Spaces:
Running
Running
| # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/04_openai_vision.ipynb. | |
| # %% auto 0 | |
| __all__ = ['SAMPLE_IMG_DIR', 'prompt1', 'extract_veg_ingredients', 'encode_image', 'format_image', 'get_gptv_completion'] | |
| # %% ../nbs/04_openai_vision.ipynb 3 | |
| import base64 | |
| import json | |
| import logging | |
| import os | |
| import statistics | |
| import time | |
| from functools import partial | |
| from glob import glob | |
| from logging.handlers import RotatingFileHandler | |
| from pathlib import Path | |
| import numpy as np | |
| import requests | |
| from PIL import Image | |
| from openai import OpenAI | |
| import constants | |
| # %% ../nbs/04_openai_vision.ipynb 7 | |
| SAMPLE_IMG_DIR = Path(f"{constants.ROOT_DIR}/assets/images/vegan_ingredients") | |
| # %% ../nbs/04_openai_vision.ipynb 8 | |
| def encode_image(image_path): | |
| with open(image_path, "rb") as image_file: | |
| return base64.b64encode(image_file.read()).decode("utf-8") | |
| # %% ../nbs/04_openai_vision.ipynb 9 | |
| # fmt: off | |
| def format_image( | |
| image: str, # Image file path | |
| size: int = 300 | |
| ): | |
| # fmt: on | |
| img = Image.open(image) | |
| width, height = img.size | |
| ratio = min(size / width, size / height) | |
| width_new, height_new = (round(width * ratio), round(height * ratio)) | |
| width_new = int(np.round(width_new / 64.0)) * 64 | |
| height_new = int(np.round(height_new / 64.0)) * 64 | |
| img = img.resize((width_new, height_new)) | |
| img = img.convert("RGB") | |
| return img | |
| # %% ../nbs/04_openai_vision.ipynb 17 | |
| # https://platform.openai.com/docs/guides/vision/low-or-high-fidelity-image-understanding | |
| def get_gptv_completion(prompt: str, img: str, detail="low"): | |
| headers = { | |
| "Content-Type": "application/json", | |
| "Authorization": f"Bearer {os.environ['OPENAI_API_KEY']}", | |
| } | |
| payload = { | |
| "model": "gpt-4o", | |
| "messages": [ | |
| { | |
| "role": "user", | |
| "content": [ | |
| {"type": "text", "text": prompt}, | |
| { | |
| "type": "image_url", | |
| "image_url": { | |
| "url": f"data:image/jpeg;base64,{encode_image(img)}", | |
| "detail": detail, | |
| }, | |
| }, | |
| ], | |
| } | |
| ], | |
| "max_tokens": 300, | |
| } | |
| response = requests.post( | |
| "https://api.openai.com/v1/chat/completions", headers=headers, json=payload | |
| ) | |
| return response.json()["choices"][0]["message"]["content"] | |
| # %% ../nbs/04_openai_vision.ipynb 27 | |
| prompt1 = "What vegan ingredients are in the image? Ouput as JSON list." | |
| # %% ../nbs/04_openai_vision.ipynb 34 | |
| extract_veg_ingredients = partial(get_gptv_completion, prompt1) | |