bvandeusen
cbfdf5289e
Phase 5: Multi-user authentication with session cookies, bcrypt passwords, first-user-is-admin pattern, per-user data isolation, backup/restore, Docker Swarm production stack with secrets and network isolation. Phase 5.1: Chat UX improvements: - Background generation architecture (GenerationBuffer + asyncio task) with SSE fan-out, reconnect support, and periodic DB flushes - LLM-generated conversation titles (first exchange + every 10th message) - Stop generation button with cancel_event and partial content preservation - Relative timestamps in sidebar (5m ago, 3h ago, then dates) - Empty chat auto-cleanup on navigation away - Save-as-note uses LLM for title generation, tags notes with "chat" - Summarize-as-note also tags with "chat" Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
110 lines
2.5 KiB
YAML
110 lines
2.5 KiB
YAML
services:
|
|
app:
|
|
build: .
|
|
ports:
|
|
- "5000:5000"
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
ollama:
|
|
condition: service_started
|
|
environment:
|
|
DATABASE_URL_FILE: /run/secrets/fabled_assistant_db_url
|
|
SECRET_KEY_FILE: /run/secrets/fabled_assistant_secret_key
|
|
OLLAMA_URL: "http://ollama:11434"
|
|
OLLAMA_MODEL: "${OLLAMA_MODEL:-llama3.1}"
|
|
LOG_LEVEL: "${LOG_LEVEL:-INFO}"
|
|
secrets:
|
|
- fabled_assistant_db_url
|
|
- fabled_assistant_secret_key
|
|
networks:
|
|
- frontend
|
|
- backend
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:5000/api/health')"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 30s
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 512M
|
|
restart_policy:
|
|
condition: on-failure
|
|
max_attempts: 5
|
|
|
|
db:
|
|
image: postgres:16-alpine
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
environment:
|
|
POSTGRES_USER: fabled
|
|
POSTGRES_PASSWORD_FILE: /run/secrets/fabled_assistant_db_password
|
|
POSTGRES_DB: fabledassistant
|
|
secrets:
|
|
- fabled_assistant_db_password
|
|
networks:
|
|
- backend
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U fabled"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
deploy:
|
|
resources:
|
|
limits:
|
|
memory: 256M
|
|
restart_policy:
|
|
condition: on-failure
|
|
max_attempts: 5
|
|
|
|
ollama:
|
|
image: ollama/ollama
|
|
volumes:
|
|
- ollama_models:/root/.ollama
|
|
networks:
|
|
- backend
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://localhost:11434/"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 15s
|
|
deploy:
|
|
placement:
|
|
constraints:
|
|
- node.role == worker
|
|
resources:
|
|
limits:
|
|
memory: 8G
|
|
restart_policy:
|
|
condition: on-failure
|
|
max_attempts: 3
|
|
# To enable GPU support, uncomment the section below
|
|
# (requires nvidia-container-toolkit)
|
|
# deploy:
|
|
# resources:
|
|
# reservations:
|
|
# devices:
|
|
# - driver: nvidia
|
|
# count: all
|
|
# capabilities: [gpu]
|
|
|
|
volumes:
|
|
pgdata:
|
|
ollama_models:
|
|
|
|
networks:
|
|
frontend:
|
|
backend:
|
|
internal: true
|
|
|
|
secrets:
|
|
fabled_assistant_secret_key:
|
|
external: true
|
|
fabled_assistant_db_password:
|
|
external: true
|
|
fabled_assistant_db_url:
|
|
external: true
|