In this section, we present how to connect Gmail accounts to MindsDB.
Gmail is a widely used and popular email service developed by Google.
By connecting your Gmail account to MindsDB, you can utilize various AI models available within MindsDB to summarize emails, detect spam, or even automate email replies.
Please note that currently you can connect your Gmail account to local MindsDB installation by providing a path to the credentials file stored locally.
If you want to connect your Gmail account to MindsDB Cloud, you can upload the credentials file, for instance, to your S3 bucket and provide a link to it as a parameter.
Before proceeding, ensure the following prerequisites are met:
The required arguments to establish a connection are as follows:
credentials_file
local path to the credentials.json or credentials_url
in case your file is uploaded to s3. Follow the instructions below to generate the credentials file.scopes
define the level of access granted. It is optional and by default it uses ‘https://…/gmail.compose’ and ‘https://…/gmail.readonly’ scopes.In order to make use of this handler and connect the Google Calendar app to MindsDB, the following syntax can be used:
Or, you can also connect by giving the credentials file from an s3 pre signed url. To do this you need to pass in the credentials_file parameter as a pre signed url. For example:
You need a Google account in order to use this integration. Here is how to get the credentials file:
Create a Google Cloud Platform (GCP) Project:
1.1 Go to the GCP Console (https://console.cloud.google.com/).
1.2 If you haven’t created a project before, you’ll be prompted to do so now.
1.3 Give your new project a name.
1.4 Click Create
to create the new project.
Enable the Gmail API:
2.1 In the GCP Console, select your project.
2.2 Navigate to APIs & Services
> Library
.
2.3 In the search bar, search for Gmail
.
2.4 Click on Gmail API
, then click Enable
.
Create credentials for the Gmail API:
3.1 Navigate to APIs & Services
> Credentials
.
3.2 Click on the Create Credentials
button and choose OAuth client ID
.
3.3 If you haven’t configured the OAuth consent screen before, you’ll be prompted to do so now. Make sure to choose External
for User Type, and select the necessary scopes. Make sure to save the changes.
Now, create the OAuth client ID. Choose Web application
for the Application Type and give it a name.
3.4 Add the following MindsDB URL to Authorized redirect URIs
:
http://localhost/verify-auth
http://cloud.mindsdb.com/verify-auth
.3.5 Click Create
.
Download the JSON file:
4.1 After creating your credentials, click the download button (an icon of an arrow pointing down) on the right side of your client ID. This will download a JSON file, so you will use the location to it in the credentials_file
param.
This creates a database called mindsdb_gmail. This database ships with a table called emails that we can use to search for emails as well as to write emails.
Now you can use your Gmail data, like this:
searching for email:
writing emails:
Now that we know how to pull emails into our database and write emails, we can make use of OpenAPI engine to write email replies.
First, create an OpenAI engine, passing your OpenAI API key:
Then, create a model using this engine:
You can check if an email is spam by using one of the Hugging Face pre-trained models.
Then, create a view that contains the snippet or the body of the email.
Finally, you can use the model to classify emails into spam or ham:
For more information about available actions and development plans, visit this page.