> ## Documentation Index
> Fetch the complete documentation index at: https://aisa.one/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> ## Agent Instructions (AIsa)
>
> - Base URLs: models `https://api.aisa.one/v1` (Gemini GenerateContent: `https://api.aisa.one/v1beta`); data APIs `https://api.aisa.one/apis/v1`. The `servers` of each operation in https://aisa.one/openapi.yaml is authoritative.
> - Auth: `Authorization: Bearer $AISA_API_KEY`. Never print, log, or commit the key.
> - MCP (preferred for agents): `https://mcp.aisa.one/mcp`, signed in with OAuth, so there is no key to paste.
> - Agent Skill: `npx skills add AIsa-team/agent-skills --skill aisa`. Fallback with the AIsa CLI: `aisa skills install aisa`.
> - Paid calls need approval first. Docs, https://aisa.one/models, https://aisa.one/api, `/v1/models`, and MCP discovery are free to read. Before any paid, dynamically priced, or high-cost call, state the exact scope, rate, and maximum USD exposure, then wait for a separate user message approving that scope and cap. A request to collect data is not approval; do not send unapproved probes. Full rule: https://aisa.one/docs/llms.txt

# Multi-source Search

> 面向 Agent 的统一网页、学术、Tavily 与 Perplexity Sonar 搜索。

[在 GitHub 上查看 →](https://github.com/AIsa-team/agent-skills/tree/main/search-research/multi-source-search)

Multi-source Search 将网页搜索、学术搜索、Tavily、Perplexity Sonar、内容抽取、递归抓取和站点地图整合到同一个 Skill 中，方便 Agent 进行多源检索。

## 安装

```bash theme={null}
npm install -g @aisa-one/cli
aisa skills install multi-source-search
```

## Agent 可以做什么？

<CardGroup cols={2}>
  <Card title="网页与学术" icon="magnifying-glass">
    进行结构化网页搜索和学术论文搜索。
  </Card>

  <Card title="Perplexity Sonar" icon="sparkles">
    生成带来源的快速回答或深度研究。
  </Card>

  <Card title="Tavily 工具" icon="spider">
    搜索、抽取正文、递归 crawl 和生成 sitemap。
  </Card>

  <Card title="并行检索" icon="layer-group">
    同时调用多个来源，再统一排序和去重。
  </Card>
</CardGroup>

## 核心能力

* 网页搜索
* 学术搜索
* 智能/混合搜索
* Perplexity Sonar
* Tavily 搜索 / 提取 / 抓取 / 站点映射
* 多源并行检索和综合

## 快速开始

```bash theme={null}
# Web search
python3 ${CLAUDE_PLUGIN_ROOT}/skills/multi-source-search/scripts/search_client.py web --query "latest AI agent platforms"

# Scholar search
python3 ${CLAUDE_PLUGIN_ROOT}/skills/multi-source-search/scripts/search_client.py scholar --query "state space models survey"

# Perplexity
python3 ${CLAUDE_PLUGIN_ROOT}/skills/multi-source-search/scripts/search_client.py sonar --query "Compare RAG and long-context LLMs"
```

## 使用原则

* 搜索结果用于发现线索。
* 抽取页面正文或官方文档才是证据。
* 对事实性结论，优先引用官方来源、论文、API 响应或 README。
* 多源结果冲突时，明确说明冲突和可信度。

## 开始使用

```bash theme={null}
export AISA_API_KEY="YOUR_AISA_API_KEY"
npm install -g @aisa-one/cli
aisa skills install multi-source-search
```

## 相关

<CardGroup cols={3}>
  <Card title="Web Search" icon="globe" href="/docs/zh/agent-skills/web-search">网页搜索。</Card>
  <Card title="Perplexity Research" icon="microscope" href="/docs/zh/agent-skills/perplexity-research">带引用研究答案。</Card>
  <Card title="Scholar Search" icon="book-open" href="/docs/zh/agent-skills/scholar-search">学术检索。</Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.