Generate Extraction Schemas - Datalab Documentation

POST

/

api

/

v1

/

marker

/

extraction

/

gen_schemas

Generate Extraction Schemas

import requests

url = "https://www.datalab.to/api/v1/marker/extraction/gen_schemas"

payload = {
    "checkpoint_id": "<string>",
    "webhook_url": "<string>",
    "processing_location": "<string>",
    "model_override_settings": {}
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

curl --request POST \
  --url https://www.datalab.to/api/v1/marker/extraction/gen_schemas \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "checkpoint_id": "<string>",
  "webhook_url": "<string>",
  "processing_location": "<string>",
  "model_override_settings": {}
}
'

const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    checkpoint_id: '<string>',
    webhook_url: '<string>',
    processing_location: '<string>',
    model_override_settings: {}
  })
};

fetch('https://www.datalab.to/api/v1/marker/extraction/gen_schemas', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

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

func main() {

	url := "https://www.datalab.to/api/v1/marker/extraction/gen_schemas"

	payload := strings.NewReader("{\n  \"checkpoint_id\": \"<string>\",\n  \"webhook_url\": \"<string>\",\n  \"processing_location\": \"<string>\",\n  \"model_override_settings\": {}\n}")

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

	req.Header.Add("X-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))

}

{
  "request_id": "<string>",
  "request_check_url": "<string>",
  "success": true,
  "error": "<string>",
  "versions": {},
  "checkpoint_reused": true
}

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

Authorizations

X-API-Key

string

header

required

Cookies

wos-session

string

datalab_active_team

string

Body

application/json

checkpoint_id

string

required

webhook_url

string | null

processing_location

string | null

Optional residency region override (e.g. us, eu). When provided, use file_url or direct-upload; multipart uploads are rejected. When omitted, the request uses the team's configured residency and profile.

model_override_settings

Model Override Settings · object | null

Response

Successful Response

request_id

string

required

The ID of the request. This ID can be used to check the status of the request.

request_check_url

string

required

The URL to check the status of the request and get results.

success

boolean

default:true

Whether the request was successful.

error

string | null

If the request was not successful, this will contain an error message.

versions

A dictionary of the versions of the libraries used in the request.

checkpoint_reused

boolean | null

True when this run automatically reused a checkpoint from a previous run of the same file, so the conversion step is not re-billed. Absent/None otherwise.

Generate Extraction Schemas

import requests

url = "https://www.datalab.to/api/v1/marker/extraction/gen_schemas"

payload = {
    "checkpoint_id": "<string>",
    "webhook_url": "<string>",
    "processing_location": "<string>",
    "model_override_settings": {}
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

curl --request POST \
  --url https://www.datalab.to/api/v1/marker/extraction/gen_schemas \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "checkpoint_id": "<string>",
  "webhook_url": "<string>",
  "processing_location": "<string>",
  "model_override_settings": {}
}
'

const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    checkpoint_id: '<string>',
    webhook_url: '<string>',
    processing_location: '<string>',
    model_override_settings: {}
  })
};

fetch('https://www.datalab.to/api/v1/marker/extraction/gen_schemas', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

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

func main() {

	url := "https://www.datalab.to/api/v1/marker/extraction/gen_schemas"

	payload := strings.NewReader("{\n  \"checkpoint_id\": \"<string>\",\n  \"webhook_url\": \"<string>\",\n  \"processing_location\": \"<string>\",\n  \"model_override_settings\": {}\n}")

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

	req.Header.Add("X-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))

}

{
  "request_id": "<string>",
  "request_check_url": "<string>",
  "success": true,
  "error": "<string>",
  "versions": {},
  "checkpoint_reused": true
}

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