[Paper Review] Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizations

Keivalya Pandya, Mehfuza S. Holia|arXiv (Cornell University)|Oct 9, 2023

AI in Service Interactions32 citations

TL;DR

The paper presents Sahaay, an open-source GPT chatbot built with LangChain for organizational customer service, using web scraping, embeddings, and fine-tuning of multiple LLMs to enable real-time, context-aware support. It argues for moving beyond FAQs toward personalized, scalable interactions across industries, with implementation details and use cases in educational settings.

ABSTRACT

In the digital age, the dynamics of customer service are evolving, driven by technological advancements and the integration of Large Language Models (LLMs). This research paper introduces a groundbreaking approach to automating customer service using LangChain, a custom LLM tailored for organizations. The paper explores the obsolescence of traditional customer support techniques, particularly Frequently Asked Questions (FAQs), and proposes a paradigm shift towards responsive, context-aware, and personalized customer interactions. The heart of this innovation lies in the fusion of open-source methodologies, web scraping, fine-tuning, and the seamless integration of LangChain into customer service platforms. This open-source state-of-the-art framework, presented as "Sahaay," demonstrates the ability to scale across industries and organizations, offering real-time support and query resolution. Key elements of this research encompass data collection via web scraping, the role of embeddings, the utilization of Google's Flan T5 XXL, Base and Small language models for knowledge retrieval, and the integration of the chatbot into customer service platforms. The results section provides insights into their performance and use cases, here particularly within an educational institution. This research heralds a new era in customer service, where technology is harnessed to create efficient, personalized, and responsive interactions. Sahaay, powered by LangChain, redefines the customer-company relationship, elevating customer retention, value extraction, and brand image. As organizations embrace LLMs, customer service becomes a dynamic and customer-centric ecosystem.

Motivation & Objective

• Motivate a shift from traditional FAQ-based customer service to responsive, context-aware interactions.
• Propose an open-source framework (Sahaay) that scales across industries using LangChain.
• Describe data collection, knowledge retrieval, and model integration techniques for organizational use.
• Demonstrate the approach with use cases in an educational institution.

Proposed method

• Data collection via web scraping to build organizational knowledge base.
• Use of embeddings for knowledge retrieval and query understanding.
• Integration of Google's Flan T5 XXL, Base, and Small language models within the LangChain-based pipeline.
• Development of an open-source framework named Sahaay for real-time support and query resolution.
• System architecture combining open-source tooling to deploy a customizable chatbot across platforms.

Experimental results

Research questions

• RQ1 Can a LangChain-based open-source framework provide real-time, context-aware customer support for organizations?
• RQ2 How effective are embeddings and multi-LLM configurations (Flan T5 XXL, Base, Small) for knowledge retrieval in a corporate chatbot?
• RQ3 What is the impact of a customized GPT chatbot on customer retention, value extraction, and brand image?
• RQ4 How can web-scraped data be transformed into a reliable knowledge source for organizational FAQs and support queries?

Key findings

• Sahaay demonstrates the feasibility of an open-source LangChain-based chatbot for organizational use.
• The approach leverages web scraping and embeddings to support knowledge retrieval and personalized responses.
• Educational institution use cases illustrate real-time query resolution and potential benefits in customer-facing contexts.
• The framework positions LangChain-powered chatbots to enhance customer retention and brand perception.