Skip to main content
POST
/
api
/
r2r
/
v3
/
retrieval
/
embedding
Reverse Proxy Auth
curl --request POST \
  --url https://api.intelligence.io.solutions/api/r2r/v3/retrieval/embedding \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "text-embedding-3-large",
  "input": "hello world"
}
'
{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}
The Embedding endpoint generates vector embeddings for the provided text using a specified model. Embeddings are dense numerical representations of text that capture semantic meaning, enabling downstream applications such as semantic search, clustering, classification, and RAG (Retrieval-Augmented Generation) operations. This endpoint provides a simple and efficient way to convert text into machine-readable vector form for use within R2R’s retrieval and analysis systems.

​
Use Cases

Embeddings generated via this endpoint can be used for:
  • Semantic search — Compare embedding vectors to find related content.
  • Clustering and classification — Group similar documents or classify them by meaning.
  • Knowledge graph enhancement — Connect semantically related entities.
  • RAG workflows — Retrieve relevant content before passing context to language models.

Authorizations

​
Authorization
string
header
required

The access token received from the authorization server in the OAuth 2.0 flow.

Headers

​
token
string

JWT token

​
Authorization
string

io.net provided API Key

​
x-api-key
string

API key set by an SDK client

Body

application/json

Raw JSON body for the embedding request. Example inputs shown below.

The body is of type object.

Response

Successful Response