{"id":17497160,"url":"https://github.com/feiskyer/ollama-kubernetes","last_synced_at":"2025-05-07T09:47:48.520Z","repository":{"id":236761892,"uuid":"793105359","full_name":"feiskyer/ollama-kubernetes","owner":"feiskyer","description":"Kubernetes Helm chart to deploy Large Language Models with Ollama","archived":false,"fork":false,"pushed_at":"2025-02-05T05:31:10.000Z","size":2975,"stargazers_count":9,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-19T20:54:01.866Z","etag":null,"topics":["chatgpt","helm","kubernetes","llm","ollama"],"latest_commit_sha":null,"homepage":"https://feisky.xyz/ollama-kubernetes/","language":"Smarty","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/feiskyer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-04-28T12:47:51.000Z","updated_at":"2025-03-26T07:20:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"bbf27bfa-3a2f-4651-9145-6629ebbb4a11","html_url":"https://github.com/feiskyer/ollama-kubernetes","commit_stats":null,"previous_names":["feiskyer/ollama-kubernetes"],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/feiskyer%2Follama-kubernetes","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/feiskyer%2Follama-kubernetes/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/feiskyer%2Follama-kubernetes/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/feiskyer%2Follama-kubernetes/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/feiskyer","download_url":"https://codeload.github.com/feiskyer/ollama-kubernetes/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252854581,"owners_count":21814708,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chatgpt","helm","kubernetes","llm","ollama"],"created_at":"2024-10-19T15:14:56.718Z","updated_at":"2025-05-07T09:47:48.501Z","avatar_url":"https://github.com/feiskyer.png","language":"Smarty","readme":"# Ollama\n\nKubernetes Helm chart to deploy Large Language Models with Ollama.\n\n## How to use this chart\n\nSetup helm chart repo:\n\n```bash\nhelm repo add ollama https://feisky.xyz/ollama-kubernetes\nhelm repo update\n```\n\nDeploy Ollama with [Open WebUI](https://github.com/open-webui/open-webui):\n\n```sh\nhelm upgrade --install ollama ollama/ollama \\\n    --namespace=ollama \\\n    --create-namespace\n```\n\nAfter the deployment, you can access the Ollama UI by port-forwarding the service:\n\n```bash\nkubectl -n ollama port-forward service/ollama-webui 8080:80\n```\n\nThen open your browser and go to `http://localhost:8080`.\n\n## Configuration\n\nThe following table lists the configurable parameters of the Ollama chart and their default values.\n\n| Parameter                | Description             | Default        |\n| ------------------------ | ----------------------- | -------------- |\n| `image.repository` | Image repository of Ollama | `\"ollama/ollama\"` |\n| `image.tag` | Image tag of Ollama | `0.5.7` |\n| `replicaCount` | Number of replicas, need storge class support of multiple read when pvc enabled and replica \u003e 1 | `1` |\n| `llm.models` | List of models to be loaded | `[\"phi3\", \"llama3\"]` |\n| `persistentVolume.enabled` | Whether to enable persistent volume for Ollama | `true` |\n| `persistentVolume.storageClass` | Storage class for Ollama persistent volume | `\"default\"` |\n| `persistentVolume.accessModes` | Access mode for Ollama persistent volume | `[\"ReadWriteOnce\"]` |\n| `persistentVolume.size` | Storage size for Ollama persistent volume | `\"100Gi\"` |\n| `persistentVolume.claimName` | Set to non-empty value to use an existing PVC for Ollama persistent volume | `\"\"` |\n| `resources.limits.cpu` | CPU limits for Ollama container | `4` |\n| `resources.limits.memory` | Memory limits for Ollama container  | `\"4Gi\"` |\n| `resources.limits.nvidia.com/gpu` | GPU limits for Ollama container  | `\"1\"` |\n| `resources.requests.cpu` | CPU requests for Ollama container | `\"100m\"` |\n| `resources.requests.memory` | Memory requests for Ollama container | `\"128Mi\"` |\n| `resources.requests.nvidia.com/gpu` | GPU requests for Ollama container | `\"1\"` |\n| `nodeSelector` | Node selector for Ollama Pod | `{}` |\n| `tolerations` | Tolerations for Ollama Pod | `[{\"key\": \"kubernetes.azure.com/scalesetpriority\", \"operator\": \"Exists\"}]` |\n| `affinity` | Affinity for Ollama Pod | `{}` |\n| `ui.enabled` | Whether to enable WebUI | `true` |\n| `ui.replicaCount` | Replica count for WebUI Pod | `1` |\n| `ui.image.repository` | Image repository of WebUI Pod | `\"ghcr.io/open-webui/open-webui\"` |\n| `ui.image.tag` | Image tag of WebUI Pod | `\"latest\"` |\n| `ui.service.type` | Service type of WebUI | `\"ClusterIP\"` |\n| `ui.service.port` | Service port of WebUI | `80` |\n| `ui.nodeSelector` | Node selector for WebUI | `{}` |\n| `ui.tolerations` | Tolerations for WebUI | `{}` |\n| `ui.affinity` | Affinity for WebUI | `{}` |\n| `ui.ingress.enabled` | Whether to enable Ingress for WebUI | `false` |\n| `ui.ingress.className` | Ingress class name for WebUI | `\"\"` |\n| `ui.ingress.hosts` | Ingress hosts for WebUI | `[{\"host\": \"chart-example.local\", \"paths\": [{\"path\": \"/\", \"pathType\": \"ImplementationSpecific\"}]}]` |\n| `ui.ingress.tls` | Ingress TLS for WebUI | `[]` |\n| `ui.persistentVolume.enabled` | Whether to enable persistent volume for WebUI | `true` |\n| `ui.persistentVolume.storageClass` | Storage class for WebUI persistent volume  | `\"default\"` |\n| `ui.persistentVolume.accessModes` | Access mode for WebUI persistent volume | `[\"ReadWriteOnce\"]` |\n| `ui.persistentVolume.size` | Storage size for WebUI persistent volume | `\"10Gi\"` |\n| `ui.persistentVolume.claimName` | Set to non-empty value to use an existing PVC for WebUI persistent volume | `\"\"` |\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffeiskyer%2Follama-kubernetes","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffeiskyer%2Follama-kubernetes","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffeiskyer%2Follama-kubernetes/lists"}