This is a Next.js project bootstrapped with create-next-app
.
Getting Started
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev
Open http://localhost:3000 with your browser to see the result.
You can start editing the page by modifying app/page.tsx
. The page auto-updates as you edit the file.
This project uses next/font
to automatically optimize and load Inter, a custom Google Font.
Learn More
To learn more about Next.js, take a look at the following resources:
- Next.js Documentation - learn about Next.js features and API.
- Learn Next.js - an interactive Next.js tutorial.
You can check out the Next.js GitHub repository - your feedback and contributions are welcome!
Deploy on Vercel
The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.
Check out our Next.js deployment documentation for more details.
- nextjs
- shadcn -> It's a collection of beautifully designed, accessible, and customizable components that you can simply copy and paste into your apps.
- clerkauth -> handle authentication. Protects route with provider. add env file.
- lucide-react -> lots of icons to use
- NeonDB
- drizzleORM and drizzle-kit -> sync schema to neondb
- 'use client'
- react-dropzone
- vectors and embeddings. cosine similarities to find the most similar vector to what's asked. embedding is the vector.
- tanstack/react-query to handle data querying from local to server endpoints. React query can cache data and return. Create a provider and wrap app with it.
- react-hot-toast
- pinecone db
- langchain
- vercel ai sdk
pinecone terms
-
index -> database to store vectors
-
namespace -> table. segment pdf vector spaces
-
obtain pdf
-
split and segment pdf
-
vectorise and embed individual documents
-
store vectors into pineconedb
search
- embed query
- query pineconedb for similar vectors
- extract out the metadata of similar vectors
- feed metadata into openai prompt