Extend Dataset Content

Extends the dataset content

POST /v2/datasets/extend

Extend Dataset Content

cURL

curl --request POST \
  --url https://api.galileo.ai/v2/datasets/extend \
  --header 'Content-Type: application/json' \
  --header 'Galileo-API-Key: <api-key>' \
  --data '
{
  "prompt_settings": {
    "logprobs": true,
    "top_logprobs": 5,
    "echo": false,
    "n": 1,
    "reasoning_effort": "medium",
    "verbosity": "medium",
    "deployment_name": "<string>",
    "model_alias": "gpt-5.1",
    "temperature": 123,
    "max_tokens": 4096,
    "stop_sequences": [
      "<string>"
    ],
    "top_p": 1,
    "top_k": 40,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "tools": [
      {}
    ],
    "tool_choice": "<string>",
    "response_format": {},
    "known_models": [
      {
        "name": "<string>",
        "alias": "<string>",
        "integration": "openai",
        "user_role": "<string>",
        "assistant_role": "<string>",
        "system_supported": false,
        "input_modalities": [],
        "alternative_names": [
          "<string>"
        ],
        "input_token_limit": 123,
        "output_token_limit": 123,
        "token_limit": 123,
        "cost_by": "tokens",
        "is_chat": false,
        "provides_log_probs": false,
        "formatting_tokens": 0,
        "response_prefix_tokens": 0,
        "api_version": "<string>",
        "legacy_mistral_prompt_format": false,
        "requires_max_tokens": false,
        "max_top_p": 123,
        "params_map": {
          "model": "<string>",
          "temperature": "<string>",
          "max_tokens": "<string>",
          "stop_sequences": "<string>",
          "top_p": "<string>",
          "top_k": "<string>",
          "frequency_penalty": "<string>",
          "presence_penalty": "<string>",
          "echo": "<string>",
          "logprobs": "<string>",
          "top_logprobs": "<string>",
          "n": "<string>",
          "api_version": "<string>",
          "tools": "<string>",
          "tool_choice": "<string>",
          "response_format": "<string>",
          "reasoning_effort": "<string>",
          "verbosity": "<string>",
          "deployment_name": "<string>"
        },
        "output_map": {
          "response": "<string>",
          "token_count": "<string>",
          "input_token_count": "<string>",
          "output_token_count": "<string>",
          "completion_reason": "<string>"
        },
        "input_map": {
          "prompt": "<string>",
          "prefix": "",
          "suffix": ""
        }
      }
    ]
  },
  "prompt": "<string>",
  "instructions": "<string>",
  "examples": [
    "<string>"
  ],
  "source_dataset": {
    "dataset_id": "<string>",
    "dataset_version_index": 123,
    "row_ids": [
      "<string>"
    ]
  },
  "data_types": [],
  "count": 10,
  "project_id": "<string>"
}
'

import requests

url = "https://api.galileo.ai/v2/datasets/extend"

