c03771751c
feat(elasticsearch): upgrade Elasticsearch version to 9.3.0 in environment and docker-compose files feat(gitlab): update GitLab version to 18.8.3-ce.0 in environment and docker-compose files feat(grafana): bump Grafana version to 12.3.2 in environment and docker-compose files feat(jenkins): upgrade Jenkins version to 2.541-lts-jdk17 in environment and docker-compose files fix(minio): remove unnecessary newline in docker-compose file feat(nginx): downgrade Nginx version to 1.28.2-alpine3.22 in environment and docker-compose files feat(ollama): update Ollama version to 0.14.3 in environment and docker-compose files feat(prometheus): upgrade Prometheus version to 3.5.1 in environment and docker-compose files feat(rabbitmq): update RabbitMQ version to 4.2.3-management-alpine in environment and docker-compose files
Ollama
This service deploys Ollama for running local LLM models.
Usage
-
Pull DeepSeek R1 7B model:
docker exec -it ollama-ollama-1 ollama pull deepseek-r1:7b -
List all local models:
docker exec -it ollama-ollama-1 ollama list -
Get all local models via API:
curl http://localhost:11434/api/tags 2> /dev/null | jq
Services
ollama: The Ollama service.
Configuration
OLLAMA_VERSION: The version of the Ollama image, default is0.12.0.OLLAMA_PORT_OVERRIDE: The host port for Ollama, default is11434.
Volumes
ollama_models: A volume for storing Ollama models.
Troubleshooting
GPU Becomes Unavailable After Long Run (Linux Docker)
If Ollama initially works on the GPU in a Docker container, but then switches to running on CPU after some period of time with errors in the server log reporting GPU discovery failures, this can be resolved by disabling systemd cgroup management in Docker.
Edit /etc/docker/daemon.json on the host and add "exec-opts": ["native.cgroupdriver=cgroupfs"] to the Docker configuration:
{
"exec-opts": ["native.cgroupdriver=cgroupfs"]
}
Then restart Docker:
sudo systemctl restart docker
For more details, see Ollama Troubleshooting - Linux Docker.