vision-agent 0.2.54__tar.gz → 0.2.56__tar.gz

{vision_agent-0.2.54 → vision_agent-0.2.56}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vision-agent
-Version: 0.2.54
+Version: 0.2.56
 Summary: Toolset for Vision Agent
 Author: Landing AI
 Author-email: dev@landing.ai
@@ -38,7 +38,6 @@ Description-Content-Type: text/markdown
     <img alt="vision_agent" height="200px" src="https://github.com/landing-ai/vision-agent/blob/main/assets/logo.jpg?raw=true">
 
 # 🔍🤖 Vision Agent
-
 [![](https://dcbadge.vercel.app/api/server/wPdN8RCYew?compact=true&style=flat)](https://discord.gg/wPdN8RCYew)
 ![ci_status](https://github.com/landing-ai/vision-agent/actions/workflows/ci_cd.yml/badge.svg)
 [![PyPI version](https://badge.fury.io/py/vision-agent.svg)](https://badge.fury.io/py/vision-agent)
@@ -52,9 +51,14 @@ accomplish the task you want. Vision Agent aims to provide an in-seconds experie
 allowing users to describe their problem in text and have the agent framework generate
 code to solve the task for them. Check out our discord for updates and roadmaps!
 
+
+## Web Application
+
+Try Vision Agent live on [va.landing.ai](https://va.landing.ai/)
+
 ## Documentation
 
-- [Vision Agent Library Docs](https://landing-ai.github.io/vision-agent/)
+[Vision Agent Library Docs](https://landing-ai.github.io/vision-agent/)
 
 
 ## Getting Started
@@ -88,28 +92,28 @@ from vision_agent.tools import load_image, grounding_sam
 def calculate_filled_percentage(image_path: str) -> float:
     # Step 1: Load the image
     image = load_image(image_path)
-    
+
     # Step 2: Segment the jar
     jar_segments = grounding_sam(prompt="jar", image=image)
-    
+
     # Step 3: Segment the coffee beans
     coffee_beans_segments = grounding_sam(prompt="coffee beans", image=image)
-    
+
     # Step 4: Calculate the area of the segmented jar
     jar_area = 0
     for segment in jar_segments:
         jar_area += segment['mask'].sum()
-    
+
     # Step 5: Calculate the area of the segmented coffee beans
     coffee_beans_area = 0
     for segment in coffee_beans_segments:
         coffee_beans_area += segment['mask'].sum()
-    
+
     # Step 6: Compute the percentage of the jar area that is filled with coffee beans
     if jar_area == 0:
         return 0.0  # To avoid division by zero
     filled_percentage = (coffee_beans_area / jar_area) * 100
-    
+
     # Step 7: Return the computed percentage
     return filled_percentage
 ```
@@ -197,12 +201,6 @@ 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-0.2.54 → vision_agent-0.2.56}/README.md

@@ -2,7 +2,6 @@
     <img alt="vision_agent" height="200px" src="https://github.com/landing-ai/vision-agent/blob/main/assets/logo.jpg?raw=true">
 
 # 🔍🤖 Vision Agent
-
 [![](https://dcbadge.vercel.app/api/server/wPdN8RCYew?compact=true&style=flat)](https://discord.gg/wPdN8RCYew)
 ![ci_status](https://github.com/landing-ai/vision-agent/actions/workflows/ci_cd.yml/badge.svg)
 [![PyPI version](https://badge.fury.io/py/vision-agent.svg)](https://badge.fury.io/py/vision-agent)
@@ -16,9 +15,14 @@ accomplish the task you want. Vision Agent aims to provide an in-seconds experie
 allowing users to describe their problem in text and have the agent framework generate
 code to solve the task for them. Check out our discord for updates and roadmaps!
 
+
+## Web Application
+
+Try Vision Agent live on [va.landing.ai](https://va.landing.ai/)
+
 ## Documentation
 
-- [Vision Agent Library Docs](https://landing-ai.github.io/vision-agent/)
+[Vision Agent Library Docs](https://landing-ai.github.io/vision-agent/)
 
 
 ## Getting Started
@@ -52,28 +56,28 @@ from vision_agent.tools import load_image, grounding_sam
 def calculate_filled_percentage(image_path: str) -> float:
     # Step 1: Load the image
     image = load_image(image_path)
-    
+
     # Step 2: Segment the jar
     jar_segments = grounding_sam(prompt="jar", image=image)
-    
+
     # Step 3: Segment the coffee beans
     coffee_beans_segments = grounding_sam(prompt="coffee beans", image=image)
-    
+
     # Step 4: Calculate the area of the segmented jar
     jar_area = 0
     for segment in jar_segments:
         jar_area += segment['mask'].sum()
-    
+
     # Step 5: Calculate the area of the segmented coffee beans
     coffee_beans_area = 0
     for segment in coffee_beans_segments:
         coffee_beans_area += segment['mask'].sum()
-    
+
     # Step 6: Compute the percentage of the jar area that is filled with coffee beans
     if jar_area == 0:
         return 0.0  # To avoid division by zero
     filled_percentage = (coffee_beans_area / jar_area) * 100
-    
+
     # Step 7: Return the computed percentage
     return filled_percentage
 ```
@@ -161,11 +165,5 @@ 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-0.2.54 → vision_agent-0.2.56}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "vision-agent"
-version = "0.2.54"
+version = "0.2.56"
 description = "Toolset for Vision Agent"
 authors = ["Landing AI <dev@landing.ai>"]
 readme = "README.md"

vision_agent-0.2.56/vision_agent/agent/__init__.py

@@ -0,0 +1,2 @@
+from .agent import Agent
+from .vision_agent import AzureVisionAgent, VisionAgent

{vision_agent-0.2.54 → vision_agent-0.2.56}/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-0.2.54/vision_agent/agent/__init__.py

@@ -1,2 +0,0 @@
-from .agent import Agent
-from .vision_agent import VisionAgent