Embeddings generieren

Create embeddings for the supplied input. input must be a string or an array of strings. Token arrays (integer IDs) are rejected with HTTP 400. LangChain OpenAIEmbeddings sends token arrays unless check_embedding_ctx_length is False. Wrappers that construct OpenAIEmbeddings without that flag, including gpt-researcher’s openai provider, still send token arrays.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

POST /embeddings

/api/v1/embeddings

cURL

curl --request POST \
  --url https://api.venice.ai/api/v1/embeddings \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "encoding_format": "float",
  "input": "The quick brown fox jumped over the lazy dog",
  "model": "text-embedding-bge-m3"
}
'

200

{
  "data": [
    {
      "embedding": [
        0.0023064255,
        -0.009327292,
        0.015797377
      ],
      "index": 0,
      "object": "embedding"
    }
  ],
  "model": "text-embedding-bge-m3",
  "object": "list",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

input muss ein String oder ein Array von Strings sein. Token-ID-Arrays werden mit HTTP 400 abgelehnt. Bei LangChain OpenAIEmbeddings muss check_embedding_ctx_length=False gesetzt werden.

Autorisierungen

BearerAuthsiwx

Authorization · string · header · erforderlich

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

Header

Accept-Encoding · string

Supported compression encodings (gzip, br)

Beispiel:

"gzip, br"

Body

application/json

Create embeddings for the supplied input.

input · string string[] · erforderlich

Input text to embed, encoded as a string or array of strings. To embed multiple inputs in a single request, pass an array of strings. The input must not exceed the max input tokens for the model (8192 tokens), cannot be an empty string, and any array must contain 2048 items or less. Token arrays are not supported and return HTTP 400. LangChain OpenAIEmbeddings sends token arrays unless you set check_embedding_ctx_length=False.

Minimum string length: 1

Beispiel:

"The quick brown fox jumped over the lazy dog"

model · string enum<string> · erforderlich

ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

Beispiel:

"text-embedding-bge-m3"

dimensions · integer

The number of dimensions the resulting output embeddings should have.

Erforderlicher Bereich: x >= 1

encoding_format · enum<string> · Standard: float

The format to return the embeddings in. Can be either float or base64.

Verfügbare Optionen: float, base64

Beispiel:

"float"

user · string

This is an unused parameter and is discarded by Venice. It is supported solely for API compatibility with OpenAI.

Antwort

200

application/json

OK

data · object[] · erforderlich

The list of embeddings generated by the model.

Show child attributes

model · string · erforderlich

The name of the model used to generate the embedding.

object · enum<string> · erforderlich

The object type, which is always "list"

Verfügbare Optionen: list

usage · object · erforderlich

The usage information for the request.

Show child attributes