It won't because the amount of documents found by the search is limited ( and so is the prompt context ) so by design the task that is being solved by the index is finding an answer within a single document in ideal scenario

LangChain seems to have an implementation for it (https://python.langchain.com/en/latest/modules/models/llms/integrations/huggingface_textgen_inference.html) so this will probably get the job done - will try tomorrow