Description

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

High accuracy on complex datasets: Vanna’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. The metadata storage layer only sees schemas, documentation, and queries.

Self learning: As you use Vanna more, your model continuously improves as we augment your training data.

Supports many databases: We have out-of-the-box support Snowflake , BigQuery, Postgres. 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. Even integrate in your web app for customers.

• #sql
• #projectmanagement
• #marketing