{"id":23009449,"url":"https://github.com/better-call-jason/docker-llaravellama","last_synced_at":"2025-06-16T01:37:16.417Z","repository":{"id":268040521,"uuid":"903017987","full_name":"Better-Call-Jason/Docker-LlaraveLlama","owner":"Better-Call-Jason","description":"Docker container image of LlaraveLlama for easy deployment of your private AI Chat Suite","archived":false,"fork":false,"pushed_at":"2025-01-09T14:35:04.000Z","size":5525,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-02T16:13:34.210Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Shell","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/Better-Call-Jason.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}},"created_at":"2024-12-13T18:49:10.000Z","updated_at":"2025-01-09T14:35:08.000Z","dependencies_parsed_at":null,"dependency_job_id":"f3333e1b-bcfa-4138-8591-352f6e8315a7","html_url":"https://github.com/Better-Call-Jason/Docker-LlaraveLlama","commit_stats":null,"previous_names":["better-call-jason/docker-llaravellama"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Better-Call-Jason/Docker-LlaraveLlama","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Better-Call-Jason%2FDocker-LlaraveLlama","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Better-Call-Jason%2FDocker-LlaraveLlama/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Better-Call-Jason%2FDocker-LlaraveLlama/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Better-Call-Jason%2FDocker-LlaraveLlama/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Better-Call-Jason","download_url":"https://codeload.github.com/Better-Call-Jason/Docker-LlaraveLlama/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Better-Call-Jason%2FDocker-LlaraveLlama/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260081960,"owners_count":22956219,"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":[],"created_at":"2024-12-15T09:13:36.386Z","updated_at":"2025-06-16T01:37:16.393Z","avatar_url":"https://github.com/Better-Call-Jason.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Docker-LlaraveLlama: Private AI Chat Suite -- Docker Version\n![Stable](https://img.shields.io/badge/status-stable-green)\n[![Issues](https://img.shields.io/github/issues/Better-Call-Jason/LlaraveLlama)](https://github.com/Better-Call-Jason/LlaraveLlama/issues)\n    \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-blue.svg\" alt=\"License: MIT\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://hub.docker.com/r/meowsaytounge/llaravellama\"\u003e\u003cimg src=\"https://img.shields.io/docker/pulls/meowsaytounge/llaravellama.svg\" alt=\"Docker Pulls\"\u003e\u003c/a\u003e\n\nWelcome to LlaraveLlama - the most user-friendly private AI chat suite that brings enterprise-grade AI to your local machine in under 3 minutes. By seamlessly combining Laravel's reliability with Ollama's AI capabilities, we've created a zero-configuration solution that gives you instant access to powerful AI models, complete with a polished interface and 20+ pre-configured AI assistants. Whether you're a privacy enthusiast, developer, or someone who wants their own private GPT-like experience without the technical hassle, LlaraveLlama delivers everything you need with just a single command.\n\nExperience the power of LlaraveLlama in action through our live demo, running efficiently on a minimal shared cloud setup with just 4GB RAM and 2 CPU cores at: [Live Demo](http://demo.llaravellama.com)\n\n## Table of Contents\n- [Preview](#-preview)\n- [Features](#-features)\n- [System Requirements](#-system-requirements)\n- [Installation Guide](#-installation-guide)\n  - [1. Clone the Repository](#1-clone-the-repository)\n  - [2. Prerequisites Setup](#2-prerequisites-setup)\n    - [A. Docker Installation](#a-docker-installation)\n    - [B. NVIDIA Setup](#b-nvidia-setup-gpu-version-only)\n  - [3. Choose Your Installation Method](#3-choose-your-installation-method)\n    - [A. CPU Version](#a-cpu-version-default)\n    - [B. GPU Version](#b-gpu-version)\n    - [C. Build From Source](#c-build-from-source)\n- [Components](#-components)\n- [Configuration](#-configuration)\n- [To Add More Ollama Models](#to-add-more-ollama-models)\n- [Accessing the Application](#-accessing-the-application)\n- [Contributing](#-contributing)\n- [License](#-license)\n- [Related Projects](#-related-projects)\n\n## 📸 Preview\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"preview.gif\" alt=\"LlaraveLlama in action\" width=\"800\"\u003e\n    \u003cbr /\u003e\n    \u003cem\u003eLlaraveLlama in action - showcasing features, themes and debug mode\u003c/em\u003e\n    \u003cbr /\u003e\n\u003c/div\u003e\n\n## ✨ Features\n\n- **Easy Deployment**: Get up and running in minutes with just a few commands\n- **Consistent Environment**: Same experience across all platforms\n- **Isolated Resources**: Run multiple instances without conflicts\n- **Simple Updates**: Pull the latest images for instant updates\n- **Zero Configuration**: No need to install PHP, Node.js, or any other dependencies\n\n## 🛠 System Requirements\n\n- Any platform that can run Docker\n- Minimum 8GB RAM recommended\n- 10GB free disk space\n- Docker Engine 20.10 or newer\n- Docker Compose v2.0 or newer\n\nTested Platforms:\n- Ubuntu 22.04/24.04 LTS\n- macOS\n- Windows with WSL2\n\n## 🚀 Installation Guide\n\n### 1. Clone the Repository\n\nFirst, clone the repository to get access to all necessary files and utilities:\n\n```bash\ngit clone https://github.com/Better-Call-Jason/Docker-LlaraveLlama.git\n```\n```bash\ncd Docker-LlaraveLlama\n```\n\n### 2. Prerequisites Setup\n\nUse our utility scripts to set up your environment:\n\n#### A. Docker Installation\nIf you don't have Docker installed:\n```bash\nchmod +x utilities/docker_setup.sh\n```\n```bash\n./utilities/docker_setup.sh\n```\n\n#### B. NVIDIA Setup (GPU Version Only)\n1. If you plan to use GPU acceleration:\n```bash\nchmod +x utilities/nvidia_setup.sh\n```\n```bash\n./utilities/nvidia_setup.sh\n```\n2. After running the nvidia_setup.sh script, you'll need to reboot your system, the script will prompt you just run :\n```bash\nsudo reboot\n```\nOnce rebooted :\n```bash\ncd Docker-LlaraveLlama\n```\n3. Check the nvidia configuration:\n```bash\nnvidia-smi\n```\n4. To continually see operation of GPU in the background :\n```bash\nwatch -n 1 nvidia-smi\n```\n\n### 3. Choose Your Installation Method\n\n#### A. CPU Version (Default)\nBest for most users and general deployment:\n\n```bash\ndocker compose up -d\n```\n\n#### B. GPU Version\nFor users with NVIDIA GPUs who want accelerated inference:\n\n```bash\ndocker compose -f docker-compose.gpu.yml up -d\n```\n\n#### C. Build From Source\nFor users who want to customize their installation:\n\nFor CPU users:\n```bash\ndocker compose -f docker-compose.build.yml build\n```\n```bash\ndocker compose -f docker-compose.build.yml up -d\n```\n\nFor GPU users:\n```bash\ndocker compose -f docker-compose.build.gpu.yml build\n```\n```bash\ndocker compose -f docker-compose.build.gpu.yml up -d\n```\n\n## 📦 Components\n\n### Docker Images\n- `meowsaytounge/llaravellama:latest`: Main application\n- `meowsaytounge/llaravellama-ollama:latest`: Ollama service with pre-configured models\n\n### Pre-installed Models\nThe Ollama container comes with:\n- llama3.2:3b\n- gemma2:2b\n- qwen2.5:3b\n\n## 🔧 Configuration\n\n### Environment Variables\nConfigure in your docker-compose.yml:\n\n```yaml\nenvironment:\n  - OLLAMA_HOST=ollama\n  - OLLAMA_BASE_URL=http://ollama:11434\n  # Add any additional Laravel environment variables here\n```\n\n### To Add More Ollama Models\n1. While the docker container is running, enter the project directory :\n```bash\ncd Docker-LlaraveLlama\n```\n2. Enter the Ollama docker container, with this command :\n```bash\ndocker exec -it docker-llaravellama-ollama-1 