AI-Cognitive-Leap/agnes-the-ai-analyst
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
agnes-the-ai-analyst/cli/skills/setup.md
ZdenekSrotyr 3701130a11 feat: add Docker, CLI tool, scheduler, and agent skills 
- Dockerfile (uv-based) + docker-compose.yml (3 services)
- CLI tool 'da' with commands: auth, sync, query, status, admin, diagnose, skills
- Scheduler sidecar service (replaces systemd timers)
- pyproject.toml for uv distribution
- Built-in skills (setup, troubleshoot) for AI agents
- 17 CLI tests, 75 total tests passing
2026-03-27 15:30:03 +01:00

1.3 KiB
Raw Blame History

Setup — Complete guide for deploying a new instance

Prerequisites

  • Docker and Docker Compose installed
  • Domain name pointing to server IP (for SSL)
  • Data source credentials (Keboola token OR BigQuery service account)

Steps

  1. Clone the repository:

    git clone <repo-url>
cd data-analyst

  2. Create configuration:

    cp config/instance.yaml.example config/instance.yaml
# Edit instance.yaml with your settings

  3. Create environment file:

    cp config/.env.template .env
# Fill in: JWT_SECRET_KEY, KEBOOLA_STORAGE_TOKEN (or BIGQUERY_PROJECT), etc.

  4. Start services:

    docker compose up -d

  5. Verify health:

    da status --server http://your-server:8000

  6. Create first admin user:

    da login --email admin@company.com --server http://your-server:8000
da admin add-user admin@company.com --role admin

  7. Trigger initial data sync:

    da admin trigger-sync

  8. Verify data:

    da status

Troubleshooting

  • Cannot connect: Check docker compose ps, verify port 8000 is exposed
  • Auth fails: Verify JWT_SECRET_KEY is set in .env
  • No data: Check data source credentials, run da diagnose