by langgenius · v0.1.11
A powerful AI-native search engine and web content extraction tool that provides highly relevant search results and raw content extraction from web pages.
This community listing does not yet include every recommended support, privacy, pricing, and permission disclosure. Review the available package permissions before installing.
Available inside your emploidai workspace after installation.
Available inside your emploidai workspace after installation.
The Tavily tool connects your Dify agents to an AI-native search engine built specifically for LLMs. Unlike traditional search APIs that return raw links, Tavily delivers clean, structured, and contextually relevant results ready for AI consumption.
| Action | Description | Best For |
|---|---|---|
| Search | AI-optimized web search with relevance scoring | General queries, real-time information, fact-checking |
| Extract | Pull structured content from specific URLs | Reading articles, parsing documentation, data extraction |
| Crawl | Deep crawl websites following internal links | Site audits, comprehensive data collection |
| Map | Discover and map all URLs within a domain | Site structure analysis, content discovery |
| Research | Multi-step autonomous research on complex topics | In-depth reports, market research, due diligence |
Sign up and get your API key at app.tavily.com.
Free tier includes 1,000 API credits/month.
Navigate to Plugin Marketplace in Dify and search for "Tavily". Click Install.
Go to Tools → Tavily → Authentication and paste your API key.
Tavily requests from the Dify integration include X-Client-Name: dify for client attribution.
Add a Node → Tool → Tavily. All five actions are available:
Fact-checking workflow:
User question → Search (include_answer: true) → LLM validates and responds
Content aggregation:
Topic → Search → Extract (top URLs) → LLM summarizes
Competitive analysis:
Competitor URL → Map → Crawl key pages → LLM analyzes