Nick Colvin

AFAIK, the `test_size` parameter refers to the number of candidate questions, so it acts as a maximum but not a guaranteed amount. My question refers to calling `generate()` or `generate_with_langchain_docs()`...

Hi @jjmachan I appreciate the response. In the above example I believe I used Biden's [state of the union](https://github.com/hwchase17/chat-your-data/blob/master/state_of_the_union.txt) for `documents` and the first 1000 lines of [tinyshakespeare](https://github.com/karpathy/char-rnn/blob/master/data/tinyshakespeare/input.txt) for `documents2`....