Search papers, labs, and topics across Lattice.
This paper introduces a multi-turn conversational shopping assistant that leverages a self-refreshing retrieval system to operate over dynamic e-commerce catalogues. By utilizing per-item hashes to track changes in product listings, the system efficiently updates its vector index without the need for complete re-indexing, allowing for real-time recommendations. The implementation, demonstrated through a WhatsApp interface, ensures that users receive the most current product information immediately after synchronization, enhancing the shopping experience in live environments.
Real-time updates in conversational recommendations can transform the e-commerce landscape by ensuring users always see the latest products without lag.
Conversational recommender systems based on large language models (LLMs) are usually evaluated on static, pre-indexed item collections, yet e-commerce catalogues change continuously as products are added or removed, repriced, and restocked. We present a merchant-agnostic, multi-turn conversational shopping assistant that operates over such live catalogues. Its central component is a self-refreshing retriever that ingests a merchant product feed, enriches the records, and synchronizes them into a vector index. On each run, per-item hashes identify which products are new, changed, deleted, or unchanged, so only the delta is processed rather than rebuilding the whole catalogue. A controller-based dialogue layer consumes this index, using an LLM only for intent classification and preference elicitation while retrieval, reranking, and diversity selection run as dedicated functions. Our demonstration is a WhatsApp shopping assistant in which catalogue changes reach the recommendations after the next successful sync. A live chatbot, documentation, and a recorded walkthrough are available at https://github.com/infobip/infobip-agentic-crs.
