vision-agent 0.2.53__py3-none-any.whl → 0.2.55__py3-none-any.whl

vision_agent/agent/__init__.py

@@ -1,2 +1,2 @@
 from .agent import Agent
-from .vision_agent import VisionAgent
+from .vision_agent import AzureVisionAgent, VisionAgent

vision_agent/agent/vision_agent.py

@@ -13,6 +13,7 @@ from rich.style import Style
 from rich.syntax import Syntax
 from tabulate import tabulate
 
+from vision_agent.llm.llm import AzureOpenAILLM
 import vision_agent.tools as T
 from vision_agent.agent import Agent
 from vision_agent.agent.vision_agent_prompts import (
@@ -29,7 +30,7 @@ from vision_agent.lmm import LMM, OpenAILMM
 from vision_agent.utils import CodeInterpreterFactory, Execution
 from vision_agent.utils.execute import CodeInterpreter
 from vision_agent.utils.image_utils import b64_to_pil
-from vision_agent.utils.sim import Sim
+from vision_agent.utils.sim import AzureSim, Sim
 from vision_agent.utils.video import play_video
 
 logging.basicConfig(stream=sys.stdout)
@@ -615,3 +616,66 @@ class VisionAgent(Agent):
     def log_progress(self, data: Dict[str, Any]) -> None:
         if self.report_progress_callback is not None:
             self.report_progress_callback(data)
+
+
+class AzureVisionAgent(VisionAgent):
+    """Vision Agent that uses Azure OpenAI APIs for planning, coding, testing.
+
+    Pre-requisites:
+    1. Set the environment variable AZURE_OPENAI_API_KEY to your Azure OpenAI API key.
+    2. Set the environment variable AZURE_OPENAI_ENDPOINT to your Azure OpenAI endpoint.
+
+    Example
+    -------
+        >>> from vision_agent import AzureVisionAgent
+        >>> agent = AzureVisionAgent()
+        >>> code = agent("What percentage of the area of the jar is filled with coffee beans?", media="jar.jpg")
+    """
+
+    def __init__(
+        self,
+        planner: Optional[Union[LLM, LMM]] = None,
+        coder: Optional[LLM] = None,
+        tester: Optional[LLM] = None,
+        debugger: Optional[LLM] = None,
+        tool_recommender: Optional[Sim] = None,
+        verbosity: int = 0,
+        report_progress_callback: Optional[Callable[[Dict[str, Any]], None]] = None,
+    ) -> None:
+        """Initialize the Vision Agent.
+
+        Parameters:
+            planner (Optional[LLM]): The planner model to use. Defaults to OpenAILLM.
+            coder (Optional[LLM]): The coder model to use. Defaults to OpenAILLM.
+            tester (Optional[LLM]): The tester model to use. Defaults to OpenAILLM.
+            debugger (Optional[LLM]): The debugger model to
+            tool_recommender (Optional[Sim]): The tool recommender model to use.
+            verbosity (int): The verbosity level of the agent. Defaults to 0. 2 is the
+                highest verbosity level which will output all intermediate debugging
+                code.
+            report_progress_callback: a callback to report the progress of the agent.
+                This is useful for streaming logs in a web application where multiple
+                VisionAgent instances are running in parallel. This callback ensures
+                that the progress are not mixed up.
+        """
+        super().__init__(
+            planner=(
+                AzureOpenAILLM(temperature=0.0, json_mode=True)
+                if planner is None
+                else planner
+            ),
+            coder=AzureOpenAILLM(temperature=0.0) if coder is None else coder,
+            tester=AzureOpenAILLM(temperature=0.0) if tester is None else tester,
+            debugger=(
+                AzureOpenAILLM(temperature=0.0, json_mode=True)
+                if debugger is None
+                else debugger
+            ),
+            tool_recommender=(
+                AzureSim(T.TOOLS_DF, sim_key="desc")
+                if tool_recommender is None
+                else tool_recommender
+            ),
+            verbosity=verbosity,
+            report_progress_callback=report_progress_callback,
+        )

