vision-agent 0.2.185__py3-none-any.whl → 0.2.186__py3-none-any.whl

vision_agent/tools/tools.py

@@ -1057,23 +1057,25 @@ def video_temporal_localization(
     prompt: str,
     frames: List[np.ndarray],
     model: str = "qwen2vl",
-    chunk_length: Optional[float] = None,
-    chunk_length_seconds: Optional[float] = None,
     chunk_length_frames: Optional[int] = 2,
 ) -> List[float]:
-    """'video_temporal_localization' is a tool that can find objects in a video given a question about it.
-    It returns a list of floats with a value of 1.0 if the object to be found is present in the chunk of video being analyzed.
+    """'video_temporal_localization' will run qwen2vl on each chunk_length_frames
+    value selected for the video. It can detect multiple objects independently per
+    chunk_length_frames given a text prompt such as a referring expression
+    but does not track objects across frames.
+    It returns a list of floats with a value of 1.0 if the objects are found in a given
+    chunk_length_frames of the video.
 
     Parameters:
         prompt (str): The question about the video
         frames (List[np.ndarray]): The reference frames used for the question
-        model (str): The model to use for the inference. Valid values are 'qwen2vl', 'gpt4o', 'internlm-xcomposer'
-        chunk_length (Optional[float]): length of each chunk in seconds
-        chunk_length_seconds (Optional[float]): alternative length for chunk in seconds
+        model (str): The model to use for the inference. Valid values are
+            'qwen2vl', 'gpt4o', 'internlm-xcomposer'
         chunk_length_frames (Optional[int]): length of each chunk in frames
 
     Returns:
-        List[float]: A list of floats with a value of 1.0 if the object to be found is present in the chunk of video
+        List[float]: A list of floats with a value of 1.0 if the objects to be found
+            are present in the chunk_length_frames of the video.
 
     Example
     -------
@@ -1088,10 +1090,6 @@ def video_temporal_localization(
         "model": model,
         "function_name": "video_temporal_localization",
     }
-    if chunk_length is not None:
-        payload["chunk_length"] = chunk_length
-    if chunk_length_seconds is not None:
-        payload["chunk_length_seconds"] = chunk_length_seconds
     if chunk_length_frames is not None:
         payload["chunk_length_frames"] = chunk_length_frames
 
@@ -1790,9 +1788,8 @@ def flux_image_inpainting(
             where 1 indicates areas to be inpainted and 0 indicates areas to be preserved.
 
     Returns:
-        np.ndarray:
-            The generated image(s) as a numpy array in RGB format
-            with values ranging from 0 to 255.
+        np.ndarray: The generated image(s) as a numpy array in RGB format with values
+            ranging from 0 to 255.
 
     -------
     Example:
@@ -2351,6 +2348,7 @@ FUNCTION_TOOLS = [
     closest_box_distance,
     qwen2_vl_images_vqa,
     qwen2_vl_video_vqa,
+    video_temporal_localization,
 ]
 
 UTIL_TOOLS = [

{vision_agent-0.2.185.dist-info → vision_agent-0.2.186.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.185
+Version: 0.2.186
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai
@@ -63,10 +63,10 @@ code to solve the task for them. Check out our discord for updates and roadmaps!
 ## Table of Contents
 - [🚀Quick Start](#quick-start)
 - [📚Documentation](#documentation)
-- [🔍🤖VisionAgent](#vision-agent-basic-usage)
+- [🔍🤖VisionAgent](#visionagent-basic-usage)
 - [🛠️Tools](#tools)
 - [🤖LMMs](#lmms)
-- [💻🤖VisionAgent Coder](#vision-agent-coder)
+- [💻🤖VisionAgent Coder](#visionagent-coder)
 - [🏗️Additional Backends](#additional-backends)
 
 ## Quick Start

{vision_agent-0.2.185.dist-info → vision_agent-0.2.186.dist-info}/RECORD

@@ -20,7 +20,7 @@ vision_agent/tools/__init__.py,sha256=KVP4_6qxOb2lpFdQgQtyDfdkMLL1O6wVZNK19MXp-x
 vision_agent/tools/meta_tools.py,sha256=by7TIbH7lsLIayX_Pe2mS1iw8aeLn2T8yqAo8SkB9Kg,32074
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=VPGqGJ2ZYEJA6AW7K9X7hQv6vRlMtAQcybE4izdToCw,8196
-vision_agent/tools/tools.py,sha256=us3fOV3JIqFB9WidEX6NT65HwJbIxhh59RRvUcMIshI,83251
+vision_agent/tools/tools.py,sha256=-oq8jzITi-yVYJ3ut5MuGJ65jd3ESRtHfw4SCAruMps,83059
 vision_agent/tools/tools_types.py,sha256=8hYf2OZhI58gvf65KGaeGkt4EQ56nwLFqIQDPHioOBc,2339
 vision_agent/utils/__init__.py,sha256=7fMgbZiEwbNS0fBOS_hJI5PuEYBblw36zLi_UjUzvj4,244
 vision_agent/utils/exceptions.py,sha256=booSPSuoULF7OXRr_YbC4dtKt6gM_HyiFQHBuaW86C4,2052
@@ -29,7 +29,7 @@ vision_agent/utils/image_utils.py,sha256=rm9GfXvD4JrjnqKrP_f2gfq4SzmqYC0IdC1kKwd
 vision_agent/utils/sim.py,sha256=ZuSS07TUXFGjipmiQoY8TKRmSes7XXCdtU9PI8PC1sw,5609
 vision_agent/utils/type_defs.py,sha256=BE12s3JNQy36QvauXHjwyeffVh5enfcvd4vTzSwvEZI,1384
 vision_agent/utils/video.py,sha256=fOPR48-SuwMbE5eB5rc2F7lVo6k1mVHn26eEJ0QCslc,5602
-vision_agent-0.2.185.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.185.dist-info/METADATA,sha256=Wgo1bRpQ3MgqxIDpBiN0Tj0YAUBwRtYCQ7DmhJwgKpY,18330
-vision_agent-0.2.185.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.185.dist-info/RECORD,,
+vision_agent-0.2.186.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.186.dist-info/METADATA,sha256=NQfESIRsq9-QWyPzNkyv6dSuRS6TGe5D2tZH4iJpeBU,18328
+vision_agent-0.2.186.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.186.dist-info/RECORD,,