repo contains sample notebooks used for testing GPT4 on various tasks related to Selenium nanoparticle reseach

All code is writen in Python 3.10.12. Vesions of packages are in requirements.txt.

Prompt engineering links:

1. https://www.promptingguide.ai
2. https://platform.openai.com/docs/guides/prompt-engineering

Parsing pdfs:

1. https://pypi.org/project/science-parse-api/

Data:

1. samples of original reserach articles and reviews in directories SeNp_research_articles and SeNp_review_articles
2. uniprot api for protein records

References:

1. J. Yang, H. Jin, R. Tang, X. Han, Q. Feng, H. Jiang, B. Yin, X. Hu, Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond, arXiv:2304.13712 27 April 2023, https://doi.org/10.48550/arXiv.2304.13712
2. A. D. White, G. M. Hocky, H. A. Gandhi, M. Ansari, S. Cox, G. P. Wellawatte, S. Sasmal, Z. Yang, K. Liu, Y. Singh, W. J. Peña Ccoa, Assessment of chemistry knowledge in large language models that generate code. ChemRxiv 2022 https://doi.org/10.26434/chemrxiv-2022-3md3n-v2
3. K. Hatakeyama-Sato, N. Yamane, Y. Igarashi, Y. Nabae & T. Hayakawa, Prompt engineering of GPT-4 for chemical research: what can/cannot be done?, STAM Methods, 3:1, 2260300, 2023, https://doi.org/10.1080/27660400.2023.2260300
4. Microsoft Research AI4Science, Microsoft Azure Quantum, The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4, https://doi.org/10.48550/arXiv.2311.07361