Features 🌟
- New: Connect self-hosted vLLM hosted models.
- Generate embeddings directly via your local vLLM server.
- Personalize vllm chatbot responses using your own data (One Key RAG).
Code 🤖
const chatbot = new Chatbot(null, SupportedChatModels.VLLM, null, { baseUrl: 'http://localhost:8000' });