payload = {
    "prompt_settings": {
        "logprobs": True,
        "top_logprobs": 5,
        "echo": False,
        "n": 1,
        "reasoning_effort": "medium",
        "verbosity": "medium",
        "deployment_name": "<string>",
        "model_alias": "gpt-5.1",
        "temperature": 123,
        "max_tokens": 4096,
        "stop_sequences": ["<string>"],
        "top_p": 1,
        "top_k": 40,
        "frequency_penalty": 0,
        "presence_penalty": 0,
        "tools": [{}],
        "tool_choice": "<string>",
        "response_format": {},
        "known_models": [
            {
                "name": "<string>",
                "alias": "<string>",
                "integration": "openai",
                "user_role": "<string>",
                "assistant_role": "<string>",
                "system_supported": False,
                "input_modalities": [],
                "alternative_names": ["<string>"],
                "input_token_limit": 123,
                "output_token_limit": 123,
                "token_limit": 123,
                "cost_by": "tokens",
                "is_chat": False,
                "provides_log_probs": False,
                "formatting_tokens": 0,
                "response_prefix_tokens": 0,
                "api_version": "<string>",
                "legacy_mistral_prompt_format": False,
                "requires_max_tokens": False,
                "max_top_p": 123,
                "params_map": {
                    "model": "<string>",
                    "temperature": "<string>",
                    "max_tokens": "<string>",
                    "stop_sequences": "<string>",
                    "top_p": "<string>",
                    "top_k": "<string>",
                    "frequency_penalty": "<string>",
                    "presence_penalty": "<string>",
                    "echo": "<string>",
                    "logprobs": "<string>",
                    "top_logprobs": "<string>",
                    "n": "<string>",
                    "api_version": "<string>",
                    "tools": "<string>",
                    "tool_choice": "<string>",
                    "response_format": "<string>",
                    "reasoning_effort": "<string>",
                    "verbosity": "<string>",
                    "deployment_name": "<string>"
                },
                "output_map": {
                    "response": "<string>",
                    "token_count": "<string>",
                    "input_token_count": "<string>",
                    "output_token_count": "<string>",
                    "completion_reason": "<string>"
                },
                "input_map": {
                    "prompt": "<string>",
                    "prefix": "",
                    "suffix": ""
                }
            }
        ]
    },
    "prompt": "<string>",
    "instructions": "<string>",
    "examples": ["<string>"],
    "source_dataset": {
        "dataset_id": "<string>",
        "dataset_version_index": 123,
        "row_ids": ["<string>"]
    },
    "data_types": [],
    "count": 10,
    "project_id": "<string>"
}
headers = {
    "Galileo-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Galileo-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt_settings: {
      logprobs: true,
      top_logprobs: 5,
      echo: false,
      n: 1,
      reasoning_effort: 'medium',
      verbosity: 'medium',
      deployment_name: '<string>',
      model_alias: 'gpt-5.1',
      temperature: 123,
      max_tokens: 4096,
      stop_sequences: ['<string>'],
      top_p: 1,
      top_k: 40,
      frequency_penalty: 0,
      presence_penalty: 0,
      tools: [{}],
      tool_choice: '<string>',
      response_format: {},
      known_models: [
        {
          name: '<string>',
          alias: '<string>',
          integration: 'openai',
          user_role: '<string>',
          assistant_role: '<string>',
          system_supported: false,
          input_modalities: [],
          alternative_names: ['<string>'],
          input_token_limit: 123,
          output_token_limit: 123,
          token_limit: 123,
          cost_by: 'tokens',
          is_chat: false,
          provides_log_probs: false,
          formatting_tokens: 0,
          response_prefix_tokens: 0,
          api_version: '<string>',
          legacy_mistral_prompt_format: false,
          requires_max_tokens: false,
          max_top_p: 123,
          params_map: {
            model: '<string>',
            temperature: '<string>',
            max_tokens: '<string>',
            stop_sequences: '<string>',
            top_p: '<string>',
            top_k: '<string>',
            frequency_penalty: '<string>',
            presence_penalty: '<string>',
            echo: '<string>',
            logprobs: '<string>',
            top_logprobs: '<string>',
            n: '<string>',
            api_version: '<string>',
            tools: '<string>',
            tool_choice: '<string>',
            response_format: '<string>',
            reasoning_effort: '<string>',
            verbosity: '<string>',
            deployment_name: '<string>'
          },
          output_map: {
            response: '<string>',
            token_count: '<string>',
            input_token_count: '<string>',
            output_token_count: '<string>',
            completion_reason: '<string>'
          },
          input_map: {prompt: '<string>', prefix: '', suffix: ''}
        }
      ]
    },
    prompt: '<string>',
    instructions: '<string>',
    examples: ['<string>'],
    source_dataset: {dataset_id: '<string>', dataset_version_index: 123, row_ids: ['<string>']},
    data_types: [],
    count: 10,
    project_id: '<string>'
  })
};

fetch('https://api.galileo.ai/v2/datasets/extend', 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://api.galileo.ai/v2/datasets/extend",
  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([
    'prompt_settings' => [
        'logprobs' => true,
        'top_logprobs' => 5,
        'echo' => false,
        'n' => 1,
        'reasoning_effort' => 'medium',
        'verbosity' => 'medium',
        'deployment_name' => '<string>',
        'model_alias' => 'gpt-5.1',
        'temperature' => 123,
        'max_tokens' => 4096,
        'stop_sequences' => [
                '<string>'
        ],
        'top_p' => 1,
        'top_k' => 40,
        'frequency_penalty' => 0,
        'presence_penalty' => 0,
        'tools' => [
                [
                                
                ]
        ],
        'tool_choice' => '<string>',
        'response_format' => [
                
        ],
        'known_models' => [
                [
                                'name' => '<string>',
                                'alias' => '<string>',
                                'integration' => 'openai',
                                'user_role' => '<string>',
                                'assistant_role' => '<string>',
                                'system_supported' => false,
                                'input_modalities' => [
                                                                
