curl -X POST "https://t.ato2.nodesms.com/v1/embeddings" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "text-embedding-ada-002",
"input": "The food was delicious and the waiter..."
}'
from openai import OpenAI
client = OpenAI(
api_key="sk-xxxxxx",
base_url="https://t.ato2.nodesms.com/v1"
)
response = client.embeddings.create(
model="text-embedding-ada-002",
input="The food was delicious and the waiter..."
)
print(response.data[0].embedding)
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
0.0023064255,
-0.009327292
]
}
],
"model": "text-embedding-ada-002",
"usage": {
"prompt_tokens": 8,
"total_tokens": 8
}
}
向量嵌入
将文本转换为向量嵌入。支持单条文本或批量文本输入,可指定输出维度和编码格式。
POST
/
v1
/
embeddings
curl -X POST "https://t.ato2.nodesms.com/v1/embeddings" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "text-embedding-ada-002",
"input": "The food was delicious and the waiter..."
}'
from openai import OpenAI
client = OpenAI(
api_key="sk-xxxxxx",
base_url="https://t.ato2.nodesms.com/v1"
)
response = client.embeddings.create(
model="text-embedding-ada-002",
input="The food was delicious and the waiter..."
)
print(response.data[0].embedding)
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
0.0023064255,
-0.009327292
]
}
],
"model": "text-embedding-ada-002",
"usage": {
"prompt_tokens": 8,
"total_tokens": 8
}
}
请求头
string
必填
使用 Bearer Token 认证。格式:
Authorization: Bearer sk-xxxxxx请求体
格式:application/json
string
必填
模型 ID
string | string[]
必填
要嵌入的文本
string
默认值:"float"
编码格式,可选值:
float、base64integer
输出向量维度
响应
200 成功创建嵌入
格式:application/json
string
固定为
liststring
使用的模型 ID
curl -X POST "https://t.ato2.nodesms.com/v1/embeddings" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "text-embedding-ada-002",
"input": "The food was delicious and the waiter..."
}'
from openai import OpenAI
client = OpenAI(
api_key="sk-xxxxxx",
base_url="https://t.ato2.nodesms.com/v1"
)
response = client.embeddings.create(
model="text-embedding-ada-002",
input="The food was delicious and the waiter..."
)
print(response.data[0].embedding)
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
0.0023064255,
-0.009327292
]
}
],
"model": "text-embedding-ada-002",
"usage": {
"prompt_tokens": 8,
"total_tokens": 8
}
}
最后修改于 2026年10月28日
此页面对您有帮助吗?