Extracting Entities

This feature allows users to create column dynamically by extract information from already existing column by defining extraction rules. This feature is useful for identifying key data points The extracted data is then stored in a new column, making it easy to use for analysis or further processing.

​

1. Select a Dataset

Before configuring retrieval, ensure you have selected a dataset. If no dataset is available, follow the steps to Add Dataset on the Future AGI platform.

​

2. Access the Extract Entities

• Navigate to your dataset under Build.
• Click on the Add Columns button (+) in the top-right menu.
• Select column type
• Under Dynamic Columns, select Extract Entities.

​

3. Configure Extract Entities

• Name: Assign a name to the newly column created using this method
• Column: Select the column which you want to use to extract information to create this new column
• Enter Instructions: Define what specific information you want to extract from the text. The instructions should be clear and specific to ensure accurate entity extraction.
• Model: Select an AI model for entity extraction. If you’re using it for the first time, a pop-up will prompt you to enter and save your API key for authentication. If you’ve already provided an API key, you can simply choose from the available models.
• Concurrency: Set the number of rows to process simultaneously.

After configuring the settings, click Test to preview the extracted entities. If the results look correct, click Create New Column to apply the extraction process. The extracted entities will be stored in a separate column in the dataset.