Exa

Search the web, find similar pages, and get page contents with Exa's neural search.

AI and MLAPI key5 actionsAll integrations

On this page

Connect
Call it from a workflow
Actions (5)
find_similar_links
get_contents
perform_search
custom_api_call
generate_answer
Details

Connect

Auth type: API key (secret_text). Paste the API key (or token) from the provider's settings into the connect dialog. It is encrypted at rest and only decrypted on the server when an action runs.

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("exa", "find_similar_links", {
    "url": "<url>"
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("Exa answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "exa-find-similar-links",
  name: "Exa: Find Similar Links",
  description: "Calls Exa when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("exa", {
      "action": "find_similar_links",
      "url": "<url>"
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/exa/find_similar_links" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"url":"<url>"}}'

Actions

find_similar_linksin catalog

Find Similar Links. Find pages similar to a given URL.

Input	Type	Description
`url`required	text	Reference URL to find semantically similar links.
`numResults`optional	number	Number of results to return (max 100).
`includeDomains`optional	array	List of domains to include in results.
`excludeDomains`optional	array	List of domains to exclude from results.
`startCrawlDate`optional	date-time (ISO)	Include links crawled after this date (ISO format).
`endCrawlDate`optional	date-time (ISO)	Include links crawled before this date (ISO format).
`startPublishedDate`optional	date-time (ISO)	Only include links published after this date (ISO format).
`endPublishedDate`optional	date-time (ISO)	Only include links published before this date (ISO format).
`includeText`optional	array	Strings that must be present in the webpage text (max 1 string of up to 5 words).
`excludeText`optional	array	Strings that must not be present in the webpage text (max 1 string of up to 5 words).

get_contentsin catalog

Get Contents. Retrieve clean HTML content from specified URLs.

Input	Type	Description
`urls`required	array	Array of URLs to crawl
`text`optional	boolean	If true, returns full page text. If false, disables text return.
`livecrawl`optional	one of "never" \| "fallback" \| "always" \| "auto"	Options for livecrawling pages.
`livecrawlTimeout`optional	number	Timeout for livecrawling in milliseconds.
`subpages`optional	number	Number of subpages to crawl.
`subpageTarget`optional	text	Keyword(s) to find specific subpages.

perform_searchin catalog

Perform Search. Search the web using semantic or keyword-based search.

Also accepted as search.

Input	Type	Description
`query`required	text	Search query to find related articles and data.
`type`optional	one of "auto" \| "keyword" \| "neural"	Type of search to perform.
`category`optional	one of "company" \| "research paper" \| "news" \| "pdf" \| "github" \| "tweet" \| "personal site" \| "linkedin profile" \| "financial report"	Category of data to focus the search on.
`numResults`optional	number	Number of results to return (max 100).
`includeDomains`optional	array	Limit results to only these domains.
`excludeDomains`optional	array	Exclude results from these domains.
`startCrawlDate`optional	date-time (ISO)	Only include results crawled after this ISO date.
`endCrawlDate`optional	date-time (ISO)	Only include results crawled before this ISO date.
`startPublishedDate`optional	date-time (ISO)	Only include results published after this ISO date.
`endPublishedDate`optional	date-time (ISO)	Only include results published before this ISO date.
`includeText`optional	array	Strings that must be present in the text of results.
`excludeText`optional	array	Strings that must not be present in the text of results.

custom_api_call

Custom API Call. Make a custom API call to a specific endpoint

Input	Type	Description
`url`required	object (depends on other props)	url
`method`required	one of "GET" \| "POST" \| "PATCH" \| "PUT" \| "DELETE" \| "HEAD"	Method
`headers`required	object	Authorization headers are injected automatically from your connection.
`queryParams`required	object	Query Parameters
`body_type`optional	one of "none" \| "json" \| "form_data" \| "raw"	Body Type
`body`optional	object (depends on other props)	Body
`response_is_binary`optional	boolean	Enable for files like PDFs, images, etc.
`failsafe`optional	boolean	No Error on Failure
`timeout`optional	number	Timeout (in seconds)
`followRedirects`optional	boolean	Follow redirects

generate_answer

Ask AI. Provides direct answers to queries by summarizing results.

Input	Type	Description
`query`required	text	Ask a question to get summarized answers from the web.
`text`optional	boolean	If true, includes full text content from the search results
`model`required	one of "exa" \| "exa-pro"	Choose the Exa model to use for the answer.

Details

Id: exa
Category: AI and ML
Tags: search, neural-search, web, ai, discovery
Package: @activepieces/piece-exa@0.1.5
Tier: Community

Exa