Streams replies over SSE from any OpenAI-compatible server (oMLX, llama.cpp, Ollama, ...). Single binary that can install itself as an OS service; docker compose bundles llama.cpp + Gemma 4 E2B.
2 lines
302 B
XML
2 lines
302 B
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32"><rect x="2" y="4" width="28" height="20" rx="7" fill="#3b6cf6"/><path d="M9 24l-3 6 9-6z" fill="#3b6cf6"/><circle cx="10" cy="14" r="2" fill="#fff"/><circle cx="16" cy="14" r="2" fill="#fff"/><circle cx="22" cy="14" r="2" fill="#fff"/></svg>
|