AWS solutions documentation change
Summary
Minor grammatical and formatting changes (e.g., hyphen removal in 'user-defined', lowercase 'backing', service name abbreviations like 'SQS'). Added documentation for feedback collection workflow involving API Gateway, Lambda, and S3.
Security assessment
Changes are typo fixes, clarifications, or feature additions (e.g., feedback collection). No explicit security vulnerabilities, mitigations, or new security controls are introduced. Security-related components like Lambda authorizers and IAM policies are mentioned but not modified in a security context.
Diff
diff --git a/solutions/latest/generative-ai-application-builder-on-aws/architecture-overview.md b/solutions/latest/generative-ai-application-builder-on-aws/architecture-overview.md index 80f7fb89f..3f1ce6560 100644 --- a//solutions/latest/generative-ai-application-builder-on-aws/architecture-overview.md +++ b//solutions/latest/generative-ai-application-builder-on-aws/architecture-overview.md @@ -42 +42 @@ The high-level process flow for the solution components deployed with the AWS Cl - 3. [AWS WAF](https://aws.amazon.com/waf/) protects the APIs from attacks. This solution configures a set of rules called a web access control list (web ACL) that allows, blocks, or counts web requests based on configurable, user-defined web security rules and conditions. + 3. [AWS WAF](https://aws.amazon.com/waf/) protects the APIs from attacks. This solution configures a set of rules called a web access control list (web ACL) that allows, blocks, or counts web requests based on configurable, user defined web security rules and conditions. @@ -48 +48 @@ The high-level process flow for the solution components deployed with the AWS Cl - 6. [AWS Lambda](https://aws.amazon.com/lambda/) provides the business logic for the REST endpoints. This _Backing_ Lambda function manages and creates the necessary resources to perform use case deployments using [AWS CloudFormation](https://aws.amazon.com/cloudformation/). + 6. [AWS Lambda](https://aws.amazon.com/lambda/) provides the business logic for the REST endpoints. This _backing_ Lambda function manages and creates the necessary resources to perform use case deployments using [AWS CloudFormation](https://aws.amazon.com/cloudformation/). @@ -52 +52 @@ The high-level process flow for the solution components deployed with the AWS Cl - 8. When a new use case is created by the admin user, the _Backing_ Lambda function initiates a CloudFormation stack creation event for the requested use case. + 8. When a new use case is created by the admin user, the _backing_ Lambda function initiates a CloudFormation stack creation event for the requested use case. @@ -86 +86 @@ The high-level process flow for the solution components deployed with the AWS Cl - 3. The web UI leverages a WebSocket integration built using API Gateway. The API Gateway is backed by a custom [Lambda authorizer](https://docs.aws.amazon.com/apigateway/latest/developerguide/apigateway-use-lambda-authorizer.html) function, which returns the appropriate [AWS Identity and Access Management](https://aws.amazon.com/iam/) (IAM) policy based on the Amazon Cognito group to which the authenticating user belongs. The policy is stored in DynamoDB. + 3. The web UI leverages a WebSocket integration built using API Gateway. The API Gateway is backed by a custom [Lambda authorizer](https://docs.aws.amazon.com/apigateway/latest/developerguide/apigateway-use-lambda-authorizer.html) function, which returns the appropriate [AWS Identity and Access Management](https://aws.amazon.com/iam/) (IAM) policy based on the Amazon Cognito group the authenticating user belongs to. The policy is stored in DynamoDB. @@ -90 +90 @@ The high-level process flow for the solution components deployed with the AWS Cl - 5. Incoming requests from the business user are passed from API Gateway to an [Amazon Simple Queue Service](https://aws.amazon.com/sqs/) queue and then to the _LangChain Orchestrator_. The _LangChain Orchestrator_ is a collection of Lambda functions and layers that provide the business logic for fulfilling requests coming from the business user. The queue enables the asynchronous operation of the API Gateway to Lambda integration. The queue passes connection information to the Lambda functions which will then post results directly back to the API Gateway WebSocket connection to support long running inference calls. + 5. Incoming requests from the business user are passed from API Gateway to an [Amazon SQS queue](https://aws.amazon.com/sqs/) and then to the _LangChain Orchestrator_. The _LangChain Orchestrator_ is a collection of Lambda functions and layers that provide the business logic for fulfilling requests coming from the business user. The queue enables the asynchronous operation of the API Gateway to Lambda integration. The queue passes connection information to the Lambda functions which will then post results directly back to the API Gateway websocket connection to support long running inference calls. @@ -92 +92 @@ The high-level process flow for the solution components deployed with the AWS Cl - 6. The _LangChain Orchestrator_ uses Parameter Store and DynamoDB to get the configured LLM options and necessary session information (such as the chat history). + 6. The _LangChain Orchestrator_ uses Amazon DynamoDB to get the configured LLM options and necessary session information (such as the chat history). @@ -94 +94 @@ The high-level process flow for the solution components deployed with the AWS Cl - 7. If the deployment has knowledge base enabled, then the _LangChain Orchestrator_ leverages [Amazon Kendra](https://aws.amazon.com/kendra/) to run a search query to retrieve document excerpts. + 7. If the deployment has a knowledge base enabled, then the _LangChain Orchestrator_ leverages [Amazon Kendra](https://aws.amazon.com/kendra/) or [Knowledge Bases for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/) to