Skip to main content

ScrapeJobCreateRequest

Request to import website content into an agent's knowledge base.

agent_idAgent Idrequired

ID of the agent (a configured AI assistant / bot persona) this record belongs to.

urlUrlrequired

Public http(s) URL of the site or page to import.

Possible values: non-empty and <= 2000 characters

context object

Free-form description of what data matters (e.g. "wine ratings and tasting notes"). Drives which pages are selected and what content is kept.

anyOf
string

Possible values: <= 8000 characters

mode object

Discovery mode. site maps the whole website; page imports the URL itself plus the pages it links to (one hop). Omit to resolve automatically from the URL shape (bare host = site, deep path = page).

anyOf
ScrapeDiscoveryMode

Possible values: [site, page]

max_pages object

Optional per-job page cap; the server clamps it to the global limit and stores the effective value.

anyOf
integer

Possible values: >= 1

directory_id object

Existing knowledge directory to ingest into. Omit to create or reuse a directory named after the website's hostname.

anyOf
integer
ScrapeJobCreateRequest
{
  "agent_id": 0,
  "url": "string",
  "context": "string",
  "mode": "site",
  "max_pages": 0,
  "directory_id": 0
}