File size: 2,566 Bytes
5d9aa5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
"""
Test the MultiModalAgent.
"""
import os
import sys
import logging
import json

# Add the current directory to sys.path to import local modules
sys.path.append(os.path.dirname(os.path.abspath(__file__)))

# Import the MultiModalAgent
from agent import MultiModalAgent

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger('test_agent')

def main():
    """Test the MultiModalAgent with some sample questions."""
    # Initialize the agent
    resource_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'resource')
    agent = MultiModalAgent(resource_dir=resource_dir)
    
    # Load test questions from metadata.jsonl
    metadata_path = os.path.join(resource_dir, 'metadata.jsonl')
    test_questions = []
    
    with open(metadata_path, 'r', encoding='utf-8') as f:
        for line in f:
            entry = json.loads(line.strip())
            if 'Question' in entry and 'file_name' in entry and entry['file_name']:
                test_questions.append({
                    'task_id': entry.get('task_id'),
                    'question': entry['Question'],
                    'file_name': entry['file_name'],
                    'expected_answer': entry.get('Final answer')
                })
                if len(test_questions) >= 5:  # Limit to 5 questions
                    break
    
    # If no questions with files were found, use some generic questions
    if not test_questions:
        test_questions = [
            {
                'question': "What's the oldest Blu-Ray in the inventory spreadsheet?",
                'file_name': None,
                'expected_answer': None
            },
            {
                'question': "How many files are in the resource directory?",
                'file_name': None,
                'expected_answer': None
            }
        ]
    
    # Test the agent with each question
    for i, q in enumerate(test_questions):
        question = q['question']
        logger.info(f"Testing question {i+1}: {question}")
        
        answer = agent(question)
        logger.info(f"Answer: {answer}")
        
        if q['expected_answer']:
            logger.info(f"Expected answer: {q['expected_answer']}")
            if answer.strip() == q['expected_answer'].strip():
                logger.info("Correct answer!")
            else:
                logger.warning("Incorrect answer.")
        
        logger.info("-" * 80)

if __name__ == "__main__":
    main()