Skip to main content
POST
Upload KB images with optional auto-caption

Request

Response

Behavior

  1. Uploads each image to Bunny CDN under kb-images/{agentId}/{docId}/…
  2. When autoCaption is true, runs the same vision captioning pipeline as dashboard KB uploads
  3. Writes kb_image_assets/{assetId} rows
  4. Creates or updates a kb doc named targetDocName with markdown image blocks — the shape runtime KB search already expects
Match existing card-search naming conventions in targetDocName so retrieval stays consistent with hand-authored galleries.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

agentId
string
required

Body

application/json
images
object[]
required
Required array length: 1 - 30 elements
targetDocName
string
required
Minimum string length: 1
autoCaption
boolean
default:true
tags
string[]

Response

Successful response

success
boolean
required
docId
string
required
assets
object[]
required