123 lines
3.7 KiB
Python
123 lines
3.7 KiB
Python
import os
|
|
from openai import OpenAI
|
|
from tkinter import Tk, Label, Entry, Button, Text, filedialog
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
def list_files(directory):
|
|
files = []
|
|
for root, dirs, filenames in os.walk(directory):
|
|
# Versteckte Verzeichnisse ausschließen
|
|
dirs[:] = [d for d in dirs if not d.startswith('.')]
|
|
for filename in filenames:
|
|
if filename.endswith(('.docx', '.pdf')):
|
|
file_path = os.path.join(root, filename)
|
|
files.append(file_path)
|
|
return files
|
|
|
|
def compare_with_openai(content, search_query):
|
|
client = OpenAI(
|
|
api_key=os.environ.get("OPENAI_API_KEY"), # This is the default and can be omitted
|
|
)
|
|
try:
|
|
completion = client.chat.completions.create(
|
|
model="gpt-4o-mini",
|
|
messages=[
|
|
{
|
|
"role": "user",
|
|
"content": f"Vergleiche den folgenden Text mit der Suchanfrage '{search_query}':\n\n{content[:1000]}...\n\nIst der Text relevant für die Suchanfrage? Antworte mit 'Ja' oder 'Nein'."
|
|
},
|
|
],
|
|
max_tokens=5,
|
|
temperature=0.0,
|
|
)
|
|
answer = completion.choices[0].message.content.strip().lower()
|
|
return "ja" in answer
|
|
except Exception as e:
|
|
print(f"Fehler bei der OpenAI-API-Anfrage: {e}")
|
|
return False
|
|
|
|
def read_file_content(file_path):
|
|
if file_path.endswith('.docx'):
|
|
try:
|
|
import docx
|
|
doc = docx.Document(file_path)
|
|
fullText = []
|
|
for para in doc.paragraphs:
|
|
fullText.append(para.text)
|
|
return '\n'.join(fullText)
|
|
except Exception as e:
|
|
print(f"Fehler beim Lesen der DOCX-Datei {file_path}: {e}")
|
|
return ''
|
|
elif file_path.endswith('.pdf'):
|
|
try:
|
|
import PyPDF2
|
|
with open(file_path, 'rb') as pdf_file:
|
|
reader = PyPDF2.PdfReader(pdf_file)
|
|
text = ''
|
|
for page in reader.pages:
|
|
page_text = page.extract_text()
|
|
if page_text:
|
|
text += page_text
|
|
return text
|
|
except Exception as e:
|
|
print(f"Fehler beim Lesen der PDF-Datei {file_path}: {e}")
|
|
return ''
|
|
else:
|
|
return ''
|
|
|
|
def search_files():
|
|
search_query = query_entry.get()
|
|
if not search_query:
|
|
print("Keine Suchanfrage eingegeben.")
|
|
return
|
|
|
|
directory = filedialog.askdirectory()
|
|
if not directory:
|
|
print("Kein Verzeichnis ausgewählt.")
|
|
return
|
|
|
|
if not os.path.exists(directory):
|
|
print("Verzeichnis existiert nicht.")
|
|
return
|
|
|
|
files = list_files(directory)
|
|
found_files = []
|
|
|
|
for file_path in files:
|
|
file_content = read_file_content(file_path)
|
|
if file_content:
|
|
if compare_with_openai(file_content, search_query):
|
|
found_files.append(file_path)
|
|
|
|
result_text.delete(1.0, 'end')
|
|
if found_files:
|
|
result_text.insert('end', "Dateien relevant für die Suchanfrage:\n")
|
|
for file in found_files:
|
|
result_text.insert('end', file + '\n')
|
|
else:
|
|
result_text.insert('end', "Keine relevanten Dateien gefunden.")
|
|
|
|
# GUI erstellen
|
|
root = Tk()
|
|
root.title("Dateisuche mit OpenAI")
|
|
root.geometry("600x400")
|
|
|
|
# Eingabefeld für die Suchanfrage
|
|
query_label = Label(root, text="Suchanfrage:")
|
|
query_label.pack(pady=5)
|
|
query_entry = Entry(root, width=50)
|
|
query_entry.pack(pady=5)
|
|
|
|
# Suchbutton
|
|
search_button = Button(root, text="Suchen", command=search_files)
|
|
search_button.pack(pady=10)
|
|
|
|
# Ergebnisanzeige
|
|
result_text = Text(root, height=15, width=70)
|
|
result_text.pack(pady=10)
|
|
|
|
root.mainloop()
|