Skip to main content
Tasks can include image attachments for processing. The framework automatically handles image loading and provides them to the model for analysis.

​
Single Image Attachment

from upsonic import Agent, Task

agent = Agent(model="openai/gpt-4o")

# Task with single image
task = Task(
    description="Describe what you see in the attached image",
    context=["image.png"]
)

result = agent.do(task)
print(result)

​
Multiple Image Attachments

from upsonic import Agent, Task

agent = Agent(model="openai/gpt-4o")

# Task with multiple images
task = Task(
    description="Compare the two attached images and identify similarities and differences",
    context=["image1.jpg", "image2.jpg"]
)

result = agent.do(task)
print(result)

​
Images with Other Context

from upsonic import Agent, Task

agent = Agent(model="openai/gpt-4o")

# Task with images and other context
task = Task(
    description="Analyze the attached chart and provide insights based on the market data",
    context=["chart.png", market_data_task],
)

result = agent.do(task)
print(result)

​
Supported Image Formats

The framework supports various image formats including:
  • PNG (.png)
  • JPEG (.jpg, .jpeg)
  • GIF (.gif)
  • BMP (.bmp)
  • TIFF (.tiff)
from upsonic import Agent, Task

agent = Agent(model="openai/gpt-4o")

# Example with different image formats
task = Task(
    description="Analyze all the attached images",
    context=["photo.jpg", "diagram.png", "chart.tiff"]
)

result = agent.do(task)
print(result)

​
Image Processing with Tools

from upsonic import Agent, Task
from upsonic.tools import tool

@tool
def image_analyzer(image_path: str) -> str:
    """Analyze image content and return description."""
    # Your image analysis logic here
    return f"Analysis of {image_path}"

agent = Agent(model="openai/gpt-4o")

# Task combining image attachments with image analysis tools
task = Task(
    description="Analyze the attached images using the image analyzer tool",
    context=["image1.jpg", "image2.png"],
    tools=[image_analyzer]
)

result = agent.do(task)
print(result)

​
Best Practices

  • File Paths: Use absolute or relative paths that are accessible to your application
  • Image Size: Consider image file sizes for performance optimization
  • Format Selection: Choose appropriate formats based on your analysis needs
  • Error Handling: Handle cases where image files might not be accessible
  • Context Integration: Combine images with relevant text context for better analysis
  • Tool Integration: Use specialized image analysis tools when available