Update README.md (#125)

updated the Readme instructions as per latest architecture with CloudFront.

Author: sridevi1209

README.md

@@ -28,17 +28,17 @@ If you are unfamiliar with LiteLLM, it provides a consistent interface to access
 
 ## Architecture
 
-![Reference Architecture Diagram ECS EKS](./media/architecture.png)
+![Reference Architecture Diagram ECS EKS](./media/Gateway-Architecture-with-CloudFront.png)
 
 ### Architecture steps
 
-1. Tenants/Client applications access the LiteLLM gateway proxy API through [Amazon Route 53](https://aws.amazon.com/route53/) URL endpoint which is protected against common web exploits using [AWS Web Application Firewall (WAF)](https://aws.amazon.com/waf/).
-2. AWS WAF forwards requests to an [Application Load Balancer (ALB)](https://aws.amazon.com/elasticloadbalancing/application-load-balancer/) to automatically distribute incoming application traffic to [Amazon Elastic Container Service (ECS)](https://aws.amazon.com/ecs/) tasks or to [Amazon Elastic Kubernetes Service (EKS)](https://aws.amazon.com/eks/) pods (depending on selected container orchestration platform) running LiteLLM Generative AI gateway containers. An AWS TLS/SSL secures traffic to the load balancer using a certificate issued by [AWS Certificate Manager (ACM)](https://aws.amazon.com/certificate-manager/).
-3. Container images for API/middleware and LiteLLM applications are built during guidance deployment and pushed into the the [Amazon Elastic Container registry (ECR)](http://aws.amazon.com/ecr/). They are used for deployment to Amazon ECS Fargate or Amazon EKS clusters that run these applications as containers in ECS tasks or EKS pods, respectively. LiteLLM provides a unified application interface for configuration and interacting with LLM providers. The API/middleware also integrates natively with [Amazon Bedrock](https://aws.amazon.com/bedrock/) to enable features not supported by [LiteLLM OSS project](https://docs.litellm.ai/).
-4. Amazon Bedrock provides model access, guardrails, prompt caching and routing to enhance the Generative AI gateway and additional controls for clients through a unified API. Access to required Bedrock models will need be properly [configured](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access-modify.html).
-5. External model providers providers (OpenAI, Anthropic, Vertex AI etc.) are configured using LiteLLM Admin UI to enable additional LLM model access via unified application interface. Pre-existing configurations of third-party providers are integrated into the Gateway using LiteLLM APIs.
-6. LiteLLM integrates with [Amazon ElastiCache (Redis OSS)](https://aws.amazon.com/elasticache/), [Amazon Relational Database Service (RDS)](https://aws.amazon.com/rds/), and [AWS Secrets Manager](https://aws.amazon.com/secrets-manager/) services. Amazon ElastiCache enables multi-tenant distribution of application settings and prompt caching. Amazon RDS enables persistence of virtual API keys and other configuration settings provided by LiteLLM. AWS Secrets Manager stores external model provider credentials and other sensitive settings securely.
-7. LiteLLM and the API/middleware store application logs in the dedicated [Amazon S3](https://aws.amazon.com/s3) storage bucket for troubleshooting and access analysis.
+1. Tenants and client applications access the LiteLLM gateway proxy API through the [Amazon Route 53](https://aws.amazon.com/route53/) URL endpoint or [Amazon CloudFront](https://aws.amazon.com/cloudfront/) distribution, which is protected against common web exploits and bots using [AWS Web Application Firewall (WAF)](https://aws.amazon.com/waf/).
+2. AWS WAF forwards requests to [Application Load Balancer (ALB)](https://aws.amazon.com/elasticloadbalancing/application-load-balancer/)to automatically distribute incoming application traffic to [Amazon Elastic Container Service (ECS)](https://aws.amazon.com/ecs/) tasks or [Amazon Elastic Kubernetes Service (EKS)](https://aws.amazon.com/eks/) pods running generative AI gateway containers. TLS/SSL encryption secures traffic using a certificate issued by [AWS Certificate Manager (ACM)](https://aws.amazon.com/certificate-manager/).
+3. Container images for API/middleware and LiteLLM applications are built during guidance deployment and pushed to [Amazon Elastic Container registry (ECR)](http://aws.amazon.com/ecr/). They are used for deployment to Amazon ECS on AWS Fargate or Amazon EKS clusters that run these applications as containers in ECS tasks or EKS pods, respectively. LiteLLM provides a unified application interface for configuration and interacting with LLM providers. The API/middleware integrates natively with [Amazon Bedrock](https://aws.amazon.com/bedrock/) to enable features not supported by the [LiteLLM Open source project](https://docs.litellm.ai/).
+4. Models hosted on [Amazon Bedrock](https://aws.amazon.com/bedrock/) and [Amazon Nova](https://aws.amazon.com/ai/generative-ai/nova/) provide model access, guardrails, prompt caching, and routing to enhance the AI gateway and additional controls for clients through a unified API. [Access to required Amazon Bedrock models](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access-modify.html) must be properly configured. 
+5. External model providers (such as OpenAI, Anthropic, or Vertex AI) are configured using the LiteLLM Admin UI to enable additional model access through LiteLLM’s unified application interface. Integrate pre-existing configurations of third-party providers into the gateway using LiteLLM APIs. 
+6. LiteLLM integrates with [Amazon ElastiCache (Redis OSS)](https://aws.amazon.com/elasticache/), [Amazon Relational Database Service (RDS)](https://aws.amazon.com/rds/), and [AWS Secrets Manager](https://aws.amazon.com/secrets-manager/) services. Amazon ElastiCache enables multi-tenant distribution of application settings and prompt caching. Amazon RDS enables persistence of virtual API keys and other configuration settings provided by LiteLLM. Secrets Manager stores external model provider credentials and other sensitive settings securely.
+7. LiteLLM and the API/middleware store application sends logs to the dedicated [Amazon S3](https://aws.amazon.com/s3) storage bucket for troubleshooting and access analysis. 
 
 ## Distribution Options