feat(documentation): Fix typo and update architecture diagrams (#31)

* fix typos and update architecture diagrams

* update changelog

CHANGELOG.md

@@ -1,3 +1,7 @@
+# CDK Emerging Tech Constructs V0.0.24 (2023-10-16)
+
+Based on CDK library version 2.99.1
+
 # CDK Emerging Tech Constructs V0.0.0 (2023-09-21)
 
 Based on CDK library version 2.96.2

CONTRIBUTING.md

@@ -134,7 +134,7 @@ BREAKING CHANGE: Description of what broke and how to achieve this behavior now
   for you when you finalize your merge commit message.
 * Make sure to update the PR title/description if things change. The PR title/description are going to be used as the
   commit title/message and will appear in the CHANGELOG, so maintain them all the way throughout the process.
-* Make sure your PR builds successfully (we have Github actions setup to automatically build all PRs)
+* Make sure your PR builds successfully (we have GitHub actions setup to automatically build all PRs)
 
 #### Build steps
 

README.md

@@ -47,10 +47,10 @@ The following constructs are available in the library:
 
 | **Construct**| Emerging Tech Area |Description| AWS Services used |
 |:-------------|:-------------|:-------------|:-------------|
-| [Data ingestion pipeline](./src/patterns/gen-ai/aws-rag-appsync-stepfn-opensearch/) | Generative AI | Ingestion pipeline providing a RAG (Retrieval Augmented Generation) source for storing documents in a knowledge base. | Amazon Opensearch, AWS Step Functions, Amazon bedrock, AWS Appsync, AWS Lambda | 
-| [Question answering](./src/patterns/gen-ai/aws-qa-appsync-opensearch/) | Generative AI | Question answering against a Large Language Model (Anthropic Claude V2) using a RAG (Retrieval Augmented Generation) source and/or long context window. | Amazon Opensearch, AWS Lambda, Amazon bedrock, AWS Appsync | 
-| [Summarization](./src/patterns/gen-ai/aws-summarization-appsync-stepfn/) | Generative AI | Document summarization using a Large Language Model (Anthropic Claude V2). | AWS Lambda, Amazon bedrock, AWS Appsync, Amazon Elasticache for Redis |
-| [Lambda layer](./src/patterns/gen-ai/aws-langchain-common-layer/) | Generative AI | Python lambda layer providing dependencies and utilities to develop Generative AI applications on AWS. | AWS Lambda, Amazon bedrock, Amazon SageMaker |  
+| [Data ingestion pipeline](./src/patterns/gen-ai/aws-rag-appsync-stepfn-opensearch/) | Generative AI | Ingestion pipeline providing a RAG (Retrieval Augmented Generation) source for storing documents in a knowledge base. | Amazon OpenSearch, AWS Step Functions, Amazon Bedrock, AWS Appsync, AWS Lambda | 
+| [Question answering](./src/patterns/gen-ai/aws-qa-appsync-opensearch/) | Generative AI | Question answering against a Large Language Model (Anthropic Claude V2) using a RAG (Retrieval Augmented Generation) source and/or long context window. | Amazon OpenSearch, AWS Lambda, Amazon Bedrock, AWS Appsync | 
+| [Summarization](./src/patterns/gen-ai/aws-summarization-appsync-stepfn/) | Generative AI | Document summarization using a Large Language Model (Anthropic Claude V2). | AWS Lambda, Amazon Bedrock, AWS Appsync, Amazon Elasticache for Redis |
+| [Lambda layer](./src/patterns/gen-ai/aws-langchain-common-layer/) | Generative AI | Python lambda layer providing dependencies and utilities to develop Generative AI applications on AWS. | AWS Lambda, Amazon Bedrock, Amazon SageMaker |  
 
 # Sample Use Cases
 
@@ -62,7 +62,7 @@ Coming soon
 
 # Roadmap
 
-Roadmap is available through the [Github Project](https://github.com/orgs/aws-samples/projects/72)
+Roadmap is available through the [GitHub Project](https://github.com/orgs/aws-samples/projects/72)
 
 ***
 © Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.

src/patterns/gen-ai/aws-qa-appsync-opensearch/README.md

@@ -22,7 +22,7 @@
 
 ## Overview
 
-This construct provides a question answering workflow (RAG + long context window) using Amazon Bedrock and a provisioned Amazon Opensearch cluster. 
+This construct provides a question answering workflow (RAG + long context window) using Amazon Bedrock and a provisioned Amazon OpenSearch cluster. 
 - If a document is provided as an input to the Appsync query, the AWS Lambda function will first verify the length of the document. If the document size is above the max number of tokens for the selected model, the Lambda will query the knowledge base (similarity search) and filter by document name. This assumes that the chunks of texts stored in the knowledge base have the document name as metadata. Otherwise, the content of the document is provided to the LLM as part of the context.
 - If no document is provided as input, the Lambda will perform a similarity search against the entire knowledge base.