@tavily/n8n-nodes-tavily

@tavily/n8n-nodes-tavily is a node for n8n that integrates the Tavily API, enabling powerful web search and content extraction within your no-code automation workflows.

Features

Tavily Search

Tavily Search allows you to query the web with powerful filtering capabilities, including options to refine results by topic, time range, and specific domains to include or exclude. You can choose to retrieve a generated answer, raw content, or even related images, depending on your workflow needs. It also supports different search depths—basic or advanced.

Tavily Extract

Tavily Extract allows you to effortlessly retrieve raw content from a list of websites, making it ideal for data collection, content analysis, and research. You can also combine Tavily Extract with our Search method: first, obtain a list of relevant documents, then perform further processing on selected links to gather additional information and use it as context for your research tasks.

Tavily Crawl

Tavily Crawl allows you to intelligently crawl a website from a starting URL to discover and extract content across multiple pages. Control depth, breadth, and apply filters to tailor your crawl for comprehensive analysis and content aggregation.

Tavily Map

Tavily Map allows you to discover and map out all the URLs within a website starting from a root URL. Unlike Crawl, which extracts content, Map focuses on efficiently building a comprehensive sitemap of a website's structure. This is ideal for understanding site architecture, planning content extraction, or identifying specific pages for further processing.

Tavily Research

Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detailed research report. Choose between different models (Mini for targeted research, Pro for comprehensive multi-angle analysis) and customize the output format with citation styles and structured schemas.

Getting a Tavily API Key

1. Go to the Tavily website and create an account
2. Navigate to the Tavily dashboard to get your API key

Configuring Credentials in n8n

1. In your n8n instance, go to the "Credentials" section
2. Click "Create Credential"
3. Search for or select "Tavily API"
4. Enter your Tavily API key in the appropriate field
5. Save the credential

Usage

Tavily Search

1. Add the "Tavily" node to your n8n workflow
2. Connect it to the preceding node in your workflow
3. Click on 'Search'
4. In the node's settings:
   • Select your Tavily API
   • Enter your search query
   • Configure any other desired search parameters (topic, search depth, etc.)
5. Run the workflow to execute the search

Tavily Extract

1. Add the "Tavily" node to your n8n workflow
2. Connect it to the preceding node
3. Click on 'Extract'
4. In the node's settings:
   • Select your Tavily API credential
   • Enter the URLs you want to extract content from
   • Configure any other extraction parameters (include images, extract depth)
5. Run the workflow to extract the content

Tavily Crawl

1. Add the "Tavily" node to your n8n workflow
2. Connect it to the preceding node
3. Click on 'Crawl'
4. In the node's settings:
   • Select your Tavily API credential
   • Enter the root URL to begin the crawl
   • Configure crawl parameters (max depth, limit, etc.)
5. Run the workflow to crawl the website and extract content

Tavily Map

1. Add the "Tavily" node to your n8n workflow
2. Connect it to the preceding node
3. Click on 'Map'
4. In the node's settings:
   • Select your Tavily API credential
   • Enter the root URL to begin mapping
   • Configure map parameters (max depth, limit, filters, etc.)
5. Run the workflow to map the website's URL structure

Tavily Research

Create Research Task

1. Add the "Tavily" node to your n8n workflow
2. Connect it to the preceding node
3. Click on 'Research'
4. Select 'Create Research Task' operation
5. In the node's settings:
   • Select your Tavily API credential
   • Enter your research task or question
   • Configure model (Auto, Mini, or Pro) and other options
6. Run the workflow to initiate the research task
7. The response will include a request_id to check the status later

Get Research Status

1. Add the "Tavily" node to your n8n workflow
2. Connect it to the preceding node
3. Click on 'Research'
4. Select 'Get Research Status' operation
5. In the node's settings:
   • Select your Tavily API credential
   • Enter the request_id from the create research task response
6. Run the workflow to get the research status and results

Parameters

Tavily Search Parameters

Parameter	Description
Query	The search query to execute
Topic	The category of the search (General, News, or Finance)
Search Depth	The depth of the search (Basic or Advanced)
Chunks Per Source (Advanced Search only)	Number of content chunks to retrieve from each source (1-3)
Max Results	Maximum number of search results to return (1-20)
Time Range	Time range filter for results (day, week, month, year)
Days (News Only)	Number of days back from the current date to include (for News topic)
Include Answer	Include an LLM-generated answer in the response (Basic or Advanced)
Include Raw Content	Include cleaned and parsed HTML content of each search result
Include Images	Perform an image search and include the results in the response
Include Image Descriptions	When including images, also add a descriptive text for each image
Include Domains	A list of domains to specifically include in the search results
Exclude Domains	A list of domains to specifically exclude from the search results
Include Favicon	Include the favicon URL for each result
Include Usage	Whether to include credit usage information in the response.
Country	Boost search results from a specific country.
Auto Parameters	When enabled, Tavily automatically configures search parameters based on your query's content and intent
Start Date	Will return all results after the specified start date (publish date). Required to be written in the format YYYY-MM-DD
End Date	Will return all results before the specified end date (publish date). Required to be written in the format YYYY-MM-DD

