Tavily is an AI-powered search tool designed to help users quickly find accurate, relevant, and up-to-date information from the web.

Categories: Artificial Intelligence

Type: tavily/v1

Connections

Version: 1

Bearer Token

Properties

Name	Label	Type	Description	Required
token	Token	STRING		true

Actions

Search

Name: search

Execute a search query.

Properties

Name	Label	Type	Description	Required
query	Query	STRING	The search query to execute.	true
topic	Topic	STRING Options general, news	The category of the search.	false
search_depth	Search Depth	STRING Options basic, advanced	The depth of the search.	false
time_range	Time Range	STRING Options day, week, month, year	The time range back from the current date to filter results.	false
max_results	Max Results	INTEGER	The maximum number of search results to return.	false
include_answer	Include Answer	BOOLEAN Options true, false	Include an LLM-generated answer to the provided query.	false
include_images	Include Images	BOOLEAN Options true, false	Perform an image search and include the results in the response.	false

Example JSON Structure

{
  "label" : "Search",
  "name" : "search",
  "parameters" : {
    "query" : "",
    "topic" : "",
    "search_depth" : "",
    "time_range" : "",
    "max_results" : 1,
    "include_answer" : false,
    "include_images" : false
  },
  "type" : "tavily/v1/search"
}

Properties

Name	Type	Description
query	STRING	The search query that was executed.
answer	STRING	A short answer to the user's query, generated by an LLM. Included in the response only if include_answer is requested.
images	ARRAY Items [{}]	List of query-related images.
results	ARRAY Items [{STRING(title), STRING(url), STRING(content), NUMBER(score)}]	A list of sorted search results, ranked by relevancy.
response_time	NUMBER	Time in seconds it took to complete the request.

Output Example

{
  "query" : "",
  "answer" : "",
  "images" : [ { } ],
  "results" : [ {
    "title" : "",
    "url" : "",
    "content" : "",
    "score" : 0.0
  } ],
  "response_time" : 0.0
}

Extract

Name: extract

Extract web page content from one or more specified URLs.

Properties

Name	Label	Type	Description	Required
urls	URLs	ARRAY Items [STRING]	A list of URLs to extract content from.	true
include_images	Include Images	BOOLEAN Options true, false	Include a list of images extracted from the URLs in the response.	false
extract_depth	Extract Depth	STRING Options basic, advanced	The depth of the extraction process.	false

Example JSON Structure

{
  "label" : "Extract",
  "name" : "extract",
  "parameters" : {
    "urls" : [ "" ],
    "include_images" : false,
    "extract_depth" : ""
  },
  "type" : "tavily/v1/extract"
}

Properties

Name	Type	Description
results	ARRAY Items [{STRING(url), STRING(raw_content), [STRING](images)}]	A list of extracted content from the provided URLs.
failed_results	ARRAY Items [{STRING(url), STRING(error)}]	A list of URLs that could not be processed.
response_time	NUMBER	Time in seconds it took to complete the request.

Output Example

{
  "results" : [ {
    "url" : "",
    "raw_content" : "",
    "images" : [ "" ]
  } ],
  "failed_results" : [ {
    "url" : "",
    "error" : ""
  } ],
  "response_time" : 0.0
}

What to do if your action is not listed here?

If this component doesn't have the action you need, you can use Custom Action to create your own. Custom Actions empower you to define HTTP requests tailored to your specific requirements, allowing for greater flexibility in integrating with external services or APIs.

To create a Custom Action, simply specify the desired HTTP method, path, and any necessary parameters. This way, you can extend the functionality of your component beyond the predefined actions, ensuring that you can meet all your integration needs effectively.

Additional Instructions

Connection Setup

Login to the dashboard at https://www.tavily.com/.
You can use default API key. To create new API key, click on "+" sign.
Name your key and click Create.
Copy the API key. Use these credentials to create a connection in ByteChef.

Tavily

On this page