Skip to main content

Combining File and Text Inputs

In this lesson, you'll learn how to send a file along with a user prompt to GPT-4.1 using the input_file and input_text types.

Prerequisites​

  • Have a file ready to upload (PDF, TXT, etc.)
  • Install the OpenAI SDK:
pip install openai

The Code​

from openai import OpenAI

client = OpenAI()

file = client.files.create(
    file=open("../files/Nexovious Project Info.pdf", "rb"),
    purpose="user_data"
)

response = client.responses.create(
    model="gpt-4.1",
    input=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_file",
                    "file_id": file.id
                },
                {
                    "type": "input_text",
                    "text": "Which services does Nexovious provide?"
                }
            ]
        }
    ]
)

print(response.output_text)

Explanation​

  • client.files.create(...): Uploads the file to OpenAI and returns a file ID.
  • type: input_file: Tells the model to look into the uploaded file.
  • type: input_text: Combines with a user question referencing the file.
  • response.output_text: Gives the assistant’s reply based on both sources.

Use Case​

Great for:

  • Asking questions about user-uploaded PDFs or documents
  • Creating assistants that summarize or search file content
  • Mixing file context with specific user queries