[Refactor] Use data parser for matching data items to multi-modal UUIDs (#32955)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-26 15:00:28 +08:00
parent ee484b3f4b
commit 11b556878b
14 changed files with 701 additions and 604 deletions
--- a/examples/pooling/plugin/prithvi_geospatial_mae_offline.py
+++ b/examples/pooling/plugin/prithvi_geospatial_mae_offline.py
@@ -59,8 +59,10 @@ class PrithviMAE:
            input_data = input_data[0]

        mm_data = {
-            "pixel_values": input_data,
-            "location_coords": location_coords,
+            "image": {
+                "pixel_values": input_data,
+                "location_coords": location_coords,
+            }
        }

        prompt = {"prompt_token_ids": [1], "multi_modal_data": mm_data}