curl --request POST \
--url https://api.mixroute.ai/v1/embeddings \
--header 'Authorization: Bearer sk-xxxxxxxxxx' \
--header 'Content-Type: application/json' \
--data '{
"model": "text-embedding-3-small",
"input": "Hello, world"
}'
from openai import OpenAI
client = OpenAI(
api_key="sk-xxxxxxxxxx",
base_url="https://api.mixroute.ai/v1"
)
response = client.embeddings.create(
model="text-embedding-3-small",
input="Hello, world"
)
print(response.data[0].embedding)
const OpenAI = require('openai');
const client = new OpenAI({
apiKey: 'sk-xxxxxxxxxx',
baseURL: 'https://api.mixroute.ai/v1'
});
const response = await client.embeddings.create({
model: 'text-embedding-3-small',
input: 'Hello, world'
});
console.log(response.data[0].embedding);
<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/embeddings', [
'headers' => [
'Authorization' => 'Bearer sk-xxxxxxxxxx',
'Content-Type' => 'application/json',
],
'json' => [
'model' => 'text-embedding-3-small',
'input' => 'Hello, world'
]
]);
echo $response->getBody();
package main
import (
"context"
"fmt"
openai "github.com/sashabaranov/go-openai"
)
func main() {
config := openai.DefaultConfig("sk-xxxxxxxxxx")
config.BaseURL = "https://api.mixroute.ai/v1"
client := openai.NewClientWithConfig(config)
resp, _ := client.CreateEmbeddings(
context.Background(),
openai.EmbeddingRequest{
Model: "text-embedding-3-small",
Input: []string{"Hello, world"},
},
)
fmt.Println(resp.Data[0].Embedding)
}
import java.net.http.*;
import java.net.URI;
HttpClient client = HttpClient.newHttpClient();
String json = """
{
"model": "text-embedding-3-small",
"input": "Hello, world"
}
""";
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://api.mixroute.ai/v1/embeddings"))
.header("Authorization", "Bearer sk-xxxxxxxxxx")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(json))
.build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
require 'net/http'
require 'json'
uri = URI('https://api.mixroute.ai/v1/embeddings')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true
request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
model: 'text-embedding-3-small',
input: 'Hello, world'
}.to_json
response = http.request(request)
puts response.body
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.0023064255, -0.009327292, 0.015797347, ...]
}
],
"model": "text-embedding-3-small",
"usage": {
"prompt_tokens": 5,
"total_tokens": 5
}
}
埋め込みシリーズ
テキスト埋め込み
テキストをベクトル埋め込みに変換
POST
/
v1
/
embeddings
curl --request POST \
--url https://api.mixroute.ai/v1/embeddings \
--header 'Authorization: Bearer sk-xxxxxxxxxx' \
--header 'Content-Type: application/json' \
--data '{
"model": "text-embedding-3-small",
"input": "Hello, world"
}'
from openai import OpenAI
client = OpenAI(
api_key="sk-xxxxxxxxxx",
base_url="https://api.mixroute.ai/v1"
)
response = client.embeddings.create(
model="text-embedding-3-small",
input="Hello, world"
)
print(response.data[0].embedding)
const OpenAI = require('openai');
const client = new OpenAI({
apiKey: 'sk-xxxxxxxxxx',
baseURL: 'https://api.mixroute.ai/v1'
});
const response = await client.embeddings.create({
model: 'text-embedding-3-small',
input: 'Hello, world'
});
console.log(response.data[0].embedding);
<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/embeddings', [
'headers' => [
'Authorization' => 'Bearer sk-xxxxxxxxxx',
'Content-Type' => 'application/json',
],
'json' => [
'model' => 'text-embedding-3-small',
'input' => 'Hello, world'
]
]);
echo $response->getBody();
package main
import (
"context"
"fmt"
openai "github.com/sashabaranov/go-openai"
)
func main() {
config := openai.DefaultConfig("sk-xxxxxxxxxx")
config.BaseURL = "https://api.mixroute.ai/v1"
client := openai.NewClientWithConfig(config)
resp, _ := client.CreateEmbeddings(
context.Background(),
openai.EmbeddingRequest{
Model: "text-embedding-3-small",
Input: []string{"Hello, world"},
},
)
fmt.Println(resp.Data[0].Embedding)
}
import java.net.http.*;
import java.net.URI;
HttpClient client = HttpClient.newHttpClient();
String json = """
{
"model": "text-embedding-3-small",
"input": "Hello, world"
}
""";
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://api.mixroute.ai/v1/embeddings"))
.header("Authorization", "Bearer sk-xxxxxxxxxx")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(json))
.build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
require 'net/http'
require 'json'
uri = URI('https://api.mixroute.ai/v1/embeddings')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true
request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
model: 'text-embedding-3-small',
input: 'Hello, world'
}.to_json
response = http.request(request)
puts response.body
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.0023064255, -0.009327292, 0.015797347, ...]
}
],
"model": "text-embedding-3-small",
"usage": {
"prompt_tokens": 5,
"total_tokens": 5
}
}
テキスト埋め込み
Embeddings APIはテキストを高次元のベクトル表現に変換し、セマンティック検索、クラスタリング、RAGアプリケーションに役立ちます。エンドポイント
POST https://api.mixroute.ai/v1/embeddings
認証
Authorization: Bearer sk-xxxxxxxxxx
リクエストボディ
| パラメーター | 型 | 必須 | 説明 |
|---|---|---|---|
model | string | はい | 埋め込みモデルID |
input | string/array | はい | 埋め込み対象のテキスト（単数または複数） |
encoding_format | string | いいえ | 出力形式: floatまたはbase64 |
input_type | string | Cohere only | search_document、search_query、classification、またはclustering。 |
dimensions | integer | いいえ | OpenAIのtext-embedding-3など、このフィールドを公開するモデル/ルートの出力次元数です。ネイティブのCohereのoutput_dimensionが同じ対応関係を持つとは限りません。 |
リクエスト例
単一テキスト
curl -X POST https://api.mixroute.ai/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-d '{
"model": "text-embedding-3-small",
"input": "The quick brown fox jumps over the lazy dog."
