I have built an RAG chatbot using "meta-

I have built an RAG chatbot using "meta-llama/Llama-2-7b-chat-hf" model to let model act as a document question answering chatbot and below are the model params

llm = HuggingFaceLLM(
model_name="meta-llama/Llama-2-7b-chat-hf",
tokenizer_name="meta-llama/Llama-2-7b-chat-hf",
query_wrapper_prompt=PromptTemplate("<|system|>\n</s>\n<|user|>\n{query_str}</s>\n<|assistant|>\n"),
context_window=3900,
max_new_tokens=256,
model_kwargs={"quantization_config": quantization_config},
# tokenizer_kwargs={},
generate_kwargs={"temperature": 0.3, "top_k": 50, "top_p": 0.95},
messages_to_prompt=messages_to_prompt,
device_map="auto",

)

I have used VectorStoreIndex to index my documents. When I query my model it is able to give answers related to the document accurately( Which is a good thing), but it is also answering questions that are out of my documents, I want to limit it to answer questions only related to my docs, How can I do that?