created qa_agents_workflow

[Itz-Antaripa]

Description

This PR introduces a QA Workflow for evaluating the performance of a question-answering agent. The workflow performs the following steps:

• Knowledge Base Creation: Scrapes data from provided website URLs, chunks the content using recursive chunking, and stores it in a vector database powered by LanceDB.
• Question Answering: The QA agent retrieves relevant context from the knowledge base and generates answers for a given evaluation dataset.
• Answer Evaluation: A judge agent evaluates the generated answers against ground truth using predefined criteria (bad, average, good) and provides reasoning for the judgment.
• Timing Metrics: Logs the time taken for knowledge base loading and answer generation.

Checklist

• My code follows Phidata's style guidelines and best practices
• I have performed a self-review of my code
• I have added docstrings and comments for complex logic
• My changes generate no new warnings or errors
• I have added cookbook examples for my new addition (if needed)
• I have updated requirements.txt/pyproject.toml (if needed)
• I have verified my changes in a clean environment