mirror of
https://github.com/DRYTRIX/TimeTracker.git
synced 2026-05-23 06:40:53 -05:00
feat(docker): bundle Ollama and wire AI helper in compose
- Add ollama and ollama-init services with ollama_data volume; app waits for the model pull and receives AI_* defaults (AI_BASE_URL=http://ollama:11434). - Document bundled stack, env vars, and Ollama vs host base URL in README and DOCKER_COMPOSE_SETUP. - Align env.example AI defaults with the compose stack. - fix(ai): include api_key_set on AIProviderConfig so from_settings(**get_ai_config()) matches the settings dict.
This commit is contained in:
Dries Peeters
@@ -709,7 +709,7 @@ docker-compose -f docker/docker-compose.remote.yml up -d
|
||||
TimeTracker includes an optional **server-side AI helper** for the web app and API clients.
|
||||
|
||||
- **Enable**: set `AI_ENABLED=true`
|
||||
- **Ollama (default)**: set `AI_PROVIDER=ollama`, `AI_BASE_URL=http://127.0.0.1:11434`, `AI_MODEL=...`
|
||||
- **Ollama (default)**: set `AI_PROVIDER=ollama`, `AI_MODEL=...`, and `AI_BASE_URL` to `http://ollama:11434` when using the bundled stack in `docker-compose.yml`, or `http://127.0.0.1:11434` when Ollama runs on the host outside Docker.
|
||||
- **Hosted OpenAI-compatible**: set `AI_PROVIDER=openai_compatible` and `AI_API_KEY=...`
|
||||
|
||||
The AI helper is exposed as:
|
||||
@@ -717,6 +717,17 @@ The AI helper is exposed as:
|
||||
- Session web UI JSON: `POST /api/ai/chat` (same-origin, login required)
|
||||
- REST API v1: `POST /api/v1/ai/chat` (API token required, scopes `read:ai`/`write:ai`)
|
||||
|
||||
### Bundled Ollama service (Docker Compose)
|
||||
|
||||
`docker-compose.yml` ships a CPU-only `ollama` service plus a one-shot `ollama-init` sidecar that pulls the model defined by `AI_MODEL` (default `llama3.1`, ~4.7 GB) on first boot. The `app` service waits for the pull to finish before starting.
|
||||
|
||||
- The app reaches it at `http://ollama:11434` over the Docker network — no host ports need to be opened.
|
||||
- Change the model by setting `AI_MODEL` in `.env` (e.g. `AI_MODEL=qwen2.5:3b` for lighter hardware) and re-running `docker compose up -d`; the init sidecar will pull the new model.
|
||||
- Pulled models are cached in the `ollama_data` named volume, so subsequent boots are instant.
|
||||
- Verify in the UI: **Admin → System Settings → AI helper**, then click *Test connection*.
|
||||
- To pull additional models manually: `docker compose exec ollama ollama pull <model>`.
|
||||
- To use a hosted provider instead, set `AI_PROVIDER=openai_compatible`, `AI_BASE_URL=https://api.your-provider.example/`, `AI_API_KEY=…` in `.env`; the in-cluster Ollama can stay running or be removed.
