Embeddings — DataMind AI Docs

Endpoint#

Endpoint

POST https://xpluse.plus/v1/embeddings

Convert text into vector representations for semantic search, clustering, classification, and similar use cases.

Request parameters#

Parameter	Type	Required	Description
`Models`	string	✅	Embedding Model，such as `openai/text-embedding-3-small`
`input`	string \| string[]	✅	Text to convert, either a single item or a batch
`encoding_format`	string	—	Output format:`float`(default) or `base64`
`dimensions`	number	—	Output vector dimensions (supported by some models)

Request example#

cURL

curl https://xpluse.plus/v1/embeddings \
  -H "Authorization: Bearer $DATAMIND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "input": "DataMind AI is an LLM Gateway"
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="https://xpluse.plus/v1", api_key="<your DATAMIND_API_KEY>")

response = client.embeddings.create(
    model="openai/text-embedding-3-small",
    input="DataMind AI is an LLM Gateway"
)

embedding = response.data[0].embedding
print(f"Embedding dimensions: {len(embedding)}")

TypeScript

const response = await client.embeddings.create({
  model: 'openai/text-embedding-3-small',
  input: 'DataMind AI is an LLM Gateway'
})

console.log(`Embedding dimensions: ${response.data[0].embedding.length}`)

ResponseFormat#

JSON

{
  "object": "list",
  "data": [
    {"object": "embedding", "index": 0, "embedding": [0.0023, -0.0091, 0.0156]}
  ],
  "model": "openai/text-embedding-3-small",
  "usage": {"prompt_tokens": 8, "total_tokens": 8}
}

Available models#

Model	Dimensions	Description
`openai/text-embedding-3-small`	1536	Cost-effective
`openai/text-embedding-3-large`	3072	Highest accuracy
`bailian/text-embedding-v4`	1024	Optimized for Chinese; Qwen embedding model

Last updated on April 28, 2026