Datasaur
Search…
⌃K

Run ML-Assisted Labeling

You can label a project using existing model that is provided by the app or your own model. Currently, this API only support the custom API, i.e. your own model. Also, this mutation is asynchronous so the response only returns the job information.

Example Request via cURL

curl --location --request POST 'https://app.datasaur.ai/graphql' \
--header 'Authorization: Bearer <access_token>' \
--header 'Content-Type: application/json' \
--data-raw '{"operationName":"AutoLabelTokenBasedProjectMutation","variables":{"input":{"labelerEmail":"[email protected]","options":{"numberOfFilesPerRequest":0,"serviceProvider":"CUSTOM"},"projectId":"HvdyIL2iwZn","targetAPI":{"endpoint":"https://custom-model.api.com/predict","secretKey":"secret"}}},"query":"mutation AutoLabelTokenBasedProjectMutation($input: AutoLabelTokenBasedProjectInput!) { result: autoLabelTokenBasedProject(input: $input) { id status progress }}"}'
Below is the more readable version of request body from cURL command above.
{
"operationName": "AutoLabelTokenBasedProjectMutation",
"variables": {
"input": {
"labelerEmail": "[email protected]",
"options": {
"numberOfFilesPerRequest": 0,
"serviceProvider": "CUSTOM"
},
"projectId": "HvdyIL2iwZn",
"targetAPI": {
"endpoint": "https://custom-model.api.com/predict",
"secretKey": "secret"
}
}
},
"query": "mutation AutoLabelTokenBasedProjectMutation($input: AutoLabelTokenBasedProjectInput!) { result: autoLabelTokenBasedProject(input: $input) { id status progress }}"
}
  • operationName: you can fill any alphanumeric string in as the operationName. AutoLabelTokenBasedProjectMutation is fine as a default. Refer this page to organize operationName properly.
  • variables
    • input: see the explanation of each variables here. See the additional information for AutoLabelProjectOptionsInput below.
      • Again, currently we only support CUSTOM serviceProvider
      • If the numberOfFilesPerRequest is 0, then it will request all lines in a document. If it's more than 0, the backend will batch the request based on how many lines for each request.
  • query: Copy it from cURL example.

Example Response

Here is the response when you execute the cURL command above.
{
"data": {
"result": {
"id": "AutoLabelQueue:dcbf6ed3-3841-46c1-8f6a-2affb53ac637",
"status": "IN_PROGRESS",
"progress": 50
}
},
"extensions": {}
}
This doesn't mean the process is finished. To make sure the job is finished or to get any other information, please see this page.