Create a new Gen AI Endpoint

curl --request POST \
  --url https://mycluster.domino.tech/api/gen-ai/beta/endpoints \
  --header 'Content-Type: application/json' \
  --header 'X-Domino-Api-Key: <api-key>' \
  --data '
{
  "collaborators": [
    {
      "name": "John Doe",
      "organizationId": "62313ce67a0af0281c01a6a5",
      "userId": "62313ce67a0af0281c01a6a5"
    }
  ],
  "configuration": {
    "maxNumberOfSequences": 256,
    "servedModelName": "my-model",
    "tensorParallelism": 1,
    "vllmArguments": "--max-model-length 4095 --gpu-memory-utilization 0.90"
  },
  "environment": {
    "environmentId": "62313ce67a0af0281c01a6a5",
    "revisionId": "62313ce67a0af0281c01a6a5"
  },
  "hardwareTierId": "62313ce67a0af0281c01a6a5",
  "modelSource": {},
  "name": "My Endpoint",
  "projectId": "62313ce67a0af0281c01a6a5",
  "description": "My Endpoint Description",
  "vanityUrl": "https://cloud-dogfood.domino.tech/endpoints/my-endpoint",
  "versionDescription": "My Endpoint Version Description",
  "versionLabel": 1
}
'

import requests

url = "https://mycluster.domino.tech/api/gen-ai/beta/endpoints"

payload = {
    "collaborators": [
        {
            "name": "John Doe",
            "organizationId": "62313ce67a0af0281c01a6a5",
            "userId": "62313ce67a0af0281c01a6a5"
        }
    ],
    "configuration": {
        "maxNumberOfSequences": 256,
        "servedModelName": "my-model",
        "tensorParallelism": 1,
        "vllmArguments": "--max-model-length 4095 --gpu-memory-utilization 0.90"
    },
    "environment": {
        "environmentId": "62313ce67a0af0281c01a6a5",
        "revisionId": "62313ce67a0af0281c01a6a5"
    },
    "hardwareTierId": "62313ce67a0af0281c01a6a5",
    "modelSource": {},
    "name": "My Endpoint",
    "projectId": "62313ce67a0af0281c01a6a5",
    "description": "My Endpoint Description",
    "vanityUrl": "https://cloud-dogfood.domino.tech/endpoints/my-endpoint",
    "versionDescription": "My Endpoint Version Description",
    "versionLabel": 1
}
headers = {
    "X-Domino-Api-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-Domino-Api-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    collaborators: [
      {
        name: 'John Doe',
        organizationId: '62313ce67a0af0281c01a6a5',
        userId: '62313ce67a0af0281c01a6a5'
      }
    ],
    configuration: {
      maxNumberOfSequences: 256,
      servedModelName: 'my-model',
      tensorParallelism: 1,
      vllmArguments: '--max-model-length 4095 --gpu-memory-utilization 0.90'
    },
    environment: {
      environmentId: '62313ce67a0af0281c01a6a5',
      revisionId: '62313ce67a0af0281c01a6a5'
    },
    hardwareTierId: '62313ce67a0af0281c01a6a5',
    modelSource: {},
    name: 'My Endpoint',
    projectId: '62313ce67a0af0281c01a6a5',
    description: 'My Endpoint Description',
    vanityUrl: 'https://cloud-dogfood.domino.tech/endpoints/my-endpoint',
    versionDescription: 'My Endpoint Version Description',
    versionLabel: 1
  })
};

fetch('https://mycluster.domino.tech/api/gen-ai/beta/endpoints', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://mycluster.domino.tech/api/gen-ai/beta/endpoints",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'collaborators' => [
        [
                'name' => 'John Doe',
                'organizationId' => '62313ce67a0af0281c01a6a5',
                'userId' => '62313ce67a0af0281c01a6a5'
        ]
    ],
    'configuration' => [
        'maxNumberOfSequences' => 256,
        'servedModelName' => 'my-model',
        'tensorParallelism' => 1,
        'vllmArguments' => '--max-model-length 4095 --gpu-memory-utilization 0.90'
    ],
    'environment' => [
        'environmentId' => '62313ce67a0af0281c01a6a5',
        'revisionId' => '62313ce67a0af0281c01a6a5'
    ],
    'hardwareTierId' => '62313ce67a0af0281c01a6a5',
    'modelSource' => [
        
    ],
    'name' => 'My Endpoint',
    'projectId' => '62313ce67a0af0281c01a6a5',
    'description' => 'My Endpoint Description',
    'vanityUrl' => 'https://cloud-dogfood.domino.tech/endpoints/my-endpoint',
    'versionDescription' => 'My Endpoint Version Description',
    'versionLabel' => 1
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-Domino-Api-Key: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://mycluster.domino.tech/api/gen-ai/beta/endpoints"

