使用多模态智能体

from crewai import Agent

agent = Agent(
    role="Image Analyst",
    goal="Analyze and extract insights from images",
    backstory="An expert in visual content interpretation with years of experience in image analysis",
    multimodal=True  # This enables multimodal capabilities
)

from crewai import Agent, Task, Crew

# Create a multimodal agent
image_analyst = Agent(
    role="Product Analyst",
    goal="Analyze product images and provide detailed descriptions",
    backstory="Expert in visual product analysis with deep knowledge of design and features",
    multimodal=True
)

# Create a task for image analysis
task = Task(
    description="Analyze the product image at https://example.com/product.jpg and provide a detailed description",
    expected_output="A detailed description of the product image",
    agent=image_analyst
)

# Create and run the crew
crew = Crew(
    agents=[image_analyst],
    tasks=[task]
)

result = crew.kickoff()

from crewai import Agent, Task, Crew

# Create a multimodal agent for detailed analysis
expert_analyst = Agent(
    role="Visual Quality Inspector",
    goal="Perform detailed quality analysis of product images",
    backstory="Senior quality control expert with expertise in visual inspection",
    multimodal=True  # AddImageTool is automatically included
)

# Create a task with specific analysis requirements
inspection_task = Task(
    description="""
    Analyze the product image at https://example.com/product.jpg with focus on:
    1. Quality of materials
    2. Manufacturing defects
    3. Compliance with standards
    Provide a detailed report highlighting any issues found.
    """,
    expected_output="A detailed report highlighting any issues found",
    agent=expert_analyst
)

# Create and run the crew
crew = Crew(
    agents=[expert_analyst],
    tasks=[inspection_task]
)

result = crew.kickoff()

class AddImageToolSchema:
    image_url: str  # Required: The URL or path of the image to process
    action: Optional[str] = None  # Optional: Additional context or specific questions about the image