Smart FAQ Generation

faq_task = Task(
    description="""Generate 10 frequently asked questions and detailed 
                   answers about "{topic}" based on the research findings.
                   
                   Requirements:
                   - 10 unique and relevant questions
                   - Questions cover different aspects from research
                   - Focus on likely reader questions
                   - Logical progression from basic to advanced
                   - Clear and specific questions
                   
                   Answer Requirements:
                   - Detailed, accurate answers from research
                   - Citations from sources
                   - Markdown formatting
                   - Concise but comprehensive
                   - Professional tone
                   - Include relevant quotes
                   
                   Citation Format:
                   > "Quote text" - [Source Title](url)""",
    expected_output="""JSON object containing array of 10 FAQ items, 
                       each with question and detailed answer supported 
                       by citations from research.""",
    agent=researcher,
    context=[research_task],  # Uses research analysis as context
    max_retries=5,
    output_pydantic=FaqTaskResult
)

class FaqItem(BaseModel):
    question: str
    answer: str  # Markdown-formatted with citations

class FaqTaskResult(BaseModel):
    faq: List[FaqItem]  # Exactly 10 items

research_content_crew = Crew(
    agents=[researcher, content_writer],
    tasks=[research_task, faq_task, content_task],
    verbose=True,
    process=Process.sequential,
    max_rpm=20
)

research_content_crew_result = await research_content_crew.kickoff_async(inputs={
    "topic": topic,
    "scraped_data": scraped_data,
    "current_time": current_time,
})

# Extract FAQ results
faq_result = faq_task.output.pydantic.faq

return {
    "blog_post": research_content_crew_result["blog_post"],
    "title": research_content_crew_result["title"],
    "faq": [faq.model_dump() for faq in faq_result]
}

const FaqList = memo(
  ({ faqs }: { faqs: { question: string; answer: string }[] }) => {
    if (!faqs || faqs.length === 0) {
      return (
        <div className="text-muted-foreground">
          No FAQs available for this notebook
        </div>
      );
    }

    return (
      <div className="space-y-6">
        {faqs.map((faq, index) => (
          <div key={index} className="space-y-2">
            <h3 className="text-lg font-semibold">{faq.question}</h3>
            <div className="markdown-container prose prose-sm">
              <ReactMarkdown
                remarkPlugins={[remarkGfm]}
                components={MarkdownComponents}
              >
                {faq.answer}
              </ReactMarkdown>
            </div>
          </div>
        ))}
      </div>
    );
  }
);