vision-agent 0.2.1__py3-none-any.whl → 0.2.3__py3-none-any.whl

vision_agent/agent/vision_agent.py

@@ -8,7 +8,12 @@ from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple, Union
 from PIL import Image
 from tabulate import tabulate
 
-from vision_agent.image_utils import overlay_bboxes, overlay_masks, overlay_heat_map
+from vision_agent.image_utils import (
+    convert_to_b64,
+    overlay_bboxes,
+    overlay_heat_map,
+    overlay_masks,
+)
 from vision_agent.llm import LLM, OpenAILLM
 from vision_agent.lmm import LMM, OpenAILMM
 from vision_agent.tools import TOOLS
@@ -423,7 +428,7 @@ class VisionAgent(Agent):
     ):
         """VisionAgent constructor.
 
-        Parameters
+        Parameters:
             task_model: the model to use for task decomposition.
             answer_model: the model to use for reasoning and concluding the answer.
             reflect_model: the model to use for self reflection.
@@ -481,6 +486,17 @@ class VisionAgent(Agent):
         if self.report_progress_callback:
             self.report_progress_callback(description)
 
+    def _report_visualization_via_callback(
+        self, images: Sequence[Union[str, Path]]
+    ) -> None:
+        """This is intended for streaming the visualization images via the callback to the client side."""
+        if self.report_progress_callback:
+            self.report_progress_callback("<VIZ>")
+            if images:
+                for img in images:
+                    self.report_progress_callback(f"<IMG>{convert_to_b64(img)}</IMG>")
+            self.report_progress_callback("</VIZ>")
+
     def chat_with_workflow(
         self,
         chat: List[Dict[str, str]],
@@ -488,6 +504,21 @@ class VisionAgent(Agent):
         reference_data: Optional[Dict[str, str]] = None,
         visualize_output: Optional[bool] = False,
     ) -> Tuple[str, List[Dict]]:
+        """Chat with the vision agent and return the final answer and all tool results.
+
+        Parameters:
+            chat: a conversation in the format of
+                [{"role": "user", "content": "describe your task here..."}].
+            image: the input image referenced in the chat parameter.
+            reference_data: a dictionary containing the reference image and mask. in the
+                format of {"image": "image.jpg", "mask": "mask.jpg}
+            visualize_output: whether to visualize the output.
+
+        Returns:
+            A tuple where the first item is the final answer and the second item is a
+            list of all the tool results. The last item in the tool results also
+            contains the visualized output.
+        """
         question = chat[0]["content"]
         if image:
             question += f" Image name: {image}"
@@ -577,9 +608,12 @@ class VisionAgent(Agent):
         )
 
         if visualize_output:
-            visualized_output = all_tool_results[-1]["visualized_output"]
-            for image in visualized_output:
-                Image.open(image).show()
+            viz_images: Sequence[Union[str, Path]] = all_tool_results[-1][
+                "visualized_output"
+            ]
+            self._report_visualization_via_callback(viz_images)
+            for img in viz_images:
+                Image.open(img).show()
 
         return final_answer, all_tool_results
 

vision_agent/image_utils.py

@@ -4,7 +4,7 @@ import base64
 from importlib import resources
 from io import BytesIO
 from pathlib import Path
-from typing import Dict, Tuple, Union, List
+from typing import Dict, List, Tuple, Union
 
 import numpy as np
 from PIL import Image, ImageDraw, ImageFont
@@ -108,7 +108,7 @@ def convert_to_b64(data: Union[str, Path, np.ndarray, ImageType]) -> str:
         data = Image.open(data)
     if isinstance(data, Image.Image):
         buffer = BytesIO()
-        data.convert("RGB").save(buffer, format="JPEG")
+        data.convert("RGB").save(buffer, format="PNG")
         return base64.b64encode(buffer.getvalue()).decode("utf-8")
     else:
         arr_bytes = data.tobytes()

vision_agent/tools/tools.py

@@ -108,8 +108,7 @@ class CLIP(Tool):
 
 
 class ImageCaption(Tool):
-    r"""ImageCaption is a tool that can caption an image based on its contents
-    or tags.
+    r"""ImageCaption is a tool that can caption an image based on its contents or tags.
 
