Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs
Summary: Chat2Data enables natural-language analysis of unstructured and structured data. Its three-layer design combines domain-aware RAG, vector databases to reduce LLM calls, and pipeline agents for decomposed multi-round reasoning—targeting hallucination, cost, and accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xinyang Zhao (Tsinghua University)
- 2. Xuanhe Zhou (Tsinghua University)
- 3. Guoliang Li (Tsinghua University)
BibTeX Citation
@article{zhao_vldb24,
title = {{Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs}},
author = {Zhao, Xinyang and Zhou, Xuanhe and Li, Guoliang},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {12},
pages = {4481--4484},
doi = {10.14778/3685800.3685905},
url = {https://doi.org/10.14778/3685800.3685905},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 12 of 12 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,658 | D-Bot: Database Diagnosis System using Large Language Models | 2024 | VLDB | 9.9642078e-05 |
| 1,991 | RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation | 2021 | VLDB | 9.2383849e-05 |
| 2,690 | Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection | 2022 | VLDB | 8.1258173e-05 |
| 3,697 | Learned Index: A Comprehensive Experimental Evaluation | 2023 | VLDB | 7.0882335e-05 |
| 8,202 | Grep: A Graph Learning Based Database Partitioning System | 2023 | SIGMOD | 5.378708e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,008 | iPDB: SQL with ML and LLM Predicates (Towards a Database Engine for AI) | 2026 | VLDB |
| 2 | 11,284 | CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines | 2025 | VLDB |
| 3 | 7,318 | An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models | 2024 | VLDB |
| 4 | 11,379 | Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models | 2025 | VLDB |
| 5 | 8,632 | DocDB: A Database for Unstructured Document Analysis | 2025 | VLDB |
| 6 | 2,606 | Text2SQL is Not Enough: Unifying AI and Databases with TAG | 2025 | CIDR |
| 7 | 10,626 | Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs | 2026 | SIGMOD |
| 8 | 11,029 | Graph-Based Retrieval-Augmented Generation: Applications, Challenges, Solutions, and Opportunities | 2026 | VLDB |
| 9 | 10,686 | SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL | 2026 | SIGMOD |
| 10 | 5,149 | LLM for Data Management | 2024 | VLDB |