Skip to main content

Connect a Data Source

Learn how to connect various data sources to your Noema AI platform for enhanced AI capabilities.

Overview​

Noema AI supports 25+ data sources and connectors, allowing you to integrate data from SharePoint, SQL databases, PDFs, cloud storage, and more to power your AI assistants and workflows.

Supported Data Sources​

Document Sources​

  • PDFs: Extract text and structure from PDF files
  • Word Documents: Process .doc and .docx files
  • Excel: Import data from spreadsheets
  • Text Files: Plain text, CSV, JSON

Cloud Storage​

  • SharePoint: Microsoft SharePoint sites and libraries
  • Google Drive: Files and folders from Google Drive
  • Dropbox: Connect to Dropbox accounts
  • OneDrive: Microsoft OneDrive integration

Databases​

  • SQL Server: Connect to Microsoft SQL Server
  • PostgreSQL: PostgreSQL databases
  • MySQL: MySQL and MariaDB
  • MongoDB: NoSQL document databases

APIs and Services​

  • REST APIs: Connect to any REST API
  • Webhooks: Receive real-time data
  • Custom Integrations: Build custom connectors

Steps to Connect a Data Source​

1. Navigate to Sources​

Go to Sources or Data Sources from the main menu.

2. Add New Source​

Click "Add Data Source" or "Connect New Source".

3. Select Source Type​

Choose from available connectors:

  • Browse by category (Documents, Databases, Cloud, etc.)
  • Search for specific source
  • View recently used sources

4. Configure Connection​

Provide connection details based on source type:

For SharePoint​

  • Site URL: Your SharePoint site address
  • Authentication: Microsoft 365 credentials or app registration
  • Permissions: Read or read/write access
  • Folders: Select specific document libraries

For SQL Database​

  • Server: Database server address
  • Port: Connection port (default: 1433)
  • Database Name: Specific database
  • Credentials: Username and password
  • Connection String: Optional advanced configuration

For Cloud Storage​

  • Authentication: OAuth or API key
  • Folders: Select folders to sync
  • File Types: Filter by file extensions
  • Sync Frequency: How often to check for updates

5. Test Connection​

Before saving:

  1. Click "Test Connection"
  2. Verify successful connection
  3. Check permissions are correct
  4. View sample data preview

6. Configure Sync Settings​

Set up data synchronization:

  • Sync Frequency: Real-time, hourly, daily, manual
  • File Filters: Include/exclude patterns
  • Metadata: What information to extract
  • Indexing: Enable full-text search

7. Save and Activate​

Click "Save" to activate the data source connection.

Using Connected Sources​

In Assistants​

Reference data sources in your AI assistants:

  1. Edit assistant configuration
  2. Go to "Knowledge Base" section
  3. Select connected data sources
  4. AI will use this data to answer questions

In Workflows​

Use data sources in workflows:

  1. Add "Data Input" step
  2. Select your connected source
  3. Configure query or filter
  4. Use data in subsequent steps

In Chats​

Enable chat assistants to access data:

  1. Edit chat configuration
  2. Link to data sources
  3. Define access permissions
  4. Test with sample queries

Managing Data Sources​

View Source Status​

Monitor your connections:

  • Active: Currently syncing
  • Connected: Available but not syncing
  • Error: Connection issue
  • Paused: Temporarily disabled

Update Credentials​

Refresh authentication:

  1. Select the data source
  2. Click "Update Credentials"
  3. Re-authenticate
  4. Test connection

Monitor Sync Activity​

Track synchronization:

  • Last sync time
  • Number of files processed
  • Errors or warnings
  • Data volume

Disconnect Source​

Remove a data source:

  1. Select the source
  2. Click "Disconnect"
  3. Confirm removal
  4. Clean up related configurations

Security and Permissions​

Access Control​

Manage who can use the data:

  • User-level permissions
  • Team-based access
  • Role-based restrictions

Data Privacy​

Ensure compliance:

  • Encryption at rest and in transit
  • Access logging and auditing
  • Data retention policies
  • GDPR/compliance settings

Best Practices​

  • Use service accounts for database connections
  • Implement least-privilege access
  • Regularly test connections
  • Monitor sync performance
  • Document data source purposes
  • Set up alerts for connection failures

Troubleshooting​

Connection Failed​

Check:

  • Credentials are correct
  • Firewall allows connection
  • Service is running
  • Network connectivity

Sync Not Working​

Verify:

  • Sync schedule is active
  • Sufficient permissions
  • No file locks or conflicts
  • Storage quota not exceeded

Slow Performance​

Optimize by:

  • Filtering unnecessary files
  • Adjusting sync frequency
  • Indexing only needed fields
  • Using incremental sync

Next Steps​