Referensi API
Panduan Integrasi
Kesalahan
Harga & Penagihan
Embeddings
POST /v1/embeddings menghasilkan embeddings teks dengan model yang dipilih untuk alur kerja pencarian semantik, clustering, dan retrieval melalui CometAPI.
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
}
}Ringkasan
API Embeddings menghasilkan representasi vektor dari teks yang menangkap makna semantik. Vektor ini dapat digunakan untuk pencarian semantik, clustering, klasifikasi, deteksi anomali, dan retrieval-augmented generation (RAG). CometAPI mendukung model embedding dari banyak provider. Kirim satu atau lebih string teks dan terima kembali vektor numerik yang dapat Anda simpan di database vektor atau gunakan langsung untuk perhitungan kemiripan.Model yang Tersedia
| Model | Dimensi | Maks Token | Paling Cocok Untuk |
|---|---|---|---|
text-embedding-3-large | 3,072 (dapat disesuaikan) | 8,191 | Embeddings kualitas tertinggi |
text-embedding-3-small | 1,536 (dapat disesuaikan) | 8,191 | Hemat biaya, cepat |
text-embedding-ada-002 | 1,536 (tetap) | 8,191 | Kompatibilitas legacy |
Catatan Penting
text-embedding-3-* mendukung parameter dimensions, yang memungkinkan Anda memendekkan vektor embedding tanpa kehilangan akurasi yang signifikan. Ini dapat mengurangi biaya penyimpanan hingga 75% sambil tetap mempertahankan sebagian besar informasi semantik.input. Ini jauh lebih efisien daripada membuat request terpisah untuk setiap teks.Otorisasi
Bearer token authentication. Use your CometAPI key.
Body
The embedding model to use. See the Models page for current embedding model IDs.
"text-embedding-3-small"
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).
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.
float, base64 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.
x >= 1A unique identifier for your end-user, which can help monitor and detect abuse.
Respons
A list of embedding vectors for the input text(s).
The object type, always list.
list "list"
An array of embedding objects, one per input text. When multiple inputs are provided, results are returned in the same order as the input.
Show child attributes
Show child attributes
The model used to generate the embeddings.
"text-embedding-3-small"
Token usage statistics for this request.
Show child attributes
Show child attributes
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
}
}