Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Amazon Bedrock Guardrails is a flexible safety system aimed at improving the compliance and security of generative AI applications developed on the Amazon Bedrock platform. This system allows developers to set up tailored controls for safety, privacy, and accuracy across a range of foundation models, which encompasses models hosted on Amazon Bedrock, as well as those that have been fine-tuned or are self-hosted. By implementing Guardrails, developers can uniformly apply responsible AI practices by assessing user inputs and model outputs according to established policies. These policies encompass various measures, such as content filters to block harmful text and images, restrictions on specific topics, word filters aimed at excluding inappropriate terms, and sensitive information filters that help in redacting personally identifiable information. Furthermore, Guardrails include contextual grounding checks designed to identify and manage hallucinations in the responses generated by models, ensuring a more reliable interaction with AI systems. Overall, the implementation of these safeguards plays a crucial role in fostering trust and responsibility in AI development.
Description
Garak evaluates the potential failures of an LLM in undesirable ways, examining aspects such as hallucination, data leakage, prompt injection, misinformation, toxicity, jailbreaks, and various other vulnerabilities. This free tool is designed with an eagerness for development, continually seeking to enhance its functionalities for better application support. Operating as a command-line utility, Garak is compatible with both Linux and OSX systems; you can easily download it from PyPI and get started right away. The pip version of Garak receives regular updates, ensuring it remains current, while its specific dependencies recommend setting it up within its own Conda environment. To initiate a scan, Garak requires the model to be analyzed and, by default, will conduct all available probes on that model utilizing the suggested vulnerability detectors for each. During the scanning process, users will see a progress bar for every loaded probe, and upon completion, Garak will provide a detailed evaluation of each probe's findings across all detectors. This makes Garak not only a powerful tool for assessment but also a vital resource for researchers and developers aiming to enhance the safety and reliability of LLMs.
API Access
Has API
API Access
Has API
Pricing Details
No price information available.
Free Trial
Free Version
Pricing Details
Free
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Amazon
Founded
1994
Country
United States
Website
aws.amazon.com/bedrock/guardrails/
Vendor Details
Company Name
garak
Website
github.com/leondz/garak/
Product Features
Product Features
Vulnerability Scanners
Asset Discovery
Black Box Scanning
Compliance Monitoring
Continuous Monitoring
Defect Tracking
Interactive Scanning
Logging and Reporting
Network Mapping
Perimeter Scanning
Risk Analysis
Threat Intelligence
Web Inspection