Skip to main content

File Reader

Retrieve files from cloud storage providers for workflow processing

What is File Reader?​

The File Reader node retrieves files from various cloud storage providers for use in your workflows. It supports AWS S3 with traditional bucket-based file access, and Google Drive with an intuitive file picker interface, making it versatile for both enterprise and personal cloud storage scenarios.

How to use it?​

To effectively use the File Reader node, follow these steps:

  1. Select Storage Provider:

    • AWS S3: Enterprise cloud storage with bucket-based file organization
    • Google Drive: Personal and business cloud storage with folder-based organization (available in V4)

  2. For AWS S3 Configuration:

    • Credentials: Configure AWS credentials with S3 access permissions
    • Region: Select the AWS region where your S3 bucket is located
    • File Path: Specify the file within the bucket
    • Bucket Name: Connect or specify the S3 bucket name containing your file

  3. For Google Drive Configuration (V4 only):

    • Connect Google Drive Service: Go to Settings → Credentials and connect the Google Drive Service Connector
    • Authorization: You'll be prompted to login with your Google account and grant access permissions
    • Credentials: Select the connected Google Drive credentials in the File Reader node
    • File Picker: Use the integrated file browser to select files from your Google Drive
    • No manual path specification needed - the picker handles file selection automatically

  4. Connect Output:

    • The File output provides the retrieved file content
    • Connect to downstream nodes that process file data (text processors, image analyzers, document splitters, etc.)

Example of usage​

Objective: Create a document processing workflow that retrieves and processes files from cloud storage.

Basic AWS S3 Setup:

  1. Provider Selection: Choose "AWS S3" from storage provider options
  2. Credentials: Configure AWS IAM credentials with s3:GetObject permissions and add them to your organization credentials in Nocodo AI
  3. Region: Select appropriate AWS region (e.g., us-east-1)
  4. File Location: Connect bucket name and file path inputs, or specify directly
  5. Processing: Connect file output to document processors, text extractors, or other analysis nodes

Workflow Integration:

  • Connect text inputs or other nodes to provide dynamic file paths and bucket names
  • Use the file output with document splitters for large text processing
  • Integrate with vector store writers for knowledge base construction
  • Process multiple file types (PDFs, images, text) through appropriate handlers

Additional information​

Node Versions:​

File Reader V3 (Standard):

  • AWS S3 support only
  • Bucket and file path configuration
  • Regional deployment options
  • Enterprise-focused functionality

File Reader V4 (Enhanced):

  • AWS S3 support (same as V3)
  • Google Drive integration with file picker
  • Expanded cloud storage options
  • User-friendly file selection interface

Required Permissions:​

AWS S3:

  • s3:GetObject - Read files from S3 buckets
  • s3:ListBucket - List bucket contents (optional, for validation)

Common Use Cases:​

Enterprise Scenarios:

  • Document processing pipelines accessing company file repositories
  • Automated report generation from stored templates and data files
  • Content management systems with centralized file storage
  • Data analysis workflows processing archived datasets

Hybrid Cloud Scenarios:

  • Workflows combining enterprise S3 storage with user Google Drive files
  • Cross-platform file synchronization and processing
  • User-generated content processing from multiple sources
  • Backup and migration workflows between cloud providers

Development and Testing:

  • Dynamic file loading for testing different document types
  • Configuration file management across environments
  • Asset pipeline processing for web applications
  • Research data processing with flexible file sources