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 Root Signals API
client = RootSignals()
# Run any of our ready-made evaluators
result = client.evaluators.Politeness(
response="You can find the instructions from our Careers page."
)
# Example result:
# {
# "score": 0.7, --> a normalized score between [0, 1]
# "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 custom evaluators.
📖 Documentation
| Resource | Link |
|---|---|
| 🐍 Python SDK | View Documentation |
| 📘 Product Docs | View Documentation |
| 📑 API Docs | View Documentation |
| 🔌 MCP | View Repo |
| 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.
2 maintainers
Metadata
2 maintainers
Release files for root-signals 1.6.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| root_signals-1.6.5.tar.gz | 202.0 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| root_signals-1.6.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 711.6 kB
Release files / root_signals-1.6.5.tar.gz
| Download URL | root_signals-1.6.5.tar.gz |
|---|---|
| Size | 202.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7030c7f9d72bc5bee57f9e6adbe78c20acc16c19844d17fd425c11ef8af4c9d8
|
|
BLAKE2b-256 checksum How to use checksums |
dde2784617e5e6ad1f079c2e6c8a725533da38f5eaa206a87a6e8824573525d5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / root_signals-1.6.5-py3-none-any.whl
| Download URL | root_signals-1.6.5-py3-none-any.whl |
|---|---|
| Size | 509.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1d8caca6faaf90082f264c8390245e606f13ef501c8daf7eec0010a376477e39
|
|
BLAKE2b-256 checksum How to use checksums |
a9fa2b442efcf40ccb100e7ba7ec22926f139798be97edc6927f14df54c015b3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Security for root-signals 1.6.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
