Skip to content

🌱 EcoLogits tracks the energy consumption and environmental footprint of using generative AI models through APIs.

License

Notifications You must be signed in to change notification settings

cjean-pierre/ecologits

 
 

Repository files navigation

EcoLogits

🌱 EcoLogits tracks the energy consumption and environmental impacts of using generative AI models through APIs.

PyPI version PyPI downloads Python version Open In Colab DOI

EcoLogits was created and is actively maintained by the GenAI Impact non-profit.

Read the full documentation on ecologits.ai.

⚙️ Installation

pip install ecologits

For integration with a specific provider, use pip install ecologits[openai]. We are currently supporting the following providers: anthropic, cohere, google-generativeai, huggingface-hub, mistralai and openai. See the full list of providers.

🚀 Usage

from ecologits import EcoLogits
from openai import OpenAI

# Initialize EcoLogits
EcoLogits.init(providers=["openai"])

client = OpenAI(api_key="<OPENAI_API_KEY>")

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Tell me a funny joke!"}
    ]
)

# Get estimated environmental impacts of the inference
print(f"Energy consumption: {response.impacts.energy.value.mean} kWh")
print(f"GHG emissions: {response.impacts.gwp.value.mean} kgCO2eq")

See package documentation on EcoLogits

💚 Sponsors & benefactors

Resilio Terra Cognita Sopht Avanade Ministère de la Culture

💪 Contributing

To get started with setting up a development environment and making a contribution to EcoLogits, see Contributing to EcoLogits.

⚖️ License

This project is licensed under the terms of the Mozilla Public License Version 2.0 (MPL-2.0).

About

🌱 EcoLogits tracks the energy consumption and environmental footprint of using generative AI models through APIs.

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.8%
  • Makefile 0.2%