|
||||
|
||||
### Encrypting stored secrets (recommended)
|
||||
|
||||
To store sensitive settings (OAuth secrets, mail password, AI API key, Peppol token, 2FA secret) encrypted at rest, set:
|
||||
|
||||
@@ -42,6 +42,7 @@ class AIProviderConfig:
|
||||
base_url: str
|
||||
model: str
|
||||
api_key: str
|
||||
api_key_set: bool
|
||||
timeout_seconds: int
|
||||
context_limit: int
|
||||
system_prompt: str
|
||||
@@ -58,7 +59,7 @@ class AIProviderConfig:
|
||||
"provider": self.provider,
|
||||
"base_url": self.base_url,
|
||||
"model": self.model,
|
||||
"api_key_set": bool(self.api_key),
|
||||
"api_key_set": self.api_key_set,
|
||||
"timeout_seconds": self.timeout_seconds,
|
||||
"context_limit": self.context_limit,
|
||||
}
|
||||
|
||||
@@ -89,6 +89,14 @@ services:
|
||||
- OTEL_METRICS_EXPORT_INTERVAL_MS=${OTEL_METRICS_EXPORT_INTERVAL_MS:-60000}
|
||||
- ENABLE_TELEMETRY=${ENABLE_TELEMETRY:-false}
|
||||
- TELE_SALT=${TELE_SALT:-8f4a7b2e9c1d6f3a5e8b4c7d2a9f6e3b1c8d5a7f2e9b4c6d3a8f5e1b7c4d9a2f}
|
||||
# AI helper (Ollama in-cluster by default; override AI_PROVIDER for hosted providers)
|
||||
- AI_ENABLED=${AI_ENABLED:-true}
|
||||
- AI_PROVIDER=${AI_PROVIDER:-ollama}
|
||||
- AI_BASE_URL=${AI_BASE_URL:-http://ollama:11434}
|
||||
- AI_MODEL=${AI_MODEL:-llama3.1}
|
||||
- AI_API_KEY=${AI_API_KEY:-}
|
||||
- AI_TIMEOUT_SECONDS=${AI_TIMEOUT_SECONDS:-60}
|
||||
- AI_CONTEXT_LIMIT=${AI_CONTEXT_LIMIT:-40}
|
||||
|
||||
# Expose only internally; nginx publishes ports
|
||||
ports: []
|
||||
@@ -99,6 +107,8 @@ services:
|
||||
depends_on:
|
||||
db:
|
||||
condition: service_healthy
|
||||
ollama-init:
|
||||
condition: service_completed_successfully
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-f", "-s", "-o", "/dev/null", "http://localhost:8080/_health"]
|
||||
@@ -107,6 +117,47 @@ services:
|
||||
retries: 3
|
||||
start_period: 40s
|
||||
|
||||
# Ollama - local LLM runtime for the TimeTracker AI helper
|
||||
# The app talks to it via the OpenAI-compatible endpoint at /v1/chat/completions.
|
||||
# First boot pulls the model defined by AI_MODEL (default llama3.1, ~4.7 GB).
|
||||
ollama:
|
||||
image: ollama/ollama:latest
|
||||
container_name: timetracker-ollama
|
||||
environment:
|
||||
- OLLAMA_HOST=0.0.0.0:11434
|
||||
- OLLAMA_KEEP_ALIVE=${OLLAMA_KEEP_ALIVE:-5m}
|
||||
volumes:
|
||||
- ollama_data:/root/.ollama
|
||||
# Internal-only by default; uncomment to expose for host tools.
|
||||
# ports:
|
||||
# - "11434:11434"
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "ollama list >/dev/null 2>&1 || exit 1"]
|
||||
interval: 15s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
start_period: 30s
|
||||
restart: unless-stopped
|
||||
|
||||
# One-shot model puller; runs to completion on each `up` (no-op if model already cached).
|
||||
ollama-init:
|
||||
image: ollama/ollama:latest
|
||||
container_name: timetracker-ollama-init
|
||||
depends_on:
|
||||
ollama:
|
||||
condition: service_healthy
|
||||
environment:
|
||||
- OLLAMA_HOST=http://ollama:11434
|
||||
entrypoint: ["/bin/sh","-c"]
|
||||
command:
|
||||
- |
|
||||
set -e
|
||||
MODEL="${AI_MODEL:-llama3.1}"
|
||||
echo "Pulling Ollama model: $$MODEL"
|
||||
ollama pull "$$MODEL"
|
||||
echo "Model ready: $$MODEL"
|
||||
restart: "no"
|
||||
|
||||
db:
|
||||
image: postgres:16-alpine
|
||||
container_name: timetracker-db
|
||||
@@ -222,4 +273,6 @@ volumes:
|
||||
loki_data:
|
||||
driver: local
|
||||
redis_data:
|
||||
driver: local
|
||||
ollama_data:
|
||||
driver: local
|
||||
@@ -52,7 +52,8 @@ docker-compose logs app --tail=100
|
||||
### 4) Optional services
|
||||
- Reverse proxy (HTTPS): See `docker-compose.yml` (services `certgen` and `nginx`).
|
||||
- **Note**: The `certgen` service is now self-contained and works with Portainer and other container orchestration tools without requiring host filesystem mounts.
