Track the environmental impact of your use of AI !
The Scope3AI Python SDK provides an easy-to-use interface for interacting with Scope3AI's API.
It allow you to record, trace, and analyze the impact of interactions with a focus on sustainability metrics.
The package scope3ai
SDK is published on pypi. You can install it using pip
:
pip install scope3ai
We personally use uv
:
uv add scope3ai
Library/SDK | Text generation | TTS | STT | Image Generation | Translation | Multimodal input | Multimodal output |
---|---|---|---|---|---|---|---|
Anthropic | ✅ | ||||||
Cohere | ✅ | ||||||
OpenAI | ✅ | ✅ | ✅ | ✅ | ✅ | Images/Audio | |
Huggingface | ✅ | ✅ | ✅ | ✅ | ✅ | ||
LiteLLM | ✅ | Images/Audio | |||||
MistralAi | ✅ | Images |
Roadmap:
- Langchain
The SDK can be initialized with your API key and custom configurations.
from scope3ai import Scope3AI
scope3 = Scope3AI.init(
api_key="YOUR_API_KEY", # Replace "YOUR_API_KEY" with your actual key
api_url="https://api.scope3.ai/v1", # Optional: Specify the API URL
enable_debug_logging=False, # Enable debug logging (default: False)
sync_mode=False, # Enable synchronous mode when sending telemetry to the API (default: False)
)
You can also use environment variable to setup the SDK:
SCOPE3AI_API_KEY
: Your Scope3AI API keySCOPE3AI_API_URL
: The API endpoint URL. Default:https://api.scope3.ai/v1
SCOPE3AI_SYNC_MODE
: IfTrue
, every interaction will be send synchronously to the API, otherwise it will use a background worker. Default:False
from scope3ai import Scope3AI
scope3 = Scope3AI.init()
Within the context of a trace
, all interactions are recorded and you can query the impact of the trace.
As the interactions are captured and send to Scope3 AI for analysis, the impact is calculated and returned asynchronously.
This will automatically wait for all traces to be processed and return the impact.
with scope3.trace() as tracer:
# Perform your interactions
interact()
interact()
# Print the impact of the recorded trace
impact = tracer.impact()
print(f"Total Energy Wh: {impact.total_energy_wh}")
print(f"Total GCO2e: {impact.total_gco2e}")
print(f"Total MLH2O: {impact.total_mlh2o}")
For a single interaction, the response is augmented with a scope3ai
attribute that contains the
request
and impact
data. The impact data is calculated asynchronously so we need to wait
for the impact to be calculated and for the attribute to be ready.
client = OpenAI()
response = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello world"}],
stream=False,
)
response.scope3ai.wait_impact()
impact = response.scope3ai.impact
print(f"Total Energy Wh: {impact.total_energy_wh}")
print(f"Total GCO2e: {impact.total_gco2e}")
print(f"Total MLH2O: {impact.total_mlh2o}")
In synchronous mode, the SDK will include the impact data directly in the interaction response. This is useful when you want to get the impact data immediately after the interaction without waiting.
scope3.sync_mode = True
response = interact()
impact = response.scope3ai.impact
print(f"Total Energy Wh: {impact.total_energy_wh}")
print(f"Total GCO2e: {impact.total_gco2e}")
print(f"Total MLH2O: {impact.total_mlh2o}")
This project use conventional commits and semantic versioning.
Also:
- pre-commit for code formatting, linting and conventional commit checks
- uv for project and dependency management.
$ pre-commit install
$ pre-commit install --hook-type commit-msg
You can use UV_ENV_FILE
or --env-file
to specify the environment file to use.
$ export UV_ENV_FILE=.env
$ uv sync --all-extras --all-groups
$ uv run python -m examples.openai-sync-chat
The typesgen.py
script is derivated from the aiapi.yaml
.
This script will download the latest YAML file, patch it if necessary
and generate the typesgen.py
file.
$ uv run tools/sync-api.py