Create an embedding

Updated:

POST/genai/{connection_id}/embedding

Creates a GenaiEmbedding. Provide the unified GenaiEmbedding fields in the request body; they are mapped to the provider's API. Returns the created GenaiEmbedding.

Parameters

fieldsstring array
Fields to return
rawstring
Raw parameters to include in the 3rd-party request. Encoded as a URL component. eg. raw parameters: foo=bar&zoo=bar -> raw=foo%3Dbar%26zoo%3Dbar
connection_idstring required
ID of the connection

Payload

model_idstring
content array
The texts to create embeddings for
enconding_format enum
Valid values:
"FLOAT"
"UINT8"
"INT8"
"BINARY"
"UBINARY"
typestring
'SEARCH_DOC' | 'SEARCH_QUERY' | 'CLUSTERING' | 'CLASSIFICATION';
dimensionnumber
256, 512, 1024, and 1536
max_tokensnumber
embeddingsstring read-only
JSON string based off of the format
tokens_usednumber read-only
idstring

Returns

Response fieldTypeRequiredDescription
model_idstringNo
contentGenaiEmbeddingContent[]NoThe texts to create embeddings for
content[].textstringYes
enconding_formatenumNoValues: FLOAT, UINT8, INT8, BINARY, UBINARY, BASE64
typestringNo'SEARCH_DOC' | 'SEARCH_QUERY' | 'CLUSTERING' | 'CLASSIFICATION';
dimensionnumberNo256, 512, 1024, and 1536
max_tokensnumberNo
embeddingsstringNoJSON string based off of the format (read-only)
tokens_usednumberNo (read-only)
idstringNo

Errors

Errors return the HTTP status code and a JSON body with statusCode, error (the short label) and message (a human-readable detail).

{
  "statusCode": 429,
  "error": "Too Many Requests",
  "message": "Too many requests to unified.to API; max requests per minute: N"
}
StatusErrorMeaning
400Bad RequestThe request was malformed or failed validation.
401UnauthorizedThe connection is likely broken; re-authorize it.
403ForbiddenThe connection is missing permissions or scopes.
404Not FoundThe requested resource does not exist.
429Too Many RequestsRate limit exceeded (see the two sources below).
500Internal Server ErrorAn unexpected error occurred.
501Not ImplementedNot supported by this integration.

Errors from the underlying integration pass through: the integration's status comes back as ours (429, 401, 403, 404 or 5xx), usually with its message. When the integration's error body is unclear, Unified extracts what it can and returns a clearer message.

429 Too Many Requests

A 429 has two possible sources:

  • The integration's own rate limit, passed through.
  • Unified's workspace limit: a rolling 60 seconds, set by plan, with the message Too many requests to unified.to API; max requests per minute: N.
const options = {
  method: 'POST',
  url: 'https://api.unified.to/genai/5de520f96e439b002043d8dc/embedding',
  headers: {
    authorization: 'bearer .....'
  },
  data: undefined,
  params: {
    fields: '',
    raw: '',
  }
};

const results = await axios.request(options);
Are we missing anything? Let us know
Was this page helpful?