     Example
     -------
@@ -120,26 +119,20 @@ class ImageCaption(Tool):
     """
 
     name = "image_caption_"
-    description = "'image_caption_' is a tool that can caption an image based on its contents or tags. It returns a text describing the image"
+    description = "'image_caption_' is a tool that can caption an image based on its contents or tags. It returns a text describing the image."
     usage = {
         "required_parameters": [
             {"name": "image", "type": "str"},
         ],
         "examples": [
             {
-                "scenario": "Can you describe this image ? Image name: cat.jpg",
+                "scenario": "Can you describe this image? Image name: cat.jpg",
                 "parameters": {"image": "cat.jpg"},
             },
             {
-                "scenario": "Can you caption this image with their main contents ? Image name: cat_dog.jpg",
+                "scenario": "Can you caption this image with their main contents? Image name: cat_dog.jpg",
                 "parameters": {"image": "cat_dog.jpg"},
             },
-            {
-                "scenario": "Can you build me a image captioning tool ? Image name: shirts.jpg",
-                "parameters": {
-                    "image": "shirts.jpg",
-                },
-            },
         ],
     }
 
@@ -487,15 +480,15 @@ class ZeroShotCounting(Tool):
         ],
         "examples": [
             {
-                "scenario": "Can you count the lids in the image ? Image name: lids.jpg",
+                "scenario": "Can you count the lids in the image? Image name: lids.jpg",
                 "parameters": {"image": "lids.jpg"},
             },
             {
-                "scenario": "Can you count the total number of objects in this image ? Image name: tray.jpg",
+                "scenario": "Can you count the total number of objects in this image? Image name: tray.jpg",
                 "parameters": {"image": "tray.jpg"},
             },
             {
-                "scenario": "Can you build me an object counting tool ? Image name: shirts.jpg",
+                "scenario": "Can you build me an object counting tool? Image name: shirts.jpg",
                 "parameters": {
                     "image": "shirts.jpg",
                 },

{vision_agent-0.2.1.dist-info → vision_agent-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.1
+Version: 0.2.3
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai
@@ -126,15 +126,18 @@ you. For example:
 | Tool | Description |
 | --- | --- |
 | CLIP | CLIP is a tool that can classify or tag any image given a set of input classes or tags. |
+| ImageCaption| ImageCaption is a tool that can generate a caption for an image. |
 | GroundingDINO | GroundingDINO is a tool that can detect arbitrary objects with inputs such as category names or referring expressions. |
 | GroundingSAM | GroundingSAM is a tool that can detect and segment arbitrary objects with inputs such as category names or referring expressions. |
-| Counter | Counter detects and counts the number of objects in an image given an input such as a category name or referring expression. |
+| DINOv | DINOv is a tool that can detect arbitrary objects with using a referring mask. |
+| ExtractFrames | ExtractFrames extracts frames with motion from a video. |
 | Crop | Crop crops an image given a bounding box and returns a file name of the cropped image. |
 | BboxArea | BboxArea returns the area of the bounding box in pixels normalized to 2 decimal places. |
 | SegArea | SegArea returns the area of the segmentation mask in pixels normalized to 2 decimal places. |
 | BboxIoU | BboxIoU returns the intersection over union of two bounding boxes normalized to 2 decimal places. |
 | SegIoU | SegIoU returns the intersection over union of two segmentation masks normalized to 2 decimal places. |
-| ExtractFrames | ExtractFrames extracts frames with motion from a video. |
+| BoxDistance | BoxDistance returns the minimum distance between two bounding boxes normalized to 2 decimal places. |
+| BboxContains | BboxContains returns the intersection of two boxes over the target box area. It is good for check if one box is contained within another box. |
 | ExtractFrames | ExtractFrames extracts frames with motion from a video. |
 | ZeroShotCounting | ZeroShotCounting returns the total number of objects belonging to a single class in a given image |
 | VisualPromptCounting | VisualPromptCounting returns the total number of objects belonging to a single class given an image and visual prompt |

