Start the GenAI Engine backend server and frontend UI. Use when you need to launch the API server and the frontend locally.
Use the Read tool to read ./genai-engine/.env.
Check that GENAI_ENGINE_OPENAI_GPT_NAMES_ENDPOINTS_KEYS is present and has a non-empty value (not just GENAI_ENGINE_OPENAI_GPT_NAMES_ENDPOINTS_KEYS= with nothing after the =).
If the value is missing or empty:
genai-engine/.env and set GENAI_ENGINE_OPENAI_GPT_NAMES_ENDPOINTS_KEYS using the format: MODEL_NAME::ENDPOINT_URL::API_KEY (e.g. gpt-4o::https://api.openai.com/::sk-...). Run the skill again once the key is set."Only proceed here if Step 1 passed. Spawn a Task sub-agent with subagent_type="Bash" and the following self-contained prompt:
Start the GenAI Engine backend and frontend. Report success or failure for each step.
Step 1 — Verify PostgreSQL is running:
cd genai-engine && docker compose ps db
If not running or unhealthy, start it:
cd genai-engine && docker compose up -d db && sleep 3
Step 2 — Start the backend server in the background:
cd genai-engine && \
set -a && source .env && set +a && \
export POSTGRES_USER=postgres \
POSTGRES_PASSWORD=changeme_pg_password \
POSTGRES_URL=localhost \
POSTGRES_PORT=5432 \
POSTGRES_DB=arthur_genai_engine \
POSTGRES_USE_SSL=false \
PYTHONPATH="src:$PYTHONPATH" \
GENAI_ENGINE_SECRET_STORE_KEY="some_test_key" \
GENAI_ENGINE_ENVIRONMENT=local \
GENAI_ENGINE_ADMIN_KEY=changeme123 \
GENAI_ENGINE_ENABLE_PERSISTENCE=enabled \
ALLOW_ADMIN_KEY_GENERAL_ACCESS=enabled && \
uv run serve &
Step 3 — Wait for the backend to become healthy:
sleep 5 && curl -s -H "Authorization: Bearer changeme123" http://localhost:3030/health
Step 4 — Start the frontend and capture the URL:
cd genai-engine/ui && yarn install && yarn dev 2>&1 | tee /tmp/vite-fe.log &
sleep 3 && grep -m1 "Local:" /tmp/vite-fe.log
Report the following when done:
/docs appendedAuthorization: Bearer changeme123