ducklm/docs/how_to_run.md

How To Run

1. Install dependencies:

python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e ".[dev]"

2. Configure:

cp .env.example .env

The default DUCK_MAIN_MODEL_PATH points to ./models/Qwen3.6/nonMTP/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf.

3. Start llama-server:

bash scripts/llama/start_main.sh start

Useful process commands:

bash scripts/llama/start_main.sh status
bash scripts/llama/start_main.sh logs --follow
bash scripts/llama/start_main.sh restart
bash scripts/llama/start_main.sh stop

4. Start DuckLM API:

python -m duck_core.api

5. Open WebChat:

http://127.0.0.1:8000/

6. Send a task:

curl -X POST http://127.0.0.1:8000/v1/chat \
  -H "Content-Type: application/json" \
  -d '{"message":"Скажи коротко, что ты DuckLM","workspace":"./workspace","debug":true}'

7. Inspect events:

curl http://127.0.0.1:8000/v1/tasks/<task_id>/events

8. Approvals:

curl http://127.0.0.1:8000/v1/approvals/pending

9. Stop services:

bash scripts/llama/start_main.sh stop
docker compose -f docker-compose.memory.yml down