GPT PDF Summarisation Pipeline

from openai import OpenAI
from pypdf import PdfReader

client = OpenAI()
MAX_CHUNK = 3000  # chars per chunk

def extract_text(pdf_path: str) -> str:
    reader = PdfReader(pdf_path)
    return '\n'.join(page.extract_text() or '' for page in reader.pages)

def chunk_text(text: str, size: int = MAX_CHUNK) -> list[str]:
    return [text[i:i+size] for i in range(0, len(text), size)]

def summarise_chunk(chunk: str) -> str:
    resp = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role':'system','content':'Summarise this text concisely.'}, {'role':'user','content':chunk}],
        max_tokens=200,
    )
    return resp.choices[0].message.content

def summarise_pdf(pdf_path: str) -> str:
    text    = extract_text(pdf_path)
    chunks  = chunk_text(text)
    summaries = [summarise_chunk(c) for c in chunks]
    combined  = '\n'.join(summaries)
    return summarise_chunk(combined)  # Final reduce

print(summarise_pdf('report.pdf'))