InferenceReference

Embeddings

A method that turns text into vectors for semantic search and document comparison.

POSThttps://api.yenisei.ru/v1/embeddings

The Embeddings method turns text into a vector: a set of numbers that lets you compare texts by meaning. Vectors are what you need when you build search over your own documents or compare texts with each other. A single request can take either one text or a list of texts.

Parameters

modelstringrequired
Name of an embedding model from the catalog, for example bge-m3.
inputstring | arrayrequired
The text or list of texts to get vectors for.

Embedding models

Model	Vector length
`bge-m3`	1024
`qwen3-embedding-4b`	2560
`qwen3-embedding-8b`	4096

Vectors from different models are not comparable with each other. If you switch models, recompute all the vectors you have already stored.

curl https://api.yenisei.ru/v1/embeddings \
  -H "Authorization: Bearer $YENISEI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-m3",
    "input": ["first text", "second text"]
  }'

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.yenisei.ru/v1",
    api_key=os.environ["YENISEI_KEY"],
)

resp = client.embeddings.create(
    model="bge-m3",
    input=["first text", "second text"],
)
print(len(resp.data[0].embedding))

Errors

The method returns the same codes as the other API methods. They are described on the Error codes page.

Back

Chat Completions

Models