Skip to main content
POST
/
v1
/
flow
/
data-jobs
Submit data job
curl --request POST \
  --url https://flow.seekr.com/v1/flow/data-jobs \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "system_prompt": "<string>",
  "instructions": "<string>",
  "vector_database_id": "<string>"
}
'
import requests

url = "https://flow.seekr.com/v1/flow/data-jobs"

payload = {
"name": "<string>",
"system_prompt": "<string>",
"instructions": "<string>",
"vector_database_id": "<string>"
}
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}

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

print(response.text)
const options = {
method: 'POST',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
name: '<string>',
system_prompt: '<string>',
instructions: '<string>',
vector_database_id: '<string>'
})
};

fetch('https://flow.seekr.com/v1/flow/data-jobs', 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://flow.seekr.com/v1/flow/data-jobs",
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([
'name' => '<string>',
'system_prompt' => '<string>',
'instructions' => '<string>',
'vector_database_id' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"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://flow.seekr.com/v1/flow/data-jobs"

payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"system_prompt\": \"<string>\",\n \"instructions\": \"<string>\",\n \"vector_database_id\": \"<string>\"\n}")

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

req.Header.Add("Authorization", "<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://flow.seekr.com/v1/flow/data-jobs")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"system_prompt\": \"<string>\",\n \"instructions\": \"<string>\",\n \"vector_database_id\": \"<string>\"\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://flow.seekr.com/v1/flow/data-jobs")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"name\": \"<string>\",\n \"system_prompt\": \"<string>\",\n \"instructions\": \"<string>\",\n \"vector_database_id\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body
{
  "id": "<string>",
  "user_id": "<string>",
  "name": "<string>",
  "job_type": "<string>",
  "alignment_job_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "origin_data_job_id": "<string>",
  "status_message": "<string>",
  "system_prompt": "<string>",
  "system_prompt_updated_at": "2023-11-07T05:31:56Z",
  "instructions": "<string>",
  "instructions_updated_at": "2023-11-07T05:31:56Z",
  "resolved_instructions": "<string>",
  "vector_database_id": "<string>"
}
{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}
Create a new data job. The job_type field determines the workflow:
  • principle_files — generates a QA pair dataset for instruction fine-tuning
  • context_grounded_files — generates context-grounded training data from uploaded documents
  • context_grounded_vector_db — generates context-grounded training data using an existing vector database
Newly created jobs have no files attached. Use POST /v1/flow/data-jobs/{id}/add-files to attach uploaded file IDs after creation. For the complete workflow, see Create instruction fine-tuning data or Create context-grounded fine-tuning data.

Authorizations

Authorization
string
header
required

Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.

Body

application/json
name
string
required
Required string length: 1 - 255
job_type
enum<string>
required

Valid job types for data jobs.

Available options:
principle_files,
context_grounded_files,
context_grounded_vector_db
system_prompt
string | null
Minimum string length: 1
instructions
string | null

Natural-language description of the task the generated dataset should support. Alignment uses it to shape the examples it produces, such as the topics and the kinds of questions a fine-tuned model should be able to handle.

Minimum string length: 1
vector_database_id
string | null

Response

Successful Response

Lightweight response for list view performance.

id
string
required
user_id
string
required
name
string
required
job_type
string
required
alignment_job_id
string | null
required
created_at
string<date-time>
required
updated_at
string<date-time>
required
status
required

Status values that exist BEFORE an alignment job is linked. Once linked, the real status comes from AlignmentJobStatus directly — see DataJobResponse.status's union type and derive_data_job_status.

Available options:
file_processing,
needs_review,
ready_to_start
origin_data_job_id
string | null
status_message
string | null
system_prompt
string | null
system_prompt_updated_at
string<date-time> | null
instructions
string | null
instructions_updated_at
string<date-time> | null
resolved_instructions
string | null
vector_database_id
string | null
Last modified on June 18, 2026