Skip to content

acyeow/deploy-rag-to-aws

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The majority of the code is from a tutorial by pixegami. The purpose of this code is my personal exploration and learning about AWS CDK, Retrival Augmented Generation and Next.js application development.

RAG Application to Chat with Mistral 7B Paper

This application uses ChromaDB to create a vector database, which will be queried to find relevant information to the prompt. To create the embeddings for the vector database, Amazon Bedrock embeddings are used and cosine similarity is used to compute the similarity between the prompt embedding and embeddings saved to the ChromaDB. This functionality is wrapped in a FastAPI endpoint which has been deployed as an AWS Lambda function. AWS CDK was used to provison resources for support this functionality. The frontend of this application was created using Next.js and deployed to Vercel.

FastAPI Endpoint

FastAPI Docs

Deployed Application

Vercel Application

About

Talk to the Mistral 7B Paper!

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • TypeScript 75.9%
  • Python 18.7%
  • CSS 2.7%
  • JavaScript 1.9%
  • Dockerfile 0.8%