$ pip3 install IPython
$ apt install qpdf

import deepdoctection as dd
from IPython.core.display import HTML
from matplotlib import pyplot as plt

analyzer = dd.get_dd_analyzer()  # instantiate the built-in analyzer similar to the Hugging Face space demo

df = analyzer.analyze(path = "/home/files/Rechnung_Muster.pdf")  # setting up pipeline
df.reset_state()                 # Trigger some initialization
doc = iter(df)
page = next(doc) 
image = page.viz()
plt.figure(figsize = (25,17))
plt.axis('off')
plt.imshow(image)
print(page.text)
# HTML(page.tables[0].html)
print(" Pages=")
print (len(page.tables))

FROM deepdoctection/deepdoctection:v.0.29.0

COPY .. .

RUN python3 -m pip install -r "requirements.txt"

CMD ["python3", "consumer.py"]

from deepdoctection import get_dd_analyzer
import pika
from pathlib import Path, PurePath
import os
import pickle


def parse_pdf(file_path):
    analyzer = get_dd_analyzer(config_overwrite=["USE_PDF_MINER=True", "USE_OCR=True"])
    df = analyzer.analyze(path=file_path)
    df.reset_state()
    doc = iter(df)
    page = next(doc)
    # with open('output.pkl', 'wb') as file:
    #     pickle.dump(chunks, file)
    chunks = [{"layout": chunk[5], "text": chunk[6]} for chunk in page.chunks]
    os.remove(file_path)
    return chunks