An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models

TL;DR

This paper introduces an interactive multi-modal query answering system that combines a novel retrieval framework, a navigation graph index, and large language models to handle complex multi-modal queries efficiently.

Contribution

It presents a new multi-modal retrieval framework and navigation graph index integrated with LLMs, enabling flexible, efficient, and precise multi-modal query answering.

Findings

Effective multi-modal retrieval demonstrated with high accuracy.

Flexible system architecture supports diverse embedding models and indexes.

Enhanced retrieval efficiency through advanced pruning techniques.

Abstract

Retrieval-augmented Large Language Models (LLMs) have reshaped traditional query-answering systems, offering unparalleled user experiences. However, existing retrieval techniques often struggle to handle multi-modal query contexts. In this paper, we present an interactive Multi-modal Query Answering (MQA) system, empowered by our newly developed multi-modal retrieval framework and navigation graph index, integrated with cutting-edge LLMs. It comprises five core components: Data Preprocessing, Vector Representation, Index Construction, Query Execution, and Answer Generation, all orchestrated by a dedicated coordinator to ensure smooth data flow from input to answer generation. One notable aspect of MQA is its utilization of contrastive learning to assess the significance of different modalities, facilitating precise measurement of multi-modal information similarity. Furthermore, the system achieves efficient retrieval through our advanced navigation graph index, refined using computational pruning techniques. Another highlight of our system is its pluggable processing framework, allowing seamless integration of embedding models, graph indexes, and LLMs. This flexibility provides users diverse options for gaining insights from their multi-modal knowledge base. A preliminary video introduction of MQA is available at https://youtu.be/xvUuo2ZIqWk.