vision-agent 0.2.4__tar.gz → 0.2.5__tar.gz

{vision_agent-0.2.4 → vision_agent-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.4
+Version: 0.2.5
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.4 → vision_agent-0.2.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.4"
+version = "0.2.5"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

{vision_agent-0.2.4 → vision_agent-0.2.5}/vision_agent/agent/vision_agent.py

@@ -366,6 +366,20 @@ def _handle_viz_tools(
     return image_to_data
 
 
+def sample_n_evenly_spaced(lst: Sequence, n: int) -> Sequence:
+    if n <= 0:
+        return []
+    elif len(lst) == 0:
+        return []
+    elif n == 1:
+        return [lst[0]]
+    elif n >= len(lst):
+        return lst
+
+    spacing = (len(lst) - 1) / (n - 1)
+    return [lst[round(spacing * i)] for i in range(n)]
+
+
 def visualize_result(all_tool_results: List[Dict]) -> Sequence[Union[str, Path]]:
     image_to_data: Dict[str, Dict] = {}
     for tool_result in all_tool_results:
@@ -584,7 +598,7 @@ class VisionAgent(Agent):
             visualized_output = visualize_result(all_tool_results)
             all_tool_results.append({"visualized_output": visualized_output})
             if len(visualized_output) > 0:
-                reflection_images = visualized_output
+                reflection_images = sample_n_evenly_spaced(visualized_output, 3)
             elif image is not None:
                 reflection_images = [image]
             else:

{vision_agent-0.2.4 → vision_agent-0.2.5}/vision_agent/lmm/lmm.py

@@ -9,10 +9,7 @@ from typing import Any, Callable, Dict, List, Optional, Union, cast
 import requests
 from openai import AzureOpenAI, OpenAI
 
-from vision_agent.tools import (
-    CHOOSE_PARAMS,
-    SYSTEM_PROMPT,
-)
+from vision_agent.tools import CHOOSE_PARAMS, SYSTEM_PROMPT
 
 _LOGGER = logging.getLogger(__name__)
 

{vision_agent-0.2.4 → vision_agent-0.2.5}/vision_agent/tools/__init__.py

@@ -12,12 +12,12 @@ from .tools import (  # Counter,
     GroundingDINO,
     GroundingSAM,
     ImageCaption,
-    ZeroShotCounting,
-    VisualPromptCounting,
-    VisualQuestionAnswering,
     ImageQuestionAnswering,
     SegArea,
     SegIoU,
     Tool,
+    VisualPromptCounting,
+    VisualQuestionAnswering,
+    ZeroShotCounting,
     register_tool,
 )

{vision_agent-0.2.4 → vision_agent-0.2.5}/vision_agent/tools/tools.py

@@ -17,9 +17,9 @@ from vision_agent.image_utils import (
     normalize_bbox,
     rle_decode,
 )
+from vision_agent.lmm import OpenAILMM
 from vision_agent.tools.video import extract_frames_from_video
 from vision_agent.type_defs import LandingaiAPIKey
-from vision_agent.lmm import OpenAILMM
 
 _LOGGER = logging.getLogger(__name__)
 _LND_API_KEY = LandingaiAPIKey().api_key