Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web
This provides an open-source tool for web developers to integrate chatbots, addressing transparency and energy efficiency issues, though it is incremental as it builds on existing RAG methods.
The authors tackled the problem of limited deployment of LLM-powered chatbots on websites due to closed-source solutions by developing Talk2X, an open-source toolkit using retrieval-augmented generation and an automatically generated vector database. Their evaluation showed that Talk2X significantly improved task completion time, correctness, and user experience compared to standard website interaction.
Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet, predominantly closed-sourced solutions limit proliferation among web hosts and suffer from a lack of transparency with regard to implementation details and energy efficiency. In this work, we propose our openly available agent Talk2X leveraging an adapted retrieval-augmented generation approach (RAG) combined with an automatically generated vector database, benefiting energy efficiency. Talk2X's architecture is generalizable to arbitrary websites offering developers a ready to use tool for integration. Using a mixed-methods approach, we evaluated Talk2X's usability by tasking users to acquire specific assets from an open science repository. Talk2X significantly improved task completion time, correctness, and user experience supporting users in quickly pinpointing specific information as compared to standard user-website interaction. Our findings contribute technical advancements to an ongoing paradigm shift of how we access information on the web.