Limadata: Research Search

Run AI web research for a natural-language query and return an answer with ranked source results.

Tool ID: limadata_research_search

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(
  'limadata_research_search',
  {
    "query": "software companies hiring engineers"
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute limadata_research_search --input '{
  "query": "software companies hiring engineers"
}' --json

Example response

The SDK returns this shape at result.toolResponse.raw. The example values illustrate the response.

{
  "data": {
    "answer": "example",
    "results": [
      {
        "title": "VP of Engineering",
        "url": "https://example.com",
        "snippet": "example"
      }
    ]
  }
}

Use deepline describe limadata_research_search --json for the latest machine-readable contract.

Input reference

This endpoint is an AI search tool. It acts as a context retrieval tool for Web content. For a natural language query, it finds online information to answer your query. It has the ability to search the web and fetch URL content to enhance understanding. #### Rate limit This endpoint is exempt from the global rate limit and can support higher concurrency. ### Cost:

Name	Type	Required	Default	Details
`payload.query`	`string`	Yes	—	Search query string Minimum length: 1.
`payload.output_type`	`"SearchResults" \| "SourcedAnswer" \| "Structured"`	No	—	The type of output to return. Allowed: `SearchResults`, `SourcedAnswer`, `Structured`.

Output reference

Standard tool result payload.

Name	Type	Required	Default	Details
`result.data`	`object`	Yes	—	Provider response payload.
`result.data.answer`	`string \| null`	No	—	A short answer to the user’s query, generated by an LLM. Included in the response only if output_type is SourcedAnswer.
`result.data.results`	`array \| null`	No	—	A list of sorted search results, ranked by relevancy.
`result.data.results[].title`	`string \| null`	No	—	—
`result.data.results[].url`	`string \| null`	No	—	—
`result.data.results[].snippet`	`string \| null`	No	—	—
`result.data.results[].extract`	`object \| null`	No	—	—
`result.data.results[].extract.url`	`string \| null`	No	—	Original URL that was processed
`result.data.results[].extract.title`	`string \| null`	No	—	Page title
`result.data.results[].extract.meta_description`	`string \| null`	No	—	Meta description
`result.data.results[].extract.favicon`	`string \| null`	No	—	Favicon URL
`result.data.results[].extract.content`	`string \| null`	No	—	Cleaned content in Markdown format
`result.data.results[].extract.images`	`array \| null`	No	—	List of image URLs found on the page (only present if include_images was requested)
`result.data.results[].extract.links`	`array \| null`	No	—	List of link URLs found on the page (only present if include_links was requested)
`result.data.results[].extract.links[].url`	`string \| null`	No	—	—
`result.data.results[].extract.links[].text`	`string \| null`	No	—	—
`result.meta`	`object`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: fixed (per call).
Estimated Deepline credits: 0.09 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