}'
複数テキストの一括処理
curl -X POST https://api.mixroute.ai/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-d '{
"model": "text-embedding-3-small",
"input": [
"First document text",
"Second document text",
"Third document text"
]
}'
カスタム次元数
効率を高めるために埋め込みの次元数を削減します。curl -X POST https://api.mixroute.ai/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-xxxxxxxxxx" \
-d '{
"model": "text-embedding-3-large",
"input": "Sample text for embedding",
"dimensions": 512
}'
対応モデル
| モデル | 次元数 | 説明 |
|---|---|---|
text-embedding-3-small | 1536 | 高速で費用対効果に優れる |
text-embedding-3-large | 3072 | より高い精度 |
text-embedding-ada-002 | 1536 | 旧モデル |
embed-v4.0 | 1536 | 長文コンテキストのテキストに対応する、多言語検索向けのCohereの埋め込みモデル。 |
embed-english-v3.0 | 1024 | 英語の検索に最適化されたCohereのテキスト埋め込みモデル。 |
embed-multilingual-v3.0 | 1024 | 言語横断検索向けのCohereテキスト埋め込みモデル。 |
Cohereの埋め込み
保存するドキュメントにはinput_type=search_document、クエリにはsearch_queryを使用してください。両方でモデルと次元数を同一にしてください。テキスト互換エンドポイントはdata[].embeddingにベクトルを返します。ネイティブの画像/PDF埋め込み入力は、このテキスト入力スキーマと相互に置き換えられるものではありません。
curl --request POST "https://api.mixroute.ai/v1/embeddings" \
--header "Authorization: Bearer $MIXROUTE_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "embed-v4.0",
"input": [
"An API reference for developers."
],
"input_type": "search_document",
"encoding_format": "float"
}'
使用例
セマンティック検索
import numpy as np
def cosine_similarity(a, b):
return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
# Compare query embedding with document embeddings
similarities = [cosine_similarity(query_embedding, doc) for doc in doc_embeddings]
ドキュメントのクラスタリング
from sklearn.cluster import KMeans
# Cluster documents by embedding similarity
kmeans = KMeans(n_clusters=5)
clusters = kmeans.fit_predict(embeddings)
ベストプラクティス
- バッチリクエスト：効率化のため、1つのリクエストで複数のテキストを送信します
- ベクトルの正規化：一貫した類似度スコアを得るために、埋め込みを正規化します
- 次元数の選択：ストレージ容量や速度を重視する場合は、少ない次元数を使用
- 長いテキストの分割: 埋め込みを生成する前に、長いドキュメントを意味のある単位に分割してください
curl --request POST \
--url https://api.mixroute.ai/v1/embeddings \
--header 'Authorization: Bearer sk-xxxxxxxxxx' \
--header 'Content-Type: application/json' \
--data '{
"model": "text-embedding-3-small",
"input": "Hello, world"
}'
from openai import OpenAI
client = OpenAI(
api_key="sk-xxxxxxxxxx",
base_url="https://api.mixroute.ai/v1"
)
response = client.embeddings.create(
model="text-embedding-3-small",
input="Hello, world"
)
print(response.data[0].embedding)
const OpenAI = require('openai');
const client = new OpenAI({
apiKey: 'sk-xxxxxxxxxx',
baseURL: 'https://api.mixroute.ai/v1'
});
const response = await client.embeddings.create({
model: 'text-embedding-3-small',
input: 'Hello, world'
});
console.log(response.data[0].embedding);
<?php
$client = new GuzzleHttp\Client();
$response = $client->post('https://api.mixroute.ai/v1/embeddings', [
'headers' => [
'Authorization' => 'Bearer sk-xxxxxxxxxx',
'Content-Type' => 'application/json',
],
'json' => [
'model' => 'text-embedding-3-small',
'input' => 'Hello, world'
]
]);
echo $response->getBody();
package main
import (
"context"
"fmt"
openai "github.com/sashabaranov/go-openai"
)
func main() {
config := openai.DefaultConfig("sk-xxxxxxxxxx")
config.BaseURL = "https://api.mixroute.ai/v1"
client := openai.NewClientWithConfig(config)
resp, _ := client.CreateEmbeddings(
context.Background(),
openai.EmbeddingRequest{
Model: "text-embedding-3-small",
Input: []string{"Hello, world"},
},
)
fmt.Println(resp.Data[0].Embedding)
}
import java.net.http.*;
import java.net.URI;
HttpClient client = HttpClient.newHttpClient();
String json = """
{
"model": "text-embedding-3-small",
"input": "Hello, world"
}
""";
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://api.mixroute.ai/v1/embeddings"))
.header("Authorization", "Bearer sk-xxxxxxxxxx")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(json))
.build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
require 'net/http'
require 'json'
uri = URI('https://api.mixroute.ai/v1/embeddings')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true
request = Net::HTTP::Post.new(uri)
request['Authorization'] = 'Bearer sk-xxxxxxxxxx'
request['Content-Type'] = 'application/json'
request.body = {
model: 'text-embedding-3-small',
input: 'Hello, world'
}.to_json
response = http.request(request)
puts response.body
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.0023064255, -0.009327292, 0.015797347, ...]
}
],
"model": "text-embedding-3-small",
"usage": {
"prompt_tokens": 5,
"total_tokens": 5
}
}