bash\n```\n3. Run the Ollama command :\n```bash\nollama\n```\nYou should see output like this :\n```bash\nroot@f03132f2eeaf:/# ollama\nUsage:\n  ollama [flags]\n  ollama [command]\n\nAvailable Commands:\n  serve       Start ollama\n  create      Create a model from a Modelfile\n  show        Show information for a model\n  run         Run a model\n  stop        Stop a running model\n  pull        Pull a model from a registry\n  push        Push a model to a registry\n  list        List models\n  ps          List running models\n  cp          Copy a model\n  rm          Remove a model\n  help        Help about any command\n\nFlags:\n  -h, --help      help for ollama\n  -v, --version   Show version information\n\nUse \"ollama [command] --help\" for more information about a command.\n```\n4. Utilize the Ollama Pull command to pull models from Ollama for example:\n```bash\nollama pull codestral\n```\n```bash\n ollama pull codellama:13b\n```\nThe install output will look like this :\n```bash\nroot@f03132f2eeaf:/# ollama pull codestral\npulling manifest \npulling 22a849aafe3d... 100% ▕██████████████████████████████████████████████████████████████████▏  12 GB                         \npulling 51707752a87c... 100% ▕██████████████████████████████████████████████████████████████████▏  480 B                         \npulling 5b68668f65de... 100% ▕██████████████████████████████████████████████████████████████████▏  11 KB                         \npulling 5dea4f4d0fff... 100% ▕██████████████████████████████████████████████████████████████████▏   63 B                         \npulling 2be2362e38c7... 100% ▕██████████████████████████████████████████████████████████████████▏  486 B                         \nverifying sha256 digest \nwriting manifest \nsuccess \nroot@f03132f2eeaf:/# ollama pull  codellama:13b\npulling manifest \npulling e73cc17c7181... 100% ▕██████████████████████████████████████████████████████████████████▏ 7.4 GB                         \npulling 8c17c2ebb0ea... 100% ▕██████████████████████████████████████████████████████████████████▏ 7.0 KB                         \npulling 590d74a5569b... 100% ▕██████████████████████████████████████████████████████████████████▏ 4.8 KB                         \npulling 2e0493f67d0c... 100% ▕██████████████████████████████████████████████████████████████████▏   59 B                         \npulling 7f6a57943a88... 100% ▕██████████████████████████████████████████████████████████████████▏  120 B                         \npulling 35e261fb2c73... 100% ▕██████████████████████████████████████████████████████████████████▏  530 B                         \nverifying sha256 digest \nwriting manifest \nsuccess \n```\n5. Exit the container or close the terminal. Now you can use these new models in your private LlaraveLlama instance, just refresh your browser page and the new models will appear in the list of available models. \n   \n\n### Debugging\nEnable debug mode by setting `APP_DEBUG=true` in your docker-compose.yml. The debug panel is fully responsive and works on mobile devices.\n\n## 📱 Accessing the Application\n\n- Local access: `http://localhost`\n- Network access: `http://your_computer_ip_address`\n- Mobile access: Ensure your device is on the same network or exposed to the internet : `http://host_ip`\n\n\n## 🤝 Contributing\n\nContributions are welcome! Feel free to submit issues and pull requests.\n\n## 📜 License\n\nLlaraveLlama is open-source software licensed under the [MIT license](LICENSE).\n\n## 🔗 Related Projects\n\n- [LlaraveLlama](https://github.com/Better-Call-Jason/LlaraveLlama) - The original non-Docker version\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbetter-call-jason%2Fdocker-llaravellama","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbetter-call-jason%2Fdocker-llaravellama","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbetter-call-jason%2Fdocker-llaravellama/lists"}