Tavily Extract Parameters

Parameter	Description
URLs	One or more URLs to extract content from
Include Images	Include a list of images extracted from each URL
Extract Depth	How deeply to parse each URL (Basic or Advanced)
Format	Format of the extracted web page content (Markdown or Text)
Include Favicon	Include the favicon URL for each result
Include Usage	Whether to include credit usage information in the response. NOTE:The value may be 0 if the total successful URL extractions has not yet reached 5 calls. See our Credits & Pricing documentation for details.

Tavily Crawl Parameters

Parameter	Description
URL	The root URL to begin the crawl
Instructions	Natural language instructions for the crawler
Max Depth	Maximum depth of the crawl (≥ 1)
Max Breadth	Maximum number of links to follow per level (≥ 1)
Limit	Maximum number of results to return (≥ 1)
Select Paths	Regex patterns to select only URLs with specific path patterns
Select Domains	Regex patterns to select crawling to specific domains or subdomains
Exclude Paths	Regex patterns to exclude URLs with specific path patterns
Exclude Domains	Regex patterns to exclude specific domains or subdomains from crawling
Allow External	Whether to allow following links that go to external domains
Include Images	Whether to include images in the crawl results
Extract Depth	Extraction depth (Basic or Advanced)
Format	Format of the extracted web page content (Markdown or Text)
Include Favicon	Include the favicon URL for each result
Include Usage	Whether to include credit usage information in the response. NOTE:The value may be 0 if the total use of /extract and /map calls has not yet reached minimum needed. See our Credits & Pricing documentation for details.

Tavily Map Parameters

Parameter	Description
URL	The root URL to begin mapping
Instructions	Natural language instructions guiding the mapping process
Max Depth	Defines how far from the base URL the crawler can explore (≥ 1)
Max Breadth	Maximum number of links to follow per level of the tree (≥ 1)
Limit	Total number of links the crawler will process before stopping (≥ 1)
Select Paths	Regex patterns to select only URLs with specific path patterns
Select Domains	Regex patterns to select crawling to specific domains or subdomains
Exclude Paths	Regex patterns to exclude URLs with specific path patterns
Exclude Domains	Regex patterns to exclude specific domains or subdomains from crawling
Allow External	Whether to include external domain links in the final results list
Timeout	Maximum time in seconds to wait for the map operation (10-150)

Tavily Research Parameters

Create Research Task

Parameter	Description
Input	The research task or question to investigate
Model	The model used by the research agent (Auto, Mini, or Pro). Mini is optimized for targeted research, Pro provides comprehensive multi-angle research
Citation Format	The format for citations in the research report (Numbered, MLA, APA, or Chicago)
Output Schema	A JSON Schema object that defines the structure of the research output
Stream	Whether to stream research results in real-time as Server-Sent Events (SSE) with progress updates and incremental results

Get Research Status

Parameter	Description
Request ID	The unique identifier of the research task returned from the Create Research Task operation

Troubleshooting

Error Codes

Error Code	Description	Solution
400 Bad Request	Invalid request parameters or unsupported values	Check all parameters and their formats
401 Unauthorized	Missing or invalid API key	Verify API key or generate a new one
429 Too Many Requests	Rate limit exceeded	Reduce request frequency or implement backoff
432 Plan Limit Exceeded	Exceeds plan limits	Upgrade your plan via Tavily Dashboard
433 Pay-As-You-Go Limit Exceeded	Exceeds pay-as-you-go limit	Increase limit via Tavily Dashboard
500 Internal Server Error	Server-side issue	Retry request after a few minutes

Cost

Head to the API Credits Overview in our documentation to learn more about how many API Credits each request costs.

License

This project is licensed under the terms of the MIT license.

Contact

If you are encountering issues while using Tavily, please email us at support@tavily.com. We'll be happy to help you.

If you want to stay updated on the latest Tavily news and releases, head to our Developer Community to learn more!