Crew AI Integration

pip install crewai docling

from crewai import Agent, Task, Crew
from crewai.knowledge.source.crew_docling_source import CrewDoclingSource

# Create a Docling knowledge source
knowledge_source = CrewDoclingSource(
    file_paths=["document.pdf"]
)

# Create an agent with the knowledge source
agent = Agent(
    role="Research Analyst",
    goal="Analyze documents and extract key insights",
    backstory="You are an expert at analyzing complex documents.",
    knowledge_sources=[knowledge_source]
)

# Create a task
task = Task(
    description="Summarize the main findings from the document",
    agent=agent,
    expected_output="A concise summary of key findings"
)

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

result = crew.kickoff()
print(result)

from crewai import Agent, Task, Crew
from crewai.knowledge.source.crew_docling_source import CrewDoclingSource

# Create knowledge source
knowledge_source = CrewDoclingSource(
    file_paths=["report.pdf", "analysis.docx"]
)

# Create specialized agents
researcher = Agent(
    role="Document Researcher",
    goal="Extract and organize information from documents",
    backstory="Expert at finding relevant information in complex documents",
    knowledge_sources=[knowledge_source]
)

analyst = Agent(
    role="Data Analyst",
    goal="Analyze extracted data and identify patterns",
    backstory="Specialist in data analysis and pattern recognition",
    knowledge_sources=[knowledge_source]
)

writer = Agent(
    role="Technical Writer",
    goal="Create comprehensive reports based on analysis",
    backstory="Skilled at synthesizing complex information into clear reports"
)

# Define tasks
research_task = Task(
    description="Extract all key data points and findings from the documents",
    agent=researcher,
    expected_output="Structured list of key findings and data"
)

analysis_task = Task(
    description="Analyze the extracted data for trends and insights",
    agent=analyst,
    expected_output="Analysis report with identified trends",
    context=[research_task]
)

writing_task = Task(
    description="Write a comprehensive report combining research and analysis",
    agent=writer,
    expected_output="Final comprehensive report",
    context=[research_task, analysis_task]
)

# Create and run crew
crew = Crew(
    agents=[researcher, analyst, writer],
    tasks=[research_task, analysis_task, writing_task],
    verbose=True
)

result = crew.kickoff()

from crewai.knowledge.source.crew_docling_source import CrewDoclingSource

# Process various document formats
knowledge_source = CrewDoclingSource(
    file_paths=[
        "financial_report.pdf",
        "presentation.pptx",
        "analysis.docx",
        "data.html"
    ]
)

agent = Agent(
    role="Document Analyzer",
    goal="Analyze documents across different formats",
    backstory="Expert at processing various document types",
    knowledge_sources=[knowledge_source]
)

# Research agent that analyzes academic papers
knowledge_source = CrewDoclingSource(
    file_paths=["paper1.pdf", "paper2.pdf", "paper3.pdf"]
)

research_agent = Agent(
    role="Academic Researcher",
    goal="Analyze research papers and identify key contributions",
    backstory="PhD-level researcher with expertise in literature review",
    knowledge_sources=[knowledge_source]
)

task = Task(
    description="Compare methodologies across the three papers",
    agent=research_agent,
    expected_output="Comparative analysis of methodologies"
)

# Compliance agent that checks documents against regulations
knowledge_source = CrewDoclingSource(
    file_paths=["contract.pdf", "policy.docx"]
)

compliance_agent = Agent(
    role="Compliance Officer",
    goal="Ensure documents meet regulatory requirements",
    backstory="Expert in regulatory compliance and risk assessment",
    knowledge_sources=[knowledge_source]
)

task = Task(
    description="Review documents for compliance issues",
    agent=compliance_agent,
    expected_output="Compliance assessment report"
)

from crewai.knowledge.source.crew_docling_source import CrewDoclingSource

# Configure Docling processing options
knowledge_source = CrewDoclingSource(
    file_paths=["document.pdf"],
    # Additional Docling options can be configured here
)

# Use with agents
agent = Agent(
    role="Document Expert",
    goal="Process documents with custom settings",
    backstory="Specialist in document processing",
    knowledge_sources=[knowledge_source],
    verbose=True
)