run a search query to retrieve document excerpts. @@ -96 +96 @@ The high-level process flow for the solution components deployed with the AWS Cl - 8. Using the chat history, query, and context from Amazon Kendra, the _LangChain Orchestrator_ creates the final prompt and sends the request to the LLM hosted on [Amazon Bedrock](https://aws.amazon.com/bedrock/) or [Amazon SageMaker AI](https://aws.amazon.com/sagemaker/). + 8. Using the chat history, query, and context from the knowledge base, the _LangChain Orchestrator_ creates the final prompt and sends the request to the LLM hosted on [Amazon Bedrock](https://aws.amazon.com/bedrock/) or [Amazon SageMaker AI](https://aws.amazon.com/sagemaker/). @@ -100 +100,5 @@ The high-level process flow for the solution components deployed with the AWS Cl - 10. Using CloudWatch, this solution collects operational metrics from various services to generate custom dashboards that allow you to monitor the deployment’s performance and operational health. + 10. Using Amazon CloudWatch, this solution collects operational metrics from various services to generate custom dashboards that allow you to monitor the deployment’s performance and operational health. + + 11. If feedback collection is enabled, a REST API endpoint, leveraging Amazon API Gateway is made available for the collection of user feedback. + + 12. The feedback backing lambda, augments the submitted feedback with additional use case specific metadata (e.g. model used) and stores the data in Amazon S3 for later analysis and reporting by the DevOps users. @@ -121 +125 @@ The high-level process flow for the solution components deployed with the AWS Cl - 1. Business users deploy the use case using the Deployment dashboard. Business users sign in to the use case UI. + 1. Admin users deploy the use case using the Deployment Dashboard. [Business users](./concepts-and-definitions.html) sign in to the use case UI. @@ -123 +127 @@ The high-level process flow for the solution components deployed with the AWS Cl - 2. CloudFront delivers the web UI, which is hosted in an S3 bucket. + 2. CloudFront delivers the web UI which is hosted in an S3 bucket. @@ -125 +129 @@ The high-level process flow for the solution components deployed with the AWS Cl - 3. The web UI uses a WebSocket integration built using API Gateway. The API Gateway is backed by a custom Lambda authorizer function, which returns the appropriate IAM policy based on the Amazon Cognito group to which the authenticating user belongs. + 3. The web UI leverages a WebSocket integration built using API Gateway. The API Gateway is backed by a custom Lambda authorizer function, which returns the appropriate [AWS Identity and Access Management](https://aws.amazon.com/iam/)(IAM) policy based on the Amazon Cognito group the authenticating user belongs to. The policy is stored in DynamoDB. @@ -129 +133,5 @@ The high-level process flow for the solution components deployed with the AWS Cl - 5. The solution passes the business user’s incoming requests from API Gateway to an Amazon Simple Queue Service (Amazon SQS) queue, and then to the Lambda function. The queue enables the asynchronous operation of the API Gateway to Lambda integration. The queue passes connection information to the Lambda function, which then posts results directly back to the API Gateway WebSocket connection to support long running inference invocations. + 5. Incoming requests from the business user are passed from API Gateway to an [Amazon SQS queue](https://aws.amazon.com/sqs/) and then to the AWS Lambda function. The queue enables the asynchronous operation of the API Gateway to Lambda integration. The queue passes connection information to the Lambda function which will then post results directly back to the API Gateway websocket connection to support long running inference calls. + + 6. The AWS Lambda function uses Amazon DynamoDB to get the use case configurations as needed + + 7. Using the user input and any relevant use case configurations, the AWS Lambda function builds and sends a request payload to the configured [Amazon Bedrock Agent](https://aws.amazon.com/bedrock/agents/) to fulfill the user intent. @@ -131 +139 @@ The high-level process flow for the solution components deployed with the AWS Cl - 6. The Lambda function uses DynamoDB to get the use case configurations as needed. + 8. When the response comes back from the Amazon Bedrock Agent, the Lambda function streams the response back through the API Gateway WebSocket to be consumed by the client application. @@ -133 +141 @@ The high-level process flow for the solution components deployed with the AWS Cl - 7. The Lambda function uses the user input and relevant use case configurations to build and send a request payload to Amazon Bedrock Agents to fulfill the user intent. + 9. Using Amazon CloudWatch, this solution collects operational metrics from various services to generate custom dashboards that allow you to monitor the deployment’s performance and operational health. @@ -135 +143 @@ The high-level process flow for the solution components deployed with the AWS Cl - 8. When the response comes back from Amazon Bedrock Agents, the Lambda function sends the response back through the API Gateway WebSocket to be consumed by the client application. + 10. If feedback collection is enabled, a REST API endpoint, leveraging Amazon API Gateway is made available for the collection of user feedback. @@ -137 +145 @@ The high-level process flow for the solution components deployed with the AWS Cl - 9. Using CloudWatch, this solution collects operational metrics from various services to generate custom dashboards that allow you to monitor the deployment’s performance and operational health. + 11. The feedback backing lambda, augments the submitted feedback with additional use case specific metadata and stores the data in Amazon S3 for later analysis and reporting by the DevOps users.