Train discovered website pages and ingest into the knowledge base

POST 
/knowledge-bases/crawler/train

Queues selected discovered pages so the AI ingests their content into the knowledge base. WHEN TO USE: use this when discoverWebsite has already found pages; use discoverWebsite to crawl first; use deleteTrainedUrlsForKnowledgeBase to untrain pages. RETURNS: whether training was queued, a status message, and the URL ids that were accepted.

Request

Version stringrequired

API Version

Available optionsv3

application/json

application/json

Body

Bodyrequired

locationIdstringrequired

Location ID as string

knowledgeBaseIdstringrequired

Knowledge base ID as string

operationIdstringrequired

Operation ID as string

urlIdsstring[]required

List of URL IDs to train

Example (auto)

{
  "locationId": "jNtgzTfHnLKErAWswvVE",
  "knowledgeBaseId": "RXzAdYGknD2phAoln3Jl",
  "operationId": "689267ba9d8d63ea160ee9c7",
  "urlIds": [
    "689267ccb27254d92da17b69"
  ]
}

application/json

Pages trained successfully

application/json

Schema

Schema

successbooleanrequired

Indicates if the operation was successful

messagestringrequired

Success message

urlIdsstring[]required

Array of URL IDs that were queued for training

Example (auto)

{
  "success": true,
  "message": "Training queued for 3 URLs",
  "urlIds": [
    "url_123",
    "url_456",
    "url_789"
  ]
}