A document loader for loading data from PDFs.

Example

const loader = new WebPDFLoader(new Blob());
const docs = await loader.load();
console.log({ docs });

Hierarchy (view full)

Constructors

  • Parameters

    • blob: Blob
    • __namedParameters: {
          parsedItemSeparator: undefined | string;
          pdfjs: undefined | (() => Promise<{
              getDocument: {
                  (src): PDFDocumentLoadingTask;
                  (src): PDFDocumentLoadingTask;
              };
              version: string;
          }>);
          splitPages: undefined | boolean;
      } = {}
      • parsedItemSeparator: undefined | string
      • pdfjs: undefined | (() => Promise<{
            getDocument: {
                (src): PDFDocumentLoadingTask;
                (src): PDFDocumentLoadingTask;
            };
            version: string;
        }>)
      • splitPages: undefined | boolean

    Returns WebPDFLoader

Properties

blob: Blob
parsedItemSeparator: string
splitPages: boolean = true

Methods

  • Loads the documents and splits them using a specified text splitter.

    Parameters

    • splitter: TextSplitter = ...

    Returns Promise<Document[]>

    A Promise that resolves with an array of Document instances, each split according to the provided TextSplitter.

Generated using TypeDoc