Create a feature engineering proposal

curl --request POST \
  --url https://api.example.com/api/automl/feature-engineering \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "target_table_name": "<string>",
  "description": "<string>",
  "source_tables": [
    "<string>"
  ],
  "entity_grain": [
    "<string>"
  ],
  "label": {
    "name": "label",
    "type": "binary",
    "column": "<string>",
    "derivation": "<string>",
    "positive_class_value": "<unknown>"
  },
  "domain": "<string>",
  "owner": "<string>",
  "join_hints": "<string>"
}
'

import requests

url = "https://api.example.com/api/automl/feature-engineering"

payload = {
    "target_table_name": "<string>",
    "description": "<string>",
    "source_tables": ["<string>"],
    "entity_grain": ["<string>"],
    "label": {
        "name": "label",
        "type": "binary",
        "column": "<string>",
        "derivation": "<string>",
        "positive_class_value": "<unknown>"
    },
    "domain": "<string>",
    "owner": "<string>",
    "join_hints": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    target_table_name: '<string>',
    description: '<string>',
    source_tables: ['<string>'],
    entity_grain: ['<string>'],
    label: {
      name: 'label',
      type: 'binary',
      column: '<string>',
      derivation: '<string>',
      positive_class_value: '<unknown>'
    },
    domain: '<string>',
    owner: '<string>',
    join_hints: '<string>'
  })
};

fetch('https://api.example.com/api/automl/feature-engineering', 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.example.com/api/automl/feature-engineering",
  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([
    'target_table_name' => '<string>',
    'description' => '<string>',
    'source_tables' => [
        '<string>'
    ],
    'entity_grain' => [
        '<string>'
    ],
    'label' => [
        'name' => 'label',
        'type' => 'binary',
        'column' => '<string>',
        'derivation' => '<string>',
        'positive_class_value' => '<unknown>'
    ],
    'domain' => '<string>',
    'owner' => '<string>',
    'join_hints' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.example.com/api/automl/feature-engineering"

	payload := strings.NewReader("{\n  \"target_table_name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"source_tables\": [\n    \"<string>\"\n  ],\n  \"entity_grain\": [\n    \"<string>\"\n  ],\n  \"label\": {\n    \"name\": \"label\",\n    \"type\": \"binary\",\n    \"column\": \"<string>\",\n    \"derivation\": \"<string>\",\n    \"positive_class_value\": \"<unknown>\"\n  },\n  \"domain\": \"<string>\",\n  \"owner\": \"<string>\",\n  \"join_hints\": \"<string>\"\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.example.com/api/automl/feature-engineering")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"target_table_name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"source_tables\": [\n    \"<string>\"\n  ],\n  \"entity_grain\": [\n    \"<string>\"\n  ],\n  \"label\": {\n    \"name\": \"label\",\n    \"type\": \"binary\",\n    \"column\": \"<string>\",\n    \"derivation\": \"<string>\",\n    \"positive_class_value\": \"<unknown>\"\n  },\n  \"domain\": \"<string>\",\n  \"owner\": \"<string>\",\n  \"join_hints\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/api/automl/feature-engineering")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"target_table_name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"source_tables\": [\n    \"<string>\"\n  ],\n  \"entity_grain\": [\n    \"<string>\"\n  ],\n  \"label\": {\n    \"name\": \"label\",\n    \"type\": \"binary\",\n    \"column\": \"<string>\",\n    \"derivation\": \"<string>\",\n    \"positive_class_value\": \"<unknown>\"\n  },\n  \"domain\": \"<string>\",\n  \"owner\": \"<string>\",\n  \"join_hints\": \"<string>\"\n}"

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

{
  "job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "target_table_name": "<string>",
  "domain": "<string>",
  "owner": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "recipe": {
    "target_table": "<string>",
    "entity_grain": [
      "<string>"
    ],
    "label": {
      "name": "label",
      "type": "binary",
      "column": "<string>",
      "derivation": "<string>",
      "positive_class_value": "<unknown>"
    },
    "features": [
      {
        "name": "<string>",
        "expression": "<string>",
        "source_table": "<string>",
        "description": "<string>",
        "data_type": "<string>"
      }
    ],
    "notes": "<string>"
  },
  "sql": "<string>",
  "validation": {
    "estimated_row_count": 123,
    "label_distribution": {},
    "high_null_columns": {},
    "warnings": [
      "<string>"
    ]
  },
  "error": "<string>"
}

{
  "error": "<string>",
  "code": 500
}

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

{
  "error": "<string>",
  "code": 500
}

POST

api

automl

feature-engineering

Create a feature engineering proposal

curl --request POST \
  --url https://api.example.com/api/automl/feature-engineering \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "target_table_name": "<string>",
  "description": "<string>",
  "source_tables": [
    "<string>"
  ],
  "entity_grain": [
    "<string>"
  ],
  "label": {
    "name": "label",
    "type": "binary",
    "column": "<string>",
    "derivation": "<string>",
    "positive_class_value": "<unknown>"
  },
  "domain": "<string>",
  "owner": "<string>",
  "join_hints": "<string>"
}
'

import requests

url = "https://api.example.com/api/automl/feature-engineering"

