zhipu-web-search（知谱网络搜索）

Zhipu Web Search

Web search via Zhipu AI's dedicated API (/paas/v4/web_search), refactored to use lightweight cURL instead of Python or jq. It defaults to using the search_pro_quark engine with 20 results.

Quick Start

Basic cURL Usage

curl --request POST \
  --url https://open.bigmodel.cn/api/paas/v4/web_search \
  --header "Authorization: Bearer $ZHIPU_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "search_query": "OpenClaw framework",
    "search_engine": "search_pro_quark",
    "search_intent": false,
    "count": 20
  }'

Script Usage

A wrapper shell script is provided for convenience.

# Basic Search (defaults to search_pro_quark and 20 results)
bash scripts/zhipu_search.sh --query "AI development trends"

# Advanced Search
bash scripts/zhipu_search.sh \
  --query "latest open source LLMs" \
  --engine "search_pro_sogou" \
  --count 50 \
  --intent \
  --recency "oneWeek"

API Parameter Reference

Search Engine Selection Guide

Response Structure

The API returns JSON directly.

{
  "id": "task-id",
  "created": 1704067200,
  "request_id": "request-id",
  "search_intent": [
    {
      "query": "original query",
      "intent": "SEARCH_ALL",
      "keywords": "rewritten keywords"
    }
  ],
  "search_result": [
    {
      "title": "title",
      "content": "content summary",
      "link": "result link",
      "media": "site name",
      "icon": "site icon",
      "refer": "reference number",
      "publish_date": "publish date"
    }
  ]
}

Environment Requirements

• Environment variable ZHIPU_API_KEY must be configured.
• curl command must be available in your system path.