Skip to main content

AI-powered Natural Language to SQL engine for Spark

Project description

Sqara

AI-powered Natural Language to SQL engine for Apache Spark


🚀 What is Sqara?

Sqara is a lightweight AI-powered engine that converts natural language into Spark SQL and executes it directly on Apache Spark.

It is designed to simplify data access for analysts, engineers, and AI applications by removing the need to manually write SQL.


⚠️ Migration Notice

This project was previously published as querix.
All future development, updates, and releases continue under sqara.


✨ Features

  • 🧠 Natural Language → SQL conversion
  • ⚡ Direct execution on Apache Spark
  • 📊 Works with structured datasets (tables, views)
  • 🔌 Simple Python API
  • 🧩 Extensible design for future AI providers
  • 🚫 No dependency on external AI services (optional integration later)

📦 Installation

pip install sqara

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

sqara-0.3.4.tar.gz (3.4 kB view details)

Uploaded Source

Built Distribution

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

sqara-0.3.4-py3-none-any.whl (4.0 kB view details)

Uploaded Python 3

File details

Details for the file sqara-0.3.4.tar.gz.

File metadata

  • Download URL: sqara-0.3.4.tar.gz
  • Upload date:
  • Size: 3.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for sqara-0.3.4.tar.gz
Algorithm Hash digest
SHA256 98453295acafa5eb78ee28e5e804c786cd52899645f751c2b41c28127c414f7d
MD5 af8d64942f4379c4613cc1b289fdd55d
BLAKE2b-256 fefc4f4c10e6cb354d5992395842d2a639836ee813bc3baa222d0f091f1bf05f

See more details on using hashes here.

File details

Details for the file sqara-0.3.4-py3-none-any.whl.

File metadata

  • Download URL: sqara-0.3.4-py3-none-any.whl
  • Upload date:
  • Size: 4.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for sqara-0.3.4-py3-none-any.whl
Algorithm Hash digest
SHA256 f33a4dd7ebe1d12fa2965e25d285e36eb9d3a1a75cc2c2a073196e126a24ffc6
MD5 db857f99eefed26b2ce05116b6ed9355
BLAKE2b-256 351747bbace7dd737081bb635fa3e0a4d5a55ee1c4e351720b490cd2e4e3fa1f

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