Update app.py

app.py

@@ -4,7 +4,7 @@ import requests
 from transformers import pipeline
 
 # Obtén el token desde las variables de entorno
-hf_token = os.getenv("HF_TOKEN")  # Esta línea solo debe aparecer una vez
+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")
@@ -15,7 +15,7 @@ def generate_recipe(description):
     headers = {"Authorization": f"Bearer {hf_token}"}
     payload = {
         "inputs": f"Give me a list of ingredients and a step-by-step recipe for a dish described as: {description}",
-        "parameters": {"max_length": 500}
+        "parameters": {"max_length": 4000}  # Increase max_length for a more detailed response
     }
 
     response = requests.post(url, headers=headers, json=payload)
@@ -24,7 +24,9 @@ def generate_recipe(description):
     # Manejo de posibles errores
     if "error" in response_data:
         return "Error generating recipe: " + response_data["error"]
-    return response_data[0]["generated_text"] if response_data else "No recipe generated."
+    
+    # Return only the generated text, without the input prompt
+    return response_data[0]["generated_text"].replace(payload["inputs"], "").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):