Get Sources

Return the extraction result enriched with per-leaf source provenance.

Each extracted leaf value is wrapped as where source contains citation content, surrounding context, and a format-specific anchor (bbox for PDFs, cell ref for spreadsheets, text span for plain text, etc.).

GET /v1/extractions/{extraction_id}/sources

Python

from retab import Retab

client = Retab()

result = client.extractions.sources("extr_01G34H8J2K")
print(result)

200

{
  "object": "extraction.sources",
  "extraction_id": "extr_01G34H8J2K",
  "document_type": "pdf",
  "file": {
    "id": "file_abc123",
    "filename": "invoice_001.pdf",
    "mime_type": "application/pdf"
  },
  "extraction": {
    "invoice_number": "INV-1032",
    "customer": {
      "name": "Acme Inc."
    },
    "total_amount": 1240.0
  },
  "sources": {
    "invoice_number": {
      "value": "INV-1032",
      "source": {
        "content": "INV-1032",
        "anchor": {
          "kind": "pdf_bbox",
          "page": 1,
          "left": 0.6,
          "top": 0.12,
          "width": 0.25,
          "height": 0.03
        }
      }
    },
    "customer": {
      "name": {
        "value": "Acme Inc.",
        "source": {
          "content": "Acme Inc.",
          "anchor": {
            "kind": "pdf_bbox",
            "page": 1,
            "left": 0.1,
            "top": 0.25,
            "width": 0.3,
            "height": 0.03
          }
        }
      }
    },
    "total_amount": {
      "value": 1240.0,
      "source": {
        "content": "1,240.00",
        "anchor": {
          "kind": "pdf_bbox",
          "page": 1,
          "left": 0.65,
          "top": 0.85,
          "width": 0.2,
          "height": 0.03
        }
      }
    }
  }
}

Python

from retab import Retab

client = Retab()

result = client.extractions.sources("extr_01G34H8J2K")
print(result)

200

{
  "object": "extraction.sources",
  "extraction_id": "extr_01G34H8J2K",
  "document_type": "pdf",
  "file": {
    "id": "file_abc123",
    "filename": "invoice_001.pdf",
    "mime_type": "application/pdf"
  },
  "extraction": {
    "invoice_number": "INV-1032",
    "customer": {
      "name": "Acme Inc."
    },
    "total_amount": 1240.0
  },
  "sources": {
    "invoice_number": {
      "value": "INV-1032",
      "source": {
        "content": "INV-1032",
        "anchor": {
          "kind": "pdf_bbox",
          "page": 1,
          "left": 0.6,
          "top": 0.12,
          "width": 0.25,
          "height": 0.03
        }
      }
    },
    "customer": {
      "name": {
        "value": "Acme Inc.",
        "source": {
          "content": "Acme Inc.",
          "anchor": {
            "kind": "pdf_bbox",
            "page": 1,
            "left": 0.1,
            "top": 0.25,
            "width": 0.3,
            "height": 0.03
          }
        }
      }
    },
    "total_amount": {
      "value": 1240.0,
      "source": {
        "content": "1,240.00",
        "anchor": {
          "kind": "pdf_bbox",
          "page": 1,
          "left": 0.65,
          "top": 0.85,
          "width": 0.2,
          "height": 0.03
        }
      }
    }
  }
}

Authorizations

Api-Key · string · header · required

Path Parameters

extraction_id · string · required

Response

200

application/json

Successful Response

An extraction's output annotated with the source that backs each value.

Returned when fetching the sources for an extraction. Carries the source file and its detected document_type, the original extraction output, and a parallel sources tree where each leaf is a {value, source} object locating the value in the document (a page region for PDFs, a cell for spreadsheets, a text span for plain text, and so on).

extraction_id · string · required

ID of the extraction

document_type · enum<string> · required

Detected document type of the source file

Available options: pdf, image, csv, xlsx, docx, txt

file · FileRef · object · required

File metadata (id, filename, mime_type)

Show child attributes

extraction · Extraction · object · required

Original extraction output

sources · Sources · object · required

Same shape as extraction but leaves are {value, source} objects

object · string · default: extraction.sources

Allowed value: "extraction.sources"