PDF analysis

PDF Analysis

Multimodal models can process and analyze PDF documents for summarization, data extraction, or question answering. Replace YOUR_VISION_MODEL_ID with a model ID that the current catalog marks as supporting PDF or file input:

python
import base64from openai import OpenAI def encode_pdf_to_base64(pdf_path):    with open(pdf_path, "rb") as pdf_file:        return base64.b64encode(pdf_file.read()).decode("utf-8") client = OpenAI(    base_url="https://api.livrouter.com/v1",    api_key="your-api-key") pdf_path = "document.pdf"base64_pdf = encode_pdf_to_base64(pdf_path)data_url = f"data:application/pdf;base64,{base64_pdf}" response = client.responses.create(    model="YOUR_VISION_MODEL_ID",    input=[{        "role": "user",        "content": [            {"type": "input_text", "text": "What is this document about?"},            {                "type": "input_file",                "file": {                    "filename": "document.pdf",                    "file_data": data_url                }            },        ],    }],) print(response.output_text)