GET

/v1/embeddings

Get embedding vector

Retrieve the embedding vector for a single article or story. Requires Pro tier or higher. Articles use OpenAI text-embedding-3-small (1536 dimensions). Stories return their cluster centroid vector.

Parameters

Name	Type	Description
`type` required query	`"article" \| "story"`	Type of embedding to retrieve e.g. `article`
`id` required query	`string`	Article url_hash or story numeric ID e.g. `a1b2c3d4e5`
`format` query	`"json" \| "base64"`	Output format — `json` returns float array, `base64` returns little-endian float32 binary Default: `json`

type required "article" | "story"

query

Type of embedding to retrieve

e.g. article

id required string

query

Article url_hash or story numeric ID

e.g. a1b2c3d4e5

format "json" | "base64"

query

Output format — `json` returns float array, `base64` returns little-endian float32 binary

Default: json

Request Examples

bash

curl "https://api.newsrank.ai/v1/embeddings?type=article&id=a1b2c3d4e5" \
  -H "Authorization: Bearer nrf_your_api_key"

Response

json

{
  "ok": true,
  "type": "article",
  "id": "a1b2c3d4e5",
  "model": "text-embedding-3-small",
  "dimensions": 1536,
  "embedding": []
}

Try it

Server

Using sandbox demo key (5 req/min) — no signup required

Authentication

Demo key (sandbox)

Endpoint

GET /v1/embeddings

type * "article" | "story"

id * string

format "json" | "base64" Default: json