Table of contents
1. Overview
This article explains how to manually activate powerful AI features in your libraries to improve asset discovery and reduce manual metadata work. We’ll walk you through key use cases and a step-by-step guide on how to get started.
2. Asset content search (OCR search)
The asset content search feature analyzes documents (pdf, docx, and pptx) and images (png, jepg, tiff) in your projects and libraries to extract and index any text content. It uses AWS Textract and Comprehend to process the files.
Main use cases
Once the text has been recognized in the files, it is stored and used to enhance the search results. All three main searches - workspace search, library page search and guideline search - can access the text content. The public API can also make use of this feature.
Being able to search through the text content of your assets can have multiple benefits.
In the workspace it can help find the documents that need updating or editing faster. There is also less manual metadata entry required on that asset for users to be able to find it.
In library pages, your teams can quickly find the right contract or image containing product text that they need for a customer or campaign.
Finally, in the guideline search, users can quickly search across libraries to find the right asset faster.
Activating the Asset content search
Open the General Library or Project settings
Toggle Asset content search to “on”
Processing starts automatically and progress is shown in the UI
To deactivate, simply toggle the setting back to “off.”
Once activated, search results will automatically include matches from the extracted text.
3. AI auto-tagging
What is it
Tags assigned by AI are a way to generate suggested tags and categorize your assets in an intelligent manner. It’s available for Media, Logo, Icon, and Document libraries, and helps reduce the time spent manually tagging assets.
AI tags appear in the asset's Metadata panel under Assigned by AI, where they can be removed with one click.
Supported formats
Auto-tagging supports the following formats: PNG, JPG, TIF, TIFF, JPEG, PSD, PSB, SVG, WEBP, HEIF, HEIC, MOV, MP4
For manual tags and metadata best practices, see our Metadata and (manual) Tags article.
If a file format isn’t supported, the AI tags will not appear.
Setting up Auto-tagging when creating a new media library
Click New in the top-right corner of the Libraries section
Choose a library type and name it
Select a workflow template or link to a Guideline
Toggle Enable AI auto-tagging to “on” in the setup modal
Auto-tagging in Existing Libraries
Open your Library and go to General Settings
Toggle the Suggested tags section to “on”
Tag generation will begin automatically within a few minutes
The auto-tagging feature should begin working after a few minutes. Generated tags will appear under the ‘Metadata’ section in ‘Assigned by AI' under the 'Tags' dropdown within the asset viewer.
If you find there are some tags that don’t actually fit with the image or video, you’re able to easily eliminate them from the list by clicking to deselect them.
If you deselect a tag by mistake, you can recover it by clicking on the tag once again. However, if you refresh, all the unchecked tags will be completely erased.
If AI auto-tagging is turned off, suggested tags will no longer appear in the metadata panel. If a file format isn’t supported, the Suggested Tags panel won’t appear.
In case you have any further questions, please don’t hesitate to contact our support team.