Sim

Tavily

Search and extract information

Tavily is an AI-powered search API designed specifically for LLM applications. It provides reliable, real-time information retrieval capabilities with features optimized for AI use cases, including semantic search, content extraction, and structured data retrieval.

With Tavily, you can:

  • Perform contextual searches: Get relevant results based on semantic understanding rather than just keyword matching
  • Extract structured content: Pull specific information from web pages in a clean, usable format
  • Access real-time information: Retrieve up-to-date data from across the web
  • Process multiple URLs simultaneously: Extract content from several web pages in a single request
  • Receive AI-optimized results: Get search results specifically formatted for consumption by AI systems

In Sim, the Tavily integration enables your agents to search the web and extract information as part of their workflows. This allows for sophisticated automation scenarios that require up-to-date information from the internet. Your agents can formulate search queries, retrieve relevant results, and extract content from specific web pages to inform their decision-making processes. This integration bridges the gap between your workflow automation and the vast knowledge available on the web, enabling your agents to access real-time information without manual intervention. By connecting Sim with Tavily, you can create agents that stay current with the latest information, provide more accurate responses, and deliver more value to users.

Usage Instructions

Integrate Tavily into the workflow. Can search the web and extract content from specific URLs. Requires API Key.

Tools

Perform AI-powered web searches using Tavily

Input

ParameterTypeRequiredDescription
querystringYesThe search query to execute
max_resultsnumberNoMaximum number of results (1-20)
topicstringNoCategory type: general, news, or finance (default: general)
search_depthstringNoSearch scope: basic (1 credit) or advanced (2 credits) (default: basic)
include_answerstringNoLLM-generated response: true/basic for quick answer or advanced for detailed
include_raw_contentstringNoParsed HTML content: true/markdown or text format
include_imagesbooleanNoInclude image search results
include_image_descriptionsbooleanNoAdd descriptive text for images
include_faviconbooleanNoInclude favicon URLs
chunks_per_sourcenumberNoMaximum number of relevant chunks per source (1-3, default: 3)
time_rangestringNoFilter by recency: day/d, week/w, month/m, year/y
start_datestringNoEarliest publication date (YYYY-MM-DD format)
end_datestringNoLatest publication date (YYYY-MM-DD format)
include_domainsstringNoComma-separated list of domains to whitelist (max 300)
exclude_domainsstringNoComma-separated list of domains to blacklist (max 150)
countrystringNoBoost results from specified country (general topic only)
auto_parametersbooleanNoAutomatic parameter configuration based on query intent
apiKeystringYesTavily API Key

Output

ParameterTypeDescription
querystringThe search query that was executed
resultsarrayresults output from the tool

tavily_extract

Extract raw content from multiple web pages simultaneously using Tavily

Input

ParameterTypeRequiredDescription
urlsstringYesURL or array of URLs to extract content from
extract_depthstringNoThe depth of extraction (basic=1 credit/5 URLs, advanced=2 credits/5 URLs)
formatstringNoOutput format: markdown or text (default: markdown)
include_imagesbooleanNoIncorporate images in extraction output
include_faviconbooleanNoAdd favicon URL for each result
apiKeystringYesTavily API Key

Output

ParameterTypeDescription
resultsarrayThe URL that was extracted

tavily_crawl

Systematically crawl and extract content from websites using Tavily

Input

ParameterTypeRequiredDescription
urlstringYesThe root URL to begin the crawl
instructionsstringNoNatural language directions for the crawler (costs 2 credits per 10 pages)
max_depthnumberNoHow far from base URL to explore (1-5, default: 1)
max_breadthnumberNoLinks followed per page level (≥1, default: 20)
limitnumberNoTotal links processed before stopping (≥1, default: 50)
select_pathsstringNoComma-separated regex patterns to include specific URL paths (e.g., /docs/.*)
select_domainsstringNoComma-separated regex patterns to restrict crawling to certain domains
exclude_pathsstringNoComma-separated regex patterns to skip specific URL paths
exclude_domainsstringNoComma-separated regex patterns to block certain domains
allow_externalbooleanNoInclude external domain links in results (default: true)
include_imagesbooleanNoIncorporate images in crawl output
extract_depthstringNoExtraction depth: basic (1 credit/5 pages) or advanced (2 credits/5 pages)
formatstringNoOutput format: markdown or text (default: markdown)
include_faviconbooleanNoAdd favicon URL for each result
apiKeystringYesTavily API Key

Output

ParameterTypeDescription
base_urlstringThe base URL that was crawled
resultsarrayThe crawled page URL

tavily_map

Discover and visualize website structure using Tavily

Input

ParameterTypeRequiredDescription
urlstringYesThe root URL to begin mapping
instructionsstringNoNatural language guidance for mapping behavior (costs 2 credits per 10 pages)
max_depthnumberNoHow far from base URL to explore (1-5, default: 1)
max_breadthnumberNoLinks to follow per level (default: 20)
limitnumberNoTotal links to process (default: 50)
select_pathsstringNoComma-separated regex patterns for URL path filtering (e.g., /docs/.*)
select_domainsstringNoComma-separated regex patterns to restrict mapping to specific domains
exclude_pathsstringNoComma-separated regex patterns to exclude specific URL paths
exclude_domainsstringNoComma-separated regex patterns to exclude domains
allow_externalbooleanNoInclude external domain links in results (default: true)
apiKeystringYesTavily API Key

Output

ParameterTypeDescription
base_urlstringThe base URL that was mapped
resultsarrayDiscovered URL

Notes

  • Category: tools
  • Type: tavily
On this page

On this page

Start building today
Trusted by over 60,000 builders.
Build Agentic workflows visually on a drag-and-drop canvas or with natural language.
Get started