Details

Asset Version: 1.0.0
Last Published: Oct 21, 2025
By: HCL Volt MX Team
The Google Gemini Document Understanding Application is a sample app that demonstrates how to leverage Google’s Gemini multimodal AI models for intelligent document analysis. It is built using the Google Gemini Document Understanding Component and provides an end-to-end workflow for users to interact with PDF documents.
Google Gemini Document Understanding enables Gemini AI to read and analyze PDFs, interpreting text, layout, images, charts, and tables to extract meaning and context.
Requirements
- HCL Volt MX Iris
- HCL Volt MX Foundry
Devices
Platforms
Features:
- Full-Context Analysis - Reads the document as a whole, considering layout, order, and visual context.
- Multi-Modal Understanding - Interprets both text and images (charts, diagrams, scanned handwriting).
- Structured Output - Can output JSON, tables, or text summaries for downstream processing.
- Flexible Input Methods
a) Inline PDF (Base64-encoded) for quick processing (≤20MB)