1887

Abstract

Summary

The recent success of Large Language Models (LLMs) is linked to their impressive applications in the daily lives of people, driving various industries to seek tailored solutions for specific contexts. This work introduces ChatPetrophysics BR, a specialist chatbot assistant that empowers users to load and manipulate structured data from Petrobras’ E&P database through a natural language interface. The methodology employs a specialized agent that orchestrates the application’s interactions and reasoning through a flexible chain of LLM calls, providing greater control over its behaviour and enabling specific actions. It also leverages the Retrieval-Augmented Generation (RAG) technique to precisely identify user needs. The assistant can import and explore structured well and field data from the database, create graphs and automatically manipulate spreadsheets. The results showcase examples of successful interactions, such as the creation of cross-plots and data manipulations for Routine Core Analysis (RCAL), that are useful for increasing petrophysicists’ productivity.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202539085
2025-03-24
2026-02-08

  • From This Site

    /content/papers/10.3997/2214-4609.202539085
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Chase, H. [2022]. LangChain. https://github.com/langchain-ai/langchain
     [Google Scholar]
  2. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Kütler, H., Lewis, M., Yih, W., Rocktaschel, T., Riedel, S., and Kiela, D. [2020]. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Advances in Neural Information Processing Systems (Vol. 33, pp. 9459–9474). https://proceedings.neurips.cc/paper/2020/file/6b493230205f780elbc26945df7481e5-Paper.pdf
     [Google Scholar]
  3. Myers, D., Mohawesh, R., Chellaboina, V. I., Sathvik, A. L., Venkatesh, P., Ho, Y.-H., Henshaw, H., Alhawawreh, M., Berdik, D., and Jararweh, Y. [2024]. Foundation and large language models: fundamentals, challenges, opportunities, and social impacts. Cluster Computing, 27(1), 1–26. https://doi.org/10.1007/s10586-023-04203-7
     [Google Scholar]
  4. OpenAI. [2024a]. Embedding models. https://platform.openai.com/docs/guides/embeddings#embedding-models
     [Google Scholar]
  5. OpenAI. [2024b]. GPT-4o. https://platform.openai.com/docs/models/gpt-4o#gpt-4o
     [Google Scholar]
  6. Patil, R., and Gudivada, V. [2024]. A Review of Current Trends, Techniques, and Challenges in Large Language Models (LLMs). Applied Sciences, 14(5), 2074. https://doi.org/10.3390/app14052074
     [Google Scholar]
  7. QDrant. [2024]. QDrant. https://github.com/qdrant/qdrant
     [Google Scholar]
  8. SeatGeek. [2020]. fuzzywuzzy. https://pypi.org/project/fuzzywuzzy/
     [Google Scholar]
  9. Streamlit. [2024]. Streamlit. https://github.com/streamlit/streamlit
     [Google Scholar]
  10. Topsakal, O., and Akinci, T. C. [2023]. Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast. International Conference on Applied Engineering and Natural Sciences, 1(1), 1050–1056. https://doi.org/10.59287/icaens.1127
     [Google Scholar]
  11. Vandersmith, R. [2023]. pandas-gpt. https://pypi.org/project/pandas-gpt/0.6.0/
     [Google Scholar]
  12. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. [2017]. Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems, 6000–6010. Red Hook, NY, USA: Curran Associates Inc.
     [Google Scholar]
  13. Wang, L., Ma, C, Feng, X., Zhang, Z., Yang, H, Zhang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., and Wen, J. [2024]. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6), 186345. https://doi.org/10.1007/s11704-024-40231-1
     [Google Scholar]
/content/papers/10.3997/2214-4609.202539085
Loading
ChatPetrophysics BR: Experimenting Generative AI on Structured E&P Data
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202539085
/content/papers/10.3997/2214-4609.202539085
/content/papers/10.3997/2214-4609.202539085
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error