Setup update (#124)

* style(makefile): 🎨 create dynamically generated help target and move phony to top of each target

    This aids in clear target expectations and keeping track of missing descriptions as Clear target was missing from help.

* style(lint): 🧱 configure black and isort in pyproject.toml

    This allows running black/isort in pre-commit or locally to use the same settings and user have the same experience.

* style(markdown): 🚨 add alt text to resolve updated markdownlint img rule

* style(black): 🚨 black format via version 24.2.0

.pre-commit-config.yaml

@@ -1,33 +1,35 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.6.0
     hooks:
       - id: check-yaml
       - id: end-of-file-fixer
       - id: trailing-whitespace
       - id: end-of-file-fixer
         types: [ python ]
-      - id: requirements-txt-fixer
 
-  - repo: https://github.com/psf/black
-    rev: 23.7.0
+  - repo: local
     hooks:
       - id: black
-        args: [ --line-length=100, --exclude="" ]
-
-  # this is not technically always safe but usually is
-  # use comments `# isort: off` and `# isort: on` to disable/re-enable isort
-  - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
-    hooks:
+        name: black
+        entry: black
+        language: system
+        pass_filenames: true
+        types: [ python ]
+      # this is not technically always safe but usually is
+      # use comments `# isort: off` and `# isort: on` to disable/re-enable isort
       - id: isort
-        args: [ --line-length=100, --profile=black ]
+        name: isort
+        entry: isort
+        language: system
+        pass_filenames: true
+        types: [ python ]
 
   # this is slightly dangerous because python imports have side effects
   # and this tool removes unused imports, which may be providing
   # necessary side effects for the code to run
   - repo: https://github.com/PyCQA/autoflake
-    rev: v2.2.0
+    rev: v2.3.1
     hooks:
       - id: autoflake
         args:
@@ -39,11 +41,11 @@ repos:
         exclude: "llm_guard/__init__.py"
 
   - repo: https://github.com/zricethezav/gitleaks
-    rev: v8.17.0
+    rev: v8.18.2
     hooks:
       - id: gitleaks
 
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.35.0
+    rev: v0.39.0
     hooks:
       - id: markdownlint

Makefile

@@ -1,41 +1,51 @@
-.PHONY: help lint test build docs-serve install-dev publish clean
+.DEFAULT_GOAL := help
 
-help:
-	@echo "Available commands:"
-	@echo "make lint                      - Check code with linters using pre-commit."
-	@echo "make test                      - Run unit tests using pytest."
-	@echo "make build                     - Build the package for PyPI."
-	@echo "make docs-serve                - Serve documentation using mkdocs."
-	@echo "make install-dev               - Install development dependencies."
-	@echo "make publish                   - Publish to PyPI."
-
-install-dev:
+.PHONY: install-dev
+install-dev: ## Install development dependencies.
 	@echo "Installing development dependencies..."
 	@python -m pip install ".[dev]"
-	@python -m pre-commit install
+	@pre-commit install
 
-lint:
+.PHONY: lint
+lint: ## Check code with linters using pre-commit.
 	@echo "Running linters..."
 	@pre-commit run --all-files
 
-test:
+.PHONY: test
+test: ## Run unit tests using pytest.
 	@echo "Running tests..."
 	@pytest --exitfirst --verbose --failed-first --cov=.
 
-build:
+.PHONY: build
+build: ## Build the package for PyPI.
 	@echo "Building for PyPI..."
 	@python -m pip install --upgrade build
 	@python -m build
 
-publish:
+.PHONY: publish
+publish: ## Publish to PyPI.
 	@echo "Publishing to PyPI..."
 	@python -m pip install --upgrade twine
 	@python -m twine upload --repository llm-guard dist/*
 
-docs-serve:
+.PHONY: docs-serve
+docs-serve: ## Serve documentation using mkdocs.
 	@echo "Serving documentation..."
 	@mkdocs serve -a localhost:8085
 
-clean:
+.PHONY: clean
+clean: ## Clean and Remove build files and pytest cache.
 	@echo "Cleaning up..."
 	@rm -rf build dist .pytest_cache .egg-info llm_guard.egg-info
+
+.PHONY: help
+help: ## List all targets and help information.
+	@echo "Available commands:"
+	@grep --no-filename -E '^([a-z.A-Z_%-/]+:.*?)##' $(MAKEFILE_LIST) | sort | \
+		awk 'BEGIN {FS = ":.*?(## ?)"}; { \
+			if (length($$1) > 0) { \
+				printf "  \033[36m%-30s\033[0m %s\n", $$1, $$2; \
+			} else { \
+				printf "%s\n", $$2; \
+			} \
+		}'

README.md

@@ -12,7 +12,7 @@ stars](https://img.shields.io/github/stars/protectai/llm-guard.svg?style=social&
 [![Downloads](https://static.pepy.tech/badge/llm-guard)](https://pepy.tech/project/llm-guard)
 [![Downloads](https://static.pepy.tech/badge/llm-guard/month)](https://pepy.tech/project/llm-guard)
 
-<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="https://github.com/protectai/llm-guard/blob/main/docs/assets/join-our-slack-community.png?raw=true" width="200"></a>
+<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="https://github.com/protectai/llm-guard/blob/main/docs/assets/join-our-slack-community.png?raw=true" width="200" alt="Join Our Slack Community"></a>
 
 ## What is LLM Guard?
 
@@ -108,7 +108,7 @@ we would love to have you as part of our community.
 Join our Slack to give us feedback, connect with the maintainers and fellow users, ask questions,
 get help for package usage or contributions, or engage in discussions about LLM security!
 
