vision-agent 0.2.1__tar.gz → 0.2.2__tar.gz

{vision_agent-0.2.1 → vision_agent-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.1
+Version: 0.2.2
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai

{vision_agent-0.2.1 → vision_agent-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.1"
+version = "0.2.2"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

{vision_agent-0.2.1 → vision_agent-0.2.2}/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
@@ -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]],
@@ -577,9 +593,12 @@ 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-0.2.1 → vision_agent-0.2.2}/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()