跳转到主要内容

​
概述

PipeLLM WebSearch 通过 Gateway 提供实时网络搜索能力，按次计费。适用于 RAG（检索增强生成）和构建具有网络访问能力的 AI Agent。

​
接口

方法端点
GEThttps://api.pipellm.ai/v1/websearch/search

​
认证

在 Authorization 头中使用您的 PipeLLM API Key： 
Authorization: Bearer YOUR_PIPELLM_API_KEY

​
请求参数

参数类型必填描述
qstring是搜索关键词

​
请求示例

curl -X GET "https://api.pipellm.ai/v1/websearch/search?q=最新AI新闻" \
  -H "Authorization: Bearer $PIPELLM_API_KEY"

​
响应格式

{
  "code": 200,
  "message": "ok",
  "took_ms": 6050,
  "data": {
    "organic": [
      {
        "title": "AI News | Latest News | Insights Powering AI-Driven Business ...",
        "link": "https://www.artificialintelligence-news.com/",
        "snippet": "AI News delivers the latest updates in artificial intelligence, machine learning, deep learning, enterprise AI, and emerging tech worldwide."
      },
      {
        "title": "The Latest AI News and AI Breakthroughs that Matter Most",
        "link": "https://www.crescendo.ai/news/latest-ai-news-and-updates",
        "snippet": "Summary: Xiaomi has announced a next-gen AI voice model optimized for in-car and smart home experiences. The model features faster response times, offline ...",
        "contexts": [
          {
            "idx": 0,
            "text": "December 26, 2025\n\n# The Latest AI News and AI Breakthroughs that Matter Most: 2025..."
          }
        ]
      }
    ]
  }
}

​
响应字段说明

字段类型描述
codeinteger200 表示成功
messagestring状态信息
took_msinteger耗时（毫秒）
data.organicarray自然搜索结果列表
data.organic[].titlestring页面标题
data.organic[].linkstring页面链接
data.organic[].snippetstring页面描述
data.organic[].contextsarray从页面提取的完整上下文（可选）
data.organic[].contexts[].idxinteger上下文索引
data.organic[].contexts[].textstring上下文内容文本

​
错误响应

{
  "code": 400,
  "message": "Bad Request, missing query parameter"
}

​
价格

项目价格
每次请求$0.05
仅对成功的请求计费，失败请求不收费。

​
使用场景

​
RAG 上下文增强

使用 WebSearch 为 LLM 提供实时上下文： 
import requests
import os
from openai import OpenAI

# 步骤 1: 搜索网络
search_response = requests.get(
    "https://api.pipellm.ai/v1/websearch/search",
    params={"q": "OpenAI o3 模型能力"},
    headers={"Authorization": f"Bearer {os.getenv('PIPELLM_API_KEY')}"}
)
search_data = search_response.json()

# 步骤 2: 提取上下文
context = "\n".join([
    f"[{r['title']}]({r['link']}): {r['snippet']}"
    for r in search_data.get("data", {}).get("organic", [])[:5]
])

# 步骤 3: 与 LLM 结合使用
client = OpenAI(
    api_key=os.getenv("PIPELLM_API_KEY"),
    base_url="https://api.pipellm.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": f"请基于以下上下文回答：\n{context}"},
        {"role": "user", "content": "OpenAI o3 有哪些主要特性？"}
    ]
)

print(response.choices[0].message.content)

​
速率限制

WebSearch 请求共享您账户的速率限制。如果收到 503 Service Unavailable 响应并带有 Retry-After 头，请等待后重试。