Skip to main content

A Python package to generate detailed meal information from natural language descriptions using Generative AI

Project description

Meal Generator

PyPI version License: MIT

A Python package that uses a Generative AI model to parse natural language descriptions of meals and returns a detailed breakdown, including components, estimated weights, and a comprehensive nutrient profile.


Features

  • Natural Language Processing: Understands descriptions of meals like "a bowl of oatmeal with a sliced banana and a drizzle of honey."
  • Component Breakdown: Identifies individual ingredients within the meal.
  • Nutrient Analysis: Provides estimated nutritional information for each component, including calories, macronutrients, and common allergens.
  • Structured Output: Returns data as organized Python objects for easy integration into your applications.

Documentation

For a complete API reference and more detailed information, please visit the full documentation on Read The Docs.


Installation

Install the package using pip:

pip install meal-generator

You will also need to have a Google Gemini API key. You can set this as an environment variable:

export GEMINI_API_KEY="your-api-key"

Usage

Here is a quick example of how to use the MealGenerator:

from meal_generator import MealGenerator, MealGenerationError

# Initialize the generator (it will use the GEMINI_API_KEY environment variable)
generator = MealGenerator()

meal_description = "A grilled chicken salad with lettuce, tomatoes, cucumbers, and a light vinaigrette dressing."

try:
    # Generate the meal object
    meal = generator.generate_meal(meal_description)

    # Print the meal's aggregated nutrient profile
    print(f"Meal: {meal.name}")
    print(f"Description: {meal.description}")
    print("\n--- Aggregated Nutrients ---")
    print(meal.nutrient_profile)

    # Print details for each component
    print("\n--- Meal Components ---")
    for component in meal.component_list:
        print(f"- {component.name} ({component.quantity}): {component.total_weight}g")
        print(f"  {component.nutrient_profile}")

except MealGenerationError as e:
    print(f"Error generating meal: {e}")
except ValueError as e:
    print(f"Input error: {e}")

Example Input & Output

Here is an example of the data generated from a specific natural language query.

Input String:

"large wrap with half a cup of rice, 100g of chilli, a tablespoon of soured cream"

Resulting meal Object Data:

The code would produce a meal object containing the following structured data:

