Measurement & Control for LLM Automations

Root Signals streamlines the evaluation of your LLM and agentic pipelines. We provide a holistic approach to GenAI measurability & observability with carefully-crafted ready-to-use evaluators based on cutting-edge LLM research as well as a framework for systematically adding your own custom evaluators.

With Root Signals you can develop your LLM application reliably, deploy them in confidence, and ensure optimal performance with continuous monitoring.

📦 Install

pip install root-signals

⚡ Quickstart

🔑 Get Your API Key

Sign up & create a key or generate a temporary key

Setup Option 1: Environment Variable

export ROOTSIGNALS_API_KEY=your-Root-API-key

Setup Option 2: .env File

echo ROOTSIGNALS_API_KEY=your-Root-API-key >> .env

Root Evaluators

from root import RootSignals

# Connect to the Root Signals API
client = RootSignals()

# Run a politeness evaluator
response = client.evaluators.Politeness(
    response="You can find the instructions from our Careers page."
)
print(response)
# {score=0.7, justification='The response is st...', execution_log_id=...}

Check the full list of Root evaluators from the Root evaluators documentation. You can also add your own evaluators.

📖 Documentation

Resource	Link
🐍 Python SDK	View Documentation
📘 Product Docs	View Documentation
📑 API Docs	View Documentation

Tutorial	Link
Quickstart
Tuning a Custom Judge
RAG Hallucination Detection with Root Judge

🌍 Community

💬 Welcome to our Discord Server! It's a great place to ask questions, get help, and discuss ideas.