vision-agent 0.2.154__tar.gz → 0.2.155__tar.gz

{vision_agent-0.2.154 → vision_agent-0.2.155}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.154
+Version: 0.2.155
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.154 → vision_agent-0.2.155}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.154"
+version = "0.2.155"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

{vision_agent-0.2.154 → vision_agent-0.2.155}/vision_agent/tools/tools.py

@@ -700,18 +700,22 @@ def countgd_counting(
             {'score': 0.98, 'label': 'flower', 'bbox': [0.44, 0.24, 0.49, 0.58},
         ]
     """
-    image_b64 = convert_to_b64(image)
+    buffer_bytes = numpy_to_bytes(image)
+    files = [("image", buffer_bytes)]
     prompt = prompt.replace(", ", " .")
-    payload = {"prompt": prompt, "image": image_b64}
+    payload = {"prompts": [prompt], "model": "countgd"}
     metadata = {"function_name": "countgd_counting"}
-    resp_data = send_task_inference_request(payload, "countgd", metadata=metadata)
+    resp_data = send_task_inference_request(
+        payload, "text-to-object-detection", files=files, metadata=metadata
+    )
+    bboxes_per_frame = resp_data[0]
     bboxes_formatted = [
         ODResponseData(
             label=bbox["label"],
-            bbox=list(map(lambda x: round(x, 2), bbox["bbox"])),
+            bbox=list(map(lambda x: round(x, 2), bbox["bounding_box"])),
             score=round(bbox["score"], 2),
         )
-        for bbox in resp_data
+        for bbox in bboxes_per_frame
     ]
     filtered_bboxes = filter_bboxes_by_threshold(bboxes_formatted, box_threshold)
     return [bbox.model_dump() for bbox in filtered_bboxes]