Search Results for "llama.cpp"

...The backend crawls selected pages, supplies their content to a configured model, and streams a synthesized response to the chat interface. It supports several hosted model services as well as custom local backends such as Ollama and llama.cpp. The web interface is designed for desktop and mobile use and exposes the service only on the local machine by default. Docker Compose provides a straightforward deployment path without requiring a dedicated GPU. The project is still described as early-stage, and actual privacy depends partly on whether users select a local or external model provider.