	payload := strings.NewReader("{\n  \"collaborators\": [\n    {\n      \"name\": \"John Doe\",\n      \"organizationId\": \"62313ce67a0af0281c01a6a5\",\n      \"userId\": \"62313ce67a0af0281c01a6a5\"\n    }\n  ],\n  \"configuration\": {\n    \"maxNumberOfSequences\": 256,\n    \"servedModelName\": \"my-model\",\n    \"tensorParallelism\": 1,\n    \"vllmArguments\": \"--max-model-length 4095 --gpu-memory-utilization 0.90\"\n  },\n  \"environment\": {\n    \"environmentId\": \"62313ce67a0af0281c01a6a5\",\n    \"revisionId\": \"62313ce67a0af0281c01a6a5\"\n  },\n  \"hardwareTierId\": \"62313ce67a0af0281c01a6a5\",\n  \"modelSource\": {},\n  \"name\": \"My Endpoint\",\n  \"projectId\": \"62313ce67a0af0281c01a6a5\",\n  \"description\": \"My Endpoint Description\",\n  \"vanityUrl\": \"https://cloud-dogfood.domino.tech/endpoints/my-endpoint\",\n  \"versionDescription\": \"My Endpoint Version Description\",\n  \"versionLabel\": 1\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-Domino-Api-Key", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://mycluster.domino.tech/api/gen-ai/beta/endpoints")
  .header("X-Domino-Api-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"collaborators\": [\n    {\n      \"name\": \"John Doe\",\n      \"organizationId\": \"62313ce67a0af0281c01a6a5\",\n      \"userId\": \"62313ce67a0af0281c01a6a5\"\n    }\n  ],\n  \"configuration\": {\n    \"maxNumberOfSequences\": 256,\n    \"servedModelName\": \"my-model\",\n    \"tensorParallelism\": 1,\n    \"vllmArguments\": \"--max-model-length 4095 --gpu-memory-utilization 0.90\"\n  },\n  \"environment\": {\n    \"environmentId\": \"62313ce67a0af0281c01a6a5\",\n    \"revisionId\": \"62313ce67a0af0281c01a6a5\"\n  },\n  \"hardwareTierId\": \"62313ce67a0af0281c01a6a5\",\n  \"modelSource\": {},\n  \"name\": \"My Endpoint\",\n  \"projectId\": \"62313ce67a0af0281c01a6a5\",\n  \"description\": \"My Endpoint Description\",\n  \"vanityUrl\": \"https://cloud-dogfood.domino.tech/endpoints/my-endpoint\",\n  \"versionDescription\": \"My Endpoint Version Description\",\n  \"versionLabel\": 1\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://mycluster.domino.tech/api/gen-ai/beta/endpoints")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-Domino-Api-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"collaborators\": [\n    {\n      \"name\": \"John Doe\",\n      \"organizationId\": \"62313ce67a0af0281c01a6a5\",\n      \"userId\": \"62313ce67a0af0281c01a6a5\"\n    }\n  ],\n  \"configuration\": {\n    \"maxNumberOfSequences\": 256,\n    \"servedModelName\": \"my-model\",\n    \"tensorParallelism\": 1,\n    \"vllmArguments\": \"--max-model-length 4095 --gpu-memory-utilization 0.90\"\n  },\n  \"environment\": {\n    \"environmentId\": \"62313ce67a0af0281c01a6a5\",\n    \"revisionId\": \"62313ce67a0af0281c01a6a5\"\n  },\n  \"hardwareTierId\": \"62313ce67a0af0281c01a6a5\",\n  \"modelSource\": {},\n  \"name\": \"My Endpoint\",\n  \"projectId\": \"62313ce67a0af0281c01a6a5\",\n  \"description\": \"My Endpoint Description\",\n  \"vanityUrl\": \"https://cloud-dogfood.domino.tech/endpoints/my-endpoint\",\n  \"versionDescription\": \"My Endpoint Version Description\",\n  \"versionLabel\": 1\n}"

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

{
  "createdAt": "2022-03-12T02:13:44.467Z",
  "creator": {
    "id": "integration test",
    "name": "Full User Name"
  },
  "generalAccess": "Restricted",
  "id": "62313ce67a0af0281c01a6a5",
  "name": "My Endpoint",
  "project": {
    "id": "62313ce67a0af0281c01a6a5",
    "name": "My Project",
    "owner": {
      "id": "integration test",
      "name": "Full User Name"
    }
  },
  "updatedAt": "2022-03-12T02:13:44.467Z",
  "url": "https://cloud-dogfood.domino.tech/endpoint/my-endpoint",
  "vanityUrl": "https://cloud-dogfood.domino.tech/endpoints/my-endpoint",
  "currentVersion": {
    "configuration": {
      "maxNumberOfSequences": 256,
      "servedModelName": "my-model",
      "tensorParallelism": 1,
      "vllmArguments": "--max-model-length 4095 --gpu-memory-utilization 0.90"
    },
    "createdAt": "2022-03-12T02:13:44.467Z",
    "creator": {
      "id": "integration test",
      "name": "Full User Name"
    },
    "endpointId": "62313ce67a0af0281c01a6a5",
    "environment": {
      "id": "62313ce67a0af0281c01a6a5",
      "name": "My Environment",
      "revisionId": "62313ce67a0af0281c01a6a5"
    },
    "hardwareTier": {
      "dataPlaneId": "62313ce67a0af0281c01a6a5",
      "dataPlaneName": "My Data Plane",
      "id": "62313ce67a0af0281c01a6a5"
    },
    "modelSource": {
      "huggingFace": {
        "commit": "62313ce67a0af0281c01a6a5",
        "modelType": "LLM",
        "path": "my-model",
        "apiToken": "62313ce67a0af0281c01a6a5"
      },
      "registeredModel": {
        "modelName": "RandomForestRegression",
        "modelVersion": 1
      }
    },
    "modelType": "LLM",
    "number": 1,
    "status": "Building",
    "description": "My Endpoint Version Description",
    "executionId": "62313ce67a0af0281c01a6a5",
    "label": 1
  },
  "description": "My Endpoint Description",
  "instructions": "Use the endpoint to generate text",
  "requestCount": 100
}

{
  "error": "<string>"
}

{
  "code": "UNAUTHORIZED",
  "message": "Authentication is required to access this resource."
}

{
  "code": "FORBIDDEN",
  "message": "You do not have permission to perform this action."
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}