Ollama
by Ben Grande · ai.useion.ollama
Not TrustedPackageUnrated
Local AI models for your other apps: Ollama on your hub, with Gemma, Llama, Qwen and the rest of its library, answering over its own API and an OpenAI-compatible one. A package: apps that ask for its API use it, it has no screen of its own. The sample for kind package and apis.
Age rating
Not rated. Nobody has said who this app is suitable for, so Personal Clouds and the Oikou app treat it as 18+.
What version 0.35.1 may do
Internet
It asks to reach these hosts, and no others:
- registry.ollama.ai
- any address under r2.cloudflarestorage.com
Personal Cloud tools
None. It uses nothing from your Personal Cloud beyond its own storage.
Notifications
It does not send push notifications.
Storage
Up to 40 GB on your Personal Cloud.
What your apps can use
Your other web apps on your Personal Cloud can use these once you let each one, on its own install:
- API “ollama”: Ollama's API: chat and generate (/api/chat, /api/generate), embeddings (/api/embed), and the models on this hub (/api/tags, /api/pull, /api/delete). api:ai.useion.ollama/ollama
- API “openai”: The same models through the OpenAI API's shape (/chat/completions, /completions, /embeddings, /models), for any OpenAI client given this base URL. api:ai.useion.ollama/openai
Add to Personal Cloud
Sign in to add this web app to a Personal Cloud of yours. It runs there, on your own computer, and you open it from there; nothing is installed on your phone.
Versions
0.35.1 Latest Shown above
Published · a ready-built bundle
Models download again. This version runs Ollama 0.34.4: Ollama 0.35.0 fetched model layers without the hub's egress proxy, so every pull failed with "redirect target not allowed".
Published · a ready-built bundle
First release: Ollama 0.35.0 as a package. Apps that ask for api:ai.useion.ollama/ollama or /openai reach its models; it has no screen of its own.