Documentation
Prepare Database Connection String

Prepare Your Database Connection String

We currently support multiple types of databases: MySQL, PostgreSQL, SQL Server, BigQuery, Snowflake, and Vertica.

Choose your engine in the database query generator guide for the corresponding query examples and a checked inventory workflow.

Here are some examples:

MySQL

mysql://user:password@host:port/database

For a complete setup and answer-validation example, follow the MySQL AI chatbot guide, including connection troubleshooting and a sales/refunds SQL fixture.

PostgreSQL

postgresql://user:password@host:port/database

Follow the PostgreSQL AI chatbot guide for connection checks, schema context and a tested example covering reporting time zones and missing dates.

MongoDB

mongodb://user:password@host:port/database

SQL Server

Data Source=host;Initial Catalog=database;User ID=user;Password=password;

We use ADO.NET format connection strings - for more details, please refer to Microsoft's official documentation (opens in a new tab).

Follow the SQL Server AI chatbot setup guide for reporting-view permissions, connection checks, and a T-SQL top-customer example with explicit tie handling.

BigQuery

For BigQuery, you need to prepare two things:

1. Project ID

  • You can find it in the credentials JSON file as the quota_project_id field
  • Or from Google Cloud Console: look at the project selector at the top of the page
  • The project ID is typically composed of lowercase letters, numbers, and hyphens

2. Credentials JSON

{
  "client_id": "764086051850-xxxxxxxxxxxxxxxxxxxx.apps.googleusercontent.com",
  "client_secret": "xxxxx-xxxxxxxxxxxxx",
  "quota_project_id": "your-project-id",
  "refresh_token": "1//0exxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
  "type": "authorized_user",
  "universe_domain": "googleapis.com"
}

Make sure your Google Cloud account has the necessary BigQuery permissions to read the datasets you want to query.

For a complete evaluation, follow the BigQuery AI chatbot guide to distinguish job and data permissions, check query costs, and validate nested-data totals.

Snowflake

Prepare the account identifier, database, username, authentication details, schema, warehouse and role for your approved reporting identity. The current web form accepts a PEM private key; verify supported authentication in your installed Desktop version and follow your Snowflake account policy.

Follow the Snowflake AI chatbot setup guide for role and warehouse checks, key-pair authentication boundaries, and a worked example that avoids counting historical order versions as duplicate revenue.

Clickhouse

You should input three parameters: url, username, password.

You can find three parameters from your Clickhouse console like this:

Clickhouse Connection String

Vertica

vertica://user:password@host:port/database

If you encounter any issues while preparing your connection string, we recommend using this utility tool (opens in a new tab).

If you don't have a database and just want to test, you can apply for a free PostgreSQL database at Neon DB (opens in a new tab).

Whitelist Our Static IP (Only Required for Website Chatbot)

You need to whitelist our server IP 43.159.146.204 to allow the Website Chatbot to connect to your database successfully.

If you're unsure how to whitelist an IP, please contact your database provider or your database administrator. (Or ask ChatGPT directly).

If you are using the Desktop app, you can skip this step. (The Desktop app connects to your database from your local computer).

If you are curious about how we connect to your database, you can refer to our security documentation.

Train to get better answerSample Databases