{vision_agent-0.2.1.dist-info → vision_agent-0.2.3.dist-info}/RECORD

@@ -5,21 +5,21 @@ vision_agent/agent/easytool.py,sha256=oMHnBg7YBtIPgqQUNcZgq7uMgpPThs99_UnO7ERkMV
 vision_agent/agent/easytool_prompts.py,sha256=zdQQw6WpXOmvwOMtlBlNKY5a3WNlr65dbUvMIGiqdeo,4526
 vision_agent/agent/reflexion.py,sha256=4gz30BuFMeGxSsTzoDV4p91yE0R8LISXp28IaOI6wdM,10506
 vision_agent/agent/reflexion_prompts.py,sha256=G7UAeNz_g2qCb2yN6OaIC7bQVUkda4m3z42EG8wAyfE,9342
-vision_agent/agent/vision_agent.py,sha256=MTxeV5_Sghqoe2aOW9EbNgiq61sVCcF3ZndJ7BZl6x0,23588
+vision_agent/agent/vision_agent.py,sha256=6AtVaEQL0ksg1QkUBn_YhytYjRfH7-M4q7G6pnds9Ds,25002
 vision_agent/agent/vision_agent_prompts.py,sha256=W3Z72FpUt71UIJSkjAcgtQqxeMqkYuATqHAN5fYY26c,7342
 vision_agent/fonts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1rtHiNC_6QosTE,1594400
-vision_agent/image_utils.py,sha256=Cg4aKO1tQiETT1gdsZ50XzORBtJnBFfMG2cKJyjaY6Q,7555
+vision_agent/image_utils.py,sha256=YvP5KE9NrWdgJKuHW2NR1glzfObkxtcXBknpmj3Gsbs,7554
 vision_agent/llm/__init__.py,sha256=BoUm_zSAKnLlE8s-gKTSQugXDqVZKPqYlWwlTLdhcz4,48
 vision_agent/llm/llm.py,sha256=gwDQ9-p9wEn24xi1019e5jzTGQg4xWDSqBCsqIqGcU4,5168
 vision_agent/lmm/__init__.py,sha256=nnNeKD1k7q_4vLb1x51O_EUTYaBgGfeiCx5F433gr3M,67
 vision_agent/lmm/lmm.py,sha256=FjxCuIk0KXuWnfY4orVmdyhJW2I4C6i5QNNEXk7gybk,10197
 vision_agent/tools/__init__.py,sha256=BlfxqbYkB0oODhnSmQg1UyzQm73AvvjCjrIiOWBIYDs,328
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
-vision_agent/tools/tools.py,sha256=gCjHs5vJuGNBFsnJWFT7PX3wTyfHgtrgX1Eq9vqknN0,34979
+vision_agent/tools/tools.py,sha256=Cwh7GNSnCYxyKKgusHlf-Cqd9NBjlbZG7d-GauQJCwI,34751
 vision_agent/tools/video.py,sha256=xTElFSFp1Jw4ulOMnk81Vxsh-9dTxcWUO6P9fzEi3AM,7653
 vision_agent/type_defs.py,sha256=4LTnTL4HNsfYqCrDn9Ppjg9bSG2ZGcoKSSd9YeQf4Bw,1792
-vision_agent-0.2.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.1.dist-info/METADATA,sha256=RAD8NCAo5N12sccgSC5Q0j4hKwU_rVKg5p_eLE-Njdc,6434
-vision_agent-0.2.1.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.1.dist-info/RECORD,,
+vision_agent-0.2.3.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.3.dist-info/METADATA,sha256=cQnQTRlWBxf0aVwsMoJS4TiiAtN3SbU00nlCrbNNb9w,6748
+vision_agent-0.2.3.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.3.dist-info/RECORD,,