                                ],
                                'alternative_names' => [
                                                                '<string>'
                                ],
                                'input_token_limit' => 123,
                                'output_token_limit' => 123,
                                'token_limit' => 123,
                                'cost_by' => 'tokens',
                                'is_chat' => false,
                                'provides_log_probs' => false,
                                'formatting_tokens' => 0,
                                'response_prefix_tokens' => 0,
                                'api_version' => '<string>',
                                'legacy_mistral_prompt_format' => false,
                                'requires_max_tokens' => false,
                                'max_top_p' => 123,
                                'params_map' => [
                                                                'model' => '<string>',
                                                                'temperature' => '<string>',
                                                                'max_tokens' => '<string>',
                                                                'stop_sequences' => '<string>',
                                                                'top_p' => '<string>',
                                                                'top_k' => '<string>',
                                                                'frequency_penalty' => '<string>',
                                                                'presence_penalty' => '<string>',
                                                                'echo' => '<string>',
                                                                'logprobs' => '<string>',
                                                                'top_logprobs' => '<string>',
                                                                'n' => '<string>',
                                                                'api_version' => '<string>',
                                                                'tools' => '<string>',
                                                                'tool_choice' => '<string>',
                                                                'response_format' => '<string>',
                                                                'reasoning_effort' => '<string>',
                                                                'verbosity' => '<string>',
                                                                'deployment_name' => '<string>'
                                ],
                                'output_map' => [
                                                                'response' => '<string>',
                                                                'token_count' => '<string>',
                                                                'input_token_count' => '<string>',
                                                                'output_token_count' => '<string>',
                                                                'completion_reason' => '<string>'
                                ],
                                'input_map' => [
                                                                'prompt' => '<string>',
                                                                'prefix' => '',
                                                                'suffix' => ''
                                ]
                ]
        ]
    ],
    'prompt' => '<string>',
    'instructions' => '<string>',
    'examples' => [
        '<string>'
    ],
    'source_dataset' => [
        'dataset_id' => '<string>',
        'dataset_version_index' => 123,
        'row_ids' => [
                '<string>'
        ]
    ],
    'data_types' => [
        
    ],
    'count' => 10,
    'project_id' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "Galileo-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://api.galileo.ai/v2/datasets/extend"

	payload := strings.NewReader("{\n  \"prompt_settings\": {\n    \"logprobs\": true,\n    \"top_logprobs\": 5,\n    \"echo\": false,\n    \"n\": 1,\n    \"reasoning_effort\": \"medium\",\n    \"verbosity\": \"medium\",\n    \"deployment_name\": \"<string>\",\n    \"model_alias\": \"gpt-5.1\",\n    \"temperature\": 123,\n    \"max_tokens\": 4096,\n    \"stop_sequences\": [\n      \"<string>\"\n    ],\n    \"top_p\": 1,\n    \"top_k\": 40,\n    \"frequency_penalty\": 0,\n    \"presence_penalty\": 0,\n    \"tools\": [\n      {}\n    ],\n    \"tool_choice\": \"<string>\",\n    \"response_format\": {},\n    \"known_models\": [\n      {\n        \"name\": \"<string>\",\n        \"alias\": \"<string>\",\n        \"integration\": \"openai\",\n        \"user_role\": \"<string>\",\n        \"assistant_role\": \"<string>\",\n        \"system_supported\": false,\n        \"input_modalities\": [],\n        \"alternative_names\": [\n          \"<string>\"\n        ],\n        \"input_token_limit\": 123,\n        \"output_token_limit\": 123,\n        \"token_limit\": 123,\n        \"cost_by\": \"tokens\",\n        \"is_chat\": false,\n        \"provides_log_probs\": false,\n        \"formatting_tokens\": 0,\n        \"response_prefix_tokens\": 0,\n        \"api_version\": \"<string>\",\n        \"legacy_mistral_prompt_format\": false,\n        \"requires_max_tokens\": false,\n        \"max_top_p\": 123,\n        \"params_map\": {\n          \"model\": \"<string>\",\n          \"temperature\": \"<string>\",\n          \"max_tokens\": \"<string>\",\n          \"stop_sequences\": \"<string>\",\n          \"top_p\": \"<string>\",\n          \"top_k\": \"<string>\",\n          \"frequency_penalty\": \"<string>\",\n          \"presence_penalty\": \"<string>\",\n          \"echo\": \"<string>\",\n          \"logprobs\": \"<string>\",\n          \"top_logprobs\": \"<string>\",\n          \"n\": \"<string>\",\n          \"api_version\": \"<string>\",\n          \"tools\": \"<string>\",\n          \"tool_choice\": \"<string>\",\n          \"response_format\": \"<string>\",\n          \"reasoning_effort\": \"<string>\",\n          \"verbosity\": \"<string>\",\n          \"deployment_name\": \"<string>\"\n        },\n        \"output_map\": {\n          \"response\": \"<string>\",\n          \"token_count\": \"<string>\",\n          \"input_token_count\": \"<string>\",\n          \"output_token_count\": \"<string>\",\n          \"completion_reason\": \"<string>\"\n        },\n        \"input_map\": {\n          \"prompt\": \"<string>\",\n          \"prefix\": \"\",\n          \"suffix\": \"\"\n        }\n      }\n    ]\n  },\n  \"prompt\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"examples\": [\n    \"<string>\"\n  ],\n  \"source_dataset\": {\n    \"dataset_id\": \"<string>\",\n    \"dataset_version_index\": 123,\n    \"row_ids\": [\n      \"<string>\"\n    ]\n  },\n  \"data_types\": [],\n  \"count\": 10,\n  \"project_id\": \"<string>\"\n}")