|
||||
- Monitoring stack: Prometheus, Grafana, Loki, Promtail are available in `docker-compose.yml`.
|
||||
- Monitoring stack: Prometheus, Grafana, Loki, Promtail are available in `docker-compose.yml` (commented out by default; uncomment services to enable).
|
||||
- **Ollama (bundled LLM)**: The root `docker-compose.yml` includes `ollama` and a one-shot `ollama-init` container that pulls `AI_MODEL` into the `ollama_data` volume. The `app` service defaults to `AI_BASE_URL=http://ollama:11434` and waits for `ollama-init` to succeed before starting. Set `AI_ENABLED=false` in `.env` to turn off the in-app AI helper without removing the containers. Details: [README.md](../../../README.md) (sections *AI Helper* and *Bundled Ollama service*).
|
||||
|
||||
---
|
||||
|
||||
@@ -148,6 +149,18 @@ All environment variables can be provided via `.env` and are consumed by the `ap
|
||||
- LOG_LEVEL: Default: `INFO`.
|
||||
- LOG_FILE: Default: `/data/logs/timetracker.log` or `/app/logs/timetracker.log` based on compose.
|
||||
|
||||
### AI helper (optional)
|
||||
Used by the server-side AI helper (`/api/ai/*`, Admin → System Settings). In the root `docker-compose.yml`, defaults target the bundled `ollama` service.
|
||||
|
||||
- AI_ENABLED: Enable the AI helper. Default in root compose: `true` (override with `false` if you do not want LLM calls).
|
||||
- AI_PROVIDER: `ollama` or `openai_compatible`. Default: `ollama`.
|
||||
- AI_BASE_URL: Provider base URL without a trailing path. Default in root compose: `http://ollama:11434` (Docker service name). For Ollama on the host: `http://127.0.0.1:11434`.
|
||||
- AI_MODEL: Model tag (e.g. `llama3.1`, `qwen2.5:3b`). Pulled automatically on startup by `ollama-init` when using the bundled stack.
|
||||
- AI_API_KEY: Required when `AI_PROVIDER=openai_compatible`. Empty for Ollama.
|
||||
- AI_TIMEOUT_SECONDS: HTTP timeout for provider requests. Default in root compose: `60`.
|
||||
- AI_CONTEXT_LIMIT: Max recent time entries included in context. Default: `40`.
|
||||
- OLLAMA_KEEP_ALIVE: Passed to the `ollama` service (how long models stay loaded). Default: `5m`.
|
||||
|
||||
### Analytics & Telemetry (optional)
|
||||
- SENTRY_DSN: Sentry DSN (empty by default).
|
||||
- SENTRY_TRACES_RATE: 0.0–1.0 sampling rate. Default: `0.0`.
|
||||
|
||||
+9
-7
@@ -40,13 +40,15 @@ IDLE_TIMEOUT_MINUTES=30
|
||||
# SMART_NOTIFY_SCHEDULER_SLOT_MINUTES=30
|
||||
|
||||
# AI helper (server-side; API keys are never sent to clients)
|
||||
# AI_ENABLED=false
|
||||
# AI_PROVIDER=ollama
|
||||
# AI_BASE_URL=http://127.0.0.1:11434
|
||||
# AI_MODEL=llama3.1
|
||||
# AI_API_KEY=
|
||||
# AI_TIMEOUT_SECONDS=30
|
||||
# AI_CONTEXT_LIMIT=40
|
||||
# Defaults below match the bundled Ollama service in docker-compose.yml.
|
||||
AI_ENABLED=true
|
||||
AI_PROVIDER=ollama
|
||||
AI_BASE_URL=http://ollama:11434
|
||||
AI_MODEL=llama3.1
|
||||
# AI_API_KEY= # only needed when AI_PROVIDER=openai_compatible
|
||||
AI_TIMEOUT_SECONDS=60
|
||||
AI_CONTEXT_LIMIT=40
|
||||
# OLLAMA_KEEP_ALIVE=5m # how long Ollama keeps the model resident in memory
|
||||
|
||||
# API token rate limits (per token; Redis recommended for multi-worker)
|
||||
# API_TOKEN_RATE_LIMIT_PER_MINUTE=100
|
||||
|
||||
Reference in New Issue
Block a user