All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
- Documentation moved to
mkdocs
- Benchmarks in the documentation
- Added documentation about adding more scanners
Makefile
with useful commands- Demo application using Streamlit deployed to HuggingFace Spaces
MaliciousURLs
scanner produced false positives when URLs are not extracted from the text
- Support of GPU inference
- Score of existing
Anonymize
patterns
URL
entity type fromAnonymize
scanner (it was producing false-positive results)
0.1.3 - 2023-09-02
- Lock
transformers
version to 4.32.0 becausespacy-transformers
require it - Update the roadmap based on the feedback from the community
- Updated
NoRefusal
scanner to use transformer to classify the output
- Jailbreak input scanner (it was doing the same as the prompt injection one)
0.1.2 - 2023-08-26
- Introduced new linters for markdown
0.1.1 - 2023-08-20
- Example integration with LangChain
- Flow picture instead of the logo
- Bump libraries
0.1.0 - 2023-08-12
- All prompt scanners: Introducing a risk score, where 0 - means no risk, 1 - means high risk
- All output scanners: Introducing a risk score, where 0 - means no risk, 1 - means high risk
- Anonymize prompt scanner: Using the transformer based Spacy model
en_core_web_trf
(reference) - Anonymize prompt scanner: Supporting faker for applicable entities instead of placeholder (
use_faker
parameter) - Anonymize prompt scanner: Remove all patterns for secrets detection, use Secrets prompt scanner instead.
- Jailbreak prompt scanner: Updated dataset with more examples, removed duplicates
- Anonymize prompt scanner: Removed
FILE_EXTENSION
entity type
0.0.3 - 2023-08-10
- Dependabot support
- CodeQL support
- More pre-commit hooks to improve linters
- Locked libraries in
requirements.txt
- Logo link in README
0.0.2 - 2023-08-07
- Fixed missing
.json
files in the package
0.0.1 - 2023-08-07
- Project structure
- Documentation
- Github Actions pipeline
- Prompt scanners with tests:
- Output scanners with tests: