Share via

Tavily (Independent Publisher) (Preview)

Tavily is a specialized search engine designed for Large Language Models (LLMs) and AI agents. It provides real-time, accurate, and unbiased information, enabling AI applications to retrieve and process data efficiently. Tavily is built with AI developers in mind, simplifying the process of integrating dynamic web information into AI-driven solutions.

This connector is available in the following products and regions:

Service Class Regions
Copilot Studio Premium All Power Automate regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Logic Apps Standard All Logic Apps regions except the following:
     -   Azure Government regions
     -   Azure China regions
     -   US Department of Defense (DoD)
Power Apps Premium All Power Apps regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Power Automate Premium All Power Automate regions except the following:
     -   US Government (GCC)
     -   US Government (GCC High)
     -   China Cloud operated by 21Vianet
     -   US Department of Defense (DoD)
Contact
Name Troy Taylor
URL https://www.hitachisolutions.com
Email ttaylor@hitachisolutions.com
Connector Metadata
Publisher Troy Taylor
Website https://tavily.com/
Privacy policy https://tavily.com/privacy
Categories Lifestyle and Entertainment;Website

Creating a connection

The connector supports the following authentication types:
Default Parameters for creating connection. All regions Not shareable

Default

Applicable: All regions

Parameters for creating connection.

This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.

Name Type Description Required
API Key securestring The API Key for this api True

Throttling Limits

Name Calls Renewal Period
API calls per connection 100 60 seconds

Actions

Tavily Crawl (Beta)

Traverse a site like a graph starting from a base URL.
Tavily Extract

Extract web page content from one or more specified URLs using Tavily Extract.
Tavily Map (Beta)

Obtain a sitemap starting from a base URL.
Tavily Search

Execute a search query using Tavily Search.

Tavily Crawl (Beta)

Operation ID:
CrawlPost

Traverse a site like a graph starting from a base URL.

Parameters

Name Key Required Type Description
URL
 url True string

The URL to crawl.
Max Depth
 max_depth integer

The maximum depth to crawl.
Max Breadth
 max_breadth integer

The maximum breadth to crawl.
Limit
 limit integer

The maximum number of pages to crawl.
Instructions
 instructions string

Instructions for the crawler.
Select Paths
 select_paths array of string

The paths to include in the crawl.
Select Domains
 select_domains array of string

The domains to include in the crawl.
Exclude Paths
 exclude_paths array of string

The paths to exclude from the crawl.
Exclude Domains
 exclude_domains array of string

The domains to exclude from the crawl.
Allow External
 allow_external boolean

Whether to allow external links.
Include Images
 include_images boolean

Whether to include images in the crawl.
Categories
 categories array of string

The categories to include in the crawl.
Extract Depth
 extract_depth string

The depth of content extraction.

Returns

Name Path Type Description
Base URL
 base_url string

The base URL to start crawling from.
Results
 results array of object
URL
 results.url string

The URL of the crawled page.
Raw Content
 results.raw_content string

The raw HTML content of the crawled page.
Response Time
 response_time float

The time taken to process the request.

Tavily Extract

Operation ID:
ExtractPost

Extract web page content from one or more specified URLs using Tavily Extract.

Parameters

Name Key Required Type Description
URLs
 urls True string

The URLs to extract content from.
Include Images
 include_images boolean

Whether to include images in the extraction.
Extract Depth
 extract_depth string

The depth of the extraction.

Returns

Name Path Type Description
Results
 results array of object
URL
 results.url string

The URL of the web page.
Raw Content
 results.raw_content string

The raw HTML content of the web page.
Images
 results.images array of string

The images found on the web page.
Failed Results
 failed_results array of object
URL
 failed_results.url string

The URL of the failed result.
Error
 failed_results.error string

The error message for the failed result.
Response Time
 response_time float

The time taken to process the request.

Tavily Map (Beta)

Operation ID:
MapPost

Obtain a sitemap starting from a base URL.

Parameters

Name Key Required Type Description
URL
 url True string

The URL to crawl.
Max Depth
 max_depth integer

The maximum depth to crawl.
Max Breadth
 max_breadth integer

The maximum breadth to crawl.
Limit
 limit integer

The maximum number of pages to crawl.
Instructions
 instructions string

Instructions for the crawler.
Select Paths
 select_paths array of string

The paths to include in the crawl.
Select Domains
 select_domains array of string

The domains to include in the crawl.
Exclude Paths
 exclude_paths array of string

The paths to exclude from the crawl.
Exclude Domains
 exclude_domains array of string

The domains to exclude from the crawl.
Allow External
 allow_external boolean

Whether to allow external links.
Categories
 categories array of string

The categories to include in the crawl.

Returns

Name Path Type Description
Base URL
 base_url string

The base URL to start crawling from.
Results
 results array of string

The URLs of the crawled pages.
Response Time
 response_time float

The time taken to process the request.
Operation ID:
SearchPost

Execute a search query using Tavily Search.

Parameters

Name Key Required Type Description
Query
 query True string

The search query.
Topic
 topic string

The topic of the search.
Search Depth
 search_depth string

The depth of the search.
Chunks Per Source
 chunks_per_source integer

The number of chunks to return per source.
Max Results
 max_results integer

The maximum number of results to return.
Time Range
 time_range string

The time range for the search.
Days
 days integer

The number of days to include in the search.
Include Answer
 include_answer boolean

Whether to include answers in the search results.
Include Raw Content
 include_raw_content boolean

Whether to include raw content in the search results.
Include Images
 include_images boolean

Whether to include images in the search results.
Include Image Descriptions
 include_image_descriptions boolean

Whether to include image descriptions in the search results.
Include Domains
 include_domains array of string

include_domains
Exclude Domains
 exclude_domains array of string

exclude_domains

Returns

Name Path Type Description
Query
 query string

The search query.
Answer
 answer string

The answer to the search query.
Images
 images array of object
URL
 images.url string

The URL of the image.
Description
 images.description string

A brief description of the image.
Results
 results array of object
Title
 results.title string

The title of the result.
URL
 results.url string

The URL of the result.
Content
 results.content string

The content of the result.
Score
 results.score float

The relevance score of the result.
Raw Content
 results.raw_content string

The raw content of the result.
Response Time
 response_time float

The time taken to process the request.