Design and Implementation of a Real-Time RAG-Based Customer Relationship Management System Using Event-Driven Knowledge Updates and Vector Embeddings

View at publisher Summarise with VIRAT
Authors: Ivan Mijić, Bećir Isaković
Cited by: 0
References: 15

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Production CRM systems increasingly use large language models, yet typical Retrieval-Augmented Generation (RAG) implementations suffer from knowledge staleness due to 5–10 min batch processing cycles. This paper presents a streaming RAG architecture for business CRM applications that provides real-time knowledge updates with average document-to-query propagation latency of 3.1 s and strong retrieval quality. The event-driven system uses Apache Kafka for document ingestion, Rust microservices for embedding generation, PostgreSQL with pgvector for vector storage, and GPT-4 for response generation. On 62 insurance policy documents from 20 users and 102 test queries, mean document-to-query propagation latency was$3.1 ~\mathrm{s}, 75-150 \times$faster than batch processing, with retrieval quality metrics of Precision@5 = 0.398, MRR$=0.938$, and NDCG${@} 10=0.942$consistent with values reported in prior literature. Additional load testing with simulated users verified production-grade performance stability (P95 latency$

Fields of Study & Subjects

Topic Modeling Information Retrieval and Search Behavior Advanced Database Systems and Queries

Publication details

Pages
1–4
Publication date
24 February 2026
Language
EN