{"id":27777845,"url":"https://github.com/foojack87/local_ai","last_synced_at":"2025-04-30T07:56:46.759Z","repository":{"id":290044491,"uuid":"973179050","full_name":"foojack87/local_ai","owner":"foojack87","description":"Local AI: Ollama + Open WebUI with GPU Support - This version intentionally binds to localhost to keep setup private and limit access strictly to your machine.","archived":false,"fork":false,"pushed_at":"2025-04-26T14:22:59.000Z","size":5,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-30T07:56:42.680Z","etag":null,"topics":["ai","llm","ollama","openwebui"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/foojack87.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-04-26T12:39:58.000Z","updated_at":"2025-04-26T14:23:02.000Z","dependencies_parsed_at":"2025-04-26T14:39:29.828Z","dependency_job_id":"7fd00261-4025-4750-a41b-ce76a1249790","html_url":"https://github.com/foojack87/local_ai","commit_stats":null,"previous_names":["foojack87/local_ai"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/foojack87%2Flocal_ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/foojack87%2Flocal_ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/foojack87%2Flocal_ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/foojack87%2Flocal_ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/foojack87","download_url":"https://codeload.github.com/foojack87/local_ai/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251666246,"owners_count":21624292,"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":["ai","llm","ollama","openwebui"],"created_at":"2025-04-30T07:56:45.864Z","updated_at":"2025-04-30T07:56:46.753Z","avatar_url":"https://github.com/foojack87.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Local AI: Ollama + Open WebUI with GPU Support\n\nThis guide helps you set up [Ollama](https://ollama.com) with [Open WebUI](https://github.com/open-webui/open-webui) on a Linux system using Docker, with GPU acceleration (NVIDIA).\nThis version intentionally binds to localhost to keep setup private and limit access strictly to your machine.\n\n---\n\n## ✅ Prerequisites\n\n- Ubuntu (native or WSL2)\n- NVIDIA GPU\n\n---\n\n## 🧰 Setup Instructions\n\n### 1. Install Docker \u0026 Docker Compose\n\n```bash\nsudo apt update\nsudo apt install docker.io docker-compose -y\nsudo usermod -aG docker $USER\n```\n\n\u003e Reboot or log out/log back in after running `usermod`.\n\n---\n\n### 2. Install NVIDIA Container Toolkit\n\nFollow this guide: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/index.html\n\n---\n\n### 3. Verify GPU Access in Docker\n\n```bash\ndocker run --rm --gpus all nvidia/cuda:12.2.0-base-ubuntu20.04 nvidia-smi\n```\n\n\u003e You should see your GPU info.\n\n---\n\n### 4. Start the Containers\n\n```bash\ndocker compose up -d\n```\n\nCheck if containers are running:\n\n```bash\ndocker ps\n```\n\n---\n\n## 📥 Download and Run Models\n\nEnter the `ollama` container:\n\n```bash\ndocker exec -it local_ai_ollama_1 bash\n```\n\nPull a model:\n\n```bash\nollama pull gemma3\n```\n\nRun it:\n\n```bash\nollama run gemma3\n```\n\n\u003e You can find more models here: https://ollama.com/library\n\n---\n\n## 🌐 Access Web UI\n\nOpen in your browser:\n\n## http://localhost:3000\n\n## 🧹 Clean Up\n\nStop and remove containers:\n\n```bash\ndocker compose down\n```\n\nRemove pulled models:\n\n```bash\nollama list\nollama rm \u003cmodel-name\u003e\n```\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffoojack87%2Flocal_ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffoojack87%2Flocal_ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffoojack87%2Flocal_ai/lists"}