Connecting Your Data

Before building a RAG application, connect the file stores that hold your documents. Dataworkz maintains all connector configurations in Configuration → Integrations - Connect to a Data Source, which is where you set up credentials and connection parameters for each source. Once configured, these connections become available when you choose a data source during RAG app creation.

Supported File Stores

Cloud Object Storage

• AWS S3 — Amazon S3 buckets

• Azure Blob Storage — Microsoft Azure Blob containers

• Google Cloud Storage — GCS buckets

• On-premise HDFS — Hadoop Distributed File System

File Shares & Drives

• Google Drive — Google Docs, Sheets, and Slides

• NAS — Network-attached storage shares

• Storage Bridge — Bridge connector for custom storage systems

• File Stream — File streaming pipelines

How to Add a Connection

1. Go to Configuration → Integrations - Connect to a Data Source in the left navigation.

2. Select the connector type you want to configure.

3. Enter the connection credentials (endpoint URL, API key, service account key, or IAM role — varies by connector).

4. Test the connection and save.

The saved connection then appears as a selectable data source when you set up ingestion in the RAG app wizard (Step 2 — Ingest) or in the Data Store.