Cleanlab Codex - Closing the AI Knowledge Gap
Codex enables you to seamlessly leverage knowledge from Subject Matter Experts (SMEs) to improve your RAG/Agentic applications.
The cleanlab-codex library provides a simple interface to integrate Codex's capabilities into your RAG application.
See immediate impact with just a few lines of code!
Demo
Install the package:
pip install cleanlab-codex
Integrating Codex into your RAG application is as simple as:
from cleanlab_codex import Project
project = Project.from_access_key(...)
# Your existing RAG code:
context = rag_retrieve_context(user_query)
prompt = rag_form_prompt(user_query, retrieved_context)
response = rag_generate_response(prompt)
# Detect bad responses and remediate with Cleanlab
results = project.validate(query=query, context=context, response=response,
messages=[..., prompt])
final_response = (
results["expert_answer"] # Codex's answer
if results["expert_answer"] is not None
else response # Your RAG system's initial response
)
Why Codex?
- Detect Knowledge Gaps and Hallucinations: Codex identifies knowledge gaps and incorrect/untrustworthy responses in your AI application, to help you know which questions require expert input.
- Save SME time: Codex ensures that SMEs see the most critical knowledge gaps first.
- Easy Integration: Integrate Codex into any RAG/Agentic application with just a few lines of code.
- Immediate Impact: SME answers instantly improve your AI, without any additional Engineering/technical work.
Documentation
Comprehensive documentation along with tutorials and examples can be found here.
License
cleanlab-codex is distributed under the terms of the MIT license.
3 maintainers
Release files for cleanlab-codex 1.0.35
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| cleanlab_codex-1.0.35.tar.gz | 35.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| cleanlab_codex-1.0.35-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 68.1 kB
Release files / cleanlab_codex-1.0.35.tar.gz
| Download URL | cleanlab_codex-1.0.35.tar.gz |
|---|---|
| Size | 35.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c8d7163def118c5d8c0fd0006cc04d79d8f9aa2f44e41f6013671a4fcba0f7e6
|
|
BLAKE2b-256 checksum How to use checksums |
acf57ef66b6f2c91994cad824622ec000a7d5f467dfac49a875eded0da5f6809
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 19, 2025.
Transparency logRelease files / cleanlab_codex-1.0.35-py3-none-any.whl
| Download URL | cleanlab_codex-1.0.35-py3-none-any.whl |
|---|---|
| Size | 32.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5ccc6e623711b7a9a22d88c3dda6de6c5011146035f2da96121903c214a46ea7
|
|
BLAKE2b-256 checksum How to use checksums |
7018ce602b63157c947663e79203af88534e7736d3ba7d23b8e6dddc83223eb3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 19, 2025.
Transparency log
