POST
/
embeddings
/
by-chunk-ids
cURL
curl --request POST \
  --url https://api.usecortex.ai/embeddings/by-chunk-ids \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: <content-type>' \
  --header 'accept: <accept>' \
  --data '{
  "chunk_ids": [
    "CortexEmbeddings123_0",
    "CortexEmbeddings123_1"
  ],
  "tenant_id": "tenant_456",
  "sub_tenant_id": "subtenant_123"
}'
{
  "embeddings": {
    "CortexEmbeddings123_0": [
      0.12,
      0.34,
      0.56,
      0.78
    ],
    "CortexEmbeddings123_1": [
      0.11,
      0.33,
      0.55,
      0.77
    ]
  },
  "not_found_chunk_ids": []
}
Retrieve embeddings for specific chunk IDs. This endpoint allows you to fetch the embedding vectors for a list of chunk IDs that you previously obtained from uploading embeddings or searching.

​
Requirements

  • chunk_ids: Array of valid chunk ID strings (cannot be empty)
  • tenant_id: Required for multi-tenancy support
  • sub_tenant_id: Optional, defaults to tenant_id if not provided

​
Response Details

  • embeddings: Dictionary mapping chunk IDs to their embedding vectors
  • not_found_chunk_ids: Array of chunk IDs that were not found in the system

​
Sample Request

curl --location 'https://api.usecortex.ai/embeddings/by-chunk-ids' \
  --header 'Authorization: Bearer {API_KEY}' \
  --header 'accept: application/json' \
  --header 'Content-Type: application/json' \
  --data '{
    "chunk_ids": [
      "CortexEmbeddings123_0",
      "CortexEmbeddings123_1", 
      "CortexEmbeddings456_0",
      "CortexEmbeddings789_2"
    ],
    "tenant_id": "{TENANT_ID}",
    "sub_tenant_id": "{SUB_TENANT_ID}"
  }'

​
Sample Response

{
  "embeddings": {
    "CortexEmbeddings123_0": [
      21.0,
      22.0,
      23.0,
      24.0,
      25.0,
      26.0
    ],
    "CortexEmbeddings123_1": [
      20.100000381469727,
      20.200000762939453,
      20.299999237060547,
      20.399999618530273,
      20.5,
      20.600000381469727
    ],
    "CortexEmbeddings456_0": [
      1.5,
      2.5,
      8.5,
      8.5,
      8.5,
      6.5
    ]
  },
  "not_found_chunk_ids": [
    "CortexEmbeddings789_2"
  ]
}

​
Error Responses

  • 400 Bad Request:
    • Empty chunk_ids array
    • Invalid chunk ID format (non-string or empty values)
  • 401 Unauthorized: Invalid or missing API key
  • 500 Internal Server Error: Server processing error

Authorizations

​
Authorization
string
header
required

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

Headers

​
Authorization
string
required

Bearer token (your API key)

​
Content-Type
string
default:application/json
required

Request content type

​
accept
string
default:application/json
required

Response content type

Body

application/json

Response

200
application/json

Embeddings retrieved successfully

The response is of type object.