import gradio as gr

# Use a pipeline as a high-level helper
from transformers import pipeline

detector = pipeline("object-detection", model="hustvl/yolos-tiny")


# Use a pipeline as a high-level helper
from transformers import pipeline

food_classifier = pipeline("image-classification", model="facebook/deit-base-distilled-patch16-384")

def get_ingridients_list(image, score_threshold=.85):
  objects = detector(image)
  ingridients = []
  for obj in objects:
    cropped_image = image.crop((obj['box']['xmin'], obj['box']['ymin'], obj['box']['xmax'], obj['box']['ymax']))
    classes = food_classifier(cropped_image)
    best_match = max(classes, key=lambda x: x['score'])
    if best_match['score'] > score_threshold:
      ingridients.append(best_match['label'])
  return list(set(ingridients))

def get_ingridients(image):
  ingridients = get_ingridients_list(image)
  return ', '.join(ingridients)


from yandex_cloud_ml_sdk import YCloudML
import os

def get_reciepe(ingridients):
    messages = [
      {
        "role": "system",
        "text": "suggest a dish that can be prepared from the suggested ingredients",
      },
      {
        "role": "user",
        "text": ingridients,
      },
    ]

    sdk = YCloudML(
        folder_id="b1ghdrfjtfkvir55hc0m",
        auth=os.getenv('YC_APIKEY'),
    )

    result = (
        sdk.models.completions("yandexgpt-lite").configure(temperature=0.5).run(messages)
    )
    return str(result[0].text)

def get_answer(image):
  ingridients = get_ingridients(image)
  return get_reciepe(ingridients)

# Create a Gradio interface
iface = gr.Interface(
    fn=get_answer,  # Function to call
    inputs=gr.Image(label="Upload an image", type="pil"),  # Input type: Image
    outputs=gr.Markdown(label="Result"),  # Output type: Markdown
    title="cook.ai",
    description="Upload an image of a food ingredients"
)

# Launch the Gradio app
iface.launch()