Requester upload PDF bundle
       ↓
PyMuPDF split by keyword (< 1 second)
       ↓
Docling extract per logical document (CPU, ~6s/scanned page)
       ↓
Structured JSON/Markdown per document type
       ↓
AI Agent (OpenAI) for business logic verification
       ↓
Recommendation → Human validation

import fitz # PyMuPDF

DOCUMENT_MARKERS = {
    "INVOICE": "invoice",
    "FAKTUR": "invoice",
    "KWITANSI": "kwitansi",
    "GOODS RECEIPT": "goods_receipt",
    "BAST": "bast",
    "BERITA ACARA": "bast",
    "FAKTUR PAJAK": "faktur_pajak",
    "SPP": "spp",
    "SURAT PERINTAH": "spp",
}

def split_bundle(pdf_path: str) -> list[dict]:
    doc = fitz.open(pdf_path)
    segments = []
    current = {"type": "unknown", "start": 0}

    for page_num in range(len(doc)):
        text = doc[page_num].get_text().upper()
        for marker, doc_type in DOCUMENT_MARKERS.items():
            if marker in text and (page_num == 0 or doc_type != current["type"]):
                if page_num > current["start"]:
                    current["end"] = page_num - 1
                    segments.append(current)
                current = {"type": doc_type, "start": page_num}
                break

    current["end"] = len(doc) - 1
    segments.append(current)
    doc.close()
    return segments

import os
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.datamodel.pipeline_options import (
    PdfPipelineOptions, RapidOcrOptions,
    TableStructureOptions, TableFormerMode,
)
from docling.datamodel.base_models import InputFormat

os.environ["OMP_NUM_THREADS"] = "4"

def create_converter():
    pipeline_options = PdfPipelineOptions(
        do_ocr=True,
        ocr_options=RapidOcrOptions(), # CPU-friendly, ~6s/page
        images_scale=2.0, # Higher resolution for numeric accuracy
        do_table_structure=True,
        table_structure_options=TableStructureOptions(
            mode=TableFormerMode.ACCURATE,
            do_cell_matching=False, # Important for scanned pages
        ),
        generate_page_images=False,
        generate_picture_images=False,
        do_code_enrichment=False,
        do_formula_enrichment=False,
    )
    return DocumentConverter(
        format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)}
    )

def process_bundle(pdf_path: str) -> dict:
    converter = create_converter()
    segments = split_bundle(pdf_path)
    extracted = {}

    for seg in segments:
        page_range = (seg["start"] + 1, seg["end"] + 1)
        result = converter.convert(pdf_path, page_range=page_range)
        doc = result.document

        entry = {
            "markdown": doc.export_to_markdown(traverse_pictures=True),
            "tables": [table.export_to_dataframe(doc=doc) for table in doc.tables],
            "json": doc.export_to_dict(),
        }

        extracted.setdefault(seg["type"], []).append(entry)

    return extracted

# Output example:
# {
# "invoice": [{"markdown": "...", "tables": [...]}],
# "kwitansi": [{"markdown": "...", "tables": [...]}],
# "faktur_pajak": [{"markdown": "...", "tables": [...]}],
# }