web-search
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseWeb Search & Extraction
网页搜索与内容提取
Search the web and extract content via inference.sh CLI.
通过inference.sh CLI进行网页搜索和内容提取。
Quick Start
快速开始
Requires inference.sh CLI (). Install instructionsinfsh
bash
infsh login需要inference.sh CLI（）。安装说明infsh
bash
infsh loginSearch the web
Search the web
infsh app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}'
undefinedinfsh app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}'
undefinedAvailable Apps
可用应用
Tavily
Tavily
| App | App ID | Description |
|---|---|---|
| Search Assistant | | AI-powered search with answers |
| Extract | | Extract content from URLs |
| 应用 | 应用ID | 描述 |
|---|---|---|
| Search Assistant | | 带答疑功能的AI驱动搜索 |
| Extract | | 从URL提取内容 |
Exa
Exa
| App | App ID | Description |
|---|---|---|
| Search | | Smart web search with AI |
| Answer | | Direct factual answers |
| Extract | | Extract and analyze web content |
| 应用 | 应用ID | 描述 |
|---|---|---|
| Search | | 带AI的智能网页搜索 |
| Answer | | 直接给出事实性答案 |
| Extract | | 提取并分析网页内容 |
Examples
示例
Tavily Search
Tavily搜索
bash
infsh app run tavily/search-assistant --input '{
"query": "What are the best practices for building AI agents?"
}'Returns AI-generated answers with sources and images.
bash
infsh app run tavily/search-assistant --input '{
"query": "What are the best practices for building AI agents?"
}'返回带来源和图片的AI生成答案。
Tavily Extract
Tavily提取
bash
infsh app run tavily/extract --input '{
"urls": ["https://example.com/article1", "https://example.com/article2"]
}'Extracts clean text and images from multiple URLs.
bash
infsh app run tavily/extract --input '{
"urls": ["https://example.com/article1", "https://example.com/article2"]
}'从多个URL提取干净的文本和图片。
Exa Search
Exa搜索
bash
infsh app run exa/search --input '{
"query": "machine learning frameworks comparison"
}'Returns highly relevant links with context.
bash
infsh app run exa/search --input '{
"query": "machine learning frameworks comparison"
}'返回带上下文的高相关性链接。
Exa Answer
Exa答疑
bash
infsh app run exa/answer --input '{
"question": "What is the population of Tokyo?"
}'Returns direct factual answers.
bash
infsh app run exa/answer --input '{
"question": "What is the population of Tokyo?"
}'返回直接的事实性答案。
Exa Extract
Exa提取
bash
infsh app run exa/extract --input '{
"url": "https://example.com/research-paper"
}'Extracts and analyzes web page content.
bash
infsh app run exa/extract --input '{
"url": "https://example.com/research-paper"
}'提取并分析网页内容。
Workflow: Research + LLM
工作流：调研 + LLM
bash
undefinedbash
undefined1. Search for information
1. Search for information
infsh app run tavily/search-assistant --input '{
"query": "latest developments in quantum computing"
}' > search_results.json
infsh app run tavily/search-assistant --input '{
"query": "latest developments in quantum computing"
}' > search_results.json
2. Analyze with Claude
2. Analyze with Claude
infsh app run openrouter/claude-sonnet-45 --input '{
"prompt": "Based on this research, summarize the key trends: <search-results>"
}'
undefinedinfsh app run openrouter/claude-sonnet-45 --input '{
"prompt": "Based on this research, summarize the key trends: <search-results>"
}'
undefinedWorkflow: Extract + Summarize
工作流：提取 + 总结
bash
undefinedbash
undefined1. Extract content from URL
1. Extract content from URL
infsh app run tavily/extract --input '{
"urls": ["https://example.com/long-article"]
}' > content.json
infsh app run tavily/extract --input '{
"urls": ["https://example.com/long-article"]
}' > content.json
2. Summarize with LLM
2. Summarize with LLM
infsh app run openrouter/claude-haiku-45 --input '{
"prompt": "Summarize this article in 3 bullet points: <content>"
}'
undefinedinfsh app run openrouter/claude-haiku-45 --input '{
"prompt": "Summarize this article in 3 bullet points: <content>"
}'
undefinedUse Cases
适用场景
- Research: Gather information on any topic
- RAG: Retrieval-augmented generation
- Fact-checking: Verify claims with sources
- Content aggregation: Collect data from multiple sources
- Agents: Build research-capable AI agents
- 调研：收集任意主题的信息
- RAG：检索增强生成
- 事实核查：通过来源验证主张
- 内容聚合：从多个来源收集数据
- Agent：构建具备调研能力的AI Agent
Related Skills
相关技能
bash
undefinedbash
undefinedFull platform skill (all 250+ apps)
Full platform skill (all 250+ apps)
npx skills add inference-sh/skills@infsh-cli
npx skills add inference-sh/skills@infsh-cli
LLM models (combine with search for RAG)
LLM models (combine with search for RAG)
npx skills add inference-sh/skills@llm-models
npx skills add inference-sh/skills@llm-models
Image generation
Image generation
npx skills add inference-sh/skills@ai-image-generation
Browse all apps: `infsh app list`npx skills add inference-sh/skills@ai-image-generation
浏览所有应用：`infsh app list`Documentation
文档
- Adding Tools to Agents - Equip agents with search
- Building a Research Agent - LLM + search integration guide
- Tool Integration Tax - Why pre-built tools matter
- Adding Tools to Agents - 为Agent配备搜索功能
- Building a Research Agent - LLM + 搜索集成指南
- Tool Integration Tax - 为何预构建工具至关重要