E-commerce recommendation and search commonly rely on sparse keyword matching (e.g., BM25), which breaks down under vocabulary mismatch when user intent has limited lexical overlap with product metadata. We cast content-based recommendation as recommendation-as-retrieval: given a natural-language intent signal (a query or review), retrieve the top-K most relevant items from a large catalog via semantic similarity. We present a scalable dense retrieval system based on a two-tower bi-encoder, fine-tuned on the Amazon Reviews 2023 (Fashion) subset using supervised contrastive learning with Multiple Negatives Ranking Loss. We construct training pairs from review text (as a query proxy) and item metadata (as the positive document) and fine-tune on 50,000 sampled interactions with a maximum sequence length of 500 tokens. For efficient serving, we combine FAISS HNSW indexing with an ONNX Runtime inference pipeline using INT8 dynamic quantization. On a review-to-title benchmark over 826,402 catalog items, our approach improves Recall@10 from 0.26 (BM25) to 0.66, while meeting practical latency and model-size constraints: 6.1 ms median CPU inference latency (batch size 1) and a 4x reduction in model size. Overall, we provide an end-to-end, reproducible blueprint for taking domain-adapted dense retrieval from offline training to CPU-efficient serving at catalog scale.

翻译：电子商务推荐与搜索通常依赖于稀疏关键词匹配（如BM25），当用户意图与产品元数据的词汇重叠有限时，该方法会因词汇失配而失效。我们将基于内容的推荐建模为检索式推荐：给定自然语言意图信号（查询或评论），通过语义相似度从大型商品目录中检索前K个最相关的商品。我们提出了一种基于双塔双编码器的可扩展稠密检索系统，该系统在Amazon Reviews 2023（时尚）子集上使用带多重负样本排序损失的监督对比学习进行微调。我们以评论文本（作为查询代理）和商品元数据（作为正例文档）构建训练对，并在最大序列长度为500个标记的50,000个采样交互上进行微调。为实现高效服务，我们将FAISS HNSW索引与采用INT8动态量化的ONNX Runtime推理流水线相结合。在包含826,402个目录商品的评论-标题基准测试中，我们的方法将Recall@10从0.26（BM25）提升至0.66，同时满足实际延迟和模型规模约束：中位CPU推理延迟为6.1毫秒（批大小为1），模型规模缩减至原尺寸的1/4。总体而言，我们提供了一个端到端、可复现的技术方案，实现了领域自适应稠密检索从离线训练到目录级规模CPU高效服务的完整流程。