S3

The S3 data source in Epsilla allows users to connect their Amazon S3 bucket to import documents directly into the knowledge base. This option is ideal for managing large datasets stored in the cloud, such as research papers, financial reports, official documents, or other files that are frequently updated or distributed.

Select Knowledge Base Type

Begin by choosing S3 as the data source type. Click Continue to proceed.

Knowledge Base Name

Provide a Knowledge Base Name. The name should begin with a letter or an underscore (_), and can contain only letters, digits, underscores, and whitespaces. Enter your desired name in the input box, for example, MyS3Docs.

S3 Configuration

• Access Key: Enter your AWS Access Key to grant Epsilla permission to access your S3 bucket.

• Secret Key: Provide your AWS Secret Key.

• Bucket: Enter the name of the S3 bucket where your files are stored, for example, research-papers.

• Prefix: Specify a prefix if you wish to narrow the data source to a specific folder within the bucket, for example, standford/. Leave it empty if using the bucket root.

Data Processing

After entering the necessary information, click Create to initiate the knowledge base setup. Epsilla will start processing the data from your S3 bucket, embedding the files into the knowledge base.

As the data is processed, you can view the status of each file in the Loaded Files section. Files that are ready for use will be marked as Ready, while those still processing will show a status of Processing data.

You can edit the configuration or view details of your S3 data source at any time by navigating to the Data Sources tab under your knowledge base.