vision-agent 0.2.34__tar.gz → 0.2.36__tar.gz

{vision_agent-0.2.34 → vision_agent-0.2.36}/PKG-INFO

@@ -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 → vision_agent-0.2.36}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.34"
+version = "0.2.36"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

{vision_agent-0.2.34 → vision_agent-0.2.36}/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-0.2.34 → vision_agent-0.2.36}/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