Lightweight hallucination risk scoring for LLM outputs
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Project description
hallx
Lightweight hallucination-risk scoring for production LLM pipelines
What Is Hallx
Hallx is a practical guardrail layer that evaluates LLM responses before they are trusted in downstream systems.
It scores responses using:
schemavalidityconsistencyacross repeated generationsgroundingagainst provided context
It returns:
confidencerisk_levelissuesrecommendation
Quick Start
pip install hallx
from hallx import Hallx
checker = Hallx(profile="balanced")
result = checker.check(prompt="p", response="r", context=["c"])
print(result.confidence, result.risk_level, result.recommendation)
Workflow
Essential Links
Languages
Community
Project details
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file hallx-1.0.4.tar.gz.
File metadata
- Download URL: hallx-1.0.4.tar.gz
- Upload date:
- Size: 23.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2fc8197bf2111dd82a79f2b9bd1fa0f539e622ab228162a78c322d867e20f9d2
|
|
| MD5 |
8c8e7fdd98f77c1a5ae0fe57a2fb99bd
|
|
| BLAKE2b-256 |
3701b10f1539f83134e1996ce7ddf141180974ea742d637e3bd866d07dc82452
|
Provenance
The following attestation bundles were made for hallx-1.0.4.tar.gz:
Publisher:
release.yml on dhanushk-offl/hallx
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
hallx-1.0.4.tar.gz -
Subject digest:
2fc8197bf2111dd82a79f2b9bd1fa0f539e622ab228162a78c322d867e20f9d2 - Sigstore transparency entry: 1691334076
- Sigstore integration time:
-
Permalink:
dhanushk-offl/hallx@80556931550d7f385dade0e860beb2ca5ba25a43 -
Branch / Tag:
refs/tags/v1.0.4 - Owner: https://github.com/dhanushk-offl
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@80556931550d7f385dade0e860beb2ca5ba25a43 -
Trigger Event:
push
-
Statement type:
File details
Details for the file hallx-1.0.4-py3-none-any.whl.
File metadata
- Download URL: hallx-1.0.4-py3-none-any.whl
- Upload date:
- Size: 25.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bd1d674683e798325794eb2597ea7cd686fac1ca95bb28a720c7a08249739367
|
|
| MD5 |
228c8ec252f6aaa820044d34c3c10a66
|
|
| BLAKE2b-256 |
2869d966cdb5b40008d8acc97c454af293c1f81cab1c7c56f4d5c652ce75468c
|
Provenance
The following attestation bundles were made for hallx-1.0.4-py3-none-any.whl:
Publisher:
release.yml on dhanushk-offl/hallx
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
hallx-1.0.4-py3-none-any.whl -
Subject digest:
bd1d674683e798325794eb2597ea7cd686fac1ca95bb28a720c7a08249739367 - Sigstore transparency entry: 1691334110
- Sigstore integration time:
-
Permalink:
dhanushk-offl/hallx@80556931550d7f385dade0e860beb2ca5ba25a43 -
Branch / Tag:
refs/tags/v1.0.4 - Owner: https://github.com/dhanushk-offl
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@80556931550d7f385dade0e860beb2ca5ba25a43 -
Trigger Event:
push
-
Statement type:
