From 8f434b286ac8813320a55dbf78a1f06f7f712021 Mon Sep 17 00:00:00 2001 From: Salman Paracha Date: Wed, 19 Mar 2025 14:03:02 -0700 Subject: [PATCH] Update README.md --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 130899f6..abb88665 100644 --- a/README.md +++ b/README.md @@ -38,11 +38,11 @@ And you think to youself, can't I move faster by focusing on higher-level object **Core Features**: - - `🚦 Routing`. Engineered with purpose-built [LLMs](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) for fast (<100ms) agent routing and hand-off. - - `⚡ Function Calling`: Improve speed for common agentic scenarios by letting Arch clarfiy and convert prompts to tools/APIs. - - `⛨ Guardrails`: Centrally configure and prevent jailbreaks and harmful outcomes, and ensure safe user interactions. - - `🔗 Unified Access to LLMs`: Centralize access and traffic to LLMs with smart retries, automatic cutover for continuous availability. - - `🕵 Observability`: W3C Trace Context compatible request tracing, ensuring compatibility with popular observability tools, and provides metrics to monitor latency, token usage, and error rates. + - `🚦 Routing`. Engineered with purpose-built [LLMs](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) for fast (<100ms) agent routing and hand-off scenarios + - `⚡ Tools Use`: For common agentic scenarios let Arch instantly clarfiy and convert prompts to tools/API calls + - `⛨ Guardrails`: Centrally configure and prevent harmful outcomes and ensure safe user interactions + - `🔗 Access to LLMs`: Centralize access and traffic to LLMs with smart retries, automatic cutover for continuous availability + - `🕵 Observability`: W3C compatible request tracing, ensuring compatibility with popular observability tools, and provides metrics to monitor latency, token usage, and error rates - `🧱 Built on Envoy`: Arch runs alongside app servers as a containerized process, and builds on top of [Envoy's](https://envoyproxy.io) proven HTTP management and scalability features to handle ingress and egress traffic related to prompts and LLMs. **High-Level Sequence Diagram**: