config.py

"""
Configuration file for RAG Analytics Application
"""
import os

# Data folder configuration
DATA_FOLDER = os.environ.get("DATA_FOLDER", "./data")

# Required columns after normalization
REQUIRED_COLUMNS = {
    'test_id',
    'config_purpose',
    'dataset_name'
}

# Metric columns that need numeric conversion to float
METRIC_COLUMNS = [
    'rmse_relevance',
    'rmse_utilization', 
    'rmse_completeness',
    'f1_score',
    'aucroc'
]

# Numeric configuration columns (also need float conversion)
NUMERIC_CONFIG_COLUMNS = [
    'chunk_size',
    'overlap',
    'stride',
    'alpha',
    'retr_k',
    'final_k',
    'summ_max',
    'summ_min',
    'test_id'
]

# Column mapping for normalization
COLUMN_MAP = {
    'test': 'test_id',
    'configurationpurpose': 'config_purpose',
    'subsets': 'dataset_name',
    'embeddingmodel': 'embedding_model',
    'rerankermodel': 'reranker_model',
    'summarizationmodel': 'summarization_model',
    'summarization': 'summarization',  # New column name (enabled/disabled)
    'chunkingstrategy': 'chunking_strategy',
    'chunksize': 'chunk_size',
    'overlap': 'overlap',
    'stride': 'stride',
    'retreivalstrategy': 'retrieval_strategy', 
    'retrievalstrategy': 'retrieval_strategy',  # Catch typo
    'alpha': 'alpha',
    'retrk': 'retr_k',
    'finalk': 'final_k',
    'repacking': 'repacking',
    'summmax': 'summ_max',
    'summmin': 'summ_min',
    '8bgptlabel': 'gpt_label',
    
    # Metrics
    'rmsetracerelevance': 'rmse_relevance',
    'rmsetraceutilization': 'rmse_utilization',
    'rmsetracecompleteness': 'rmse_completeness',
    'aucroc': 'aucroc',
    'f1score': 'f1_score',
    'failedtotalsamples': 'failed_samples'
}

# Metadata columns (excluded from constant/variable analysis)
METADATA_COLUMNS = [
    'rmse_relevance', 'rmse_utilization', 'rmse_completeness',
    'aucroc', 'f1_score',
    'test_id', 'config_purpose', 'dataset_name'
]

# Debug mode
DEBUG = True