> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/tavily.md).

# Tavily

Tavily provides AI-optimized search, content extraction, website crawling, and site mapping. Search the web for real-time information, extract structured content from URLs, crawl entire websites, or generate comprehensive site maps with intelligent discovery.

## Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector | Authentication |
| --------- | -------------- |
| Tavily    | API Key        |

### Tavily

Connect to Tavily API for AI-powered search and retrieval. Supports searching the web, news, and documents for information. Search designed for Large Language Models (LLMs).

#### Set up in Tavily

1. Sign up for or sign in to Tavily and open your account dashboard (app.tavily.com).
2. Find the API Keys section and copy your API key (create one if needed).

#### Set up in StackAI

1. Open **Settings → Connections**, add a connection, and select **Tavily**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                                    |
| ------------- | -------- | ---------------------------------------------------------------------------------------------------------------- |
| API Key       | Yes      | Your Tavily API key. Find your API key in your Tavily account. [Provider instructions](https://api.tavily.com/). |

**Provider documentation:** [Setup reference](https://docs.tavily.com/documentation/quickstart).

### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

## Use an action

1. Add the required **Tavily** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

## Actions

### Tavily Search

Search the web using Tavily's AI-optimized search engine. Get real-time, accurate, and unbiased information designed for AI applications.

#### Inputs

| Field                      | Type            | Required | Description                                                                                                                                                |
| -------------------------- | --------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Query                      | string          | Yes      | Enter the search query for Tavily.                                                                                                                         |
| Auto Parameters            | boolean         | No       | Let Tavily automatically tune search options like topic, search depth, and time filters based on your query's content and intent. Default: false.          |
| Topic                      | select (string) | No       | The topic of the search query. General, News, or Finance. Available values: General, News, Finance. Default: general.                                      |
| Search Depth               | select (string) | No       | Choose search depth: basic (1 credit, generic snippets) or advanced (2 credits, most relevant sources). Available values: Basic, Advanced. Default: basic. |
| Chunks per Source          | number          | No       | The number of chunks per source from 1 to 3. Default: 3.                                                                                                   |
| Maximum Search Results     | number          | No       | The maximum number of search results to return from 0 to 20. Default: 5.                                                                                   |
| Include Answer             | select (string) | No       | Choose the type of answer to include: basic (concise) or advanced (detailed). Leave empty to not include an answer. Available values: Basic, Advanced.     |
| Include Images             | boolean         | No       | Whether to include images in the search results. Default: false.                                                                                           |
| Include Image Descriptions | boolean         | No       | Whether to include image descriptions in the search results. Default: false.                                                                               |

#### Outputs

| Field           | Type          | Description                                                    |
| --------------- | ------------- | -------------------------------------------------------------- |
| Status Code     | integer       | HTTP status code of the response.                              |
| Query           | string        | The search query used to search for the results.               |
| Answer          | string        | The LLM-generated answer to the search query.                  |
| Results         | object\_array | The search results.                                            |
| Images          | object\_array | The images returned from the search results.                   |
| Auto Parameters | dict          | The auto configured parameters used to search for the results. |

### Tavily Extract

Extract structured content from one or more URLs. Returns clean, formatted content with optional images.

#### Inputs

| Field          | Type            | Required | Description                                                                                                                                                                       |
| -------------- | --------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| URLs           | string          | Yes      | Enter comma-separated URLs to extract content from (max 20 URLs).                                                                                                                 |
| Include Images | boolean         | No       | Include a list of images extracted from the URLs in the response. Default: false.                                                                                                 |
| Extract Depth  | select (string) | No       | Choose extraction depth: basic (1 credit per 5 URLs) or advanced (2 credits per 5 URLs, includes tables and embedded content). Available values: Basic, Advanced. Default: basic. |
| Format         | select (string) | No       | Choose output format: markdown or plain text. Available values: Markdown, Text. Default: markdown.                                                                                |

#### Outputs

| Field          | Type          | Description                                            |
| -------------- | ------------- | ------------------------------------------------------ |
| Status Code    | integer       | HTTP status code of the response.                      |
| URLs           | string\_array | Array of URLs that were successfully extracted.        |
| Raw Content    | string\_array | Array of extracted content from the URLs.              |
| Images         | string\_array | Flattened array of all images extracted from all URLs. |
| Failed Results | object\_array | URLs that could not be processed.                      |

### Tavily Crawl

Crawl entire websites starting from a root URL. Explores multiple paths in parallel with intelligent discovery and automatic content extraction.

#### Inputs

| Field          | Type            | Required | Description                                                                                                                                               |
| -------------- | --------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
| URL            | string          | Yes      | Enter the root URL to begin the crawl (e.g., docs.tavily.com).                                                                                            |
| Instructions   | string          | No       | Natural language instructions to guide the crawler. Increases cost to 2 credits per 10 pages (vs 1 credit without instructions).                          |
| Max Depth      | number          | No       | Maximum depth of crawl from the base URL (1-5). Default: 1.                                                                                               |
| Limit          | number          | No       | Total number of links to process before stopping. Default: 50.                                                                                            |
| Include Images | boolean         | No       | Include images in the crawl results. Default: false.                                                                                                      |
| Extract Depth  | select (string) | No       | Choose extraction depth: basic (1 credit per 5 extractions) or advanced (2 credits per 5 extractions). Available values: Basic, Advanced. Default: basic. |
| Format         | select (string) | No       | Choose output format: markdown or plain text. Available values: Markdown, Text. Default: markdown.                                                        |

#### Outputs

| Field       | Type          | Description                       |
| ----------- | ------------- | --------------------------------- |
| Status Code | integer       | HTTP status code of the response. |
| Base URL    | string        | The base URL that was crawled.    |
| Results     | object\_array | The crawl results.                |

### Tavily Map

Discover and map all URLs on a website starting from a root URL. Returns a list of discovered URLs without extracting content.

#### Inputs

| Field        | Type   | Required | Description                                                                                                                      |
| ------------ | ------ | -------- | -------------------------------------------------------------------------------------------------------------------------------- |
| URL          | string | Yes      | Enter the root URL to begin the mapping (e.g., docs.tavily.com).                                                                 |
| Instructions | string | No       | Natural language instructions to guide the crawler. Increases cost to 2 credits per 10 pages (vs 1 credit without instructions). |
| Max Depth    | number | No       | Maximum depth of mapping from the base URL (1-5). Default: 3.                                                                    |

#### Outputs

| Field       | Type          | Description                       |
| ----------- | ------------- | --------------------------------- |
| Status Code | integer       | HTTP status code of the response. |
| Base URL    | string        | The base URL that was mapped.     |
| Results     | string\_array | Discovered URLs from the mapping. |

## Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/tavily.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
