Multimodal data

from datasets import Dataset

ingredients = Dataset.from_list([
    {
        "spice_level": "very spicy",
        "image_url": "https://cdn.tasteatlas.com//images/ingredients/fcee541cd2354ed8b68b50d1aa1acad8.jpeg",
    },
    {
        "spice_level": "not so spicy",
        "image_url": "https://cdn.tasteatlas.com//images/dishes/da5fd425608f48b09555f5257a8d3a86.jpg",
    },
])

from bespokelabs import curator


class RecipeGenerator(curator.LLM):
    """Generate a recipe from a photo of ingredients."""

    def prompt(self, input: dict):
        text = f"Create me a {input['spice_level']} recipe from the ingredients image."
        return text, curator.types.Image(url=input["image_url"])

    def parse(self, input: dict, response: str) -> dict:
        return {"recipe": response}

recipe_generator = RecipeGenerator(model_name="gpt-4o-mini", backend="openai")

recipes = recipe_generator(ingredients)
print(recipes.dataset.to_pandas())