#62 · Primary category: Business Intelligence & Analytics

dataherald

ai database finetuning llm nl-to-sql rag sql text-to-sql

Interact with your SQL database, Natural Language to SQL using LLMs

Project last updated:07/24/24

GitHub Stars

3.6K

Forks

261

Contributors

21

License

Apache-2.0

Why we included this project

Business teams that need answers from a relational database but can't write SQL are the natural audience here. Dataherald wraps a text-to-SQL engine in a self-hostable API, so people can ask questions in plain English and get results without waiting on a data analyst. Beyond the core engine, the monorepo includes an enterprise layer with authentication and user management, an admin console for configuring and monitoring queries, and a Slackbot for asking from chat. There's also built-in evaluation and fine-tuning support, which helps you tighten accuracy over time instead of treating the model as a black box. If you already have a data stack and want a deployment-ready bridge between conversational questions and SQL, this is a practical fit.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category