docs.neptuneplayer.com
Warning: If this is a folder, all contents including subfolders and documents will be deleted.
Define path-based access rules for sections of your wiki, then assign users to groups in the Users tab. Rules are evaluated in order. First match wins.
Create and manage backups of your wiki data. Backups include all documents, images, and configuration files.
Language model configuration for Neptune's AI features. None of this is required; Neptune works fully without it. Neptune AI is the built-in, zero-setup hosted provider included with Neptune Pro; supported bring-your-own providers keep the same features available without Pro.
With a model configured, you unlock:
The master toggle. When on, Neptune automatically uses AI to understand complex or conceptual searches when local results look weak. When off, the sparkle features stay out of your way entirely.
| Provider | Type | Setup |
|---|---|---|
| Neptune AI | Hosted | Neptune Pro; built in, nothing to configure |
| Ollama | Local | Point at your own machine (e.g. http://localhost:11434) |
| Gemini | Cloud | API key |
| OpenRouter | Cloud | One API key, many models |
Each provider row takes a server URL where relevant, an API key, and a model, with a Test Connection button to verify before saving.
Claude, OpenAI, and GLM are visible as planned providers but are not active yet.
With several providers enabled, Set Model Priority controls the fallback order. If your primary provider is down or times out, the next one takes over automatically.
AI requests contain only the prompt and minimal context, and they only happen when an AI feature actually runs. Local providers like Ollama keep everything on your network. See Neptune AI privacy and the privacy notes on AI Search.