This study uses publicly available online question and answering dataset in Arabic language. There are almost 430K questions and answers for 20 diseases specific categories. GPT-3.5-turbo model was fine-tuned with a portion of this dataset.

1. Download original file from https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/Y2JBEZ source.
2. In case you are unable to convert to csv file, you can download it from https://www.dropbox.com/scl/fi/y392p992605bd6kg11nse/ds5b.csv?rlkey=2beoqwhkcie36vhb07ix2887e&dl=0 (cite orignial author)
3. The file is in db format.
4. We converted them them to csv format.
5. Then we converted them json format to train the model.
6. gpt3.5turbo.ipynb train the model
7. Test file are different test cases