Text & embeddings

Embeddings

Convert text into vector embeddings for search, clustering and RAG.

POST /v1/embeddings

Compatible with the OpenAI Embeddings API. Returns a vector for each input text; use the vectors for semantic search, retrieval-augmented generation (RAG), clustering or classification.

Authentication

Authorization: Bearer sk-xxxx

Request body

Parameter	Type	Required	Description
`model`	string	Yes	Embedding model ID, e.g. `text-embedding-3-small`.
`input`	string \| array	Yes	Text to embed, or an array of texts for a batch. Each item must fit within the model's context length.
`encoding_format`	string	No	`float` (default) or `base64`.
`dimensions`	integer	No	Number of output dimensions. Supported by `text-embedding-3-*` and some other models.
`user`	string	No	Stable end-user identifier.

Request example

cURL

curl https://rutoken.ai/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["The food was delicious.", "The service was slow."]
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="https://rutoken.ai/v1", api_key="sk-xxxx")
resp = client.embeddings.create(
    model="text-embedding-3-small",
    input=["The food was delicious.", "The service was slow."],
)
for item in resp.data:
    print(item.index, len(item.embedding))

Node.js

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://rutoken.ai/v1", apiKey: "sk-xxxx" });
const resp = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: ["The food was delicious.", "The service was slow."],
});
for (const item of resp.data) console.log(item.index, item.embedding.length);

Response

json

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023064255, -0.009327292, 0.015797347]
    },
    {
      "object": "embedding",
      "index": 1,
      "embedding": [-0.012174723, 0.004532318, -0.020815546]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}

The vectors are shortened here; text-embedding-3-small returns 1536 dimensions by default.

Field	Type	Description
`data[].index`	integer	Position of the corresponding input.
`data[].embedding`	array \| string	The vector, or a base64 string when `encoding_format` is `base64`.
`usage.prompt_tokens`	integer	Input tokens used for billing.

Notes

Compare vectors with cosine similarity. OpenAI embeddings are normalized to length 1, so a dot product gives the same ranking.
Gemini embedding models can also be called through this endpoint with the same request format.
To re-order search results by relevance, use Rerank.

← Previous

Completions (legacy)

Rerank