AI-powered SQL answer engine - ask questions about your databases
Project description
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
| Command | Description |
|---|---|
urim setup |
First-time setup wizard (provider, API key, name) |
urim init <path> |
Register a SQLite database or CSV file |
urim list |
List all registered databases |
urim chat <name> |
Interactive chat session with a database |
urim sync <name> |
Re-sync schema metadata after data changes |
urim config [key] [value] |
View or modify settings |
urim export <name> |
Export data dictionary (xlsx or markdown) |
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.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file urimai-0.1.5.tar.gz.
File metadata
- Download URL: urimai-0.1.5.tar.gz
- Upload date:
- Size: 82.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
edf0cc85be4a8cfcea1eaa8353ebe2e7c9826810de89fa3deeb88dc79d21ce1e
|
|
| MD5 |
536937b4d8cecbfbfde7329ce14b39f0
|
|
| BLAKE2b-256 |
ccb52dfc30724506f3f9128192af58398a3779458945c8863f9a13e10f498e04
|
Provenance
The following attestation bundles were made for urimai-0.1.5.tar.gz:
Publisher:
python-publish.yml on shivakharbanda/urimAI
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
urimai-0.1.5.tar.gz -
Subject digest:
edf0cc85be4a8cfcea1eaa8353ebe2e7c9826810de89fa3deeb88dc79d21ce1e - Sigstore transparency entry: 893697073
- Sigstore integration time:
-
Permalink:
shivakharbanda/urimAI@743585b1dc5b78592701ae68619949f0b7e192ff -
Branch / Tag:
refs/tags/v0.1.5 - Owner: https://github.com/shivakharbanda
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@743585b1dc5b78592701ae68619949f0b7e192ff -
Trigger Event:
release
-
Statement type:
File details
Details for the file urimai-0.1.5-py3-none-any.whl.
File metadata
- Download URL: urimai-0.1.5-py3-none-any.whl
- Upload date:
- Size: 98.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
76a5469557df37210189f9f9213a38815d4bae2ad2e869a7cf9c2ae840f5202e
|
|
| MD5 |
999139dcf3b7d7780d79d299cd40b580
|
|
| BLAKE2b-256 |
3e05df08b40d91e619027c882cc9b7c005d4358e275a566dba71dacde6ea8a6b
|
Provenance
The following attestation bundles were made for urimai-0.1.5-py3-none-any.whl:
Publisher:
python-publish.yml on shivakharbanda/urimAI
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
urimai-0.1.5-py3-none-any.whl -
Subject digest:
76a5469557df37210189f9f9213a38815d4bae2ad2e869a7cf9c2ae840f5202e - Sigstore transparency entry: 893697086
- Sigstore integration time:
-
Permalink:
shivakharbanda/urimAI@743585b1dc5b78592701ae68619949f0b7e192ff -
Branch / Tag:
refs/tags/v0.1.5 - Owner: https://github.com/shivakharbanda
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
python-publish.yml@743585b1dc5b78592701ae68619949f0b7e192ff -
Trigger Event:
release
-
Statement type: