DocumentExtractionResult

Properties

Name

Type

Description

Notes

id

str

ID of the document extraction result

document_id

str

ID of the document that was processed. Null when the extraction was run on uploaded files without a collection.

[optional]

document_name

str

Name of the document that was processed

content

object

The extracted content. A JSON object when the extractor has an input JSON schema, since the schema constrains the output to an object. A JSON string holding the free-form text the LLM produced when the extractor has no input JSON schema.

error

str

Contains error in case extraction failed for this document. Otherwise empty.

Example

from h2ogpte.rest_sync.models.document_extraction_result import DocumentExtractionResult

# TODO update the JSON string below
json = "{}"
# create an instance of DocumentExtractionResult from a JSON string
document_extraction_result_instance = DocumentExtractionResult.from_json(json)
# print the JSON string representation of the object
print(DocumentExtractionResult.to_json())

# convert the object into a dict
document_extraction_result_dict = document_extraction_result_instance.to_dict()
# create an instance of DocumentExtractionResult from a dict
document_extraction_result_from_dict = DocumentExtractionResult.from_dict(document_extraction_result_dict)