Create a new embedding chunk

Creates a new embedding chunk for an existing upload. The chunk text is vectorized automatically using the institution’s configured embedding model. The new chunk is appended after the last existing chunk (highest chunkIndex + 1).

Use this to manually extend a file’s RAG segments with additional text content that wasn’t captured during automatic ingestion.

POST /api/user/embedding

Create a new embedding chunk

cURL

curl --request POST \
  --url https://pria.praxislxp.com/api/user/embedding \
  --header 'Content-Type: application/json' \
  --header 'x-access-token: <api-key>' \
  --data '
{
  "upload": "665a1b2c3d4e5f6789012300",
  "chunkText": "This is a new manually-added paragraph for RAG search..."
}
'

201

{
  "success": true,
  "message": "Embedding created!",
  "data": {
    "_id": "665a1b2c3d4e5f6789012345",
    "chunkText": "This is a paragraph from the uploaded document...",
    "chunkLen": 512,
    "chunkIndex": 0,
    "upload": "665a1b2c3d4e5f6789012300",
    "chunkUrl": "#page=2",
    "created": "2023-11-07T05:31:56Z",
    "usage": 128
  }
}

Authorizations

x-access-token · string · header · required

JWT token passed in x-access-token header

Body

application/json

upload · string · required

The ID of the upload to add the embedding chunk to

Example:

"665a1b2c3d4e5f6789012300"

chunkText · string · required

The text content for the new chunk (max ~32K characters). A vector embedding is generated automatically.

Example:

"This is a new manually-added paragraph for RAG search..."

Response

201

application/json

Embedding chunk created successfully

success · boolean

Example:

true

message · string

Example:

"Embedding created!"

data · object

Show child attributes