LangChain Retrieval Augmented Generation (RAG) with Flask

Introduction

In this project you’ll learn how to build a Retrieval Augmented Generation (RAG) app using Flask and LangChain. RAG is a technique that can augment LLM responses with custom data. It's a very powerful technique to learn.

In this project you'll learn how to build a RAG chat app using Python, Flask, Pinecone, and LangChain. You will create two API endpoints: one for uploading the source file which will be saved in Pinecone vector DB, and the second for performing chat operations. Users of the API will be able to upload a doc, have it processed into embeddings and stored in a vector DB, and then start chatting with it.

TIME

60 min.

DIFFICULTY

Medium

  • Cloud Provider: AWS
  • Language(s): Python
  • Tooling: LangChain
  • AI Tutor: Enabled
  • AI Platform: OpenAI
  • AI Model: GPT-4
  • Category: ai

This project is available with a paid Skillmix subscription.