Commencer maintenant
Exa Tools

Exa Get Contents Action

Utilisez Exa Get Contents Action avec Exa Tools via Aident Loadout. Vérifiez les entrées, sorties, la configuration, le tarif et le risque avant exécution.

Action d'écritureNiveau de risque 2 sur 5Accès géré par Aident

Description du fournisseur

Retrieve text / highlights / summary / subpages from URLs. The endpoint returns HTTP 200 even when individual URLs fail — always inspect `statuses[]` for CRAWL_NOT_FOUND, CRAWL_LIVECRAWL_TIMEOUT, SOURCE_NOT_AVAILABLE. Control freshness with `maxAgeHours` (0 = always livecrawl, -…

Tarifs et limites

Tarif
Paiement unifié
Pris en charge par votre solde Aident en USD

Entrées

  • idsarray
    (Deprecated alias for 'urls') A list of document IDs or URLs. Use 'urls' parameter instead for consistency with the Exa API.
  • text
    Controls text extraction. Accepts a boolean or a `TextOptions` object. If `True` (the default for this tool), sends Exa's documented `text=true` mode and extracts full-page text using default settings. If `False` or `None`, no text is extracted. Provide a `TextOptions` object to…
  • urlsarray
    A list of fully qualified URLs (e.g., 'https://example.com/article') or document IDs (strings obtained from Exa search results) for which to retrieve content. At least one URL or ID must be provided.
  • extrasobject
    Configuration for extracting additional metadata from documents.
  • summary
    Controls AI-generated summary extraction. Accepts a boolean or `SummaryOptions`. If `True`, generates a summary; if `False` or `None`, no summary. Use `SummaryOptions` for custom settings (e.g., `query`, `schema`).
  • subpagesinteger
    Number of subpages to crawl per URL. Enables crawling linked pages within a site in one request. Defaults to 0 (no subpage crawling).
  • highlights
    Controls highlight extraction. Accepts a boolean or `HighlightOptions`. If `True`, extracts AI highlights (default settings); if `False` or `None`, no highlights. Use `HighlightOptions` for custom settings (e.g., `query`, `max_characters`).
  • maxAgeHoursinteger
    Controls content freshness. `0` = always livecrawl, `-1` = never livecrawl (cache only), `None` or positive integer = livecrawl as fallback if cached content is older than specified hours.
  • subpageTarget
    Keywords to prioritize for subpage selection when crawling subpages. Can be a single string or list of strings. Only relevant when `subpages` > 0.
  • livecrawlTimeoutinteger
    Timeout in milliseconds for livecrawl operations. Recommended: 10000-15000 when forcing livecrawl. Defaults to 10000.

Sortie observable

  • data
    Obligatoire
    Data from the action execution
  • errorstring
    Error if any occurred during the execution of the action
  • successfulboolean
    Obligatoire
    Whether or not the action execution was successful or not

Skills qui utilisent cette Action

Cas d’usage associés

Aucun cas d’usage associé et vérifié pour le moment.

Source officielle

Source du fournisseur