WarriorsCommentaryAPI
NBA Basketball + realtime analytics + multimodal LLMs running on SingleStore.
Install / Use
/learn @apeng-singlestore/WarriorsCommentaryAPIREADME
Real-time NBA Analytics App
An innovative NBA analytics application featuring AI commentary, live score tracking, and a (very unscientific) win probability over time. Built with Next.js, it utilizes SingleStore for real-time data analytics and the LLaVa 1.5 multimodal model hosted on Groq for millisecond latency inference.
Features
- AI Commentary: Real-time AI-generated insights on games and player performances.
- Live Score Tracking: Up-to-the-second scores and stats from ongoing NBA games.
- Win Probability Over Time: Visual representation of each team's chance to win as the game progresses.
Prerequisites
- Node.js: Version 14 or higher.
- npm or Yarn: For dependency management.
- SingleStore Account: For real-time analytics.
- Groq API Key: Access to the LLaVa 1.5 model.
- OpenAI API Key: For additional AI functionalities.
Installation
npm install
SingleStore Connection Details
- DATABASE_HOST=your-singlestore-host
- DATABASE_USERNAME=your-singlestore-username
- DATABASE_PASSWORD=your-singlestore-password
- DATABASE_NAME=your-singlestore-database-name
Groq API Key
- GROQ_API_KEY=your-groq-api-key
OpenAI API Key
- OPENAI_API_KEY=your-openai-api-key
Running the project
npm run dev
You can access the project at localhost:3001
Related Skills
feishu-drive
347.0k|
things-mac
347.0kManage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database)
clawhub
347.0kUse the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com
codebase-memory-mcp
1.2kHigh-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 66 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
