> ## 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

> Unified web, academic, Tavily, and Perplexity Sonar search for autonomous agents. One skill covers ranked web results, scholar papers, citation-backed answers, content extraction, recursive crawling, and site mapping.

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

**Multi-source intelligent retrieval for autonomous agents.** One `AISA_API_KEY` unlocks structured web search, academic paper lookup, Tavily extraction/crawling, and the full Perplexity Sonar family for citation-rich answers.

## Install

<CodeGroup>
  ```bash npx skills theme={null}
  npx skills add AIsa-team/agent-skills --skill multi-source-search
  ```

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

Start a new agent session after installing so the skill loads.

## What can agents do with it?

<CardGroup cols={2}>
  <Card title="Fast web lookup" icon="magnifying-glass">
    "Summarize the latest AI infrastructure launches this month."
  </Card>

  <Card title="Scholar-backed research" icon="book-open">
    "Find recent academic papers on self-correcting agent frameworks."
  </Card>

  <Card title="Citation-rich answers" icon="quote-left">
    "Answer this question with inline citations using Perplexity Sonar Pro."
  </Card>

  <Card title="Deep research reports" icon="file-lines">
    "Generate a 2,000-word report on autonomous browser agents."
  </Card>

  <Card title="Content extraction" icon="scissors">
    "Pull the main article text from these 5 URLs for analysis."
  </Card>

  <Card title="Site intelligence" icon="sitemap">
    "Map the structure of this docs site and crawl it for RAG."
  </Card>
</CardGroup>

## Core capabilities

* **Web search** (`/scholar/search/web`) — structured web results for current information
* **Scholar search** (`/scholar/search/scholar`) — academic papers with optional date filtering
* **Smart/hybrid search** (`/scholar/search/mixed`) — combines web + scholar in one call
* **Explain search** (`/scholar/search/explain`) — explanatory synthesis over results
* **Perplexity Sonar family** — `sonar`, `sonar-pro`, `sonar-reasoning-pro`, `sonar-deep-research`
* **Tavily** — `search`, `extract`, `crawl`, `map`
* **Verity multi-source** — parallel retrieval across source types

## Quick start

```bash theme={null}
export AISA_API_KEY="your-key"
```

### Web + scholar

```bash theme={null}
# Structured web search
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/web" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "latest AI infrastructure launches 2026"}'

# Academic papers
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "self-correcting agent frameworks"}'

# Smart hybrid (web + scholar)
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/mixed" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "retrieval-augmented generation"}'
```

### Perplexity Sonar

```bash theme={null}
# Fast answers
curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "sonar", "messages": [{"role": "user", "content": "What is MCP?"}]}'

# Deep research
curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar-deep-research" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "sonar-deep-research", "messages": [{"role": "user", "content": "State of agentic payments in 2026"}]}'
```

### Tavily utilities

```bash theme={null}
# Search
curl -X POST "https://api.aisa.one/apis/v1/tavily/search" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "LLM agent frameworks"}'

# Extract clean article text
curl -X POST "https://api.aisa.one/apis/v1/tavily/extract" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"urls": ["https://example.com/article"]}'

# Recursive crawl
curl -X POST "https://api.aisa.one/apis/v1/tavily/crawl" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com", "depth": 2}'

# Site map
curl -X POST "https://api.aisa.one/apis/v1/tavily/map" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'
```

## Python client

```bash theme={null}
# Web + scholar + smart
python3 scripts/search_client.py web --query "AI agent news"
python3 scripts/search_client.py scholar --query "self-correcting agents"
python3 scripts/search_client.py smart --query "RAG patterns"

# Perplexity
python3 scripts/search_client.py sonar --query "What is MCP?"
python3 scripts/search_client.py sonar-pro --query "Compare MCP and A2A for agent tooling"
python3 scripts/search_client.py sonar-reasoning-pro --query "Analyze x402 adoption"
python3 scripts/search_client.py sonar-deep-research --query "State of agentic payments"

# Tavily
python3 scripts/search_client.py tavily-search --query "LLM agents"
python3 scripts/search_client.py tavily-extract --urls "https://example.com/article"
python3 scripts/search_client.py tavily-crawl --url "https://example.com" --depth 2
python3 scripts/search_client.py tavily-map --url "https://example.com"

# Multi-source parallel retrieval
python3 scripts/search_client.py verity --query "AI agent benchmarks 2026"
```

## Endpoint reference

| Endpoint | Method | Purpose |
| - | - | - |
| `/scholar/search/web` | POST | [Web search](/docs/api-reference/scholar/post_scholar-search-web) |
| `/scholar/search/scholar` | POST | [Academic papers](/docs/api-reference/scholar/post_scholar-search-scholar) |
| `/scholar/search/mixed` | POST | [Smart hybrid search](/docs/api-reference/scholar/post_scholar-search-mixed) |
| `/scholar/search/explain` | POST | [Explain search](/docs/api-reference/scholar/post_scholar-search-explain) |
| `/perplexity/sonar` | POST | [Sonar — fast answers](/docs/api-reference/perplexity/post_perplexity-sonar) |
| `/perplexity/sonar-pro` | POST | [Sonar Pro — synthesis](/docs/api-reference/perplexity/post_perplexity-sonar-pro) |
| `/perplexity/sonar-reasoning-pro` | POST | [Sonar Reasoning Pro](/docs/api-reference/perplexity/post_perplexity-sonar-reasoning-pro) |
| `/perplexity/sonar-deep-research` | POST | [Sonar Deep Research](/docs/api-reference/perplexity/post_perplexity-sonar-deep-research) |
| `/tavily/search` | POST | [Tavily search](/docs/api-reference/search/post_tavily-search) |
| `/tavily/extract` | POST | [Tavily extract](/docs/api-reference/search/post_tavily-extract) |
| `/tavily/crawl` | POST | [Tavily crawl](/docs/api-reference/search/post_tavily-crawl) |
| `/tavily/map` | POST | [Tavily map](/docs/api-reference/search/post_tavily-map) |

## Get started

1. Sign up at [aisa.one](https://aisa.one) and create an API key in the console.
2. Set it in your shell: `export AISA_API_KEY="your-key"`.
3. Install the skill with one of the commands under [Install](#install), then start a new agent session.

## Related

<CardGroup cols={3}>
  <Card title="Search API reference" icon="magnifying-glass" href="/docs/api-reference/search/post_tavily-search">
    Tavily search, extract, crawl, map — with live playgrounds.
  </Card>

  <Card title="Scholar API reference" icon="book-open" href="/docs/api-reference/scholar/post_scholar-search-web">
    Web, scholar, smart, and explain endpoints.
  </Card>

  <Card title="Perplexity API reference" icon="sparkles" href="/docs/api-reference/perplexity/post_perplexity-sonar">
    Full Sonar family endpoint docs.
  </Card>
</CardGroup>


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