NeuralSearchX: Serving a Multi-billion-parameter Reranker for Multilingual Metasearch at a Low Cost

TL;DR

NeuralSearchX introduces a cost-effective, large multilingual reranker for metasearch engines that outperforms Google API in domain-specific retrieval tasks, with competitive efficiency and near state-of-the-art results.

Contribution

The paper presents NeuralSearchX, a unified, large reranking model architecture optimized for cost and performance in multilingual metasearch applications.

Findings

Outperforms Google API in domain-specific nDCG@10 scores

Achieves competitive QPS with lower costs

Close to state-of-the-art on public benchmarks

Abstract

The widespread availability of search API's (both free and commercial) brings the promise of increased coverage and quality of search results for metasearch engines, while decreasing the maintenance costs of the crawling and indexing infrastructures. However, merging strategies frequently comprise complex pipelines that require careful tuning, which is often overlooked in the literature. In this work, we describe NeuralSearchX, a metasearch engine based on a multi-purpose large reranking model to merge results and highlight sentences. Due to the homogeneity of our architecture, we could focus our optimization efforts on a single component. We compare our system with Microsoft's Biomedical Search and show that our design choices led to a much cost-effective system with competitive QPS while having close to state-of-the-art results on a wide range of public benchmarks. Human evaluation on two domain-specific tasks shows that our retrieval system outperformed Google API by a large margin in terms of nDCG@10 scores. By describing our architecture and implementation in detail, we hope that the community will build on our design choices. The system is available at https://neuralsearchx.nsx.ai.