Extract structured metadata from files using Box AI. Uses Large Language Models (LLMs) to extract metadata as key-value pairs from files. Requires Box AI access (ai.readwrite scope). Supports two extraction approaches: 1. **Using fields**: Define custom fields with 'key', option…
itemsRequiredarrayThe files to extract metadata from. Provide 1-25 file items. Each item must have 'id' (Box file ID) and 'type' set to 'file'.
fieldsarrayCustom field definitions for extraction. Each field needs at least a 'key'. Optional: 'description', 'displayName', 'prompt', 'type', 'options'. Use EITHER 'fields' OR 'metadata_template' parameters, but NOT both.
metadata__template__typestringMust be set to 'metadata_template' when using a metadata template. Required if metadata_template_template_key is provided.
metadata__template__scopestringThe scope of the metadata template. Use 'global' for Box-provided templates or 'enterprise_{enterprise_id}' for custom enterprise templates. Required if metadata_template_template_key is provided.
metadata__template__template__keystringThe template_key of the metadata template to use for extraction. Required if using metadata_template approach instead of fields.
dataRequiredData from the action execution
errorstringError if any occurred during the execution of the action
successfulRequiredbooleanWhether or not the action execution was successful or not
OAuth connection. Risk level 2 of 5.
Free Action
No published Skills explicitly reference this Action yet.