Tavily - Crawl website action ​

The Crawl website action traverses a website starting from a root URL using Tavily and returns extracted content for each page.

Input ​

Input fieldDescription
URLEnter the root URL to begin crawling from.
InstructionsEnter natural-language guidance for the crawler.
Chunks per sourceEnter the number of chunks to use for each source. Only used when the Instructions field is populated.
Select pathsEnter a regex path pattern to include in the crawl.
Select domainsEnter a regex domain pattern to include in the crawl.
Exclude pathsEnter a regex path pattern to exclude in the crawl.
Exclude domainsEnter a regex domain pattern to exclude in the crawl.
Include imagesInclude images found during the crawl.
Include faviconSelect whether to include the favicon URL for each result.
Include usageSelect whether to include credit usage information in the result.

Output ​

Output fieldDescription
Base URLThe root URL the crawl started from.
ResultsThe crawled pages. Each result includes the URL, raw content, favicon, and images.
Response timeThe time Tavily took to process the crawl, in seconds.
UsageThe number of credits the crawl consumed.
Request IDThe unique identifier for this crawl request.

Last updated: