# DS SERVE: A Framework for Efficient and Scalable Neural Retrieval

arXiv: https://arxiv.org/abs/2602.22224 · HTML: https://mlsanity.com/paper/2602.22224/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 5 of 5)

- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [Scaling Retrieval-Based Language Models with a Trillion-Token Datastore](https://mlsanity.com/paper/2407.12854/) (2024)
- [HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving](https://mlsanity.com/paper/2507.09138/) (2025)

## Built on by (most cited first, 2 of 2)

- [RAG over Thinking Traces Can Improve Reasoning Tasks](https://mlsanity.com/paper/2605.03344/) (2026)
- [PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.28344/) (2026)

## Abstract (arXiv)

We present DS-Serve, a framework that transforms large-scale text datasets, comprising half a trillion tokens, into a high-performance neural retrieval system. DS-Serve offers both a web interface and API endpoints, achieving low latency with modest memory overhead on a single node. The framework also supports inference-time trade-offs between latency, accuracy, and result diversity. We anticipate that DS-Serve will be broadly useful for a range of applications, including large-scale retrieval-augmented generation (RAG), training data attribution, training search agents, and beyond.