Regarding Question and Answer modeling Using NLP

[Devangkaruskar]

I am working with tinyroberta-squad2,roberta-base-squad2 but what i get answer from question is too small or one liner. I want some descriptive answer. can anyone plzz help!

[julian-risch]

Hi @Devangkaruskar I would recommend to look at the following three tutorials:

1. Tutorials 1 covers extractive question answering and printing not only the answer but also its context: https://github.com/deepset-ai/haystack-tutorials/blob/main/tutorials/01_Basic_QA_Pipeline.ipynb

from haystack.utils import print_answers

# Change `minimum` to `medium` or `all` to raise the level of detail
print_answers(prediction, details="all")

2. Tutorial 7 is about generative question answering with RAG: https://github.com/deepset-ai/haystack-tutorials/blob/main/tutorials/07_RAG_Generator.ipynb

3. Tutorial 12 is about generative question answering with LFQA: https://github.com/deepset-ai/haystack-tutorials/blob/main/tutorials/12_LFQA.ipynb