Let Vanna.AI write your SQL for you
The fastest way to get actionable insights from your database just by asking questions
import vanna
from vanna.remote import VannaDefault
vn = VannaDefault(model='chinook', api_key=vanna.get_api_key('my-email@example.com'))
vn.connect_to_sqlite('https://vanna.ai/Chinook.sqlite')
vn.ask('What are the top 10 artists by sales?')
from vanna.flask import VannaFlaskApp
VannaFlaskApp(vn).run()
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 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 Vanna find the relevant tables and columns across your data estate."
Why ?
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 unless you specifically enable features that require it. 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, 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. Even integrate in your web app for customers.
Vanna.AI
The fastest way to get insights from your database just by asking questions
Pricing
Open Source
Bring your own LLM
- Integrate with any LLM
- Local metadata storage using ChromaDB or other vector database
- Use via self-hosted Streamlit, Flask app, Slackbot
- Customize however you like
Free Tier
Easiest to start
- Free (daily rate-limited) use of LLM
- Free use of hosted metadata storage
- GPT 3.5 Foundational Model
Paid Tier
Use in production
- No Rate Limits
- GPT-4 (with load-balanced fallback to other LLMs)
- Available SLAs
Enterprise customization.
Many large enterprises need customization in deployment. Vanna is open-source so you can do this yourself. If you need help, contact us and we'll connect you with experienced developers.
- Any LLM