Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Leveraging Large Language Models to Build and Execute Computational Workflows (2312.07711v1)

Published 12 Dec 2023 in cs.AI

Abstract: The recent development of LLMs with multi-billion parameters, coupled with the creation of user-friendly application programming interfaces (APIs), has paved the way for automatically generating and executing code in response to straightforward human queries. This paper explores how these emerging capabilities can be harnessed to facilitate complex scientific workflows, eliminating the need for traditional coding methods. We present initial findings from our attempt to integrate Phyloflow with OpenAI's function-calling API, and outline a strategy for developing a comprehensive workflow management system based on these concepts.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (17)
  1. 2023. LangChain. https://github.com/langchain-ai/langchain. Accessed: 2023-08-16.
  2. 2023. Workflow Description Language (WDL). https://github.com/openwdl/wdl. Accessed: 2023-08-16.
  3. PhyloFlow: A fully customizable and automatic workflow for phylogenetic reconstruction. In 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 1–7. https://doi.org/10.1109/BIBM.2014.6999303
  4. Apache. [n. d.]. Airflow. https://airflow.apache.org.
  5. Parsl: Pervasive Parallel Programming in Python. In Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing (Phoenix, AZ, USA) (HPDC ’19). Association for Computing Machinery, New York, NY, USA, 25–36. https://doi.org/10.1145/3307681.3325400
  6. A. Buscemi. 2023. A Comparative Study of Code Generation using ChatGPT 3.5 across 10 Programming Languages. arXiv:2308.04477 [cs.SE]
  7. H. Chase. 2023. langchain API Reference. https://api.python.langchain.com/en/latest/api_reference.html##module-langchain.tools. Accessed: 2023-08-16.
  8. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG]
  9. Methods Included: Standardizing Computational Reuse and Portability with the Common Workflow Language. Commun. ACM 65, 6 (May 2022), 54–63. https://doi.org/10.1145/3486897
  10. A. Duque and A. Syed. 2023. Phyloflow-Parsl Implementation. https://github.com/grimloc-aduque/Phyloflow-Parsl-Implementation. Accessed: 2023-08-16.
  11. GitHub. 2022. Github Copilot. https://docs.github.com/en/copilot. Accessed: 2023-08-16.
  12. Broad Institute. 2023. Cromwell. https://github.com/broadinstitute/cromwell. Accessed: 2023-08-16.
  13. OpenAI. 2022. ChatGPT. https://chat.openai.com/chat. Accessed: 2023-08-16.
  14. OpenAI. 2023a. ChatGPT plugins: Code Interpreter. https://openai.com/blog/chatgpt-plugins##code-interpreter. Accessed: 2023-08-16.
  15. OpenAI. 2023b. GPT Models: Function Calling. https://platform.openai.com/docs/guides/gpt/function-calling. Accessed: 2023-08-16.
  16. Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv:2302.04761 [cs.CL]
  17. Toil enables reproducible, open source, big biomedical data analyses. , 314–316 pages. https://doi.org/10.1038/nbt.3772
Citations (1)

Summary

We haven't generated a summary for this paper yet.