Skip to main content

Getting Started with Ingestion Configuration

This guide introduces you to configuring data ingestion in the Zeta Alpha platform. You'll learn about the different types of connectors available, how to set them up, and best practices for managing your data ingestion workflows.

Overview​

Data ingestion is the process of importing and indexing content from various sources into the Zeta Alpha platform. The platform provides two main approaches to data ingestion:

  1. Pre-built Connectors: Ready-to-use connectors for popular enterprise systems like SharePoint, Google Drive, Box, and others
  2. Custom Connectors: Flexible connectors that allow you to ingest data from your own sources via the Ingestion API

Both approaches allow you to configure field mappings, access controls, and processing workflows tailored to your organization's needs.

Prerequisites​

Before you begin configuring data ingestion, ensure you have:

  1. Access to the Zeta Alpha Platform UI - You'll need administrative access to configure connectors
  2. A tenant created - Your organization's Zeta Alpha tenant must be set up
  3. An index created - You'll need at least one index to receive ingested documents
  4. Appropriate credentials - Depending on your connector type, you may need authentication credentials such as API tokens, OAuth credentials, or service account keys. See the specific connector guide for detailed requirements.

Key Concepts​

Connectors​

A connector is a configuration that defines how the Zeta Alpha platform should retrieve and process documents from a specific source. Each connector includes:

  • Source credentials: Authentication details for accessing the data source
  • Field mappings: Rules for mapping source fields to index fields
  • Crawl configuration: Filters and patterns that determine what content to ingest
  • Processing workflows: Steps for transforming and enriching documents

Content Sources​

A content source is an instance of a connector attached to a specific index. You can create multiple content sources using the same connector type, each with different configurations. For example, you might have separate content sources for different SharePoint sites or Google Drive folders.

Field Mappings​

Field mappings define how fields from your source documents correspond to fields in your Zeta Alpha index. This allows you to:

  • Map source-specific field names to standardized index fields
  • Transform nested data structures
  • Combine multiple source fields into a single index field

Workflows​

Workflows define the sequence of processing steps that documents go through during ingestion. Common workflow steps include:

  • Text extraction from various file formats
  • Metadata extraction using AI agents
  • Field validation and transformation
  • Indexing

Next Steps​

Choose a guide based on your data source:

For Enterprise Systems​

For Custom Data Sources​

For Advanced Features​

Getting Help​

If you encounter issues or have questions:

  • Review the connector-specific guides linked above
  • Check the API Reference documentation for detailed endpoint information
  • Contact Zeta Alpha support for assistance with complex configurations