Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Arch is a sophisticated gateway designed to safeguard, monitor, and tailor AI agents through effortless API integration. Leveraging the power of Envoy Proxy, Arch ensures secure data management, intelligent request routing, comprehensive observability, and seamless connections to backend systems, all while remaining independent of business logic. Its out-of-process architecture supports a broad range of programming languages, facilitating rapid deployment and smooth upgrades. Crafted with specialized sub-billion parameter Large Language Models, Arch shines in crucial prompt-related functions, including function invocation for API customization, prompt safeguards to thwart harmful or manipulative prompts, and intent-drift detection to improve retrieval precision and response speed. By enhancing Envoy's cluster subsystem, Arch effectively manages upstream connections to Large Language Models, thus enabling robust AI application development. Additionally, it acts as an edge gateway for AI solutions, providing features like TLS termination, rate limiting, and prompt-driven routing. Overall, Arch represents an innovative approach to AI gateway technology, ensuring both security and adaptability in a rapidly evolving digital landscape.
Description
Llama Guard is a collaborative open-source safety model created by Meta AI aimed at improving the security of large language models during interactions with humans. It operates as a filtering mechanism for inputs and outputs, categorizing both prompts and replies based on potential safety risks such as toxicity, hate speech, and false information. With training on a meticulously selected dataset, Llama Guard's performance rivals or surpasses that of existing moderation frameworks, including OpenAI's Moderation API and ToxicChat. This model features an instruction-tuned framework that permits developers to tailor its classification system and output styles to cater to specific applications. As a component of Meta's extensive "Purple Llama" project, it integrates both proactive and reactive security measures to ensure the responsible use of generative AI technologies. The availability of the model weights in the public domain invites additional exploration and modifications to address the continually changing landscape of AI safety concerns, fostering innovation and collaboration in the field. This open-access approach not only enhances the community's ability to experiment but also promotes a shared commitment to ethical AI development.
API Access
Has API
API Access
Has API
Integrations
Llama
OpenAI
Amazon Web Services (AWS)
Envoy
Honeycomb
Jaeger
Mistral AI
OpenTelemetry
SigNoz
Integrations
Llama
OpenAI
Amazon Web Services (AWS)
Envoy
Honeycomb
Jaeger
Mistral AI
OpenTelemetry
SigNoz
Pricing Details
Free
Free Trial
Free Version
Pricing Details
No price information available.
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
Arch
Country
United States
Website
www.archgw.com
Vendor Details
Company Name
Meta
Founded
2004
Country
United States
Website
ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/