vision-agent 0.2.34__py3-none-any.whl → 0.2.36__py3-none-any.whl

vision_agent/agent/vision_agent.py

@@ -264,15 +264,19 @@ def retrieve_tools(
     )
     tool_info = []
     tool_desc = []
+    tool_list: List[Dict[str, str]] = []
     for task in plan:
         tools = tool_recommender.top_k(task["instructions"], k=2, thresh=0.3)
         tool_info.extend([e["doc"] for e in tools])
         tool_desc.extend([e["desc"] for e in tools])
+        tool_list.extend(
+            {"description": e["desc"], "documentation": e["doc"]} for e in tools
+        )
     log_progress(
         {
             "type": "tools",
             "status": "completed",
-            "payload": tools,
+            "payload": tool_list,
         }
     )
     if verbosity == 2:

vision_agent/tools/tools.py

@@ -58,9 +58,10 @@ def grounding_dino(
     box_threshold: float = 0.20,
     iou_threshold: float = 0.20,
 ) -> List[Dict[str, Any]]:
-    """'grounding_dino' is a tool that can detect and count objects given a text prompt
-    such as category names or referring expressions. It returns a list and count of
-    bounding boxes, label names and associated probability scores.
+    """'grounding_dino' is a tool that can detect and count multiple objects given a text
+    prompt such as category names or referring expressions. The categories in text prompt
+    are separated by commas or periods. It returns a list and count of bounding boxes,
+    label names and associated probability scores.
 
     Parameters:
         prompt (str): The prompt to ground to the image.
@@ -111,9 +112,10 @@ def grounding_sam(
     box_threshold: float = 0.20,
     iou_threshold: float = 0.20,
 ) -> List[Dict[str, Any]]:
-    """'grounding_sam' is a tool that can detect and segment objects given a text
-    prompt such as category names or referring expressions. It returns a list of
-    bounding boxes, label names and masks file names and associated probability scores.
+    """'grounding_sam' is a tool that can detect and segment multiple objects given a
+    text prompt such as category names or referring expressions. The categories in text
+    prompt are separated by commas or periods. It returns a list of bounding boxes,
+    label names, mask file names and associated probability scores.
 
     Parameters:
         prompt (str): The prompt to ground to the image.
@@ -343,9 +345,9 @@ def image_question_answering(image: np.ndarray, prompt: str) -> str:
 
 
 def clip(image: np.ndarray, classes: List[str]) -> Dict[str, Any]:
-    """'clip' is a tool that can classify an image given a list of input classes or tags.
-    It returns the same list of the input classes along with their probability scores
-    based on image content.
+    """'clip' is a tool that can classify an image or a cropped detection given a list
+    of input classes or tags. It returns the same list of the input classes along with
+    their probability scores based on image content.
 
     Parameters:
         image (np.ndarray): The image to classify or tag

{vision_agent-0.2.34.dist-info → vision_agent-0.2.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.34
+Version: 0.2.36
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.34.dist-info → vision_agent-0.2.36.dist-info}/RECORD

@@ -11,7 +11,7 @@ vision_agent/agent/easytool_v2.py,sha256=CjY-sSj3abxnSq3ZHZMt-7YvRWDXEZsC6RN8FFI
 vision_agent/agent/easytool_v2_prompts.py,sha256=MZSIwovYgB-f-kdJ6btaNDVXptJn47bfOL3-Zn6NiC0,8573
 vision_agent/agent/reflexion.py,sha256=AlM5AvBJvCslXlYQdZiadq4oVHsNBm3IF_03DglTxRo,10506
 vision_agent/agent/reflexion_prompts.py,sha256=G7UAeNz_g2qCb2yN6OaIC7bQVUkda4m3z42EG8wAyfE,9342
-vision_agent/agent/vision_agent.py,sha256=SAk1-UWVxdpjMbcUsx2afbgQO8VjbwfKUKdM_MUs8Ck,16640
+vision_agent/agent/vision_agent.py,sha256=WMClrV5qhPyqnQscNgek2vVes6-A1jNwaHH0vzgy6Zk,16802
 vision_agent/agent/vision_agent_prompts.py,sha256=0YbiS59IEWbiE43gCvOqfWrpudIAhTn8FHzXW0Y-Gaw,8201
 vision_agent/fonts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1rtHiNC_6QosTE,1594400
@@ -23,14 +23,14 @@ vision_agent/tools/__init__.py,sha256=oZa_sslb1UqEgpdWROChDcz5JHdB475ejJX78FMLYv
 vision_agent/tools/easytool_tools.py,sha256=pZc5dQlYINlV4nYbbzsDi3-wauA-fCeD2iGmJUMoUfE,47373
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=wzRacbUpqk9hhfX_Y08rL8qP0XCN2w-8IZoYLi3Upn4,869
-vision_agent/tools/tools.py,sha256=nXjefpW9L-Xuos73ObDqpmJfOyUAJVrzoiHsxEE7O10,23346
+vision_agent/tools/tools.py,sha256=RVBuaP8KZrBVppEPaqP0Tey3Am6O5zoNIaZpBSW125c,23523
 vision_agent/utils/__init__.py,sha256=xsHFyJSDbLdonB9Dh74cwZnVTiT__2OQF3Brd3Nmglc,116
 vision_agent/utils/execute.py,sha256=8_SfK-IkHH4lXF0JVyV7sDFszZn9HKsh1bFITKGCJ1g,3881
 vision_agent/utils/image_utils.py,sha256=_cdiS5YrLzqkq_ZgFUO897m5M4_SCIThwUy4lOklfB8,7700
 vision_agent/utils/sim.py,sha256=oUZ-6eu8Io-UNt9GXJ0XRKtP-Wc0sPWVzYGVpB2yDFk,3001
 vision_agent/utils/type_defs.py,sha256=BlI8ywWHAplC7kYWLvt4AOdnKpEW3qWEFm-GEOSkrFQ,1792
 vision_agent/utils/video.py,sha256=xTElFSFp1Jw4ulOMnk81Vxsh-9dTxcWUO6P9fzEi3AM,7653
-vision_agent-0.2.34.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.34.dist-info/METADATA,sha256=G7TLFwGHMZmxNOCXouYlajbIwhIE4YTbyRCOOeBVpPY,6698
-vision_agent-0.2.34.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.34.dist-info/RECORD,,
+vision_agent-0.2.36.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.36.dist-info/METADATA,sha256=aKsyRoGvUDMRtezD5RCoJP3aTn6cky5DFO5t2vVaHx4,6698
+vision_agent-0.2.36.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.36.dist-info/RECORD,,