Hi everyone I am using openai gpt-3.5 as my llm for my chat engine and it is answering questions outside of the knowledge base. Is there anything i can do to either ensure a closed domain or stop the hallucination?

Hi - I was wondering if there were any query transformations for chat engines? Also I was wondering if llama index supported any other query normalization or any personalization features?

Also would it be possible to use any of the llama cpp moddels on GPU?

Hi all, another question is it possible to use llama cpp with the blokes GPTQ models instad of GGML