-
Notifications
You must be signed in to change notification settings - Fork 12
New genai connector pattern - kendra-bedrock-rds-postgresql-sam #13
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
New genai connector pattern - kendra-bedrock-rds-postgresql-sam #13
Conversation
* [Git Installed](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) | ||
* [AWS Serverless Application Model](https://docs.aws.amazon.com/serverless-application-model/latest/developerguide/serverless-sam-cli-install.html) (AWS SAM) installed | ||
* [Request Amazon Bedrock Model Access for Anthropic Claude models on Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html) | ||
* Before deploying the solution, you need to set up an [Amazon RDS PostgreSQL DB](https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/CHAP_GettingStarted.CreatingConnecting.PostgreSQL.html) if you don't already have one. Prior to the RDS PostgreSQL setup, [Create and configure a VPC](https://docs.aws.amazon.com/vpc/latest/userguide/create-vpc.html) with at least two private subnets. During the database setup: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Put VPC prereq before RDS Postgres prereq so there isn't backtracking. Optional: hyperlink highlight to documentation that can do all this for you https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/CHAP_GettingStarted.CreatingConnecting.PostgreSQL.html#:~:text=(Optional)-,Create%20VPC%2C%20EC2%20instance%2C%20and%20PostgreSQL%20instance%20using%20AWS%20CloudFormation,-Instead%20of%20using
confirm_changeset = true | ||
capabilities = "CAPABILITY_NAMED_IAM" | ||
disable_rollback = true | ||
parameter_overrides = "ModelId=\"anthropic.claude-v2\" DatabaseHost=\"database-2.c96kksuaccrd.us-east-1.rds.amazonaws.com\" DatabaseName=\"medical\" TableName=\"patient_records\" SecretArn=\"arn:aws:secretsmanager:us-east-1:009160043239:secret:kendra-aurora-secret-byxLyk\" ChangeDetectingColumns=\"date_of_admission,discharge_date\" DocumentIdColumnName=\"id\" DocumentDataColumnName=\"medical_condition\" VpcId=\"vpc-00c024e8c89eb0a00\" SubnetIds=\"subnet-0433e65c91fabef8c, subnet-0f169b6a3bb23d25b, subnet-0360923af5f233b3f\" SecurityGroupIds=\"sg-004dadcb2eaa84be8\" KendraEdition=\"ENTERPRISE_EDITION\"" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Redact some of these as they're unique IDs anyways and also SecretArn reveals your Account ID
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This diagram has to be updated to include the data source is PostgreSQL on RDS instead of the generic one that will apply for almost all patterns on repo
}, | ||
"gitHub": { | ||
"template": { | ||
"repoURL": "https://github.com/aws-samples/serverless-patterns/tree/main/lambda-kendra-bedrock", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
While this file as a whole isn't entirely relevant to this repo (since we aren't publishing this pattern as a blog on ServerlessLand) can you update these lines to reflect this pattern
e96bf18
to
4e618cc
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Description of changes:
Adding new genAI connector pattern Amazon RDS PostgreSQL for SAM
Security Review:
rds_postgresql_cfn_nag_result.txt
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.