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

	req.Header.Add("Galileo-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://api.galileo.ai/v2/datasets/extend")
  .header("Galileo-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt_settings\": {\n    \"logprobs\": true,\n    \"top_logprobs\": 5,\n    \"echo\": false,\n    \"n\": 1,\n    \"reasoning_effort\": \"medium\",\n    \"verbosity\": \"medium\",\n    \"deployment_name\": \"<string>\",\n    \"model_alias\": \"gpt-5.1\",\n    \"temperature\": 123,\n    \"max_tokens\": 4096,\n    \"stop_sequences\": [\n      \"<string>\"\n    ],\n    \"top_p\": 1,\n    \"top_k\": 40,\n    \"frequency_penalty\": 0,\n    \"presence_penalty\": 0,\n    \"tools\": [\n      {}\n    ],\n    \"tool_choice\": \"<string>\",\n    \"response_format\": {},\n    \"known_models\": [\n      {\n        \"name\": \"<string>\",\n        \"alias\": \"<string>\",\n        \"integration\": \"openai\",\n        \"user_role\": \"<string>\",\n        \"assistant_role\": \"<string>\",\n        \"system_supported\": false,\n        \"input_modalities\": [],\n        \"alternative_names\": [\n          \"<string>\"\n        ],\n        \"input_token_limit\": 123,\n        \"output_token_limit\": 123,\n        \"token_limit\": 123,\n        \"cost_by\": \"tokens\",\n        \"is_chat\": false,\n        \"provides_log_probs\": false,\n        \"formatting_tokens\": 0,\n        \"response_prefix_tokens\": 0,\n        \"api_version\": \"<string>\",\n        \"legacy_mistral_prompt_format\": false,\n        \"requires_max_tokens\": false,\n        \"max_top_p\": 123,\n        \"params_map\": {\n          \"model\": \"<string>\",\n          \"temperature\": \"<string>\",\n          \"max_tokens\": \"<string>\",\n          \"stop_sequences\": \"<string>\",\n          \"top_p\": \"<string>\",\n          \"top_k\": \"<string>\",\n          \"frequency_penalty\": \"<string>\",\n          \"presence_penalty\": \"<string>\",\n          \"echo\": \"<string>\",\n          \"logprobs\": \"<string>\",\n          \"top_logprobs\": \"<string>\",\n          \"n\": \"<string>\",\n          \"api_version\": \"<string>\",\n          \"tools\": \"<string>\",\n          \"tool_choice\": \"<string>\",\n          \"response_format\": \"<string>\",\n          \"reasoning_effort\": \"<string>\",\n          \"verbosity\": \"<string>\",\n          \"deployment_name\": \"<string>\"\n        },\n        \"output_map\": {\n          \"response\": \"<string>\",\n          \"token_count\": \"<string>\",\n          \"input_token_count\": \"<string>\",\n          \"output_token_count\": \"<string>\",\n          \"completion_reason\": \"<string>\"\n        },\n        \"input_map\": {\n          \"prompt\": \"<string>\",\n          \"prefix\": \"\",\n          \"suffix\": \"\"\n        }\n      }\n    ]\n  },\n  \"prompt\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"examples\": [\n    \"<string>\"\n  ],\n  \"source_dataset\": {\n    \"dataset_id\": \"<string>\",\n    \"dataset_version_index\": 123,\n    \"row_ids\": [\n      \"<string>\"\n    ]\n  },\n  \"data_types\": [],\n  \"count\": 10,\n  \"project_id\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.galileo.ai/v2/datasets/extend")

