mirror of
https://github.com/kevinveenbirkenbach/computer-playbook.git
synced 2025-09-24 11:06:24 +02:00
Kevin Veen-Birkenbach
5d1210d651
• Add svc-ai category under roles and load it in constructor stage
• Create new 'svc-ai-ollama' role (vars, tasks, compose, meta, README) and dedicated network
• Refactor former AI stack into separate app roles: web-app-flowise and web-app-openwebui
• Add web-app-minio role; adjust config (no central DB), meta (fa-database, run_after), compose networks include, volume key
• Provide user-focused READMEs for Flowise, OpenWebUI, MinIO, Ollama
• Networks: add subnets for web-app-openwebui, web-app-flowise, web-app-minio; rename web-app-ai → svc-ai-ollama
• Ports: rename ai_* keys to web-app-openwebui / web-app-flowise; keep minio_api/minio_console
• Add group_vars/all/17_ai.yml (OLLAMA_BASE_LOCAL_URL, OLLAMA_LOCAL_ENABLED)
• Replace hardcoded include paths with path_join in multiple roles (svc-db-postgres, sys-service, sys-stk-front-proxy, sys-stk-full-stateful, sys-svc-webserver, web-svc-cdn, web-app-keycloak)
• Remove obsolete web-app-ai templates/vars/env; split Flowise into its own role
• Minor config cleanups (CSP flags to {}, central_database=false)
https://chatgpt.com/share/68d15cb8-cf18-800f-b853-78962f751f81
Ollama
Description
Ollama is a local model server that runs open LLMs on your hardware and exposes a simple HTTP API. It’s the backbone for privacy-first AI: prompts and data stay on your machines.
Overview
After the first model pull, Ollama serves models to clients like Open WebUI (for chat) and Flowise (for workflows). Models are cached locally for quick reuse and can run fully offline when required.
Features
- Run popular open models (chat, code, embeddings) locally
- Simple, predictable HTTP API for developers
- Local caching to avoid repeated downloads
- Works seamlessly with Open WebUI and Flowise
- Offline-capable for air-gapped deployments
Further Resources
- Ollama — https://ollama.com
- Ollama Model Library — https://ollama.com/library