Let STW.AI write your SQL for you

The fastest way to get actionable insights from your database just by asking questions

Whitepaper: How to get high SQL accuracy rates using AI

TLDR: It all has to do with the training data you give it, which is what STW AI helps with.

"Why use AI to chat with your database in the first place? To start, it allows you spend less time writing SQL and more time generating insights on your data. You no longer have to be an expert in SQL to get information from the database. And if you are an expert, save some time writing a query when you can just ask for it. In fact, everyone benefits by being able to ask the database about business questions and getting the answer; have STW find the relevant tables and columns across your data estate."

Anoop Mishra

Senior Product Manager, Azure SQL Database

Read More On

Why STW.AI?

Open Source

The STW Python package and the various frontend integrations are all open-source. You can run Vanna on your own infrastructure.

High accuracy on datasets

STW’s capabilities are tied to the training data you give it. More training data means better accuracy for large and complex datasets.

Designed for security

Your database contents are never sent to the LLM unless you specifically enable features that require it.

Self learning

As you use STW more, your model continuously improves as we augment your training data.

Supports many databases

We have out-of-the-box support Snowflake , BigQuery, Postgres, and many others. You can easily make a connector for any database.

Choose your front end

Start in a Jupyter Notebook. Expose to business users via Slackbot, web app, Streamlit app, any other frontend.

Fully customizable to match your unique needs

Database

Postgres

The SQL is run wherever your Python code is running

Snowflake

The SQL is run wherever your Python code is running

Microsoft SQL Server

The SQL is run wherever your Python code is running

BigQuery

The SQL is run wherever your Python code is running

MySQL

The SQL is run wherever your Python code is running

SQLite

The SQL is run wherever your Python code is running

DuckDB

The SQL is run wherever your Python code is running

Oracle

The SQL is run wherever your Python code is running

Other Database

Use STW to generate queries for any SQL database

LLM

OpenAI via STW.AI

Use STW.AI for free to generate your queries

Ollama

Use Ollama locally for free. Requires additional setup.

OpenAI

Use OpenAI with your own API key

Google Gemini

Use Google Gemini with your Gemini or Vertex API Key

Azure OpenAI

If you have OpenAI models deployed on Azure

Azure OpenAI

If you have a Mistral API key

Anthropic

Use Anthropics Claude with your Anthropic API Key

Other LLM

If you have a different LLM model

Metadata Storage

Vanna Hosted Vector DB

Use STW.AIs hosted vector database (pgvector) for free. This is usable across machines with no additional setup.

Qdrant

Use Qdrants open-source vector database

Marqo

Use Marqo locally for free. Requires additional setup. Or use their hosted option.

ChromaDB

Use ChromaDBs open-source vector database for free locally. No additional setup is necessary -- all database files will be created and stored locally.

Other VectorDB

Use any other vector database. Requires additional setup.

Pricing

The core STW package is open-source and configurable. We offer hosted components and enterprise services.

Enterprise customization

Many large enterprises need customization in deployment. STW.AI is open-source so you can do this yourself. If you need help, contact us and we’ll connect you with experienced developers.

We can connect you with developers who can help you deploy

Ready to Automate your Business Process?

Reach out to us today!

[contact-form-7 id="6eaa67e" title="Reach Out Form"]

We help you connect with the right technology for your Business

Copyright @ 2024 STW Services LLP | All rights reserved.