How sandy3559/clarinotes works
Project type and purpose
• This is a full-stack Next.js web application that enables users to upload, view, and annotate PDFs in a workspace enriched with AI/ML features.
• It uses Next.js’s App Router for page routing, API routes for serverless endpoints, and Convex as the real-time database, authentication, and serverless function platform.
File structure
• Top-level directories:
• app/ – Next.js pages, layouts, server/client components (auth, dashboard, workspace, public pages)
• components/ – UI primitives (buttons, dialogs, inputs, progress)
• convex/ – Convex schema, serverless actions, file storage integration, LangChain DB adapter
• lib/ – shared utilities
• public/ – static assets
• Key files:
• app/api/pdf-loader/route.js – serverless API endpoint for ingesting PDFs
• middleware.js – Next.js middleware, likely for authentication or redirects
• configs/AIModel.js – configuration for AI model usage (e.g., OpenAI keys)
• next.config.mjs, postcss.config.mjs, jsconfig.json – build and tooling configs
README for additional insights
• Basic Next.js bootstrapped README; no architecture details.
• Confirms use of next/font, standard Vercel deployment.
Detailed capture of essential elements
• Break out the UI sub-components under the dashboard and workspace into a zoomed-in inset if needed (Header, SideBar, PdfViewer, TextEditor)