Create an embedding

Given a cue, the model will return one or more predicted completions, and may also return probabilities of alternative labels for each location.

Related guidelines:Embedding

Create complete for provided hints and parameters

POST /v1/completions

Give a typical example

{
  "model": "text-embedding-ada-002",
  "input": "The food was delicious and the waiter..."
}

JavaScript

var myHeaders = new Headers();
myHeaders.append("Authorization", "Bearer ");
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
   "model": "text-embedding-ada-002",
   "input": "The food was delicious and the waiter..."
});

var requestOptions = {
   method: 'POST',
   headers: myHeaders,
   body: raw,
   redirect: 'follow'
};

fetch("{{BASE_URL}}/v1/embeddings", requestOptions)
   .then(response => response.text())
   .then(result => console.log(result))
   .catch(error => console.log('error', error));

Python

import http.client
import json

conn = http.client.HTTPSConnection("{{BASE_URL}}")
payload = json.dumps({
   "model": "text-embedding-ada-002",
   "input": "The food was delicious and the waiter..."
})
headers = {
   'Authorization': 'Bearer ',
   'Content-Type': 'application/json'
}
conn.request("POST", "/v1/embeddings", payload, headers)
res = conn.getresponse()
data = res.read()
print(data.decode("utf-8"))

Ruby

require "uri"
require "json"
require "net/http"

url = URI("{{BASE_URL}}/v1/embeddings")

http = Net::HTTP.new(url.host, url.port);
request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer "
request["Content-Type"] = "application/json"
request.body = JSON.dump({
   "model": "text-embedding-ada-002",
   "input": "The food was delicious and the waiter..."
})

response = http.request(request)
puts response.read_body

Give a typical example OK

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.0023064255,
        -0.009327292,
        .... (1536 floats total for ada-002)
        -0.0028842222
      ],
      "index": 0
    }
  ],
  "model": "text-embedding-ada-002",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}