Embeddings — POST /v1/embeddings

Endpoint /v1/embeddings menghasilkan embedding vektor untuk input teks. Embedding merepresentasikan makna semantik teks sebagai array float berdimensi tinggi, yang memungkinkan pencarian kemiripan, pengelompokan, dan retrieval-augmented generation (RAG). Endpoint ini kompatibel dengan OpenAI Embeddings API.

Endpoint

POST https://router.flatkey.ai/v1/embeddings

Model embedding yang didukung

Model	Dimensi	Penyedia
`gemini-embedding-001`	3072	Google
`text-embedding-3-small`	1536	OpenAI
`text-embedding-3-large`	3072	OpenAI

Lihat Direktori Model untuk ketersediaan dan harga terkini.

Permintaan

Header	Nilai
`Authorization`	`Bearer $FLATKEY_API_KEY`
`Content-Type`	`application/json`

Parameter body

string

wajib

ID model embedding. Contoh: "gemini-embedding-001", "text-embedding-3-small".

string | array

wajib

Teks yang akan di-embed. Dapat berupa string tunggal atau array string untuk embedding batch.

string

"float" (default) mengembalikan array float. "base64" mengembalikan string yang dikodekan base64.

integer

Jumlah dimensi untuk output embedding. Tidak didukung oleh semua model.

Contoh permintaan

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FLATKEY_API_KEY"],
    base_url="https://router.flatkey.ai/v1",
)

# Single text
response = client.embeddings.create(
    model="gemini-embedding-001",
    input="The quick brown fox jumps over the lazy dog",
)

embedding = response.data[0].embedding
print(f"Embedding dimensions: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FLATKEY_API_KEY"],
    base_url="https://router.flatkey.ai/v1",
)

# Batch embedding
texts = [
    "What is machine learning?",
    "How does neural network training work?",
    "Explain gradient descent",
]

response = client.embeddings.create(
    model="gemini-embedding-001",
    input=texts,
)

for i, item in enumerate(response.data):
    print(f"{texts[i]}: {len(item.embedding)} dimensions")

curl https://router.flatkey.ai/v1/embeddings \
  -H "Authorization: Bearer $FLATKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-embedding-001",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Respons

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023064255, -0.009327292, ...]
    }
  ],
  "model": "gemini-embedding-001",
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 9
  }
}

Kolom respons

array

Array objek embedding, satu per string input.

Tampilkan objek embedding

integer

Posisi dalam array input.

array

Array float dari vektor embedding.

integer

Jumlah token yang diproses.

Contoh kemiripan kosinus

python

import os
import numpy as np
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FLATKEY_API_KEY"],
    base_url="https://router.flatkey.ai/v1",
)

def embed(text):
    return client.embeddings.create(
        model="gemini-embedding-001",
        input=text,
    ).data[0].embedding

def cosine_similarity(a, b):
    a, b = np.array(a), np.array(b)
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

q = embed("capital city of France")
doc1 = embed("Paris is the capital and most populous city of France.")
doc2 = embed("The Eiffel Tower is a famous landmark.")

print(cosine_similarity(q, doc1))  # higher — more relevant
print(cosine_similarity(q, doc2))  # lower

​Endpoint

​Model embedding yang didukung

​Permintaan

​Header

​Parameter body

​Contoh permintaan

​Respons

​Kolom respons

​Contoh kemiripan kosinus

Endpoint

Model embedding yang didukung

Permintaan

Header

Parameter body

Contoh permintaan

Respons

Kolom respons

Contoh kemiripan kosinus