Developing A Chatbot: A Hybrid Approach Using Deep Learning and RAG
Vrajkumar Patel, Parth Tejani, Jay Parekh, Kai Huang, Xing Tan · 2024
The rapid growth of online shopping has underscored the need for effective customer service techniques that go beyond traditional channels such as email, mobile responses, and FAQs. In this dynamic landscape, chatbots have emerged as indispensable tools for enhancing customer satisfaction and streamlining consumer interactions. These artificial intelligence-powered chatbots are reshaping the online retail industry by providing human-like engagement. Our study introduces a hybrid approach to developing a context-aware chatbot. We combine intent recognition using deep learning models with a retrieval-based argument approach, leveraging OpenAI's Large Language Model (LLM). Specifically, we compare two intent recognition models: LSTM and BERT. Additionally, we implement a retriever system that gathers relevant supporting data from a vector database storing the vector embeddings of our products. The outcome is a dynamic and customer-centric chatbot experience that harnesses the capabilities of OpenAI's LLM. Finally, we have built an Electronic Shopping Assistant capable of answering a wide range of product-related questions based on our extensive knowledge base.