urimai

AI-powered SQL answer engine — ask questions about your databases in plain English.

What is urimai?

urimai lets you query SQLite databases and CSV files using natural language. Point it at your data, ask a question, and urimai figures out the right SQL, runs it, and explains the results. It also profiles your columns and runs data-quality checks automatically when you register a database, so you can understand your dataset before you start exploring.

Key features

• Natural language SQL — ask questions in plain English, get SQL + results + explanations
• CSV import — drop in a CSV file and urimai converts it to SQLite with LLM-powered schema inference
• Data profiling — automatic column-level statistics (min, max, nulls, distributions)
• Quality checks — data-quality rules generated and evaluated by the LLM
• Export — data dictionaries in Excel or Markdown
• Multi-provider LLM — supports Google Gemini and OpenAI out of the box

Requirements

• Python 3.11 or later — download here
• An API key from Google Gemini or OpenAI

Quick start

pip install urimai        # install from PyPI
urim setup                # configure your API provider and key
urim init ./mydata.db     # register a SQLite database (or CSV)
urim chat mydata          # start asking questions

Command reference

Links

• Documentation: https://urimai.readthedocs.io/en/latest/
• PyPI: https://pypi.org/project/urimai/
• Source: https://github.com/shivakharbanda/urimAI

License

urimai is licensed under the Elastic License 2.0 (ELv2). You are free to use, copy, distribute, and modify the software for any purpose except providing it as a managed service to third parties. See the LICENSE file for full terms.

Contributing

Contributions are welcome! See the developer guide for setup instructions and project architecture.