89 أسطر
2.9 KiB
Python
89 أسطر
2.9 KiB
Python
import os
|
|
import argparse
|
|
from openai import OpenAI
|
|
import PyPDF2
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
# Load the API key from the .env file
|
|
client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"), base_url="https://genai.ghaymah.systems")
|
|
|
|
def extract_text_from_pdf(pdf_path):
|
|
"""Extracts text from a PDF file."""
|
|
print(f"Extracting text from {pdf_path}...")
|
|
text = ""
|
|
try:
|
|
with open(pdf_path, "rb") as f:
|
|
reader = PyPDF2.PdfReader(f)
|
|
for page in reader.pages:
|
|
text += page.extract_text()
|
|
except FileNotFoundError:
|
|
print(f"Error: The file at {pdf_path} was not found.")
|
|
return None
|
|
except Exception as e:
|
|
print(f"An error occurred while reading the PDF: {e}")
|
|
return None
|
|
print("Text extraction complete.")
|
|
return text
|
|
|
|
def summarize_text(text, model="DeepSeek-V3-0324"):
|
|
"""Summarizes the text using a specified model."""
|
|
print(f"Summarizing text using {model}...")
|
|
try:
|
|
response = client.chat.completions.create(
|
|
model=model,
|
|
messages=[
|
|
{"role": "system", "content": "You are a helpful assistant that summarizes text."},
|
|
{"role": "user", "content": f"Please summarize the following text:\n\n{text}"}
|
|
]
|
|
)
|
|
return response.choices[0].message.content
|
|
except Exception as e:
|
|
print(f"An error occurred during summarization: {e}")
|
|
return None
|
|
|
|
def refine_summary(summary, model="DeepSeek-V3-0324"):
|
|
"""Refines the summary using another model."""
|
|
print(f"Refining summary using {model}...")
|
|
try:
|
|
response = client.chat.completions.create(
|
|
model=model,
|
|
messages=[
|
|
{"role": "system", "content": "You are a helpful assistant that refines and improves summaries."},
|
|
{"role": "user", "content": f"Please refine and improve the following summary:\n\n{summary}"}
|
|
]
|
|
)
|
|
return response.choices[0].message.content
|
|
except Exception as e:
|
|
print(f"An error occurred during summary refinement: {e}")
|
|
return None
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description="Summarize a PDF document using AI models.")
|
|
parser.add_argument("pdf_path", help="The path to the PDF file to summarize.")
|
|
args = parser.parse_args()
|
|
|
|
# 1. Extract text from the PDF
|
|
pdf_text = extract_text_from_pdf(args.pdf_path)
|
|
if pdf_text is None:
|
|
return
|
|
|
|
# 2. Create an initial summary
|
|
initial_summary = summarize_text(pdf_text)
|
|
if initial_summary is None:
|
|
return
|
|
|
|
# 3. Refine the summary
|
|
refined_summary = refine_summary(initial_summary)
|
|
if refined_summary is None:
|
|
return
|
|
|
|
print("\n--- Initial Summary ---")
|
|
print(initial_summary)
|
|
print("\n--- Refined Summary ---")
|
|
print(refined_summary)
|
|
|
|
if __name__ == "__main__":
|
|
main()
|