Create app.py

app.py

@@ -0,0 +1,123 @@
+import os
+import pdfplumber
+import re
+import gradio as gr
+from transformers import pipeline, AutoModelForQuestionAnswering, AutoTokenizer
+
+"""
+Extract the text from a section of a PDF file  between 'wanted_section' and 'next_section'.
+Parameters: 
+- path (str): The file path to the PDF file.
+- wanted_section (str): The section to start extracting text from.
+- next_section (str): The section to stop extracting text at.
+Returns:
+- text (str): The extracted text from the specified section range.
+"""
+
+
+def get_section(path, wanted_section, next_section):
+    print(wanted_section)
+
+    # Open the PDF file
+    doc = pdfplumber.open(BytesIO(path)) 
+    start_page = []
+    end_page = []
+
+    # Find the all the pages for the specified sections
+    for page in range(len(doc.pages)):
+        if len(doc.pages[page].search(wanted_section, return_chars=False, case=False)) > 0:
+            start_page.append(page)
+        if len(doc.pages[page].search(next_section, return_chars=False, case=False)) > 0:
+            end_page.append(page)
+
+    # Extract the text between the start and end page of the wanted section
+    text = []
+    for page_num in range(max(start_page), max(end_page)+1):
+        page = doc.pages[page_num]
+        text.append(page.extract_text())
+    text = " ".join(text)
+    final_text = text.replace("\n", " ")
+    return final_text
+
+
+def extract_between(big_string, start_string, end_string):
+    # Use a non-greedy match for content between start_string and end_string
+    pattern = re.escape(start_string) + '(.*?)' + re.escape(end_string)
+    match = re.search(pattern, big_string, re.DOTALL)
+
+    if match:
+        # Return the content without the start and end strings
+        return match.group(1)
+    else:
+        # Return None if the pattern is not found
+        return None
+
+def format_section1(section1_text):
+    result_section1_dict = {}
+
+    result_section1_dict['TOPIC'] = extract_between(section1_text, "Sektor", "EZ-Programm")
+    result_section1_dict['PROGRAM'] = extract_between(section1_text, "Sektor", "EZ-Programm")
+    result_section1_dict['PROJECT DESCRIPTION'] = extract_between(section1_text, "EZ-Programmziel", "Datum der letzten BE")
+    result_section1_dict['PROJECT NAME'] = extract_between(section1_text, "Modul", "Modulziel")
+    result_section1_dict['OBJECTIVE'] = extract_between(section1_text, "Modulziel", "Berichtszeitraum")
+    result_section1_dict['PROGRESS'] = extract_between(section1_text, "Zielerreichung des Moduls", "Massnahme im Zeitplan")
+    result_section1_dict['STATUS'] = extract_between(section1_text, "Massnahme im Zeitplan", "Risikoeinschätzung")
+    result_section1_dict['RECOMMENDATIONS'] = extract_between(section1_text, "Vorschläge zur Modulanpas-", "Voraussichtliche")
+
+    return result_section1_dict
+
+def answer_questions(text,language="de"):
+    # Initialize the zero-shot classification pipeline
+    model_name = "deepset/gelectra-large-germanquad"
+    model = AutoModelForQuestionAnswering.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+    # Initialize the QA pipeline
+    qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
+    questions = [
+        "Welches ist das Titel des Moduls?",
+        "Welches ist das Sektor oder das Kernthema?",
+        "Welches ist das Land?",
+        "Zu welchem Program oder EZ-Programm gehort das Projekt?"
+        #"Welche Durchführungsorganisation aus den 4 Varianten 'giz', 'kfw', 'ptb' und 'bgr' implementiert das Projekt?"
+        # "In dem Dokument was steht bei Sektor?",
+        # "In dem Dokument was steht von 'EZ-Programm' bis 'EZ-Programmziel'?",
+        # "In dem Dokument was steht bei EZ-Programmziel?",
+        # "In dem Dokument in dem Abschnitt '1. Kurzbeschreibung' was steht bei Modul?",
+        # "In dem Dokument was steht bei Zielerreichung des Moduls?",
+        # "In dem Dokument in dem Abschnitt '1. Kurzbeschreibung' was steht bei Maßnahme im Zeitplan?",
+        # "In dem Dokument was steht bei Vorschläge zur Modulanpassung?",
+        # "In dem Dokument in dem Abschnitt 'Anlage 1: Wirkungsmatrix des Moduls' was steht unter Laufzeit als erstes Datum?",
+        # "In dem Dokument in dem Abschnitt 'Anlage 1: Wirkungsmatrix des Moduls' was steht unter Laufzeit als zweites Datum?"
+    ]
+
+    # Iterate over each question and get answers
+    for question in questions:
+        result = qa_pipeline(question=question, context=text)
+        # print(f"Question: {question}")
+        # print(f"Answer: {result['answer']}\n")
+        answers_dict[question] = result['answer']
+    return answers_dict
+
+
+def process_pdf(path):
+    results_dict = {}
+    results_dict["1. Kurzbeschreibung"] = \
+        get_section(path, "1. Kurzbeschreibung", "2. Einordnung des Moduls")
+    answers = answer_questions(results_dict["1. Kurzbeschreibung"])
+    return result_section1_dict['TOPIC']
+
+def get_first_page_text(file_data):
+    doc = pdfplumber.open(BytesIO(file_data)) 
+    if len(doc.pages):
+        return doc.pages[0].extract_text()
+
+# Define the Gradio interface
+# iface = gr.Interface(fn=process_pdf, 
+iface = gr.Interface(fn=get_first_page_text, 
+                     inputs=gr.File(type="binary", label="Upload PDF"),
+                     outputs=gr.Textbox(label="Extracted Text"),
+                     title="PDF Text Extractor",
+                     description="Upload a PDF file to extract.")
+
+iface.launch()