gpt_processing.py

import json
import os

from openai import OpenAI

openai_api_key = os.environ.get("OPENAI_API_KEY")
if openai_api_key:
    print("OPENAI_API_KEY found.")
    # print(openai_api_key)
else:
    print("OPENAI_API_KEY not found.")

client = OpenAI(
    api_key=openai_api_key
)


def gpt_process_image(input_image64, model_name, prompt, system_instruction="", temperatura=0.0):
    if input_image64 is None:
        return None, "No objects detected."
    # print (prompt)
    print("model_name:", model_name)
    print("Temperatura:", temperatura)

    response = client.chat.completions.create(
        model=model_name,
        messages=[
            {"role": "system", "content": f"{system_instruction}"},
            {"role": "user", "content": [
                {"type": "text", "text": f"{prompt}"},
                {"type": "image_url", "image_url": {
                    "url": f"data:image/jpg;base64,{input_image64}"}
                 }
            ]}
        ],
        temperature=temperatura,
        response_format={"type": "json_object"}
    )

    json_content = json.loads(response.choices[0].message.content)

    json_content['input_tokens'] = response.usage.prompt_tokens
    json_content['output_tokens'] = response.usage.completion_tokens
    json_content['total_tokens'] = response.usage.total_tokens

    print(json_content)

    return json.dumps(json_content, indent=4)