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

request = Net::HTTP::Post.new(url)
request["Galileo-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt_settings\": {\n    \"logprobs\": true,\n    \"top_logprobs\": 5,\n    \"echo\": false,\n    \"n\": 1,\n    \"reasoning_effort\": \"medium\",\n    \"verbosity\": \"medium\",\n    \"deployment_name\": \"<string>\",\n    \"model_alias\": \"gpt-5.1\",\n    \"temperature\": 123,\n    \"max_tokens\": 4096,\n    \"stop_sequences\": [\n      \"<string>\"\n    ],\n    \"top_p\": 1,\n    \"top_k\": 40,\n    \"frequency_penalty\": 0,\n    \"presence_penalty\": 0,\n    \"tools\": [\n      {}\n    ],\n    \"tool_choice\": \"<string>\",\n    \"response_format\": {},\n    \"known_models\": [\n      {\n        \"name\": \"<string>\",\n        \"alias\": \"<string>\",\n        \"integration\": \"openai\",\n        \"user_role\": \"<string>\",\n        \"assistant_role\": \"<string>\",\n        \"system_supported\": false,\n        \"input_modalities\": [],\n        \"alternative_names\": [\n          \"<string>\"\n        ],\n        \"input_token_limit\": 123,\n        \"output_token_limit\": 123,\n        \"token_limit\": 123,\n        \"cost_by\": \"tokens\",\n        \"is_chat\": false,\n        \"provides_log_probs\": false,\n        \"formatting_tokens\": 0,\n        \"response_prefix_tokens\": 0,\n        \"api_version\": \"<string>\",\n        \"legacy_mistral_prompt_format\": false,\n        \"requires_max_tokens\": false,\n        \"max_top_p\": 123,\n        \"params_map\": {\n          \"model\": \"<string>\",\n          \"temperature\": \"<string>\",\n          \"max_tokens\": \"<string>\",\n          \"stop_sequences\": \"<string>\",\n          \"top_p\": \"<string>\",\n          \"top_k\": \"<string>\",\n          \"frequency_penalty\": \"<string>\",\n          \"presence_penalty\": \"<string>\",\n          \"echo\": \"<string>\",\n          \"logprobs\": \"<string>\",\n          \"top_logprobs\": \"<string>\",\n          \"n\": \"<string>\",\n          \"api_version\": \"<string>\",\n          \"tools\": \"<string>\",\n          \"tool_choice\": \"<string>\",\n          \"response_format\": \"<string>\",\n          \"reasoning_effort\": \"<string>\",\n          \"verbosity\": \"<string>\",\n          \"deployment_name\": \"<string>\"\n        },\n        \"output_map\": {\n          \"response\": \"<string>\",\n          \"token_count\": \"<string>\",\n          \"input_token_count\": \"<string>\",\n          \"output_token_count\": \"<string>\",\n          \"completion_reason\": \"<string>\"\n        },\n        \"input_map\": {\n          \"prompt\": \"<string>\",\n          \"prefix\": \"\",\n          \"suffix\": \"\"\n        }\n      }\n    ]\n  },\n  \"prompt\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"examples\": [\n    \"<string>\"\n  ],\n  \"source_dataset\": {\n    \"dataset_id\": \"<string>\",\n    \"dataset_version_index\": 123,\n    \"row_ids\": [\n      \"<string>\"\n    ]\n  },\n  \"data_types\": [],\n  \"count\": 10,\n  \"project_id\": \"<string>\"\n}"

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

200

{
  "dataset_id": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

ClassicAPIKeyHeaderAPIKeyHeaderOAuth2PasswordBearerHTTPBasic

Galileo-API-Key · string · header · required

Body

application/json

Request for a synthetic dataset run job.

prompt_settings · PromptRunSettings · object

Only the model is used.

Show child attributes

prompt · string | null

instructions · string | null

examples · string[]

source_dataset · SyntheticDataSourceDataset · object | null

Configuration for dataset examples in synthetic data generation.

Show child attributes

data_types · enum<string>[] | null

Available options: General Query, Prompt Injection, Off-Topic Query, Toxic Content in Query, Multiple Questions in Query, Sexist Content in Query

count · integer · default: 10

project_id · string<uuid4> | null

Response

200

application/json

Successful Response

Response for synthetic dataset extension requests.

dataset_id · string<uuid4> · required