Open Access Open Access  Restricted Access Subscription Access

AI Supply Chain Control Center: An Agentic Retrieval-Augmented Generation Framework for Vendor Contract and Shipment Risk Analysis

Nandhini S, Santhiya M, Shrinithi N, Vijaya Sri Kesavan

Abstract


Supply-chain decision-makers routinely reconcile information held in unstructured vendor contracts with information held in structured shipment and logistics records. These sources differ in representation, access mechanisms, and analytical requirements, making cross-domain investigation slow and error-prone when performed manually. This paper presents an AI Supply Chain Control Center, a conversational decision-support prototype that unifies vendor-contract retrieval, structured shipment-data analysis, and hybrid reasoning in a single interface. The system is implemented as a Streamlit application with a LangGraph-based orchestration layer. Natural-language queries are routed to a contract Retrieval-Augmented Generation (RAG) workflow backed by ChromaDB, a structured shipping-data profiling workflow based on Pandas, or a hybrid workflow that combines both sources. A Groq-hosted large language model performs the final reasoning and response generation. The project also incorporates clause-aware document chunking for contract retrieval and structured profiling of uploaded shipment CSV files. The manuscript documents the architecture, methodology, implementation, functional capabilities, evaluation design, practical implications, and limitations of the prototype. The work is positioned as a reproducible application-level integration of agentic orchestration, RAG, and structured-data analysis for supply-chain vendor and shipment-risk investigation. Numerical benchmark claims are intentionally not reported where ground-truth datasets and measured evaluation values are not available in the project materials.

 

 


Full Text:

PDF

References


Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I. and Amodei, D. (2020), “Language models are few-shot learners”, Advances in Neural Information Processing Systems, Vol. 33, pp. 1877-1901.

Hendrycks, D., Burns, C., Chen, A. and Ball, S. (2021), “CUAD: an expert-annotated NLP dataset for legal contract review”, Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, Vol. 1.

Johnson, J., Douze, M. and Jégou, H. (2019), “Billion-scale similarity search with GPUs”, IEEE Transactions on Big Data, Vol. 7 No. 3, pp. 535-547.

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S. and Kiela, D. (2020), “Retrieval-augmented generation for knowledge-intensive NLP tasks”, Advances in Neural Information Processing Systems, Vol. 33, pp. 9459-9474.

Pournader, M., Ghaderi, H., Hassanzadegan, A. and Fahimnia, B. (2021), “Artificial intelligence applications in supply chain management”, International Journal of Production Economics, Vol. 241, 108250.

Toorajipour, R., Sohrabpour, V., Nazarpour, A., Oghazi, P. and Fischl, M. (2021), “Artificial intelligence in supply chain management: a systematic literature review”, Journal of Business Research, Vol. 122, pp. 502-517.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, Ł. and Polosukhin, I. (2017), “Attention is all you need”, Advances in Neural Information Processing Systems, Vol. 30, pp. 5998-6008.

Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, 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, Vol. 18 No. 6, 186345.


Refbacks

  • There are currently no refbacks.