Lessons From Building E-Commerce Search on Qdrant - Qdrant

This post details building an e-commerce search system on Qdrant, focusing on practical implementation strategies. Key contributions include: demonstrating hybrid retrieval with dense and BM25 sparse vectors fused in a single query; advocating for filtering within the query for efficiency and accurate facet counts; emphasizing embedding relevant product fields over using larger models; proposing quantization in RAM without rescoring for performance gains; shifting personalization from retrieval to ranking for better control; implementing merchandising as weighted formulas in a single rescore pass; and introducing a multi-faceted evaluation approach using an LLM judge, recall@10, intrusion, and persona overlap metrics. It also identifies a specific gotcha related to query fusion and sharding.