BrainWave
An intelligent note-taking app with AI integration, built with OpenAI, Pinecone, and Next.js to provide users with an AI chat assistant that can retrieve information from their notes.
Role
Full Stack Developer
- Timeline
- February 2024
Technologies
- Next.js
- Typescript
- TailwindCSS
- Prisma
- MongoDB
- Vercel AI
- ChatGPT API
- Pinecone
Tools
- GitHub
- Clerk
- Shadcn UI
Background
Traditional note-taking apps lack intelligent search, making it difficult for users to find specific information quickly and conversationally. This project aimed to solve the challenge of inefficient information retrieval in personal notes.
Solution
BrainWave integrates a state-of-the-art AI chatbot using the Vercel AI SDK, ChatGPT, and Pinecone. This allows users to ask questions in natural language and receive intelligent, context-aware answers sourced directly from their own notes.
Process
- Set up the Next.js project with Shadcn UI, configuring MongoDB, Prisma, and Clerk for the database and user authentication.
- Developed the core application layout and pages, implementing features like the navbar, note creation, and dark theme support.
- Integrated OpenAI and Pinecone to create vector embeddings for notes and used the Vercel AI SDK to build the AI chat functionality.
Final Product
Impact
- Implemented an AI chat feature with response streaming using the Vercel AI SDK and OpenAI.
- Integrated intelligent document retrieval by leveraging ChatGPT vector embeddings and Pinecone for efficient information extraction.
- Built user-facing features such as theme toggling and secure user authentication using Clerk.
Reflection
- Practiced configuring and connecting multiple services in a modern tech stack, including Next.js, Prisma, and MongoDB.
- Recognized the importance of detailed architecture planning upfront to reduce setup complexity and potential integration issues.
- Identified opportunities to improve AI performance through fine-tuning vector embeddings and optimizing chat response handling.