Visual Search
Learn how to search for visually similar media using an uploaded image as the query.
How This Helps
Visual Search lets you upload an external image and use it to find similar content within your dataset. This helps surface lookalikes, variations, or duplicates based on visual similarity—not just metadata.
Step 1: Upload an Image for Search
To begin, upload the query image using this endpoint:
Request Parameters
file
: The image file to use for similarity searchbounding_box
(optional): X, Y, Width, Height (if you’re targeting a region)
Step 2: Explore Similar Images
Once your query is uploaded and processed, use the returned anchor_media_id
to explore visually similar results:
Parameters
ENTITY_TYPE
:IMAGES
orOBJECTS
anchor_media_id
: Retrieved from the upload responseanchor_type
: Type returned with the media IDPAGE_NUMBER
: Which page of results to view (e.g.,0
for start)
Example
Response: Returns a list of Visual Layer image clusters that are visually similar to the uploaded image.
For a full working example, check out this API notebook.