File size: 1,422 Bytes
823bf5e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
import openai
import os
from youtube_transcript_api import YouTubeTranscriptApi
from dotenv import load_dotenv
import fitz # PyMuPDF
load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
# ---------- PDF Summarization ----------
def extract_text_from_pdf(pdf_path):
text = ""
with fitz.open(pdf_path) as doc:
for page in doc:
text += page.get_text()
return text
# ---------- YouTube Summarization ----------
def get_youtube_transcript(video_url):
try:
video_id = video_url.split("v=")[-1].split("&")[0]
transcript = YouTubeTranscriptApi.get_transcript(video_id)
full_text = " ".join([entry["text"] for entry in transcript])
return full_text
except Exception as e:
return f"Error fetching transcript: {str(e)}"
# ---------- Summarization using GPT ----------
def summarize_text(text, engine="gpt-3.5-turbo"):
try:
response = openai.ChatCompletion.create(
model=engine,
messages=[
{"role": "system", "content": "You are a helpful summarization assistant."},
{"role": "user", "content": f"Summarize this:\n{text}"}
],
temperature=0.5,
max_tokens=500
)
summary = response['choices'][0]['message']['content']
return summary
except Exception as e:
return f"Error during summarization: {str(e)}"
|