deep-searcher/test_web_search.py

#!/usr/bin/env python3
"""
测试网页搜索功能
"""

import sys
import os
sys.path.append(os.path.dirname(os.path.abspath(__file__)))

from deepsearcher.web_search import WebSearch
from deepsearcher import configuration

def test_web_search():
    """测试网页搜索功能"""
    print("=== 测试网页搜索功能 ===")

    # 初始化网页搜索
    web_search = WebSearch()

    # 测试查询
    test_query = "Milvus是什么"
    print(f"测试查询: {test_query}")

    # 执行搜索
    results = web_search.search_with_retry(test_query, size=4)

    if results:
        print(f"找到 {len(results)} 个搜索结果:")
        for i, result in enumerate(results, 1):
            print(f"\n--- 结果 {i} ---")
            print(f"标题: {result.metadata.get('title', 'N/A')}")
            print(f"链接: {result.reference}")
            print(f"分数: {result.score}")
            print(f"内容长度: {len(result.text)} 字符")
            print(f"内容预览: {result.text[:200]}...")
    else:
        print("未找到搜索结果")

def test_integration():
    """测试与DeepSearch的集成"""
    print("\n=== 测试与DeepSearch的集成 ===")

    # 初始化配置
    configuration.init_config(configuration.config)

    # 创建DeepSearch实例（启用网页搜索）
    from deepsearcher.agent.deep_search import DeepSearch

    searcher = DeepSearch(
        llm=configuration.llm,
        embedding_model=configuration.embedding_model,
        vector_db=configuration.vector_db,
        max_iter=2,
        enable_web_search=True
    )

    # 测试查询
    test_query = "Milvus是什么"
    print(f"测试查询: {test_query}")

    # 执行搜索
    results, sub_queries = searcher.retrieve(test_query, max_iter=2)

    print(f"生成的子问题: {sub_queries}")
    print(f"找到 {len(results)} 个搜索结果")
    # 显示结果统计
    web_results = [r for r in results if r.metadata and r.metadata.get("source") == "webpage"]
    vector_results = [r for r in results if not r.metadata or r.metadata.get("source") != "webpage"]

    print(f"网页搜索结果: {len(web_results)} 个")
    print(f"向量数据库结果: {len(vector_results)} 个")

if __name__ == "__main__":
    test_web_search()
    test_integration()