Tavily API Search Endpoint

Base URL: https://api.tavily.com/search Method: POST

Required Parameters

• query: The search query string
• api_key: Your Tavily API key

Optional Parameters

• search_depth: "basic" or "advanced" (default: "basic")
• topic: "general" or "news" (default: "general")
• max_results: Maximum number of results to return (default: 5)
• include_images: Include query-related images (default: false)
• include_answer: Include AI-generated answer (default: false)
• include_raw_content: Include parsed HTML content (default: false)
• include_domains: List of domains to include
• exclude_domains: List of domains to exclude
• time_range: Filter by time range ("day", "week", "month", "year")
• days: Number of days back for news results (default: 3)

Example Request

{
    "api_key": "tvly-REPLACE_WITH_CREDENTIAL",
    "query": "Who is Leo Messi?",
    "search_depth": "basic",
    "include_answer": false,
    "include_images": true,
    "max_results": 5
}

Tavily API Extract Endpoint

Base URL: https://api.tavily.com/extract Method: POST

Required Parameters

• urls: Single URL string or array of URLs
• api_key: Your Tavily API key

Optional Parameters

• include_images: Include extracted images (default: false)

Example Request

{
    "api_key": "tvly-REPLACE_WITH_CREDENTIAL", 
    "urls": [
        "https://en.wikipedia.org/wiki/Artificial_intelligence",
        "https://en.wikipedia.org/wiki/Machine_learning"
    ]
}

Tavily API Documentation

The Tavily REST API provides seamless access to Tavily Search, a powerful search engine for LLM agents, and Tavily Extract, an advanced web scraping solution optimized for LLMs.

https://docs.tavily.com/docs/rest-api/examples

https://docs.tavily.com/docs/rest-api/api-reference#parameters

The Tavily API provides two main endpoints for search and data extraction.

The API returns JSON responses containing:

• Search results with titles, URLs, and content
• Extracted raw content from specified URLs
• Response time metrics
• Any error messages for failed requests

Note: Error handling should check for failed results in the response before processing.

Tavily Use Cases

📜 Why Use Tavily API for Data Enrichment?

https://docs.tavily.com/docs/use-cases/data-enrichment

💡 Why Use Tavily API for Company Research?

https://docs.tavily.com/docs/use-cases/company-research

🔍 GPT Researcher

https://docs.tavily.com/docs/gpt-researcher/introduction

Tavily API Overview

https://docs.tavily.com/docs/welcome

The Tavily API provides a specialized search engine built specifically for AI agents and LLM applications, offering two main endpoints:

Search Endpoint

The search endpoint enables intelligent web searching with:

Key Features

• Query-based search with customizable depth ("basic" or "advanced")
• Topic filtering for general or news content
• Control over result quantity and content type
• Domain inclusion/exclusion capabilities
• Time range filtering and news date restrictions

Extract Endpoint

The extract endpoint focuses on content retrieval:

Key Features

• Single or batch URL processing
• Raw content extraction
• Optional image extraction
• Structured response format

Implementation Benefits

For AI Integration

• Optimized for RAG (Retrieval Augmented Generation)
• Single API call handles searching, scraping and filtering
• Customizable response formats
• Built-in content relevance scoring

Technical Advantages

• JSON response format
• Error handling for failed requests
• Response time metrics
• Flexible content filtering options

This API is designed to simplify the integration of real-time web data into AI applications while ensuring high-quality, relevant results through intelligent processing and filtering.

Tavily API Key

https://app.tavily.com/home

🔍🛠️ Tavily Search & Extract - Template

Purpose and structure

This folder contains the 🔍🛠️ Tavily Search & Extract - Template workflow. Its executable nodes use chainLlm, chatTrigger, httpRequest, lmChatOpenAi, set. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

Provide search topic via Chat window

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Http/1617_HTTP_Stickynote_Automation_Webhook.json MIT; preserve source notices.