NeedleDB: A Generative-AI Based System for Accurate and Efficient Image Retrieval using Complex Natural Language Queries
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908919140450304 |
|---|---|
| author | Erfanian, Mahdi Asudeh, Abolfazl |
| author_facet | Erfanian, Mahdi Asudeh, Abolfazl |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27464 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NeedleDB: A Generative-AI Based System for Accurate and Efficient Image Retrieval using Complex Natural Language Queries Erfanian, Mahdi Asudeh, Abolfazl Databases Multimedia 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. |
| title | NeedleDB: A Generative-AI Based System for Accurate and Efficient Image Retrieval using Complex Natural Language Queries |
| topic | Databases Multimedia |
| url | https://arxiv.org/abs/2603.27464 |