perplexity-search

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Perplexity AI Search

Perplexity AI 搜索

Web search with AI-powered answers, deep research, and chain-of-thought reasoning.

基于AI生成答案、深度调研与思维链推理的网页搜索工具。

When to Use

适用场景

Direct web search for ranked results (no AI synthesis)
AI-synthesized research with citations
Chain-of-thought reasoning for complex decisions
Deep comprehensive research on topics

直接网页搜索获取排序结果（无AI合成）
带引用的AI合成调研内容
用于复杂决策的思维链推理
针对特定主题的深度全面调研

Models (2025)

模型（2025年）

Model	Purpose
`sonar`	Lightweight search with grounding
`sonar-pro`	Advanced search for complex queries
`sonar-reasoning-pro`	Chain of thought reasoning
`sonar-deep-research`	Expert-level exhaustive research

模型	用途
`sonar`	带事实依据的轻量级搜索
`sonar-pro`	针对复杂查询的进阶搜索
`sonar-reasoning-pro`	思维链推理
`sonar-deep-research`	专家级全面调研

Usage

使用方法

Quick question (AI answer)

快速提问（AI生成答案）

bash

uv run python scripts/mcp/perplexity_search.py \
    --ask "What is the latest version of Python?"

bash

uv run python scripts/mcp/perplexity_search.py \
    --ask "What is the latest version of Python?"

Direct web search (ranked results, no AI)

直接网页搜索（排序结果，无AI处理）

bash

uv run python scripts/mcp/perplexity_search.py \
    --search "SQLite graph database patterns" \
    --max-results 5 \
    --recency week

bash

uv run python scripts/mcp/perplexity_search.py \
    --search "SQLite graph database patterns" \
    --max-results 5 \
    --recency week

AI-synthesized research

AI合成调研内容

bash

uv run python scripts/mcp/perplexity_search.py \
    --research "compare FastAPI vs Django for microservices"

bash

uv run python scripts/mcp/perplexity_search.py \
    --research "compare FastAPI vs Django for microservices"

Chain-of-thought reasoning

思维链推理

bash

uv run python scripts/mcp/perplexity_search.py \
    --reason "should I use Neo4j or SQLite for small graph under 10k nodes?"

bash

uv run python scripts/mcp/perplexity_search.py \
    --reason "should I use Neo4j or SQLite for small graph under 10k nodes?"

Deep comprehensive research

深度全面调研

bash

uv run python scripts/mcp/perplexity_search.py \
    --deep "state of AI agent observability 2025"

bash

uv run python scripts/mcp/perplexity_search.py \
    --deep "state of AI agent observability 2025"

Parameters

参数说明

Parameter	Description
`--ask`	Quick question with AI answer (sonar)
`--search`	Direct web search - ranked results without AI synthesis
`--research`	AI-synthesized research (sonar-pro)
`--reason`	Chain-of-thought reasoning (sonar-reasoning-pro)
`--deep`	Deep comprehensive research (sonar-deep-research)

参数	描述
`--ask`	快速提问获取AI答案（使用sonar模型）
`--search`	直接网页搜索 - 获取无AI合成的排序结果
`--research`	AI合成调研内容（使用sonar-pro模型）
`--reason`	思维链推理（使用sonar-reasoning-pro模型）
`--deep`	深度全面调研（使用sonar-deep-research模型）

Search-specific options

搜索专属选项

Parameter	Description
`--max-results N`	Number of results (1-20, default: 10)
`--recency`	Filter: `day` , `week` , `month` , `year`
`--domains`	Limit to specific domains

参数	描述
`--max-results N`	结果数量（1-20，默认值：10）
`--recency`	时间过滤选项： `day` 、 `week` 、 `month` 、 `year`
`--domains`	限定搜索特定域名

Mode Selection Guide

模式选择指南

Need	Use	Why
Quick fact	`--ask`	Fast, lightweight
Find sources	`--search`	Raw results, no AI overhead
Synthesized answer	`--research`	AI combines multiple sources
Complex decision	`--reason`	Chain-of-thought analysis
Comprehensive report	`--deep`	Exhaustive multi-source research

需求	使用参数	原因
快速获取事实	`--ask`	快速、轻量
查找来源	`--search`	原始结果，无AI处理开销
合成答案	`--research`	AI整合多来源信息
复杂决策	`--reason`	思维链分析
全面报告	`--deep`	详尽的多来源调研

Examples

示例

bash

undefined

bash

undefined

Find recent sources on a topic

查找某主题的近期来源

uv run python scripts/mcp/perplexity_search.py
--search "OpenTelemetry AI agent tracing"
--recency month --max-results 5

Get AI synthesis

获取AI合成内容

uv run python scripts/mcp/perplexity_search.py
--research "best practices for AI agent logging 2025"

Make a decision

辅助决策

uv run python scripts/mcp/perplexity_search.py
--reason "microservices vs monolith for startup MVP"

Deep dive

深度研究

uv run python scripts/mcp/perplexity_search.py
--deep "comprehensive guide to building feedback loops for autonomous agents"

undefined

uv run python scripts/mcp/perplexity_search.py
--deep "comprehensive guide to building feedback loops for autonomous agents"

undefined

API Key Required

需要API密钥

Requires

PERPLEXITY_API_KEY

in environment or

~/.claude/.env

需在环境变量或

~/.claude/.env

文件中配置

PERPLEXITY_API_KEY

。