SCDL-RAG Python SDK

Detect and fix RAG hallucinations.

Install

pip install scdl-rag

Usage

from scdl_rag import Client

client = Client(api_key="sk_live_...")

result = client.detect(
    question="What is RL?",
    answer="nodes called neurons",
    documents=[{"id": "doc1", "content": "RL is about..."}],
)

if result.hallucination_detected:
    print(f"Hallucination found: {result.explanation}")
else:
    print(f"Coherent (score: {result.mu_score})")

API

See https://api.scdl-rag.com/docs for full API reference.

Metadata

Release files for scdl-rag 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for scdl-rag 1.0.0
File	Size	Uploaded	Provenance	Actions
scdl_rag-1.0.0.tar.gz	2.9 kB	Jun 20, 2026	Without provenance	Details for scdl_rag-1.0.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for scdl-rag 1.0.0
File	Interpreter	ABI	Platform	Actions Reset
scdl_rag-1.0.0-py3-none-any.whl 3.0 kB Jun 20, 2026 Without provenance	Python 3	none	any	Details for scdl_rag-1.0.0-py3-none-any.whl

Total release size: 5.9 kB

Release files / scdl_rag-1.0.0.tar.gz

Download URL	scdl_rag-1.0.0.tar.gz
Size	2.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`23688fea8b2548b83c24aa0d2876a96651761d96a69a4a64ee5eb6868f70a9d3`
BLAKE2b-256 checksum How to use checksums	`c14072346e293be509c27204e2b577fd5f3fc0313aa6b57dc0733cd394a2ffdc`
Upload date	Jun 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.10.6`

Release files / scdl_rag-1.0.0-py3-none-any.whl

Download URL	scdl_rag-1.0.0-py3-none-any.whl
Size	3.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`bc769edadae28aaad2a79007b9030137c12722e63546d3a0c8b42e884e36535a`
BLAKE2b-256 checksum How to use checksums	`0166d4684706f3b0de26e84369a7cde1f870d3beb4c04e095cf558aab6d49632`
Upload date	Jun 20, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.10.6`

Security for scdl-rag 1.0.0

Report project as malware

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.

Release history Release notifications | RSS feed

This release

1.0.0 This release

Jun 20, 2026 2 release files No provenance

scdl-rag 1.0.0