Langsung ke konten utama
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 mendukung model embedding dari berbagai provider melalui satu endpoint. Kirim satu atau lebih string teks dan terima vektor numerik untuk semantic search, clustering, classification, atau retrieval-augmented generation (RAG). Lihat daftar model untuk model embedding yang tersedia dan harganya.
Model text-embedding-3-* mendukung parameter dimensions, yang memendekkan vektor embedding tanpa kehilangan akurasi yang signifikan. Ini dapat mengurangi biaya penyimpanan sambil tetap mempertahankan sebagian besar informasi semantik.
Untuk membuat embedding beberapa teks dalam satu request, kirim array string ke parameter input. Input batch jauh lebih efisien dibandingkan membuat request satu per satu.

Otorisasi

​
Authorization
string
header
wajib

Bearer token authentication. Use your CometAPI key.

Body

application/json
​
model
string
wajib

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

Contoh:

"text-embedding-3-small"

​
input
wajib

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>
default: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.

Opsi yang tersedia:
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.

Rentang yang diperlukan: 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.

Opsi yang tersedia:
list
Contoh:

"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.

Contoh:

"text-embedding-3-small"

​
usage
object

Token usage statistics for this request.