#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
File: vectorize_save_noun.py
Date: 2025-05-15
Description: 专业名词向量化和保存的示例程序
"""

import os
import json
from dotenv import load_dotenv
import sys
from rag2_0.intent_recognition import ProfessionalNounVectorizer
import logging

# 加载环境变量
load_dotenv()

def main():
    """
    主函数：创建索引并保存
    """
    # 指定文件路径
    current_dir = os.path.dirname(os.path.abspath(__file__))
    output_dir = os.path.join(current_dir, "..", "..", "data", "nouns")
    
    # 创建向量化器并指定路径
    noun_vectorizer = ProfessionalNounVectorizer(
        output_dir=output_dir
    )
    file_paths = [
        os.path.join(current_dir, "..", "..", "data/nouns/merged_nouns.json"),
    ]
    # 执行向量化和保存（一步完成）
    success = noun_vectorizer.vectorize_files_and_save(file_paths)
    if success:
        logging.info("✓ 索引创建和保存成功")
        logging.info(f"  索引保存路径: {os.path.join(output_dir, 'professional_nouns_index')}")
    else:
        logging.error("✗ 索引创建失败")

if __name__ == "__main__":
    # 配置日志输出到控制台
    logging.basicConfig(
        level=logging.INFO,
        format='%(message)s'
    )
    main()