Tavily Search V2 — Tavily 搜索 V2

Tavily 搜索

搜索 the 网页 and 获取 relevant 结果s 优化d for LLM consumption.

Authentication

获取 your API key at https://tavily.com and 添加 to your OpenClaw config:

{ "技能s": { "entries": { "tavily-搜索": { "enabled": true, "APIKey": "tvly-YOUR_API_KEY_HERE" } } } }

Or 设置 the 环境 variable:

导出 TAVILY_API_KEY="tvly-YOUR_API_KEY_HERE"

Quick 启动 Using the Script node {baseDir}/scripts/搜索.mjs "查询" node {baseDir}/scripts/搜索.mjs "查询" -n 10 node {baseDir}/scripts/搜索.mjs "查询" --deep node {baseDir}/scripts/搜索.mjs "查询" --topic news

Examples # Basic 搜索 node {baseDir}/scripts/搜索.mjs "python a同步 patterns"

# With more 结果s node {baseDir}/scripts/搜索.mjs "React hooks tutorial" -n 10

# Advanced 搜索 node {baseDir}/scripts/搜索.mjs "machine learning" --deep

# News 搜索 node {baseDir}/scripts/搜索.mjs "AI news" --topic news

# DomAIn-过滤器ed 搜索 node {baseDir}/scripts/搜索.mjs "Python docs" --include-domAIns docs.python.org

Options Option Description Default -n Number of 结果s (1-20) 10 --depth 搜索 depth: ultra-fast, fast, basic, advanced basic --topic Topic: general or news general --time-range Time range: day, week, month, year - --include-domAIns Comma-separated domAIns to include - --exclude-domAIns Comma-separated domAIns to exclude - --raw-content Include full page content false --json 输出 raw JSON false 搜索 Depth Depth Latency Relevance Use Case ultra-fast Lowest Lower Real-time chat, autocomplete fast Low Good Need chunks but latency matters basic Medium High General-purpose, balanced advanced Higher Highest Precision matters, re搜索 Tips Keep queries under 400 characters - Think 搜索 查询, not prompt Break complex queries into sub-queries - Better 结果s than one massive 查询 Use --include-domAIns to focus on trusted sources Use --time-range for recent in格式化ion 过滤器 by score (0-1) to 获取 highest relevance 结果s