Custom Conversion

curl -X POST "${DOCLING_SERVICE_URL}/v1/convert/source/async" \
  -H "X-Api-Key: ${DOCLING_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "sources": [
      {
        "kind": "http",
        "url": "https://arxiv.org/pdf/2501.17887"
      }
    ],
    "options": {
      "to_formats": ["html"]
    }
  }'

from pathlib import Path
from docling.datamodel.service.options import ConvertDocumentsOptions
from docling.service_client import DoclingServiceClient
import os

SERVICE_URL = os.getenv("DOCLING_SERVICE_URL")
API_KEY = os.getenv("DOCLING_API_KEY")

with DoclingServiceClient(url=SERVICE_URL, api_key=API_KEY) as client:
    options = ConvertDocumentsOptions(
        to_formats=["html"],
    )
    result = client.convert(
        source=Path("path/to/doc.pdf"),
        options=options
    )
    
    print(result.document.export_to_markdown())

import json
import logging
import time
import os 
from pathlib import Path

from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
from docling.datamodel.accelerator_options import AcceleratorDevice, AcceleratorOptions
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
    OcrMacOptions,
    PdfBackend,
    PdfPipelineOptions,
    TableStructureOptions,
    TesseractCliOcrOptions,
    TesseractOcrOptions,
)
from docling.datamodel.service.options import ConvertDocumentsOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.service_client import DoclingServiceClient

_log = logging.getLogger(__name__)


def main():
    logging.basicConfig(level=logging.INFO)

    def create_pipeline_options(
        do_ocr: bool, do_table_structure: bool, do_cell_matching: bool
    ) -> PdfPipelineOptions:
        pipeline_options = PdfPipelineOptions()
        pipeline_options.do_ocr = do_ocr
        pipeline_options.do_table_structure = do_table_structure
        pipeline_options.table_structure_options = TableStructureOptions(
            do_cell_matching=do_cell_matching
        )
        return pipeline_options

    ###########################################################################

    # The sections below demo combinations of PdfPipelineOptions and backends.
    # Tip: Uncomment exactly one section at a time to compare outputs.

    # PyPdfium without EasyOCR
    # --------------------
    # pipeline_options = create_pipeline_options(do_ocr=False, do_table_structure=True, do_cell_matching=False)
    # backend = PyPdfiumDocumentBackend

    # PyPdfium with EasyOCR
    # -----------------
    # pipeline_options = create_pipeline_options(do_ocr=True, do_table_structure=True, do_cell_matching=True)
    # backend = PyPdfiumDocumentBackend

    # Docling Parse without EasyOCR
    # -------------------------
    # pipeline_options = create_pipeline_options(do_ocr=False, do_table_structure=True, do_cell_matching=True)
    # backend = None

    # Docling Parse with EasyOCR (default)
    # -------------------------------
    # Enables OCR and table structure with EasyOCR, using automatic device
    # selection via AcceleratorOptions.
    pipeline_options = create_pipeline_options(
        do_ocr=True, do_table_structure=True, do_cell_matching=True
    )
    pipeline_options.accelerator_options = AcceleratorOptions(
        num_threads=4, device=AcceleratorDevice.AUTO
    )
    backend = None

    # Docling Parse with EasyOCR (CPU only)
    # -------------------------------------
    # pipeline_options = create_pipeline_options(do_ocr=True, do_table_structure=True, do_cell_matching=True)
    # pipeline_options.ocr_options.use_gpu = False
    # backend = None

    # Docling Parse with Tesseract
    # ----------------------------
    # pipeline_options = create_pipeline_options(do_ocr=True, do_table_structure=True, do_cell_matching=True)
    # pipeline_options.ocr_options = TesseractOcrOptions()
    # backend = None

    # Docling Parse with Tesseract CLI
    # --------------------------------
    # pipeline_options = create_pipeline_options(do_ocr=True, do_table_structure=True, do_cell_matching=True)
    # pipeline_options.ocr_options = TesseractCliOcrOptions()
    # backend = None

