介绍
# Exa - Neural Web Search
强大的 AI 驱动搜索，涵盖 LinkedIn、新闻、研究论文等。
## 设置
创建 `~/.clawdbot/credentials/exa/config.json`： ```json {"apiKey": "your-exa-api-key"} ```
## 命令
### 通用搜索 ```bash bash scripts/search.sh "query" [options] ```
选项（作为环境变量）： - `NUM=10` - 结果数量（最多 100） - `TYPE=auto` - 搜索类型：auto, neural, fast, deep - `CATEGORY=` - 类别：news, company, people, research paper, github, tweet, pdf, financial report - `DOMAINS=` - 包含域名（逗号分隔） - `EXCLUDE=` - 排除域名（逗号分隔） - `SINCE=` - 发布日期之后（ISO 日期） - `UNTIL=` - 发布日期之前（ISO 日期） - `LOCATION=NL` - 用户位置（国家代码）
### 示例
```bash # Basic search bash scripts/search.sh "AI agents 2024"
# LinkedIn people search CATEGORY=people bash scripts/search.sh "software engineer Amsterdam"
# Company search CATEGORY=company bash scripts/search.sh "fintech startup Netherlands"
# News from specific domain CATEGORY=news DOMAINS="reuters.com,bbc.com" bash scripts/search.sh "Netherlands"
# Research papers CATEGORY="research paper" bash scripts/search.sh "transformer architecture"
# Deep search (comprehensive) TYPE=deep bash scripts/search.sh "climate change solutions"
# Date-filtered news CATEGORY=news SINCE="2026-01-01" bash scripts/search.sh "tech layoffs" ```
### 获取内容
从 URL 中提取全文： ```bash bash scripts/content.sh "url1" "url2" ```