Image input instead of PDF

[JiriKonecny-Granton]

Hello,
I would like to ask how to setup Doclink to accept only documents in the form of images (jpg., png. etc.)? I am using a custom OCR engine that I managed to implement in Doclink but Doclink requires documents only in PDF format.

I tried something like this:

input_doc = Path(f"path to image file")

ocr_options = GoogleVisionOcrOptions(
    credentials=GCP_SERVICE_ACCOUNT_CREDENTIALS,
    force_full_page_ocr=True,
)

pipeline_options = PipelineOptions(
    do_ocr=True,
    enable_remote_services=True,
    ocr_options=ocr_options
)

converter = DocumentConverter(
    format_options={
        InputFormat.IMAGE: ImageFormatOption(
            pipeline_options=pipeline_options,
        )
    }
)

result = converter.convert(input_doc)
doc = result.document
md = doc.export_to_markdown()
print(md)

Instead of PipilineOptions, I also tested the basic PdfPipelineOptions, unfortunetelly unsucesfully.

Or is it necessary to convert the images to PDF and then post them to Doclink?

Thanks for any help,
Sincerely,
Jiri Konecny

[mudassir206]

we have been using pdfpipelineoptions for image Format as well.the results are good enough