{
  "meal": {
    "name": "Chilli Con Carne Wrap",
    "description": "A large wheat tortilla wrap filled with chilli con carne, white rice, and a tablespoon of soured cream.",
    "components": [
      {
        "name": "Large Wrap (Wheat Tortilla)",
        "brand": null,
        "quantity": "large wrap",
        "totalWeight": 70.0,
        "nutrientProfile": {
          "energy": 220.0,
          "fats": 5.0,
          "saturated_fats": 1.0,
          "carbohydrates": 38.0,
          "sugars": 1.0,
          "fibre": 2.0,
          "protein": 6.0,
          "salt": 0.8,
          "contains_dairy": false,
          "contains_high_dairy": false,
          "contains_gluten": true,
          "contains_high_gluten": true,
          "contains_histamines": false,
          "contains_high_histamines": false,
          "contains_sulphites": false,
          "contains_high_sulphites": false,
          "contains_salicylates": false,
          "contains_high_salicylates": false,
          "contains_capsaicin": false,
          "contains_high_capsaicin": false,
          "is_processed": true,
          "is_ultra_processed": true
        }
      },
      {
        "name": "Cooked White Rice",
        "brand": null,
        "quantity": "half a cup",
        "totalWeight": 95.0,
        "nutrientProfile": {
          "energy": 125.0,
          "fats": 0.3,
          "saturated_fats": 0.1,
          "carbohydrates": 28.0,
          "sugars": 0.0,
          "fibre": 0.3,
          "protein": 2.5,
          "salt": 0.0,
          "contains_dairy": false,
          "contains_high_dairy": false,
          "contains_gluten": false,
          "contains_high_gluten": false,
          "contains_histamines": false,
          "contains_high_histamines": false,
          "contains_sulphites": false,
          "contains_high_sulphites": false,
          "contains_salicylates": false,
          "contains_high_salicylates": false,
          "contains_capsaicin": false,
          "contains_high_capsaicin": false,
          "is_processed": false,
          "is_ultra_processed": false
        }
      },
      {
        "name": "Chilli (Con Carne/Stew)",
        "brand": null,
        "quantity": "100g",
        "totalWeight": 100.0,
        "nutrientProfile": {
          "energy": 130.0,
          "fats": 6.0,
          "saturated_fats": 2.5,
          "carbohydrates": 10.0,
          "sugars": 3.0,
          "fibre": 4.0,
          "protein": 12.0,
          "salt": 0.6,
          "contains_dairy": false,
          "contains_high_dairy": false,
          "contains_gluten": false,
          "contains_high_gluten": false,
          "contains_histamines": true,
          "contains_high_histamines": false,
          "contains_sulphites": false,
          "contains_high_sulphites": false,
          "contains_salicylates": true,
          "contains_high_salicylates": false,
          "contains_capsaicin": true,
          "contains_high_capsaicin": false,
          "is_processed": true,
          "is_ultra_processed": false
        }
      },
      {
        "name": "Soured Cream",
        "brand": null,
        "quantity": "a tablespoon",
        "totalWeight": 15.0,
        "nutrientProfile": {
          "energy": 35.0,
          "fats": 3.8,
          "saturated_fats": 2.2,
          "carbohydrates": 0.5,
          "sugars": 0.5,
          "fibre": 0.0,
          "protein": 0.5,
          "salt": 0.02,
          "contains_dairy": true,
          "contains_high_dairy": true,
          "contains_gluten": false,
          "contains_high_gluten": false,
          "contains_histamines": true,
          "contains_high_histamines": false,
          "contains_sulphites": false,
          "contains_high_sulphites": false,
          "contains_salicylates": false,
          "contains_high_salicylates": false,
          "contains_capsaicin": false,
          "contains_high_capsaicin": false,
          "is_processed": true,
          "is_ultra_processed": false
        }
      }
    ]
  }
}

Contributing

Contributions are welcome! Please feel free to submit a pull request or open an issue on the GitHub repository.


License

This project is licensed under the MIT License. See the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

meal_generator-1.5.2.tar.gz (18.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

meal_generator-1.5.2-py3-none-any.whl (14.3 kB view details)

Uploaded Python 3

File details

Details for the file meal_generator-1.5.2.tar.gz.

File metadata

  • Download URL: meal_generator-1.5.2.tar.gz
  • Upload date:
  • Size: 18.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for meal_generator-1.5.2.tar.gz
Algorithm Hash digest
SHA256 95c35e740a77541747c5f0875235dc76b7ef81ff08ab004fa3e795d14ef2f46b
MD5 51bd233e487232330587cf0aa6ecd5d3
BLAKE2b-256 64ae7b2c8cf4ae896e397677e1b735e8e78e655d445ce2422826de23330e0da3

See more details on using hashes here.

Provenance

The following attestation bundles were made for meal_generator-1.5.2.tar.gz:

Publisher: publish-to-pypi.yml on TomMcKenna1/meal-generator

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file meal_generator-1.5.2-py3-none-any.whl.

File metadata

  • Download URL: meal_generator-1.5.2-py3-none-any.whl
  • Upload date:
  • Size: 14.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for meal_generator-1.5.2-py3-none-any.whl
Algorithm Hash digest
SHA256 810f4e18faaa1700e6b9026ebcc0c52183f253607d0a242f4baa46d32047c53f
MD5 04986b0d361693bb8dc6e8386cfad25b
BLAKE2b-256 ed8472c768b303e5e9257cea99d5d1febfcfa02b1a45207b5654b9b24e385e11

See more details on using hashes here.

Provenance

The following attestation bundles were made for meal_generator-1.5.2-py3-none-any.whl:

Publisher: publish-to-pypi.yml on TomMcKenna1/meal-generator

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page