Vector Databases and Retrieval-Augmented Generation for Accurate AI-Driven Project Estimation
Abstract: Large Language Models (LLMs) can analyse unstructured enterprise documents but lack organizational memory, resulting in inconsistent and unreliable software project estimations. Retrieval-Augmented Generation (RAG) addresses this limitation by integrating vector databases that store semantic embeddings of historical project artifacts. Using similarity-based retrieval rather than keyword matching, RAG enables LLMs to ground estimations in relevant past projects despite variations in terminology or technology. This evidence-driven approach improves estimation accuracy, consistency, and explainability, providing a scalable foundation for AI-assisted software project estimation in enterprise environments.
Keywords: Vector Database, Retrieval-Augmented Generation (RAG), Large Language Models, Software Project Estimation, Semantic Search, AI Decision Support Systems
How to Cite?: Sangeeta Manna (nee Datta), "Vector Databases and Retrieval-Augmented Generation for Accurate AI-Driven Project Estimation", Volume 15 Issue 1, January 2026, International Journal of Science and Research (IJSR), Pages: 100-104, https://www.ijsr.net/getabstract.php?paperid=SR251231215738, DOI: https://dx.doi.org/10.21275/SR251231215738