Naar hoofdinhoud gaan
POST
/
v1
/
embeddings
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cometapi.com/v1",
    api_key="<COMETAPI_KEY>",
)

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The food was delicious and the waiter was friendly.",
)

print(response.data[0].embedding[:5])  # First 5 dimensions
print(f"Dimensions: {len(response.data[0].embedding)}")
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        -0.0021,
        -0.0491,
        0.0209,
        0.0314,
        -0.0453
      ]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  }
}

Documentation Index

Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt

Use this file to discover all available pages before exploring further.

CometAPI ondersteunt embedding-modellen van meerdere providers via één endpoint. Geef één of meer tekststrings door en ontvang numerieke vectoren voor semantisch zoeken, clustering, classificatie of retrieval-augmented generation (RAG). Bekijk de modellenlijst voor beschikbare embedding-modellen en prijzen.
De text-embedding-3-*-modellen ondersteunen de parameter dimensions, waarmee de embedding-vector wordt verkort zonder noemenswaardig nauwkeurigheidsverlies. Dit kan de opslagkosten verlagen terwijl de meeste semantische informatie behouden blijft.
Om meerdere teksten in één request te embedden, geef je een array van strings door aan de parameter input. Batchinvoer is aanzienlijk efficiënter dan afzonderlijke requests doen.

Autorisaties

​
Authorization
string
header
vereist

Bearer token authentication. Use your CometAPI key.

Body

application/json
​
model
string
vereist

The embedding model to use. See the Models page for current embedding model IDs.

Voorbeeld:

"text-embedding-3-small"

​
input
vereist

The text to embed. Can be a single string, an array of strings, or an array of token arrays. Each input must not exceed the model's maximum token limit (8,191 tokens for text-embedding-3-* models).

​
encoding_format
enum<string>
standaard:float

The format of the returned embedding vectors. float returns an array of floating-point numbers. base64 returns a base64-encoded string representation, which can reduce response size for large batches.

Beschikbare opties:
float,
base64
​
dimensions
integer

The number of dimensions for the output embedding vector. Only supported by text-embedding-3-* models. Reducing dimensions can lower storage costs while maintaining most of the embedding's utility.

Vereist bereik: x >= 1
​
user
string

A unique identifier for your end-user, which can help monitor and detect abuse.

Respons

200 - application/json

A list of embedding vectors for the input text(s).

​
object
enum<string>

The object type, always list.

Beschikbare opties:
list
Voorbeeld:

"list"

​
data
object[]

An array of embedding objects, one per input text. When multiple inputs are provided, results are returned in the same order as the input.

​
model
string

The model used to generate the embeddings.

Voorbeeld:

"text-embedding-3-small"

​
usage
object

Token usage statistics for this request.