Get Extractor

import { ExtendClient, ExtendEnvironment } from "extend-ai";
async function main() {
    const client = new ExtendClient({
        environment: ExtendEnvironment.Production,
        token: "YOUR_TOKEN_HERE",
    });
    await client.extractors.retrieve("extractor_id_here");
}
main();

{
  "object": "extractor",
  "id": "ex_Xj8mK2pL9nR4vT7qY5wZ",
  "name": "Invoice Extractor",
  "createdAt": "2024-03-21T16:45:00Z",
  "updatedAt": "2024-04-10T12:30:00Z",
  "draftVersion": {
    "object": "extractor_version",
    "id": "exv_xK9mLPqRtN3vS8wF5hB2cQ",
    "description": "Updated extraction fields for new invoice format",
    "version": "draft",
    "config": {
      "baseProcessor": "extraction_performance",
      "baseVersion": "4.5.2",
      "extractionRules": "Extract invoice number, date, total amount, and vendor details with high accuracy.",
      "schema": {
        "type": "object",
        "properties": {
          "invoiceNumber": {
            "type": "string",
            "description": "Unique invoice identifier"
          },
          "invoiceDate": {
            "type": "string",
            "format": "date",
            "description": "Date when the invoice was issued"
          },
          "totalAmount": {
            "type": "number",
            "description": "Total amount due on the invoice"
          },
          "vendor": {
            "type": "object",
            "properties": {
              "name": {
                "type": "string",
                "description": "Vendor company name"
              },
              "address": {
                "type": "string",
                "description": "Vendor address"
              }
            },
            "required": [
              "name"
            ]
          }
        },
        "required": [
          "invoiceNumber",
          "invoiceDate",
          "totalAmount",
          "vendor"
        ]
      },
      "advancedOptions": {
        "modelReasoningInsightsEnabled": true,
        "advancedMultimodalEnabled": true,
        "citationsEnabled": true,
        "arrayCitationStrategy": "item",
        "arrayStrategy": {
          "type": "large_array_heuristics"
        },
        "chunkingOptions": {
          "chunkingStrategy": "standard",
          "pageChunkSize": 2,
          "chunkSelectionStrategy": "intelligent",
          "customSemanticChunkingRules": "Split chunks at invoice section headers."
        },
        "excelSheetRanges": [
          {
            "start": 0,
            "end": 2
          }
        ],
        "excelSheetSelectionStrategy": "intelligent",
        "pageRanges": [
          {
            "start": 1,
            "end": 10
          },
          {
            "start": 20,
            "end": 30
          }
        ],
        "reviewAgent": {
          "enabled": true
        }
      },
      "parseConfig": {
        "target": "markdown",
        "chunkingStrategy": {
          "type": "page",
          "options": {
            "minCharacters": 500,
            "maxCharacters": 10000
          }
        },
        "engine": "parse_performance",
        "engineVersion": "latest",
        "blockOptions": {
          "figures": {
            "enabled": true,
            "figureImageClippingEnabled": true
          },
          "tables": {
            "enabled": true,
            "targetFormat": "html",
            "tableHeaderContinuationEnabled": false,
            "cellBlocksEnabled": false,
            "agentic": {
              "enabled": false,
              "customInstructions": "Review table extraction accuracy and correct OCR errors."
            }
          },
          "text": {
            "signatureDetectionEnabled": false,
            "agentic": {
              "enabled": false,
              "customInstructions": "Check for OCR errors in text blocks."
            }
          }
        },
        "advancedOptions": {
          "pageRotationEnabled": true,
          "pageRanges": [
            {
              "start": 1,
              "end": 10
            },
            {
              "start": 20,
              "end": 30
            }
          ],
          "excelParsingMode": "basic",
          "excelSkipHiddenContent": false,
          "verticalGroupingThreshold": 1,
          "returnOcr": {
            "words": false
          }
        }
      }
    },
    "extractorId": "ex_Xj8mK2pL9nR4vT7qY5wZ",
    "createdAt": "2024-03-21T16:45:00Z"
  }
}

Get details of an extractor.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Path parameters

idstringRequired

The ID of the extractor to get.

Example: "ex_Xj8mK2pL9nR4vT7qY5wZ"

Response

Extractor details

objectenum

The type of object. Will always be "extractor".

Allowed values:

idstring

The ID of the extractor.

Example: "ex_Xj8mK2pL9nR4vT7qY5wZ"

namestring

The name of the extractor.

Example: "Invoice Extractor"

createdAtstringformat: "date-time"

The time (in UTC) at which the object was created. Will follow the RFC 3339 format.

Example: "2024-03-21T16:45:00Z"

updatedAtstringformat: "date-time"

The time (in UTC) at which the object was last updated. Will follow the RFC 3339 format.

Example: "2024-03-21T16:45:00Z"

draftVersionobject

The draft version of the extractor. This is the editable version in the Extend dashboard.

Authentication

Path parameters

Headers

Response

Errors