    # Docling Parse with ocrmac (macOS only)
    # --------------------------------------
    # pipeline_options = create_pipeline_options(do_ocr=True, do_table_structure=True, do_cell_matching=True)
    # pipeline_options.ocr_options = OcrMacOptions()
    # backend = None

    ###########################################################################
    input_doc_path = "path/to/doc.pdf"

    start_time = time.time()

    SERVE_URL = os.getenv("DOCLING_SERVICE_URL")
    API_KEY = os.getenv("DOCLING_API_KEY")

    table_cell_matching = getattr(pipeline_options.table_structure_options, 'do_cell_matching', True) if pipeline_options.table_structure_options else True
    pdf_backend = PdfBackend.PYPDFIUM2 if backend == PyPdfiumDocumentBackend else PdfBackend.DOCLING_PARSE
    options = ConvertDocumentsOptions(
        do_ocr=pipeline_options.do_ocr,
        do_table_structure=pipeline_options.do_table_structure,
        table_cell_matching=table_cell_matching,
        pdf_backend=pdf_backend,
        )
    with DoclingServiceClient(url=SERVE_URL, api_key=API_KEY) as client:
        conv_result = client.convert(Path(input_doc_path), options=options)

    _log.info(f"Document converted in {time.time() - start_time:.2f} seconds.")

    # Export results
    output_dir = Path("scratch")
    output_dir.mkdir(parents=True, exist_ok=True)
    doc_filename = Path(input_doc_path).stem

    # Export Docling document JSON format:
    with (output_dir / f"{doc_filename}.json").open("w", encoding="utf-8") as fp:
        fp.write(json.dumps(conv_result.document.export_to_dict()))

    # Export Text format (plain text via Markdown export):
    with (output_dir / f"{doc_filename}.txt").open("w", encoding="utf-8") as fp:
        fp.write(conv_result.document.export_to_markdown(strict_text=True))

    # Export Markdown format:
    with (output_dir / f"{doc_filename}.md").open("w", encoding="utf-8") as fp:
        fp.write(conv_result.document.export_to_markdown())

    # Export Document Tags format:
    with (output_dir / f"{doc_filename}.doctags").open("w", encoding="utf-8") as fp:
        fp.write(conv_result.document.export_to_doctags())


if __name__ == "__main__":
    main()

import java.net.URI;

import ai.docling.serve.api.DoclingServeApi;
import ai.docling.serve.api.convert.request.ConvertDocumentRequest;
import ai.docling.serve.api.convert.request.options.ConvertDocumentOptions;
import ai.docling.serve.api.convert.request.options.ImageRefMode;
import ai.docling.serve.api.convert.request.options.OutputFormat;
import ai.docling.serve.api.convert.request.source.HttpSource;
import ai.docling.serve.api.convert.response.InBodyConvertDocumentResponse;

public class Main {
    public static void main(String[] args) {
        String serviceUrl = System.getenv("DOCLING_SERVICE_URL");
        String apiKey = System.getenv("DOCLING_API_KEY");

        DoclingServeApi client = DoclingServeApi.builder()
            .baseUrl(serviceUrl)
            .apiKey(apiKey)
            .build();

        ConvertDocumentRequest request = ConvertDocumentRequest.builder()
            .source(HttpSource.builder()
                .url(URI.create("https://arxiv.org/pdf/2501.17887"))
                .build())
            .options(ConvertDocumentOptions.builder()
                .toFormat(OutputFormat.HTML)
                .imageExportMode(ImageRefMode.EMBEDDED)
                .doOcr(true)
                .build())
            .build();

        InBodyConvertDocumentResponse response =
            (InBodyConvertDocumentResponse) client.convertSource(request);
        System.out.println(response.getDocument().getHtmlContent());
    }
}