Skip to content

Generating SQL for BigQuery using OpenAI via Vanna.AI (Recommended), Vanna Hosted Vector DB (Recommended)

This notebook runs through the process of using the vanna Python package to generate SQL using AI (RAG + LLMs) including connecting to a database and training. If you're not ready to train on your own database, you can still try it using a sample SQLite database.

Run Using Colab Open in GitHub

Which LLM do you want to use?

Where do you want to store the 'training' data?


%pip install 'vanna[bigquery]'
import vanna
from vanna.remote import VannaDefault
api_key = # Your API key from 

vanna_model_name = # Your model name from 
vn = VannaDefault(model=vanna_model_name, api_key=api_key)

Which database do you want to query?



You only need to train once. Do not train again unless you want to add more training data.

# The information schema query may need some tweaking depending on your database. This is a good starting point.
df_information_schema = vn.run_sql("SELECT * FROM INFORMATION_SCHEMA.COLUMNS")

# This will break up the information schema into bite-sized chunks that can be referenced by the LLM
plan = vn.get_training_plan_generic(df_information_schema)

# If you like the plan, then uncomment this and run it to train
# vn.train(plan=plan)
# The following are methods for adding training data. Make sure you modify the examples to match your database.

# DDL statements are powerful because they specify table names, colume names, types, and potentially relationships
        id INT PRIMARY KEY,
        name VARCHAR(100),
        age INT

# Sometimes you may want to add documentation about your business terminology or definitions.
vn.train(documentation="Our business defines OTIF score as the percentage of orders that are delivered on time and in full")

# You can also add SQL queries to your training data. This is useful if you have some queries already laying around. You can just copy and paste those from your editor to begin generating new SQL.
vn.train(sql="SELECT * FROM my-table WHERE name = 'John Doe'")
# At any time you can inspect what training data the package is able to reference
training_data = vn.get_training_data()
# You can remove training data if there's obsolete/incorrect information. 

```## Asking the AI
Whenever you ask a new question, it will find the 10 most relevant pieces of training data and use it as part of the LLM prompt to generate the SQL.

Launch the User Interface


from vanna.flask import VannaFlaskApp
app = VannaFlaskApp(vn)

Vanna Logo Vanna.AI

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