How can I include PDF content in a single GPT-4 API request along with an image?

I'm working on a Python project that uses OpenAI's GPT-4 API to analyze screenshots and PDFs. My goal is to send both the screenshot and the PDF in a single request. Although the screenshot is processed correctly, the API ignores any content within the attached PDF.

I've tried encoding the PDF and adding it to the payload, both in the commented-out section using the file type and in the files field, but neither approach works. Below are the relevant parts of my code for reference:

PYTHONCopied
from PyPDF2 import PdfReader

PYTHONCopied
def encode_pdf_to_base64(pdf_path):
    """
    Encodes PDF to base64
    """
    try:
        with open(pdf_path, "rb") as pdf_file:
            return base64.b64encode(pdf_file.read()).decode('utf-8')
    except FileNotFoundError:
        print(f"Error: The file '{pdf_path}' was not found.")
        return None

PYTHONCopied
def analyze_with_pdf_and_screenshot(screenshot_path, pdf_path=None):
    """
    Analyzes the Screenshot with the help of the PDF
    """
    base64_image = encode_image(screenshot_path)
    base64_pdf = encode_pdf_to_base64(pdf_path) if pdf_path else None

    payload = {
        "model": "gpt-4o",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Analyze the given Screenshot with the help of the attached PDF and answer with its help"
                    },
                    # Also tried this one and it didnt work
                    #{
                    #    "type": "file",
                    #    "file": {
                    #        "name": os.path.basename(pdf_path),
                    #        "type": "application/pdf",
                    #        "content": base64_pdf
                    #    }
                    #},
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_image}"
                        }
                    },
                ],
                "files": [
                    {
                        "name": os.path.basename(pdf_path),
                        "type": "application/pdf",
                        "content": base64_pdf
                    }
                ]
            }
        ],
        "max_tokens": 2500
    }

    try:
        headers = {
            "Content-Type": "application/json",
            "Authorization": f"Bearer {api_key}"
        }
        response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
        response.raise_for_status()
        result = response.json()
        print("API-Answer:", json.dumps(result, indent=2))  
        return ""

    except requests.RequestException as e:
        print(f"Error analyzing file: {e}")
        return ""

If there's any guidance or workarounds (such as extracting the PDF text locally) to have the API process the PDF content, please advise.