WebUI
|
|
# Chat de IA privado. Sin cuenta, sin API key.
|
|
#
|
|
# Local: ./deploy.sh local → http://localhost:3000
|
|
# VPS: ./deploy.sh vps → http://TU_IP:3000
|
|
#
|
|
# Requisitos: Docker + 4 GB RAM mínimo
|
|
# Incluye: Ollama (IA local) + Open WebUI (interfaz web)
|
|
# Modelo por defecto: llama3.2:3b (~2 GB, corre en 4 GB RAM)
|
|
services:
|
|
ollama:
|
|
container_name: d0a1-ollama
|
|
image: ollama/ollama:0.33.3
|
|
restart: unless-stopped
|
|
ports:
|
|
- "${OLLAMA_PORT:-11434}:11434"
|
|
volumes:
|
|
- ollama_data:/root/.ollama
|
|
environment:
|
|
OLLAMA_HOST: "0.0.0.0"
|
|
OLLAMA_KEEP_ALIVE: "5m"
|
|
OLLAMA_NUM_PARALLEL: "1"
|
|
healthcheck:
|
|
test: ["CMD", "ollama", "ps"]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 10
|
|
start_period: 30s
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 6G
|
|
|
|
openwebui:
|
|
container_name: d0a1-openwebui
|
|
image: ghcr.io/open-webui/open-webui:0.11.3
|
|
restart: unless-stopped
|
|
ports:
|
|
- "${WEBUI_PORT:-3000}:8080"
|
|
volumes:
|
|
- openwebui_data:/app/backend/data
|
|
environment:
|
|
OLLAMA_BASE_URL: "http://ollama:11434"
|
|
WEBUI_NAME: "d0a1"
|
|
WEBUI_AUTH: "false"
|
|
DEFAULT_LOCALE: "es"
|
|
ENABLE_SIGNUP: "true"
|
|
ENABLE_WEB_SEARCH: "false"
|
|
ENABLE_DIRECT_CONNECTIONS: "false"
|
|
depends_on:
|
|
ollama:
|
|
condition: service_healthy
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 2G
|
|
|
|
volumes:
|
|
ollama_data:
|
|
driver: local
|
|
openwebui_data:
|
|
driver: local |