This project is part of the Level Supermind Hackathon, focusing on analyzing social media engagement using Next.js, Langflow, DataStax Astra DB, and Nvidia - Mixtral integration. It provides actionable insights into post performance based on mock engagement data.
- Visit Website: Kaizen-mu.vercel.app
- Post Performance Analysis: Analyze engagement metrics (likes, shares, comments) for different post types (carousel, reels, static images).
- AI-Driven Insights: Generate intelligent recommendations using Nvidia - Mixtral integration.
- Langflow Integration: Visual workflow creation for data querying and analysis.
- Deployed on Vercel: Seamless and fast web hosting.
- Next.js Framework: Scalable and high-performance React framework for development.
Watch our Video Demonstration of Kaizen and How we built using DataStax Langflow, Astra DB and Nvidia - Mixtral model.
- Frontend: Next.js
- Backend: DataStax Astra DB for database operations
- AI/Workflow: Langflow with Nvidia:mistralai/mixtral-8x22b-instruct-v0.1
- Deployment: Vercel
Here is the Langflow we used to build this RAG app using DataStax platform with AstraDB, Nvidia - Mixtral Integration.
├── app
│ └── page.tsx # Main application page
├── public # Static assets
├── components # Reusable UI components
├── lib # Utility functions and helpers
└── README.md # Project documentation- First, Clone and Install packages:
git clone https://github.com/amitverma-cf/supermind_hackathon.gitnpm install- Now, Create .env file and add this key into .env file:
DATASTAX_APPLICATION_TOKEN=[Your_DataStax_Langflow_Api_Key]- Then, run the development server:
npm run dev- Open http://localhost:3000 with your browser to see the result.
This project is licensed under the MIT License.