Custom API

Supported Labeling Types: Span labeling, Row labeling, Bounding box labeling , Document labeling

We also support Custom API in case you want to use your own model for ML-assisted labeling by simply providing the API URL. Ensure your custom API follows the required request structure to integrate smoothly with the Datasaur platform. Here’s how to set it up:

Setting Up Your Custom API for ML-Assisted Labeling

1. Create an API: Build an API for your model that adheres to a specific request and response format compatible with the Datasaur App. For guidance, refer to the API Creation Example.

2. Request and response structure: You can find example request and response body near the API URL input field or in the examples below.

3. Enter your API URL: Once your API is ready, fill in the API URL in the designated field under the extension.

4. For span labeling project

   1. Sentences per request (0 = all): Determine how many text you want to include in 1 request to your API service.

5. For row labeling project

   1. Target text: Choose the text input that your model will use as a reference.

   2. Target question: Select the output column your model will predict.

   3. Faster prediction speed: Optionally, toggle this feature to run predictions faster via the backend.

6. Confidence score: Adjust the value according to your needs.

7. Apply labels: After setting up, click Predict labels to automatically apply labels to your document based on your model's predictions.

Custom API for Span Based

ML-assisted labeling with Custom API for span labeling

Request Body

{
    "id": "[project_id]",
    "name": "[project_name]",
    "documents": [
      {
        "id": "[document_id_1]",
        "sentences": [
          {
            "id": 0, // zero-based line number of the document
            "text": "first message",
            "metadata": []
          },
          {
            "id": 1,
            "text": "first message",
            "metadata": []
          },
        ]
      }
    ]
  }

Response Body

{
  "id": "[project_id]",
  "documents": [
    {
      "id": "[document_id_1]",
      "labels": [
        {
          "id": 0,
          "entities": [
            {
              "label": "LOCATION",
              "start_char": 10,
              "end_char": 18,
              "layer": 0
            },
            {
              "label": "PERSON",
              "start_char": 20,
              "end_char": 29,
              "layer": 1
            },
          ]
        },
        {
          "id": 1,
          "entities": []
        }
      ]
    }
  ]
}

Custom API for Row Based

ML-assisted labeling with Custom API for row labeling

Request Body

[
  { "id": 0, "text": "I feel good." },
  { "id": 1, "text": "I don't like it." }
]

Response Body

[
  { "id": 0, "label": "POSITIVE" },
  { "id": 1, "label": "NEGATIVE" }
]

Custom API for Bounding Box Labeling

ML-assisted labeling with Custom API for bounding box labeling

Request Body

{
    "document": {
      "id": "[document_id_1]",
      "presignedURL": "[document_presigned_url]",
    },
    "readingResult": [
      {
        "id":"[bbox_id_1]",
        "label": "O",
        "caption": "First"
        "shapes": [
          {
            "pageIndex": 0,
            "points": [
                {
                  "x": 211.51411561127316,
                  "y": 99.08677657682311
                },
                {
                  "x": 266.385241834969,
                  "y": 99.08677657682311
                },
                {
                  "x": 266.385241834969,
                  "y": 105.74680188808318
                },
                {
                  "x": 211.51411561127316,
                  "y": 105.74680188808318
                }
              ]
            }
          }
        ]
      },
      {
        "id":"[bbox_id_2]",
        "label": "O",
        "caption": "Message"
        "shapes": [
          {
            "pageIndex": 0,
            "points": [
                {
                  "x": 269.38763779813405,
                  "y": 99.09397660418664
                },
                {
                  "x": 318.98117111775315,
                  "y": 99.09397660418664
                },
                {
                  "x": 318.98117111775315,
                  "y": 105.73240183335614
                },
                {
                  "x": 269.38763779813405,
                  "y": 105.73240183335614
                }
              ]
            }
          }
        ]
      }
    ]
  }

Response Body

{
    "id": "[document_id_1]",
    "labels": [
      {
        "id":"[bbox_id_1]",
        "label": "LOCATION",
        "caption": "First",
        "confidence_score": 0.90,
        "shapes": [
          {
            "pageIndex": 0,
            "points": [
              {
                "x": 211.51411561127316,
                "y": 99.08677657682311
              },
              {
                "x": 266.385241834969,
                "y": 99.08677657682311
              },
              {
                "x": 266.385241834969,
                "y": 105.74680188808318
              },
              {
                "x": 211.51411561127316,
                "y": 105.74680188808318
              }
            ]
          }
        ]
      },
      {
        "id":"[bbox_id_2]",
        "label": "PERSON",
        "caption": "Message",
        "confidence_score": 0.90,
        "shapes": [
          {
            "pageIndex": 0,
            "points": [
              {
                "x": 269.38763779813405,
                "y": 99.09397660418664
              },
              {
                "x": 318.98117111775315,
                "y": 99.09397660418664
              },
              {
                "x": 318.98117111775315,
                "y": 105.73240183335614
              },
              {
                "x": 269.38763779813405,
                "y": 105.73240183335614
              }
            ]
          }
        ]
      }
    ]
  }

Custom API for Document Based

ML-assisted labeling with Custom API for document labeling

Request Body

{
  "document": {
    "id": "[document_id_1]",
    "presignedURL": "[document_presigned_url]"
  }
}

Response Body

{
  "id": "[document_id_1]",
  "[your_document_question_a]": "POSITIVE",
  "[your_document_question_b_with_multiple_answer]": ["NEWS", "ARTICLE"]
}