kevinveenbirkenbach/computer-playbook
1
0
Fork 0
mirror of https://github.com/kevinveenbirkenbach/computer-playbook.git synced 2025-09-24 11:06:24 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
c181c7f6cdd739045b9e329fae9e1ad9bc5bf4d0
computer-playbook/roles/svc-ai-ollama
History
Kevin Veen-Birkenbach 426ba32c11 feat(services): add CPU/RAM/PIDs defaults for heavy roles and align service names 
Add per-service resource overrides (cpus, mem_reservation, mem_limit, pids_limit) for ollama, mariadb, postgres, confluence, gitlab, jira, keycloak, nextcloud; light formatting fixes in wordpress.

Rename service keys from generic 'application/web' to concrete names (jira, confluence, gitlab, keycloak) and update compose templates accordingly.

Jira: introduce JIRA_STORAGE_PATH and switch mounts/README accordingly.

https://chatgpt.com/share/68d2d96c-9bf4-800f-bbec-d4f2c0051c06
2025-09-23 21:43:50 +02:00
..
config
feat(services): add CPU/RAM/PIDs defaults for heavy roles and align service names
2025-09-23 21:43:50 +02:00
meta
feat(ai): introduce dedicated AI roles and wiring; clean up legacy AI stack
2025-09-22 18:40:20 +02:00
tasks
Open WebUI OIDC & proxy fixes + Ollama preload + async-safe pull
2025-09-23 04:27:46 +02:00
templates
feat(ai): introduce dedicated AI roles and wiring; clean up legacy AI stack
2025-09-22 18:40:20 +02:00
vars
Open WebUI OIDC & proxy fixes + Ollama preload + async-safe pull
2025-09-23 04:27:46 +02:00
README.md
feat(ai): introduce dedicated AI roles and wiring; clean up legacy AI stack
2025-09-22 18:40:20 +02:00

README.md

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