Text-to-SQL for Enterprise Data Analytics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913949527572480 |
|---|---|
| author | Chen, Albert Bundele, Manas Ahlawat, Gaurav Stetz, Patrick Wang, Zhitao Fei, Qiang Jung, Donghoon Chu, Audrey Jayaraman, Bharadwaj Panth, Ayushi Arora, Yatin Jain, Sourav Varma, Renjith Ilin, Alexey Melnychuk, Iuliia Chueh, Chelsea Sil, Joyan Wang, Xiaofeng |
| author_facet | Chen, Albert Bundele, Manas Ahlawat, Gaurav Stetz, Patrick Wang, Zhitao Fei, Qiang Jung, Donghoon Chu, Audrey Jayaraman, Bharadwaj Panth, Ayushi Arora, Yatin Jain, Sourav Varma, Renjith Ilin, Alexey Melnychuk, Iuliia Chueh, Chelsea Sil, Joyan Wang, Xiaofeng |
| contents | The introduction of large language models has brought rapid progress on Text-to-SQL benchmarks, but it is not yet easy to build a working enterprise solution. In this paper, we present insights from building an internal chatbot that enables LinkedIn's product managers, engineers, and operations teams to self-serve data insights from a large, dynamic data lake. Our approach features three components. First, we construct a knowledge graph that captures up-to-date semantics by indexing database metadata, historical query logs, wikis, and code. We apply clustering to identify relevant tables for each team or product area. Second, we build a Text-to-SQL agent that retrieves and ranks context from the knowledge graph, writes a query, and automatically corrects hallucinations and syntax errors. Third, we build an interactive chatbot that supports various user intents, from data discovery to query writing to debugging, and displays responses in rich UI elements to encourage follow-up chats. Our chatbot has over 300 weekly users. Expert review shows that 53% of its responses are correct or close to correct on an internal benchmark set. Through ablation studies, we identify the most important knowledge graph and modeling components, offering a practical path for developing enterprise Text-to-SQL solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Text-to-SQL for Enterprise Data Analytics Chen, Albert Bundele, Manas Ahlawat, Gaurav Stetz, Patrick Wang, Zhitao Fei, Qiang Jung, Donghoon Chu, Audrey Jayaraman, Bharadwaj Panth, Ayushi Arora, Yatin Jain, Sourav Varma, Renjith Ilin, Alexey Melnychuk, Iuliia Chueh, Chelsea Sil, Joyan Wang, Xiaofeng Computation and Language Artificial Intelligence Databases Human-Computer Interaction The introduction of large language models has brought rapid progress on Text-to-SQL benchmarks, but it is not yet easy to build a working enterprise solution. In this paper, we present insights from building an internal chatbot that enables LinkedIn's product managers, engineers, and operations teams to self-serve data insights from a large, dynamic data lake. Our approach features three components. First, we construct a knowledge graph that captures up-to-date semantics by indexing database metadata, historical query logs, wikis, and code. We apply clustering to identify relevant tables for each team or product area. Second, we build a Text-to-SQL agent that retrieves and ranks context from the knowledge graph, writes a query, and automatically corrects hallucinations and syntax errors. Third, we build an interactive chatbot that supports various user intents, from data discovery to query writing to debugging, and displays responses in rich UI elements to encourage follow-up chats. Our chatbot has over 300 weekly users. Expert review shows that 53% of its responses are correct or close to correct on an internal benchmark set. Through ablation studies, we identify the most important knowledge graph and modeling components, offering a practical path for developing enterprise Text-to-SQL solutions. |
| title | Text-to-SQL for Enterprise Data Analytics |
| topic | Computation and Language Artificial Intelligence Databases Human-Computer Interaction |
| url | https://arxiv.org/abs/2507.14372 |