tools/pdf_extractor.py

from smolagents import tool
import PyPDF2


@tool
def extract_text_from_pdf(pdf_path: str) -> str:
    """Extracts all text content from a PDF file.

    Args:
        pdf_path: The file path to the PDF file to extract text from (e.g., '/tmp/document.pdf')

    Returns:
        The extracted text content from the PDF file
    """
    try:
        extracted_text = []
        with open(pdf_path, 'rb') as pdf_file:
            pdf_reader = PyPDF2.PdfReader(pdf_file)
            num_pages = len(pdf_reader.pages)
            
            for page_num in range(num_pages):
                page = pdf_reader.pages[page_num]
                text = page.extract_text()
                extracted_text.append(f"--- Page {page_num + 1} ---\n{text}")

        return "\n\n".join(extracted_text)
    except FileNotFoundError:
        return f"Error: PDF file not found at path: {pdf_path}"
    except Exception as e:
        return f"Error extracting text from PDF: {str(e)}"