Data Lakes

Data Lakes#

Data Lakes provide a cloud storage solution integrated into Gen AI Builder. Comprised of Bucket and Asset resources, Data Lakes can be accessed using Gen AI Builder with the GriptapeCloudFileManagerDriver . In Gen AI Builder, Data Lakes can be used as a Data Source Types .

Buckets#

You can create a Bucket in the Gen AI Builder console by specifying the required configuration for your chosen Data Source in the cloud console.

Assets#

You can create Assets in the Gen AI Builder console inside of a specific Bucket. File assets are uploaded via the ‘Upload’ button. Folder assets are created via the ‘Create Folder’ button.

Asset Aliases#

A combination of an Asset’s Bucket ID and Name, this field is a unique identifier for an Asset. Formatted as <bucket_id>/<asset_name> .

Asset Paths#

A Data Lake path that can be used as a prefix filter for Assets inside of a Bucket. Ex: Asset Path foo/ encompasses both foo/bar.txt and foo/baz.txt .