Skip to main content

AI-powered SQL answer engine - ask questions about your databases

Project description

urimai

AI-powered SQL answer engine — ask questions about your databases using AI.

Installation

# From PyPI
pip install urimai

# From source
git clone https://github.com/shivakharbanda/urimAI
cd urimAI
uv sync

Quick Start

urim setup              # First-time config wizard
urim init ./chinook.db  # Register a database
urim chat chinook       # Start chatting

Commands

Command Description
urim setup Run 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 <db_name> Start interactive chat session
urim sync <db_name> Re-sync database schema metadata
urim config [key] [value] View or modify settings
urim export <db_name> Export data dictionary (xlsx/markdown)

urim setup

Run the first-time setup wizard to configure your AI provider, API key, and display name.

urim init <path>

Register a SQLite database or CSV file. CSV files are automatically converted to SQLite with LLM-powered schema inference.

urim init ./my_database.db
urim init ./data.csv --name my_data --table-name sales --delimiter "," --encoding utf-8
Option Description
--name Custom name for the database (default: filename)
--table-name Table name for CSV import (default: LLM-suggested)
--delimiter CSV delimiter character (default: ,)
--encoding CSV file encoding (default: utf-8)

urim list

List all registered databases.

urim list

urim chat <db_name>

Start an interactive chat session with a registered database.

urim chat chinook

urim sync <db_name>

Re-sync schema metadata for a registered database. Useful after the source data changes.

urim sync chinook

urim config [key] [value]

View or modify configuration settings.

urim config                          # Show all settings
urim config provider.default openai  # Set default provider
urim config --reset                  # Reset to defaults
urim config --path                   # Show directory paths
Option Description
--reset Reset config to defaults
--path Show config/data directory paths
(no args) Show all current settings

urim export <db_name>

Export data dictionary for a registered database.

urim export chinook
urim export chinook -f markdown -o chinook_dict.md
urim export chinook --include-sample-data
Option Description
--format / -f Output format: xlsx or markdown (default: xlsx)
--output / -o Output file path
--include-sample-data Include sample data rows (default: off)
--include-profile Include column profile statistics (default: on)
--include-quality Include quality report data (default: on)

Global option

Option Description
--model <provider> Override the default AI provider for a single command

Configuration

  • Config file: ~/.urimai/config.toml
  • API keys: stored in the system keyring, or set via environment variables (GOOGLE_API_KEY, OPENAI_API_KEY)
  • Supported providers: Google Gemini, OpenAI

License

Elastic License 2.0 (ELv2)

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

urimai-0.1.1.tar.gz (82.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

urimai-0.1.1-py3-none-any.whl (98.4 kB view details)

Uploaded Python 3

File details

Details for the file urimai-0.1.1.tar.gz.

File metadata

  • Download URL: urimai-0.1.1.tar.gz
  • Upload date:
  • Size: 82.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.14

File hashes

Hashes for urimai-0.1.1.tar.gz
Algorithm Hash digest
SHA256 3d6e0cbfcc9e2443248a39f7fe32d0be202db73a85a89300b2fd9f8f958304b6
MD5 454e41b6028a01cda4d7ea3274c71e62
BLAKE2b-256 327880fa3e4765523d7b23b4599a6979066b11ce616d2b7d86c1e92093078c2f

See more details on using hashes here.

File details

Details for the file urimai-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: urimai-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 98.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.14

File hashes

Hashes for urimai-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 6f687b07a6d482a7fb97b47ad93fddea0ea26b1fcb53a566ae3362dc618b67b6
MD5 55f38d65ce9bd5e33f9b5fa5eba278f6
BLAKE2b-256 6c579b7f3a85dee1b9a0c35e51f66602289e054a72dc8b061e39caf0bd1f0522

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page