michael 236d1ddbd8 Initial commit: Netflix GraphRAG marketing chatbot

Full-stack application combining LlamaIndex vector search with Neo4j
knowledge graph (GraphRAG) for answering queries about Netflix marketing
materials. Flask/Hypercorn backend with custom ReAct agent, React frontend.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-23 10:28:33 -06:00

1.6 KiB

Raw Blame History

Netflix GPD Key Art Playbook Chatbot

A React frontend for the Netflix GPD Key Art Playbook Chatbot, providing a chat interface to query the Netflix marketing knowledge base.

Features

Clean chat interface for asking questions about Netflix marketing materials
Sources and reasoning display for transparency
Session-based memory for contextual conversations
Conversation management system

Development

Prerequisites

Node.js 18+
npm or yarn

Setup

Clone the repository
Install dependencies:

npm install

Start the development server:

npm run dev

Configuration

The application uses environment variables for configuration. Create a .env file in the root directory with the following variables:

# Backend API URL
VITE_BACKEND_URL=https://ai-sandbox.oliver.solutions/netflix_back_v2

# Base URL for the app (changes in production)
VITE_APP_BASE_URL=/

Changing the Backend URL

If you need to change the backend API URL:

Edit the .env and .env.production files to update the VITE_BACKEND_URL value
Or use the provided script: ./update-backend.sh which will update the URL and rebuild the application
Then rebuild the application with npm run build

Building for Production

To create a production build:

npm run build

The output will be in the dist directory, ready for deployment.

Deployment

See DEPLOY.md for detailed deployment instructions.

Technologies Used

React 18
Vite
TailwindCSS
Microsoft Authentication Library (MSAL)
Shadcn/ui components

1.6 KiB Raw Blame History