Skip to main content

​
How it works

The S3 connector retrieves all documents stored in a specified Amazon S3 bucket, supporting a range of file formats such as PDF, DOC, DOCX, TXT, and others. Document syncing occurs once every 24 hours.

​
Setting Up

​
Authorization

Three authorization methods are available - choose whichever best suits your setup:
  • AWS Access Keys – Authenticates using standard access key credentials
  • IAM Role-Based Authorization – Leverages AWS IAM roles for enhanced security
  • Assume Role – Automatically draws on the EC2 instance’s assigned role to access S3

​
Indexing

  1. Open the S3 connector Go to the ASSIST AI Admin Panel and navigate to the S3 Connector.
  2. Configure authorization In Step 1, set up your authorization method. Select from existing credentials, or click Create New to add fresh ones: Access Keys (enter your AWS Access Key ID and Secret Access Key), IAM Role (enter your Role ARN), or Assume Role (no credentials needed).
  3. Save your configuration Click Create to store your settings.
  4. Proceed with your credential Make sure the correct credential is selected, then click Continue.
  5. Enter bucket details In Step 2, fill in your S3 bucket information: a Connector Name, the Bucket Name, an optional Prefix to narrow indexing to a specific path, and the Access Type (Public or Private).
  6. Launch the connector Click Create Connector to kick off indexing.
Once running, the connector will begin indexing your bucket. You can add additional buckets or adjust settings at any time.
S3

​
Understanding S3 Structure

Amazon S3 organizes data into buckets. Each bucket can contain an unlimited number of objects (files). You can think of a bucket as a root directory, and the objects as files within that directory. For more information on S3 structure, visit the Amazon S3 documentation.