Parallel: Extract

Extract the content of public URLs, including JavaScript-heavy pages and PDFs, as excerpts focused on an objective or as full text.

Tool ID: parallel_extract

Run this action

Use the TypeScript SDK for one call. Use ctx.tools.execute(...) inside a Play for durable calls, scheduled calls, or CSV processing.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'parallel_extract',
  {
    "urls": [
      "https://example.com"
    ]
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute parallel_extract --input '{
  "urls": [
    "https://example.com"
  ]
}' --json

Example response

The static output schema lacks the details for a reliable example. Use deepline describe parallel_extract --json for the complete live contract.

Input reference

Parallel extract input.

Name	Type	Required	Default	Details
`payload.urls`	`array`	Yes	—	Required. List of URLs to extract (max 10). Minimum items: 1.
`payload.objective`	`string`	No	—	—
`payload.search_queries`	`array`	No	—	—
`payload.fetch_policy`	`object`	No	—	Parallel fetch policy.
`payload.excerpts`	`boolean \| object`	No	—	—
`payload.full_content`	`boolean \| object`	No	—	—
`payload.betas`	`string \| array`	No	—	—

Output reference

Parallel result payload.

Name	Type	Required	Default	Details
`result.data`	`record`	Yes	—	Provider response payload.
`result.meta`	`record`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: per_result (per result).
Estimated Deepline credits: 0.02 per pricing unit.

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation