Overview
Multi-modal Knowledge Extraction is a feature that extracts information from unstructured data sources by processing multiple data modalities simultaneously, including text, images, structured data, and visual content. This feature enables comprehensive knowledge extraction from complex, heterogeneous data sources.Category
Unstructured Data - This feature is designed to work with unstructured data sources such as documents, PDFs, images, and other non-tabular formats.Input
The Multi-modal Knowledge Extraction feature accepts data from the following input sources:- File Upload - Upload unstructured files directly from your local system. Supported formats include PDFs, images, text files, and documents with embedded content.
-
Live Data Connectors - Connect directly to live data sources without duplicating data:
- Blob Storage: Amazon S3, Azure Blob Storage, Google Cloud Storage (GCS) buckets
- Databases: Snowflake, Databricks, and other database systems
The input data source must be marked as “Unstructured Type” in your data room.
Output
Corvic Table - The Multi-modal Knowledge Extraction feature produces a new Corvic Table containing:- Extracted Text Table: Structured text content extracted from documents
- Image Table: Image-related information and metadata
- Knowledge Entities: Identified entities such as people, organizations, locations, dates, products, and concepts
- Relationships: Connections and relationships between extracted entities
- Structured Information: Additional structured data derived from the input data
The output Corvic Table provides a comprehensive structured representation of all knowledge extracted from your multi-modal input data, ready for use in downstream analysis, embeddings, or agent workflows.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
input_data_source | string | Yes | The unstructured data source to extract knowledge from. Select a data source from your data room that contains the content you want to process. The data source must be marked as “Unstructured Type” and can contain text, images, PDFs, documents, or mixed content. |
output_name | string | No | Optional custom name for the output Corvic Table. If not provided, a default name will be automatically generated based on the input data source name. |
Usage Example
To use Multi-modal Knowledge Extraction in a Data App:- Add your unstructured data source to the Data App canvas
- Click the ”+” button next to the data source
- Select “Multi-modal Knowledge Extraction” from the actions menu
- Select the input data source (if not already selected)
- Optionally provide a name for the output Corvic Table
- Run the Data App to execute the extraction
- Review the generated Corvic Table containing extracted text table, image table, knowledge entities, relationships, and structured information