Overview
LLM Augment enables you to enhance and transform Corvic Tables using Large Language Models (LLMs). This feature allows you to perform data cleaning, processing, augmentation, and targeted knowledge extraction through natural language prompts, making complex data operations accessible without extensive coding.Category
Corvic Tables - This feature is designed to work with Corvic Tables, enabling you to enhance and transform existing structured data using LLM capabilities.Input
Corvic Table - LLM Augment 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 - LLM Augment produces a new Corvic Table with augmented data based on your LLM prompt. The output includes:- Enhanced Columns: New columns containing LLM-generated results
- Processed Data: Cleaned, transformed, or enriched data based on your natural language instructions
- Extracted Information: Targeted knowledge or information extracted using LLM capabilities
The output Corvic Table maintains the structure of your input while adding new columns with LLM-generated content. 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. |
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. |
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. |
Usage Example
To use LLM Augment in a Data App:- Add your Corvic Table to the Data App canvas
- Click the ”+” button next to the Corvic Table
- Select “LLM Augment” from the actions menu
- Select the input Corvic Table (if not already selected)
- Provide a natural language prompt describing what you want to do
- Select the LLM model to use
- Specify the output column name
- Select the input columns that should be used for augmentation
- Optionally provide a name for the output Corvic Table
- Run the Data App to execute the LLM augmentation
- Review the generated Corvic Table with augmented data