Skip to main content

BigQuery User Connector Setup Guide

The BigQuery user connector lets a Custom Chatbot run queries against BigQuery under each end user's own Google identity. Users sign in with Google once, and every query then runs with their own BigQuery permissions.

BigQuery is a database user connector: it is used through a Custom Chatbot and is not a direct chat tool for RouteLLM.

Prerequisites​

Create the organization-level BigQuery connector first by following the BigQuery setup guide, and verify that it is active.

Build a Custom Chatbot on the connector​

Follow Use a database connector in a Custom Chatbot: create a Custom Chatbot project, train the model with Structured data source → External Databases, select the BigQuery connector and add the tables to use, then deploy and test it.

End-user sign-in​

When a user enters their first question, they are asked to sign in once with Google. After signing in with their own credentials, the chatbot answers using only the BigQuery data that user is allowed to access.