{vision_agent-0.2.53.dist-info → vision_agent-0.2.55.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.53
+Version: 0.2.55
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai
@@ -197,12 +197,6 @@ You can then run Vision Agent using the Azure OpenAI models:
 ```python
 import vision_agent as va
 import vision_agent.tools as T
-agent = va.agent.VisionAgent(
-    planner=va.llm.AzureOpenAILLM(),
-    coder=va.lmm.AzureOpenAILLM(),
-    tester=va.lmm.AzureOpenAILLM(),
-    debugger=va.lmm.AzureOpenAILLM(),
-    tool_recommender=va.utils.AzureSim(T.TOOLS_DF, sim_key="desc"),
-)
+agent = va.agent.AzureVisionAgent()
 ```
 

{vision_agent-0.2.53.dist-info → vision_agent-0.2.55.dist-info}/RECORD

@@ -1,5 +1,5 @@
 vision_agent/__init__.py,sha256=GVLHCeK_R-zgldpbcPmOzJat-BkadvkuRCMxDvTIcXs,108
-vision_agent/agent/__init__.py,sha256=5OO2NAELYV-TZALCxF8DGvPbDHltZEAVkL665O-ck94,63
+vision_agent/agent/__init__.py,sha256=IUwfbPMcT8X_rnXMLmI8gJ4ltsHy_XSs9eLiKURJxeY,81
 vision_agent/agent/agent.py,sha256=TXh93MOwmArNRieOkYrhliq1rf7wIkhxvCdTiGhTqFs,538
 vision_agent/agent/agent_coder.py,sha256=IBGQYw_XT08GIZYi9Q9i9GJU_icneGaQ9r1EIxP-G4g,7228
 vision_agent/agent/agent_coder_prompts.py,sha256=CJe3v7xvHQ32u3RQAXQga_Tk_4UgU64RBAMHZ3S70KY,5538
@@ -11,7 +11,7 @@ vision_agent/agent/easytool_v2.py,sha256=LY2cqzjVHBr7QMn4WsrZ7AfpWrDN0LjJIrd5tMo
 vision_agent/agent/easytool_v2_prompts.py,sha256=MZSIwovYgB-f-kdJ6btaNDVXptJn47bfOL3-Zn6NiC0,8573
 vision_agent/agent/reflexion.py,sha256=scck3YcME6DhX5Vs4Wr1rYb8S4wkBUkN9UksyazfrZg,10506
 vision_agent/agent/reflexion_prompts.py,sha256=G7UAeNz_g2qCb2yN6OaIC7bQVUkda4m3z42EG8wAyfE,9342
-vision_agent/agent/vision_agent.py,sha256=wGGISg6pDVNseF2fIAN1jH66OX2qZk2nDhuobeSNGHk,20957
+vision_agent/agent/vision_agent.py,sha256=fM_-0qIHHGPwa4S0dtcY7ikzXUaht0BjHo4wVRwwWsE,23720
 vision_agent/agent/vision_agent_prompts.py,sha256=9QVQA-YTSHhYHYbxiqCWFVBHIa6uV4WF0z6599mV_Oc,8470
 vision_agent/fonts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1rtHiNC_6QosTE,1594400
@@ -30,7 +30,7 @@ vision_agent/utils/image_utils.py,sha256=_cdiS5YrLzqkq_ZgFUO897m5M4_SCIThwUy4lOk
 vision_agent/utils/sim.py,sha256=rGRGnjsy91IOn8qzt7k04PIRj5jyiaQyYAQl7ossPt8,4195
 vision_agent/utils/type_defs.py,sha256=BlI8ywWHAplC7kYWLvt4AOdnKpEW3qWEFm-GEOSkrFQ,1792
 vision_agent/utils/video.py,sha256=rNmU9KEIkZB5-EztZNlUiKYN0mm_55A_2VGUM0QpqLA,8779
-vision_agent-0.2.53.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.53.dist-info/METADATA,sha256=0p9P33esnEQAWlqOsXC9YLxcR1R5E0oKURtWZ40hf_U,6887
-vision_agent-0.2.53.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.53.dist-info/RECORD,,
+vision_agent-0.2.55.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.55.dist-info/METADATA,sha256=p5yZXgthGKhq9l8qMEiYxPu1mYjPkKuTkuJbjBm6tp8,6677
+vision_agent-0.2.55.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.55.dist-info/RECORD,,