piedpiper-sdk 0.2.0

Python SDK for Pied Piper multimodal compression

Pied Piper Python SDK

Pied Piper is a lightweight Python SDK for the Pied Piper multimodal compression service.

Install

python -m pip install -e app/packaging

Configure

Set your API key:

export PIED_PIPER_API_KEY="your-shared-api-key"

The SDK defaults to the production Pied Piper service URL. PIED_PIPER_BASE_URL is only needed if you want to override that for local development or a non-production deployment.

Quickstart

import pied_piper

result = pied_piper.compress("Long inline text to compress", fidelity=0.33)
print(result.status)
print(result.text)

Mixed inputs

from pathlib import Path

from pied_piper import Client

client = Client()
result = client.compress(
    [
        "inline text",
        Path("paper.pdf"),
        Path("diagram.png"),
        Path("demo.mp4"),
    ],
    fidelity=0.55,
)

Current behavior:

• text is extracted and compressed remotely
• images are accepted as passthrough items
• video inputs return an inline MP4 artifact on item.output_file

video_item = next(item for item in result.items if item.modality == "video")
video_bytes = video_item.output_file.as_bytes()