Create Extractor

import { ExtendClient, ExtendEnvironment } from "extend-ai";
async function main() {
    const client = new ExtendClient({
        environment: ExtendEnvironment.Production,
        token: "YOUR_TOKEN_HERE",
    });
    await client.extractors.create({
        name: "Invoice Extractor",
        config: {
            schema: {
                "type": "object",
                "properties": {
                    vendor_name: {
                        type: "string",
                        description: "The name of the vendor",
                    },
                    invoice_number: {
                        type: "string",
                        description: "The invoice number",
                    },
                    total_amount: {
                        type: "number",
                        description: "The total amount due",
                    },
                },
            },
        },
    });
}
main();

{
  "object": "extractor",
  "id": "ex_Xj8mK2pL9nR4vT7qY5wZ",
  "name": "Invoice Extractor",
  "createdAt": "2024-03-21T16:45:00Z",
  "updatedAt": "2024-03-21T16:45:00Z",
  "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 vendor details, invoice number, and total amount with high accuracy.",
      "schema": {},
      "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 and totals."
        },
        "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 for multi-page invoices."
            }
          },
          "text": {
            "signatureDetectionEnabled": false,
            "agentic": {
              "enabled": false,
              "customInstructions": "Check OCR text for signature fields."
            }
          }
        },
        "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"
  }
}

Create a new extractor.

Authentication

AuthorizationBearer

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

Request

This endpoint expects an object.

namestringRequired

The name of the extractor.

cloneExtractorIdstringOptional

The ID of an existing extractor to clone. If provided, the new extractor will be created with the same config as the extractor with this ID. Cannot be provided together with config.

Example: "ex_BMdfq_yWM3sT-ZzvCnA3f"

configobjectOptional

The configuration for the extractor. Cannot be provided together with cloneExtractorId.

Response

Extractor created successfully

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.

Create Extractor

Authentication

Headers

Request

Response

Errors