Embeddings

Embeddings convert text into vectors of floating‑point numbers. Distances between vectors correlate with semantic similarity.

---

Create embeddings

POST https://api.aifoundryhub.com/v1/embeddings

Creates one or more embeddings for the given input.

---

Example request

curl

curl -X POST "https://api.aifoundryhub.com/v1/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AI_FOUNDRY_HUB_API_KEY" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["Hello world"],
    "dimensions": 1536
  }'

node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AI_FOUNDRY_HUB_API_KEY,
  baseURL: "https://api.aifoundryhub.com/v1",
});

const emb = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: ["Hello world"],
  dimensions: 1536,
});

console.log(emb.data[0].embedding.length);

go

package main

import (
  "context"
  "fmt"
  "os"

  openai "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey(os.Getenv("AI_FOUNDRY_HUB_API_KEY")),
    option.WithBaseURL("https://api.aifoundryhub.com/v1"),
  )

  params := openai.EmbeddingNewParams{
    Model:      "text-embedding-3-small",
    Input:      openai.EmbeddingNewParamsInputUnion{
      OfString: openai.String("The quick brown fox jumped over the lazy dog"),
    },
    Dimensions: openai.Int(1536),
  }

  ctx := context.Background()
  resp, err := client.Embeddings.New(ctx, params)
  if err != nil {
    panic(err)
  }

  fmt.Println(len(resp.Data[0].Embedding))
}

python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("AI_FOUNDRY_HUB_API_KEY"),
    base_url="https://api.aifoundryhub.com/v1",
)

resp = client.embeddings.create(
    model="text-embedding-3-small",
    input=["Hello world"],
    dimensions=1536,
)

print(len(resp.data[0].embedding))

Returns

An embedding response object containing one vector per input.

Example response

{
  "id": "embd_abc123",
  "object": "embedding_response",
  "created": 1714569952,
  "model": "text-embedding-3-small",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0456, 0.0089]
    }
  ],
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  }
}

---

Objects

The embeddings response object

The embedding object