Class ExtractionClient

ExtractionClient provides methods for extracting structured data from document files using AI-driven processing.

Index

Methods

createPdf extractDataFromDocumentFile extractDataFromDocumentUrl

Methods

createPdf

createPdf(request: CreatePdfRequest): Promise<CreatePdfResponse>
Creates a PDF document from the provided request parameters.
Parameters
- request: CreatePdfRequest
  The request containing details for PDF creation, such as content or url.
Returns Promise<CreatePdfResponse>
A promise that resolves with the response containing the URL of the created PDF. The url will expire after 1 hour.

extractDataFromDocumentFile

extractDataFromDocumentFile(
file: File,
options?: ExtractDataFromDocumentOptions,
): Promise<ExtractDataFromDocumentResponse>
Extracts structured text data from a document file using AI.
Parameters
- file: File
  The document file to extract data from.
- Optionaloptions: ExtractDataFromDocumentOptions
  (Optional) Extraction options such as parsing hints or preprocessing flags.
Returns Promise<ExtractDataFromDocumentResponse>
A promise that resolves with the extracted document data.

extractDataFromDocumentUrl

extractDataFromDocumentUrl(
url: string,
options?: ExtractDataFromDocumentOptions,
): Promise<ExtractDataFromDocumentResponse>
Extracts structured text data from a document at a remote URL using AI.
Parameters
- url: string
  The URL of the document to extract data from.
- Optionaloptions: ExtractDataFromDocumentOptions
  (Optional) Extraction options such as parsing hints or preprocessing flags.
Returns Promise<ExtractDataFromDocumentResponse>
A promise that resolves with the extracted document data.