langchaingo
aws-lambda-go-api-proxy
langchaingo | aws-lambda-go-api-proxy | |
---|---|---|
9 | 10 | |
3,195 | 1,005 | |
- | 2.1% | |
9.8 | 4.5 | |
2 days ago | 24 days ago | |
Go | Go | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
langchaingo
-
How to use Retrieval Augmented Generation (RAG) for Go applications
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!
-
Build a Serverless GenAI solution with Lambda, DynamoDB, LangChain and Amazon Bedrock
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:
- LangChain for Go, the easiest way to write LLM-based programs in Go
- Langchaingo – LangChain in Idiomatic Go
- Agency: Pure Go LangChain Alternative
-
Building LangChain applications with Amazon Bedrock and Go - An introduction
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.
-
Zep: A long-term memory store for LLM apps, written in Go
Langchain Go is being actively developed https://github.com/tmc/langchaingo
aws-lambda-go-api-proxy
-
Build a Serverless GenAI solution with Lambda, DynamoDB, LangChain and Amazon Bedrock
I really like the extensibility of LangChain. While I understand that langchaingo may not be as popular as the original python version (I hope it will reach there in due time 🤞), but it's nice to be able to use it as a foundation and build extensions as required. Previously, I had written about how to use the AWS Lambda Go Proxy API to run existing Go applications on AWS Lambda. The AWS Lambda Web Adapter offers similar functionality but it has lots of other benefits, including response streaming and the fact that it is language agnostic.
-
What AWS service do you find most frustrating?
A frustration shoutout to the aws maintainers that are ignoring PRs that enhance the usability of their services... even for over a year. https://github.com/awslabs/aws-lambda-go-api-proxy/pull/136
-
Running gqlgen + Gin in AWS Lambda
Check out https://github.com/awslabs/aws-lambda-go-api-proxy. It will allow you to run gin (or other http servers) in lambda.
-
Is good or the most bad idea write a Lambda AWS using fx package? (Dependency Injection)
For REST APIs, I create standard Go HTTP handlers, and use a library like https://github.com/a-h/awsapigatewayv2handler (mine, for API Gateway V2 only), or AWS's https://github.com/awslabs/aws-lambda-go-api-proxy or github.com/akrylysov/algnhsa to convert from Lambda handlers to standard Go HTTP handlers.
-
Serverless application development in Golang with AWS
Hey I liked this post, seems really nice. I used Golang for an API in my current work, I used the gorillamux with this library https://github.com/awslabs/aws-lambda-go-api-proxy. It wraps the API into the APIGateway Proxy. You can use it too if you want to create a small API, there are examples with cloudformation there.
-
101 AWS Lambda tutorial for Go developers — API Gateway
using {proxy+} on api gateway, route handler needs to be included. People should consider using github.com/awslabs/aws-lambda-go-api-proxy (with gin or mux)
-
Build Scalable Applications with AWS Lambda and Go
This does something similar: https://github.com/awslabs/aws-lambda-go-api-proxy
-
Bootstrapping a Startup on AWS with AWS Serverless and Go
As you can see, we defined that any path and method can trigger our lambda over API Gateway that we had previously created. With this approach and with using this solution with the Go Echo framework, we reduced the number of lambdas (also with this approach we solved the problem with a hard limit of total size that all lambdas can have). Using the aws-lambda-go-api-proxy with echo framework we defined a REST controller that is managing real paths and methods that our lambda consumes.
-
Cloud Serverless Lock-in doesn't exist (if your Team knows Hexagoxal Architecture)
For our example which use the Go Gin framework, to minimize the changes we could also use the great AWS Lambda Go API Proxy. You can find an example of lambda function in the article repository
-
How do you guys debug AWS Lambda locally with SAM?
AWS actually provides wrappers for most HTTP handler functions in their adapter package: https://github.com/awslabs/aws-lambda-go-api-proxy
What are some alternatives?
yao - :rocket: A performance app engine to create web services and applications in minutes.Suitable for AI, IoT, Industrial Internet, Connected Vehicles, DevOps, Energy, Finance and many other use-cases.
gateway - Drop-in replacement for Go net/http when running in AWS Lambda & API Gateway
langchain - 🦜🔗 Build context-aware reasoning applications
hexagonal-architecture
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
aws-sam-cli - CLI tool to build, test, debug, and deploy Serverless applications using AWS SAM
zep - Zep: Long-Term Memory for AI Assistants.
tflint - A Pluggable Terraform Linter
TaskEaseGPT - (WIP) A user-friendly, AI-powered task manager emphasizing efficient work over planning. Streamlines workflow with intelligent task generation & execution. Boost your productivity today!
go-lambda - Template project for working with AWS Lambda and Go
langchaingo-amazon-bedrock-llm - Amazon Bedrock extension for langchaingo
gqlgen-lambda - My implementation prototype on how to run a zero cost graphql layer in lambda with Go and GqlGen