deepsearch-service
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese功能
Features
基于 LLM 的迭代式深度搜索服务,能够:
- 将复杂问题分解为多个子查询
- 迭代搜索收集多源信息
- 评估信息充分性,动态调整搜索策略
- 综合生成结构化分析报告
LLM-based iterative deep search service that can:
- Decompose complex problems into multiple sub-queries
- Iteratively search and collect multi-source information
- Evaluate information sufficiency and dynamically adjust search strategies
- Synthesize and generate structured analysis reports
适用场景
Application Scenarios
- 复杂问题需要多角度分析
- 需要综合多个来源的信息
- 要求生成完整的研究报告
- Complex problems requiring multi-angle analysis
- Need to synthesize information from multiple sources
- Require generating complete research reports
调用方式
Calling Method
python
from services.deepsearch_service.client import DeepSearchClient
client = DeepSearchClient()python
from services.deepsearch_service.client import DeepSearchClient
client = DeepSearchClient()健康检查
健康检查
status = client.health_check()
status = client.health_check()
深度搜索(默认参数)
深度搜索(默认参数)
result = client.search("Python异步编程的最佳实践有哪些?")
result = client.search("Python异步编程的最佳实践有哪些?")
自定义参数
自定义参数
result = client.search(
query="如何设计一个高可用的微服务架构?",
max_iterations=3, # 最大迭代次数 (1-5)
queries_per_iteration=3, # 每轮查询数 (1-5)
depth_level="deep" # 搜索深度: quick/normal/deep
)
result = client.search(
query="如何设计一个高可用的微服务架构?",
max_iterations=3, # 最大迭代次数 (1-5)
queries_per_iteration=3, # 每轮查询数 (1-5)
depth_level="deep" # 搜索深度: quick/normal/deep
)
获取报告和来源
获取报告和来源
print(result["report"])
for source in result["sources"]:
print(f"- {source['title']}: {source['url']}")
undefinedprint(result["report"])
for source in result["sources"]:
print(f"- {source['title']}: {source['url']}")
undefined返回格式
Return Format
json
{
"query": "Python异步编程的最佳实践有哪些?",
"report": "# Python异步编程最佳实践\n\n## 1. 核心概念...",
"sources": [
{
"title": "Python官方asyncio文档",
"url": "https://docs.python.org/...",
"relevance": 0.95,
"snippet": "asyncio是Python标准库中的异步I/O框架..."
}
],
"iterations": [
{
"iteration": 1,
"queries": ["Python asyncio 教程", "async await 用法"],
"results_count": 6,
"key_findings": ["asyncio是标准库组件"]
}
],
"total_iterations": 2,
"total_sources": 8,
"elapsed_seconds": 45.32,
"search_timestamp": "2025-12-28T18:30:00"
}json
{
"query": "Python异步编程的最佳实践有哪些?",
"report": "# Python异步编程最佳实践\n\n## 1. 核心概念...",
"sources": [
{
"title": "Python官方asyncio文档",
"url": "https://docs.python.org/...",
"relevance": 0.95,
"snippet": "asyncio是Python标准库中的异步I/O框架..."
}
],
"iterations": [
{
"iteration": 1,
"queries": ["Python asyncio 教程", "async await 用法"],
"results_count": 6,
"key_findings": ["asyncio是标准库组件"]
}
],
"total_iterations": 2,
"total_sources": 8,
"elapsed_seconds": 45.32,
"search_timestamp": "2025-12-28T18:30:00"
}与 websearch_service 的区别
Differences from websearch_service
| 特性 | WebSearch | DeepSearch |
|---|---|---|
| 搜索模式 | 单轮搜索 | 迭代多轮搜索 |
| 查询策略 | 直接使用输入 | LLM 分解/优化 |
| 输出格式 | 结构化列表 | 综合报告 + 来源 |
| 响应时间 | 10-30s | 30-120s |
| Feature | WebSearch | DeepSearch |
|---|---|---|
| Search Mode | Single-round search | Multi-round iterative search |
| Query Strategy | Direct use of input | LLM decomposition/optimization |
| Output Format | Structured list | Comprehensive report + sources |
| Response Time | 10-30s | 30-120s |