aws-lambda-web-adapter VS langchaingo

In the next part of the series I'll make the introduction to the AWS Lambda Web Adapter and explain how our Serverless Spring Boot application on AWS can make use of it.

Lambda Web Adapter (LWA) is an open-source project that enables running Web apps on Lambda functions without the need to change or adapt the code.

Thanks to the AWS Lambda Web Adapter, the application built as a (good old) REST/HTTP API using a familiar library (in this case, Gin.

Using the excellent Lambda web adapter extension with a container, you can very easily move a function from Lambda to Fargate or Apprunner if cost becomes an issue. This optionality is of high value, and shouldn't be overlooked.

We will use AWS Lambda Web Adapter to run our Node.js Application on AWS Lambda.

For such frameworks, I would look at Lambda Web Adapter (https://github.com/awslabs/aws-lambda-web-adapter/tree/main/examples). Both frameworks have specific examples for them that allow for the execution of those within a Lambda context with few, if any, code changes. For spring, specifically, using Lambda Snapstart can significantly improve cold-start performance. You can read more about Java and Spring framework in this blog post that contains also a code example https://aws.amazon.com/blogs/compute/reducing-java-cold-starts-on-aws-lambda-functions-with-snapstart/ With regards to Flask, you can also use a project like: https://pypi.org/project/flask-lambda/

With the lambda web adapter[1], you shouldn't need to make any code changes for web projects, just some dockerfile changes which are only used if it is running as a lambda, so the same container image should still work on ecs or another cloud. [1]https://github.com/awslabs/aws-lambda-web-adapter

Additionally, there is this tool you can use to use the same image in a lambda and any other container runtime. https://github.com/awslabs/aws-lambda-web-adapter

You can point your platform team to this: https://github.com/awslabs/aws-lambda-web-adapter , which they can use to get your service running in Lambda.

Generative AI development has been democratised, thanks to powerful Machine Learning models (specifically Large Language Models such as Claude, Meta's LLama 2, etc.) being exposed by managed platforms/services as API calls. This frees developers from the infrastructure concerns and lets them focus on the core business problems. This also means that developers are free to use the programming language best suited for their solution. Python has typically been the go-to language when it comes to AI/ML solutions, but there is more flexibility in this area. In this post you will see how to leverage the Go programming language to use Vector Databases and techniques such as Retrieval Augmented Generation (RAG) with langchaingo. If you are a Go developer who wants to how to build learn generative AI applications, you are in the right place!

This use-case here is a similar one - a chat application. I will switch back to implementing things in Go using langchaingo (I used Python for the previous one) and continue to use Amazon Bedrock. But there are few unique things you can explore in this blog post:

langchaingo is the LangChain implementation for the Go programming language. This blog post covers how to extend langchaingo to use foundation model from Amazon Bedrock.

Langchain Go is being actively developed https://github.com/tmc/langchaingo