NeedleDB: A Generative-AI Based System for Accurate and Efficient Image Retrieval using Complex Natural Language Queries

TL;DR

NeedleDB is an open-source database system that uses generative AI to improve image retrieval accuracy for complex natural language queries, outperforming existing contrastive-learning methods.

Contribution

It introduces a generative AI approach for visual query synthesis, transforming text-to-image retrieval into image-to-image search, with a scalable architecture and provable error bounds.

Findings

Improves Mean Average Precision by up to 93% over baselines.

Achieves sub-second query latency on challenging benchmarks.

Provides a full-featured, modular system with CLI and Web UI.

Abstract

We demonstrate NeedleDB, an open-source, deployment-ready database system for answering complex natural language queries over image data. Unlike existing approaches that rely on contrastive-learning embeddings (e.g., CLIP), which degrade on compositional or nuanced queries, NeedleDB leverages generative AI to synthesize guide images that represent the query in the visual domain, transforming the text-to-image retrieval problem into a more tractable image-to-image search. The system aggregates nearest-neighbor results across multiple vision embedders using a weighted rank-fusion strategy grounded in a Monte Carlo estimator with provable error bounds. NeedleDB ships with a full-featured command-line interface (needlectl), a browser-based Web UI, and a modular microservice architecture backed by PostgreSQL and Milvus. On challenging benchmarks, it improves Mean Average Precision by up to 93% over the strongest baseline while maintaining sub-second query latency. In our demonstration, attendees interact with NeedleDB through three hands-on scenarios that showcase its retrieval capabilities, data ingestion workflow, and pipeline configurability.