app.py

import os
import gradio as gr
import requests
from transformers import pipeline

# Obtén el token desde las variables de entorno
hf_token = os.getenv("HF_TOKEN")

# Paso 1: Cargar el modelo de image-to-text
image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

# Paso 2: Función para llamar a la API de Qwen con el token seguro
def generate_recipe(description):
    url = "https://api-inference.huggingface.co/models/Qwen/Qwen2.5-72B-Instruct"
    headers = {"Authorization": f"Bearer {hf_token}"}
    
    # Añade el system input para definir el rol del modelo
    system_input = (
        "Act as a professional chef. Your task is to explain to a regular person "
        "how to cook a given dish, providing a step-by-step guide and a list of ingredients with exact quantities."
    )
    
    prompt = (
        f"{system_input} The dish is described as: {description}. "
        "Provide a list of ingredients followed by detailed cooking instructions."
    )
    
    payload = {
        "inputs": prompt,
        "parameters": {
            "max_length": 5000,   # Maximum length for the response
            "min_length": 2000     # Minimum length for the response
        }
    }

    response = requests.post(url, headers=headers, json=payload)
    response_data = response.json()
    
    # Manejo de posibles errores
    if "error" in response_data:
        return "Error generating recipe: " + response_data["error"]
    
    # Return only the generated text, without the input prompt
    return response_data[0]["generated_text"].replace(prompt, "").strip() if response_data else "No recipe generated."

# Paso 3: Define la función principal para procesar la imagen y generar la receta
def process_image(image):
    # Paso 3.1: Generar descripción del plato
    description = image_to_text(image)[0]['generated_text']
    
    # Paso 3.2: Generar receta a partir de la descripción
    recipe = generate_recipe(description)
    
    return description, recipe

# Paso 4: Crear la interfaz de Gradio
iface = gr.Interface(
    fn=process_image,
    inputs=gr.Image(type="pil"),
    outputs=["text", "text"],
    title="Recipe Generator from Dish Image",
    description="Upload an image of a dish to get a description, ingredient list, and step-by-step recipe."
)

# Lanzar la aplicación de Gradio
iface.launch()