From 8635555243ddc8c5548af3ddded7ad5a36d642ad Mon Sep 17 00:00:00 2001 From: Salman Paracha Date: Wed, 19 Mar 2025 13:48:30 -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 37f35173..71fb873b 100644 --- a/README.md +++ b/README.md @@ -39,11 +39,11 @@ And you think to youself, can't I move faster by focusing on higher-level object **Core Features**: - `Agent Routing`. Engineered with purpose-built [LLMs](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) for blazng fast (<100ms) routing and hand-off decisions to downstream agents. - - **Blazing Fast ⚡ Function Calling**: For common agentic scenarios, expose tools as APIs and let Arch detect, clarify and convert prompts to structured APIs - - **Prompt [Guardrails](https://huggingface.co/collections/katanemo/arch-guard-6702bdc08b889e4bce8f446d)**: Centralizes guardrails to prevent jailbreak attempts and harmful outcomes, and ensure safe user interactions without writing a single line of code. - - **Unified Access to (any) LLM**: Arch centralizes calls to LLMs used by your applications, offering smart retries, automatic cutover, and resilient upstream connections for continuous availability. - - **Rich Observability**: Arch uses the W3C Trace Context standard to enable complete request tracing across applications, ensuring compatibility with observability tools, and provides metrics to monitor latency, token usage, and error rates, helping optimize AI application performance. - - **Built on [Envoy](https://envoyproxy.io)**: Arch runs alongside application servers as a separate containerized process, and builds on top of Envoy's proven HTTP management and scalability features to handle ingress and egress traffic related to prompts and LLMs. + - `Blazing Fast ⚡ Function Calling`: For common agentic scenarios, expose tools as APIs and let Arch detect, clarify and convert prompts to structured APIs + - `Prompt [Guardrails](https://huggingface.co/collections/katanemo/arch-guard-6702bdc08b889e4bce8f446d)`: Centralizes guardrails to prevent jailbreak attempts and harmful outcomes, and ensure safe user interactions without writing a single line of code. + - `Unified Access to (any) LLM`: Arch centralizes calls to LLMs used by your applications, offering smart retries, automatic cutover, and resilient upstream connections for continuous availability. + - `Rich Observability`: Arch uses the W3C Trace Context standard to enable complete request tracing across applications, ensuring compatibility with observability tools, and provides metrics to monitor latency, token usage, and error rates, helping optimize AI application performance. + - `Built on [Envoy](https://envoyproxy.io)`: Arch runs alongside application servers as a separate containerized process, and builds on top of Envoy's proven HTTP management and scalability features to handle ingress and egress traffic related to prompts and LLMs. **High-Level Sequence Diagram**: ![alt text](docs/source/_static/img/arch_network_diagram_high_level.png)