CORE CONCEPTS
Images and sensors
Use images, image views, depth frames, GPS, IMU, BLE, Wi-Fi, or other sensor readings to add visual and device-state context to a spatial request.
Context, not the primary signal
Images and sensor readings supplement geometry; they do not replace it. Rowe answers measurement questions from the structured scene. A photograph helps disambiguate what an object is, not how big it is.
What you can attach
Raster frames, multi-view image sets, depth maps, and device state all ride alongside the scene in the same request, so one call carries both the geometry and whatever observed it. Attach only what the task needs: every field you send counts as input spatial tokens.
- image / images — single or multiple raster frames
- image_views — multi-view context for one object
- sensor_readings — IMU, GPS, altimeter, or other device state
Sending images alone
A request with images and no cad_scene or point_cloud_scene is doing image reasoning, not spatial reasoning. It will return something, but nothing in it is grounded in measured geometry — do not treat those numbers as measurements.
Request fields
The full input contract, shared by every task.
modelstringModel id. Use rowe-1.0.
input.task_typestringfit, stability, placement, embed, understand, reconstruct, predict, act, or optimize.
input.cad_sceneobjectNative CAD scene with B-rep solids, drawing entities, dimensions, constraints, and optional feature_tree. Preferred for STEP, IGES, DXF, PDF, SVG, and draw.io workflows.
input.previous_cad_sceneobjectOptional previous native CAD scene for compare and temporal tasks.
input.point_cloud_sceneobjectCurrent 3D scene with one or more point cloud groups.
input.previous_point_cloud_sceneobjectOptional previous scene for temporal prediction.
input.image / input.imagesobjectOptional raster frames, depth maps, or multi-view visual context.
input.sensor_readingsobjectOptional IMU, GPS, BLE, WiFi, altimeter, or device state readings.
input.goalobjectOptional target state for action, routing, placement, or optimization tasks.
input.object_idstringPrimary object id used by fit, stability, placement, and tracking tasks.
input.secondary_idstringTarget or container object id for fit and placement tasks.
input.detailstringUse compact to reduce structured prediction detail for small or latency-sensitive requests.