Embeddings API

Example

Request

# pip install openai

from openai import OpenAI # openai==1.52.2

client = OpenAI(
    api_key="UPSTAGE_API_KEY_INJECT",
    base_url="https://api.upstage.ai/v1"
)

response = client.embeddings.create(
    input="Solar embeddings are awesome",
    model="solar-embedding-2-query"
)

print(response.data[0].embedding)

Response

Success - HTTP Status 200 OK - Single input response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0.01850688,
        -0.0066606696,
        ...
        0.009938696,
        0.006452979
      ]
    }
  ],
  "model": "solar-embedding-2-query",
  "usage": {
    "prompt_tokens": 21,
    "total_tokens": 21
  }
}

Document classification

Classify documents into user-defined types without templates or retraining — request parameters, examples, and response format.

Upload file

Upload a document for a Studio agent to process. Covers the multipart/form-data request, the file object returned (id, bytes, filename, purpose, created_at), and an example request and response.

Embeddings API

Example

Request

Response

On this page

Embeddings API

Example

Request

Response

On this page

Authorization

`Authorization`
Required
Bearer <token>

Request Body

`model`
Required
string

`input`
Required
string | array<string>

Response

On this page

Response

On this page

Body

AuthorizationRequiredBearer <token>

modelRequiredstring

inputRequiredstring | array<string>

Object 1

`Authorization`
Required
Bearer <token>

`model`
Required
string

`input`
Required
string | array<string>