payload = {
    "target_table_name": "<string>",
    "description": "<string>",
    "source_tables": ["<string>"],
    "entity_grain": ["<string>"],
    "label": {
        "name": "label",
        "type": "binary",
        "column": "<string>",
        "derivation": "<string>",
        "positive_class_value": "<unknown>"
    },
    "domain": "<string>",
    "owner": "<string>",
    "join_hints": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    target_table_name: '<string>',
    description: '<string>',
    source_tables: ['<string>'],
    entity_grain: ['<string>'],
    label: {
      name: 'label',
      type: 'binary',
      column: '<string>',
      derivation: '<string>',
      positive_class_value: '<unknown>'
    },
    domain: '<string>',
    owner: '<string>',
    join_hints: '<string>'
  })
};

fetch('https://api.example.com/api/automl/feature-engineering', 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.example.com/api/automl/feature-engineering",
  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([
    'target_table_name' => '<string>',
    'description' => '<string>',
    'source_tables' => [
        '<string>'
    ],
    'entity_grain' => [
        '<string>'
    ],
    'label' => [
        'name' => 'label',
        'type' => 'binary',
        'column' => '<string>',
        'derivation' => '<string>',
        'positive_class_value' => '<unknown>'
    ],
    'domain' => '<string>',
    'owner' => '<string>',
    'join_hints' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.example.com/api/automl/feature-engineering"

	payload := strings.NewReader("{\n  \"target_table_name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"source_tables\": [\n    \"<string>\"\n  ],\n  \"entity_grain\": [\n    \"<string>\"\n  ],\n  \"label\": {\n    \"name\": \"label\",\n    \"type\": \"binary\",\n    \"column\": \"<string>\",\n    \"derivation\": \"<string>\",\n    \"positive_class_value\": \"<unknown>\"\n  },\n  \"domain\": \"<string>\",\n  \"owner\": \"<string>\",\n  \"join_hints\": \"<string>\"\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.example.com/api/automl/feature-engineering")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"target_table_name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"source_tables\": [\n    \"<string>\"\n  ],\n  \"entity_grain\": [\n    \"<string>\"\n  ],\n  \"label\": {\n    \"name\": \"label\",\n    \"type\": \"binary\",\n    \"column\": \"<string>\",\n    \"derivation\": \"<string>\",\n    \"positive_class_value\": \"<unknown>\"\n  },\n  \"domain\": \"<string>\",\n  \"owner\": \"<string>\",\n  \"join_hints\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/api/automl/feature-engineering")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"target_table_name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"source_tables\": [\n    \"<string>\"\n  ],\n  \"entity_grain\": [\n    \"<string>\"\n  ],\n  \"label\": {\n    \"name\": \"label\",\n    \"type\": \"binary\",\n    \"column\": \"<string>\",\n    \"derivation\": \"<string>\",\n    \"positive_class_value\": \"<unknown>\"\n  },\n  \"domain\": \"<string>\",\n  \"owner\": \"<string>\",\n  \"join_hints\": \"<string>\"\n}"

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

{
  "job_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "target_table_name": "<string>",
  "domain": "<string>",
  "owner": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "recipe": {
    "target_table": "<string>",
    "entity_grain": [
      "<string>"
    ],
    "label": {
      "name": "label",
      "type": "binary",
      "column": "<string>",
      "derivation": "<string>",
      "positive_class_value": "<unknown>"
    },
    "features": [
      {
        "name": "<string>",
        "expression": "<string>",
        "source_table": "<string>",
        "description": "<string>",
        "data_type": "<string>"
      }
    ],
    "notes": "<string>"
  },
  "sql": "<string>",
  "validation": {
    "estimated_row_count": 123,
    "label_distribution": {},
    "high_null_columns": {},
    "warnings": [
      "<string>"
    ]
  },
  "error": "<string>"
}

{
  "error": "<string>",
  "code": 500
}

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

{
  "error": "<string>",
  "code": 500
}

Authorizations

Authorization

string

header

required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json

Top-level request to start a feature engineering proposal.

target_table_name

string

required

Fully qualified output table. For example iceberg.automl_credit_risk.training_v1. Schema must be under the AutoML namespace.

description

string

required

Natural-language description of the prediction problem.

source_tables

string[]

required

Fully qualified source tables in catalog.schema.table format.

Minimum array length: 1

entity_grain

string[]

required

Columns that uniquely identify a training row.

Minimum array length: 1

label

LabelSpec · object

required

How to derive the label column for the training table.

Provide exactly one of column or derivation. column refers to an existing column or a simple SQL expression over source columns. derivation is a natural-language description that the crew translates into SQL.

Show child attributes

domain

string

required

DataHub domain or business domain for governance.

owner

string

required

Username who owns the resulting training table.

join_hints

string | null

Optional natural-language join guidance for the crew.

Response

Crew run started. Poll the job for the proposal.

The crew's proposal returned to the user for review.

job_id

string<uuid>

required

status

enum<string>

required

Lifecycle of an AutoML feature engineering job.

Available options:

running,

pending_approval,

failed,

approved,

materializing,

complete

target_table_name

string

required

domain

string

required

owner

string

required

created_at

string<date-time>

required

updated_at

string<date-time>

required

recipe

FeatureRecipe · object | null

Structured recipe describing the training table the crew designed.

Show child attributes

sql

string | null

The CREATE TABLE AS SELECT query the crew produced.

validation

ValidationSummary · object | null

Result of running the CTAS query with a row limit during validation.

Kept intentionally lean. Large agents produce more than 10 KB of JSON when this grows with per-column null rates and sample rows. That often exceeds output-token limits. Run the SQL directly to inspect rows. Only persist what's cheap and structurally useful.

Show child attributes

error

string | null

⌘I