Skip to content

Latest commit

 

History

History

cdk_stacks

README.md

RAG Application CDK Python project!

rag_with_opensearch_arch

This is an QA application with LLMs and RAG project for CDK development with Python.

The cdk.json file tells the CDK Toolkit how to execute your app.

This project is set up like a standard Python project. The initialization process also creates a virtualenv within this project, stored under the .venv directory. To create the virtualenv it assumes that there is a python3 (or python for Windows) executable in your path with access to the venv package. If for any reason the automatic creation of the virtualenv fails, you can create the virtualenv manually.

To manually create a virtualenv on MacOS and Linux:

$ python3 -m venv .venv

After the init process completes and the virtualenv is created, you can use the following step to activate your virtualenv.

$ source .venv/bin/activate

If you are a Windows platform, you would activate the virtualenv like this:

% .venv\Scripts\activate.bat

Once the virtualenv is activated, you can install the required dependencies.

(.venv) $ pip install -r requirements.txt

To add additional dependencies, for example other CDK libraries, just add them to your setup.py file and rerun the pip install -r requirements.txt command.

Upload Lambda Layer code

Before deployment, you should uplad zipped code files to s3 like this example:

⚠️ Important: Replace lambda-layer-resources with your s3 bucket name for lambda layer zipped code. :warning: To create a bucket outside of the us-east-1 region, aws s3api create-bucket command requires the appropriate LocationConstraint to be specified in order to create the bucket in the desired region. For more information, see these examples.

⚠️ Make sure you have Docker installed.

(.venv) $ aws s3api create-bucket --bucket lambda-layer-resources --region us-east-1
(.venv) $ cat <requirements-lambda_layer.txt
 > sagemaker==2.188
 > cfnresponse==1.1.2
 > urllib3==1.26.16
 > EOF
(.venv) $ docker run -v "$PWD":/var/task "public.ecr.aws/sam/build-python3.10" /bin/sh -c "pip install -r requirements-lambda_layer.txt -t python/lib/python3.10/site-packages/; exit"
(.venv) $ zip -r sagemaker-python-sdk-lib.zip python > /dev/null
(.venv) $ aws s3 cp sagemaker-python-sdk-lib.zip s3://lambda-layer-resources/pylambda-layer/

For more information about how to create a package for Amazon Lambda Layer, see here.

Deploy

Before synthesizing the CloudFormation, you should set approperly the cdk context configuration file, cdk.context.json.

For example:

{
  "opensearch_domain_name": "llm-rag-vectordb",
  "sagemaker_domain_name": "rag-workshop-studio-in-vpc",
  "lambda_layer_lib_s3_path": "s3://lambda-layer-resources/pylambda-layer/sagemaker-python-sdk-lib.zip",
  "sagemaker_jumpstart_model_info": {
    "model_id": "meta-textgeneration-llama-2-7b",
    "endpoint_name": "llama-2-7b"
  }
}

Now this point you can now synthesize the CloudFormation template for this code.

(.venv) $ export CDK_DEFAULT_ACCOUNT=$(aws sts get-caller-identity --query Account --output text)
(.venv) $ export CDK_DEFAULT_REGION=us-east-1 # your-aws-account-region
(.venv) $ cdk synth --all

Now we will be able to deploy all the CDK stacks at once like this:

(.venv) $ cdk deploy --require-approval never --all

Or, we can provision each CDK stack one at a time like this:

Step 1: List all CDK Stacks

(.venv) $ cdk list
RAGHaystackVpcStack
RAGHaystackOpenSearchStack
RAGHaystackBastionHost
RAGHaystackSageMakerStudioStack
RAGHaystackSMPySDKLambdaLayerStack
RAGHaystackSMEndpointRoleStack
RAGHaystackSMJSModelDeployLambdaStack
RAGHaystackSMJSModelEndpointStack

Step 2: Create OpenSearch cluster

(.venv) $ cdk deploy --require-approval never RAGHaystackVpcStack \
                                              RAGHaystackOpenSearchStack \
                                              RAGHaystackBastionHost

Step 3: Create SageMaker Studio

(.venv) $ cdk deploy --require-approval never RAGHaystackSageMakerStudioStack

Step 4: Deploy Text Generation LLM Endpoint

(.venv) $ cdk deploy --require-approval never RAGHaystackSMPySDKLambdaLayerStack \
                                              RAGHaystackSMEndpointRoleStack \
                                              RAGHaystackSMJSModelDeployLambdaStack \
                                              RAGHaystackSMJSModelEndpointStack

Once all CDK stacks have been successfully created, proceed with the remaining steps of the overall workflow.

Clean Up

Delete the CloudFormation stacks by running the below command.

(.venv) $ cdk destroy --all

Useful commands

  • cdk ls list all stacks in the app
  • cdk synth emits the synthesized CloudFormation template
  • cdk deploy deploy this stack to your default AWS account/region
  • cdk diff compare deployed stack with current state
  • cdk docs open CDK documentation

Enjoy!

References

Troubleshooting