Deployment guide
AWS Lambda deployment
AWS Lambda is the most popular serverless compute platform. SuperCompress's tiny footprint and CPU-only operation make it ideal for Lambda deployment.
Lambda deployment guide
# Create a Lambda deployment package
pip install supercompress -t package/
cp lambda_function.py package/
cd package && zip -r ../deploy.zip .
Lambda function code
from supercompress import Compressor
comp = Compressor()
def lambda_handler(event, context):
body = json.loads(event["body"])
result = comp.compress(body["context"], body["query"])
return {
"statusCode": 200,
"body": json.dumps({
"compressed_text": result.compressed_text,
"original_tokens": result.original_tokens,
"kept_tokens": result.kept_tokens
})
}
Frequently asked questions
What Lambda configuration works best?
512MB memory, Python 3.11 runtime. Expect ~300ms cold start + ~60ms compression.
Can I use Lambda with API Gateway?
Yes. Deploy behind API Gateway for a RESTful compression endpoint.
Build with less context
Put compression in front of your next LLM call.
Use the hosted API or run SuperCompress locally. Keep the evidence, drop the token waste, and measure the savings before it reaches your model.