FAQ
Short answers about local mode and product boundaries.
Does Prometheus send my notes to the cloud?
No. In the base product, indexing, search, and generation run locally through Prometheus Runtime and Ollama. Notes are not sent to OpenAI, Anthropic, Google, or similar services.
Does it work offline?
Yes, after the Runtime binary and embedding / LLM models are installed. Later chat and search do not need the internet.
Is mobile supported?
No. Prometheus is desktop-only: the Runtime sidecar and local Ollama process are not available in Obsidian mobile apps.
What if the answer is not in my notes?
Prometheus should not fill gaps from the model’s general knowledge. It reports
that the vault does not contain enough information (insufficient_context).
Can I use my own Runtime binary?
Yes. In Settings → Runtime choose Custom binary and set an absolute path to
prometheus-runtime instead of the managed download.
Do I need to install Ollama separately?
Yes. In 0.1 the plugin does not install Ollama for you: install Ollama, run
ollama pull …, then pick the model in Chat / Settings.
Where is the index stored?
The vector index and Runtime state live outside the vault (and outside
.obsidian/plugins) so they stay out of Obsidian Sync and Git.
Source Markdown remains in the vault.
How is Chat different from Search?
Search returns relevant fragments without calling the LLM. Chat runs retrieval and then grounded generation with cited sources.
What license is the project under?
Need architecture detail?
The repository also has Architecture.md and 0.1 release notes.