“IDOL Ingest for AWS enhances data ingestion, enrichment, and entity extraction capabilities, aligning with existing search and analysis tools. It ensures a comprehensive understanding of document content and metadata, regardless of format or source.
Key Features:
Diverse Data Sources: Ingests content from over 1500 file types and 150 different repositories, including PDFs, Word docs, and various image files.
Comprehensive Content Extraction: Extracts text, metadata, and all content from files to enhance search experiences with relevant context.
Entity Extraction: Helps comply with privacy regulations like GDPR or CCPA by automatically identifying, managing, and redacting sensitive information using a vast library of global entities.
Index Agnostic: Compatible with multiple index repositories (e.g., Vertica, AWS Elasticsearch), providing flexibility in usage.
Usage-Based Pricing: Adopts a usage-based pricing model, considering the number of enriched documents. For large-scale usage, custom pricing options are available upon inquiry.”
