CAPRAG: A Large Language Model Solution for Customer Service and Automatic Reporting using Vector and Graph Retrieval-Augmented Generation

TL;DR

CAPRAG is a hybrid retrieval-augmented generation system that uses vector and graph databases to improve customer service chatbots in digital banking, providing relevant information efficiently.

Contribution

This paper introduces CAPRAG, a novel hybrid retrieval-augmented generation framework combining vector and graph databases for enhanced banking customer service.

Findings

Effective handling of relationship-based and contextual queries

Improved customer engagement in digital banking

Efficient retrieval using vector and graph databases

Abstract

The introduction of new features and services in the banking sector often overwhelms customers, creating an opportunity for banks to enhance user experience through financial chatbots powered by large language models (LLMs). We initiated an AI agent designed to provide customers with relevant information about banking services and insights from annual reports. We proposed a hybrid Customer Analysis Pipeline Retrieval-Augmented Generation (CAPRAG) that effectively addresses both relationship-based and contextual queries, thereby improving customer engagement in the digital banking landscape. To implement this, we developed a processing pipeline to refine text data, which we utilized in two main frameworks: Vector RAG and Graph RAG. This dual approach enables us to populate both vector and graph databases with processed data for efficient retrieval. The Cypher query component is employed to effectively query the graph database. When a user submits a query, it is first expanded by a query expansion module before being routed to construct a final query from the hybrid Knowledge Base (KB). This final query is then sent to an open-source LLM for response generation. Overall, our innovative, designed to international banks, serves bank's customers in an increasingly complex digital environment, enhancing clarity and accessibility of information.