top of page
Writer's pictureMegha Arora

AI Developers Meet - RAG with Serverless Postgres Neon

We will build an AI-powered RAG chatbot created with Next.js, Neon Postgres (pgvector), OpenAI, and LlamaIndex.


We can use this RAG chatbot to input data, which will be embedded using the OpenAI text embedding API and stored in the Neon database with the original text.

The app processes the user's input, embeds it, and performs a similarity or vector search in the Neon database to get relevant answers.

It then uses the OpenAI API to generate a specialised and more appropriate response based on the data entered.


Prerequisites:

  1. Vector Database: For setting up Neon Serverless Postgres which also acts as Vector Database for free, you can start with a Neon Free Tier

2. An OpenAI API key: You can sign up and go to the API keys page to create an API key.




Original Source and Github Repos :


How RAG Works?


This image explains how RAG works with the help of LLM Frameworks, LLMs and a vector database
How RAG Works


Follow Me for More

For daily updates and tips on cracking top tech job interviews, follow us on our social media platforms:

Stay tuned for more content to help you succeed in your tech career!

93 views0 comments

Comments


bottom of page