Overview
Augment is a feature that enables data cleaning, processing, augmentation, and targeted knowledge or information extraction from Corvic Tables using either code or ML/AI (including LLMs). This feature allows you to transform and enrich your data through natural language prompts, making it easy to perform complex data operations without extensive manual coding.
Category
Corvic Tables - This feature is designed to work with Corvic Tables, enabling you to enhance and transform existing structured data.
Corvic Table - The Augment feature accepts a Corvic Table as input. Select an existing Corvic Table from your data room that you want to augment, clean, process, or extract information from.
The input must be a Corvic Table. You can create Corvic Tables from data sources using features like Sanitize Parquet for structured data or Multi-modal Knowledge Extraction for unstructured data.
Output
Corvic Table - The Augment feature produces a new Corvic Table with augmented data based on your specifications. The output includes:
- Enhanced Columns: New or modified columns based on the augmentation type
- Processed Data: Cleaned, transformed, or enriched data ready for downstream operations
- Extracted Information: Targeted knowledge or information extracted from the input data
The output Corvic Table maintains the structure of your input while adding the augmented columns and transformations you specified. This enables seamless integration with downstream workflows, embeddings, and agent operations.
Parameters
| Parameter | Type | Required | Description |
|---|
input | string | Yes | The Corvic Table to augment. Select a Corvic Table from your data room that contains the data you want to process, clean, augment, or extract information from. |
type | string | Yes | The type of augmentation to perform. Options: llm_augment for LLM-based augmentation or code_augment for code-based augmentation. |
output_name | string | Auto-generated | Optional custom name for the output Corvic Table. If not provided, a default name will be automatically generated based on the input Corvic Table name and augmentation type. |
LLM Augment Parameters
When type is set to llm_augment, configure the following additional parameters:
| Parameter | Type | Required | Description |
|---|
prompt | string | Yes | Natural language description of what you want to do using the LLM. Describe the augmentation, transformation, or extraction task you want to perform on your data. |
llm_model | selection | Yes | LLM model selection. Choose from available models or use “bring your own” if your admin has added custom LLM endpoints. Options include GPT models, Claude, and custom models configured by administrators. |
output_column_name | string | Yes | Name for the output column that will contain the augmented results. |
input_columns | array | Auto-generated | Input columns selected based on the prompt. Automatically generated based on your prompt, or you can manually specify which columns from the input Corvic Table should be used for the LLM augmentation. |
Code Augment Parameters
When type is set to code_augment, configure the following additional parameters:
| Parameter | Type | Required | Description |
|---|
prompt | string | Yes | Natural language description of what you want to do using code. Describe the data cleaning, processing, augmentation, or transformation task you want to perform. |
input_columns | array | Auto-generated | Input columns that will be used for the code augmentation. Automatically generated based on your prompt, or you can manually specify which columns from the input Corvic Table should be processed. |
code | string | Auto-generated | The code to apply for augmentation. Automatically generated based on your prompt, or you can provide custom code. The code will be applied to the selected input columns. |
Usage Example
To use Augment in a Data App:
- Add your Corvic Table to the Data App canvas
- Click the ”+” button next to the Corvic Table
- Select “Augment” from the actions menu
- Select the input Corvic Table (if not already selected)
- Choose the augmentation type: LLM Augment or Code Augment
- Configure the type-specific parameters:
- For LLM Augment: Provide prompt, select LLM model, specify output column name, and select input columns
- For Code Augment: Provide prompt, select input columns, and review/generate the code
- Optionally provide a name for the output Corvic Table
- Run the Data App to execute the augmentation
- Review the generated Corvic Table with augmented data