-<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="https://github.com/protectai/llm-guard/blob/main/docs/assets/join-our-slack-community.png?raw=true" width="200"></a>
+<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="https://github.com/protectai/llm-guard/blob/main/docs/assets/join-our-slack-community.png?raw=true" width="200" alt="Join Our Slack Community"></a>
 
 ### Production Support
 

docs/index.md

@@ -4,7 +4,7 @@ LLM Guard by [Protect AI](https://protectai.com/llm-guard) is a comprehensive to
 
 [**Playground**](https://huggingface.co/spaces/ProtectAI/llm-guard-playground) | [**Changelog**](./changelog.md)
 
-<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="./assets/join-our-slack-community.png" width="200"></a>
+<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="./assets/join-our-slack-community.png" width="200" alt="Join Our Slack Community"></a>
 
 ## What is LLM Guard?
 
@@ -55,4 +55,4 @@ we would love to have you as part of our community.
 Join our Slack to give us feedback, connect with the maintainers and fellow users, ask questions,
 get help for package usage or contributions, or engage in discussions about LLM security!
 
-<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="./assets/join-our-slack-community.png" width="200"></a>
+<a href="https://join.slack.com/t/laiyerai/shared_invite/zt-28jv3ci39-sVxXrLs3rQdaN3mIl9IT~w"><img src="./assets/join-our-slack-community.png" width="200" alt="Join Our Slack Community"></a>

llm_guard/__init__.py

@@ -1,2 +1,3 @@
 """LLM Guard package"""
+
 from .evaluate import scan_output, scan_prompt

llm_guard/input_scanners/__init__.py

@@ -1,4 +1,5 @@
 """Input scanners init"""
+
 from .anonymize import Anonymize
 from .ban_code import BanCode
 from .ban_competitors import BanCompetitors

llm_guard/input_scanners/anonymize.py

@@ -318,9 +318,11 @@ def scan(self, prompt: str) -> (str, bool, float):
         )
 
         risk_score = round(
-            max(analyzer_result.score for analyzer_result in analyzer_results)
-            if analyzer_results
-            else 0.0,
+            (
+                max(analyzer_result.score for analyzer_result in analyzer_results)
+                if analyzer_results
+                else 0.0
+            ),
             2,
         )
         analyzer_results = self._remove_conflicts_and_get_text_manipulation_data(analyzer_results)

llm_guard/input_scanners/anonymize_helpers/transformers_recognizer.py

@@ -148,9 +148,9 @@ def _load_pipeline(
                 self.model.onnx_path,
                 export=False,
                 subfolder=self.model.onnx_subfolder,
-                provider="CUDAExecutionProvider"
-                if device().type == "cuda"
-                else "CPUExecutionProvider",
+                provider=(
+                    "CUDAExecutionProvider" if device().type == "cuda" else "CPUExecutionProvider"
+                ),
                 revision=self.model.onnx_revision,
                 file_name=self.model.onnx_filename,
                 use_io_binding=True if device().type == "cuda" else False,

llm_guard/input_scanners/secrets_plugins/adafruit.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Adafruit keys
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/adobe.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Adobe keys
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/age_secret_key.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Age secret keys
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/airtable_api_key.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Airtable API keys
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/algolia_api_key.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Algolia API keys
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/alibaba.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Alibaba secrets
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/asana.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Asana secrets
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/atlassian_api_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Atlassian API tokens
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/authress_access_key.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Authress Service Client Access Keys
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/beamer_api_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Beamer API tokens
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/bitbucket.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Bitbucket Client ID and Client Secret
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/bittrex.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Bittrex Access Key and Secret Key
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/clojars_api_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Clojars API tokens
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/codecov_access_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Codecov Access Token
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/coinbase_access_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Coinbase Access Token
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/confluent.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Confluent Access Token and Confluent Secret Key
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/contentful_api_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Contentful delivery API token.
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/databricks_api_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Databricks API token.
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/datadog_access_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Datadog Access Tokens.
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/defined_networking_api_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for Defined Networking API Tokens.
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/input_scanners/secrets_plugins/github_token.py

@@ -1,6 +1,7 @@
 """
 This plugin searches for GitHub tokens
 """
+
 import re
 
 from detect_secrets.plugins.base import RegexBasedDetector

llm_guard/output_scanners/__init__.py

@@ -1,4 +1,5 @@
 """LLM output scanners init"""
+
 from .ban_code import BanCode
 from .ban_competitors import BanCompetitors
 from .ban_substrings import BanSubstrings

llm_guard/output_scanners/relevance.py

@@ -83,9 +83,9 @@ def __init__(
                 subfolder=model.onnx_subfolder,
                 file_name=model.onnx_filename,
                 revision=model.onnx_revision,
-                provider="CUDAExecutionProvider"
-                if device().type == "cuda"
-                else "CPUExecutionProvider",
+                provider=(
+                    "CUDAExecutionProvider" if device().type == "cuda" else "CPUExecutionProvider"
+                ),
                 use_io_binding=True if device().type == "cuda" else False,
                 **model.kwargs,
             )