{"id":32675589,"url":"https://github.com/ellttdave/athlete-performance-platform-showcase","last_synced_at":"2026-04-07T20:31:45.046Z","repository":{"id":321464929,"uuid":"1085952698","full_name":"ellttdave/athlete-performance-platform-showcase","owner":"ellttdave","description":"Technical showcase production application demonstrating LLM integration, MCP pattern, RAG systems, and modern architecture.","archived":false,"fork":false,"pushed_at":"2025-11-07T01:04:11.000Z","size":37,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-07T02:32:55.164Z","etag":null,"topics":["anthropic-claude","embeddings","healthcare-technology","llm-integration-tool-calling","mcp","nextjs","nodejs","openai-text-embeddings","performance-analytics","pgvector","postgresql","prisma-orm","rag-retrieval-augmented-generation","react","sports-science","tailwindcss","tool-calling","typescript","vector-search","vercel"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ellttdave.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-29T18:29:08.000Z","updated_at":"2025-11-07T01:04:15.000Z","dependencies_parsed_at":"2025-10-29T20:47:32.407Z","dependency_job_id":null,"html_url":"https://github.com/ellttdave/athlete-performance-platform-showcase","commit_stats":null,"previous_names":["ellttdave/athlete-performance-platform-showcase"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ellttdave/athlete-performance-platform-showcase","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellttdave%2Fathlete-performance-platform-showcase","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellttdave%2Fathlete-performance-platform-showcase/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellttdave%2Fathlete-performance-platform-showcase/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellttdave%2Fathlete-performance-platform-showcase/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ellttdave","download_url":"https://codeload.github.com/ellttdave/athlete-performance-platform-showcase/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellttdave%2Fathlete-performance-platform-showcase/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31528309,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T16:28:08.000Z","status":"ssl_error","status_checked_at":"2026-04-07T16:28:06.951Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["anthropic-claude","embeddings","healthcare-technology","llm-integration-tool-calling","mcp","nextjs","nodejs","openai-text-embeddings","performance-analytics","pgvector","postgresql","prisma-orm","rag-retrieval-augmented-generation","react","sports-science","tailwindcss","tool-calling","typescript","vector-search","vercel"],"created_at":"2025-11-01T06:01:41.712Z","updated_at":"2026-04-07T20:31:45.030Z","avatar_url":"https://github.com/ellttdave.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Release](https://img.shields.io/github/v/release/ellttdave/athlete-performance-platform-showcase?display_name=tag)](https://github.com/ellttdave/athlete-performance-platform-showcase/releases)\n[![License](https://img.shields.io/github/license/ellttdave/athlete-performance-platform-showcase)](./LICENSE)\n[![Last commit](https://img.shields.io/github/last-commit/ellttdave/athlete-performance-platform-showcase)](https://github.com/ellttdave/athlete-performance-platform-showcase/commits)\n[![Stars](https://img.shields.io/github/stars/ellttdave/athlete-performance-platform-showcase)](https://github.com/ellttdave/athlete-performance-platform-showcase/stargazers)\n\n![Top language](https://img.shields.io/github/languages/top/ellttdave/athlete-performance-platform-showcase)\n![Repo size](https://img.shields.io/github/repo-size/ellttdave/athlete-performance-platform-showcase)\n\n# Athlete Performance Analytics Platform - Technical Showcase\n\n\u003e A production application demonstrating advanced LLM integration, RAG systems, and modern full-stack architecture patterns.\n\n## 🎯 Project Overview\n\nThis repository showcases the technical architecture and implementation patterns from a production application that integrates:\n\n- **LLM Integration** (Anthropic Claude) with structured tool calling\n- **RAG System** (Retrieval-Augmented Generation) with vector embeddings\n- **MCP-like Architecture** for clean separation of concerns\n- **Modern Full-Stack** development with Next.js, TypeScript, and PostgreSQL\n\n**Note**: This repository contains sanitized code examples and architecture documentation for showcaase purposes. The full production application remains private to protect intellectual property.\n\n## 🏗️ Architecture Highlights\n\n### MCP-Like Tool Integration Pattern\nA custom architecture pattern that mimics Model Context Protocol (MCP) to provide clean separation between LLM communication logic and data functions.\n\n**Key Benefits:**\n- Single gateway for all LLM tool calls\n- Easy migration path to real MCP server\n- Extensible tool registry pattern\n- Comprehensive error handling\n\n[View Architecture Details →](./docs/MCP_ARCHITECTURE.md)\n\n### RAG Implementation\nA production-ready RAG system using vector embeddings and semantic search.\n\n**Key Features:**\n- Google Document AI for advanced text extraction (Form Parser, Layout Parser)\n- Automatic PDF splitting for large files (\u003e15 pages or \u003e4MB)\n- OpenAI embeddings (text-embedding-3-small)\n- pgvector for PostgreSQL vector similarity search\n- Vercel Blob Storage for document persistence\n- Individual document re-processing to avoid timeout issues\n- Fallback mechanisms (unpdf) for reliability\n- Automatic knowledge base integration\n- Top-K retrieval with similarity scoring\n\n**Architecture Note:**\n- RAG is used for general knowledge, research articles, and contextual explanations\n- Precise numeric/reference data is stored in PostgreSQL (not RAG) for deterministic queries\n\n[View RAG Implementation →](./docs/RAG_IMPLEMENTATION.md)\n\n### Full-Stack Design\nModern web application architecture with:\n\n- **Frontend**: Next.js 14, React 18, TypeScript, Tailwind CSS\n- **Backend**: Next.js API Routes, Server Actions\n- **Database**: PostgreSQL (Neon) with Prisma ORM, pgvector extension\n- **AI/ML**: Anthropic Claude API, OpenAI Embeddings\n- **Document Processing**: Google Document AI, pdf-lib for PDF splitting\n- **Storage**: Vercel Blob Storage for document persistence\n- **Deployment**: Vercel\n\n[View Tech Stack Details →](./docs/TECH_STACK.md)\n\n## 📚 Documentation\n\n- **[Architecture Overview](./docs/ARCHITECTURE.md)** - System design and architecture patterns\n- **[MCP Architecture](./docs/MCP_ARCHITECTURE.md)** - Tool registry pattern and implementation\n- **[RAG Implementation](./docs/RAG_IMPLEMENTATION.md)** - Vector embeddings and semantic search\n- **[LLM Integration](./docs/LLM_INTEGRATION.md)** - Tool calling and structured outputs\n- **[Tech Stack](./docs/TECH_STACK.md)** - Technology choices and rationale\n\n## 💻 Code Examples\n\nSanitized code examples demonstrating key patterns:\n\n- **[MCP Router Pattern](./showcase/mcp-router/)** - Tool registry and routing\n- **[RAG Implementation](./showcase/rag/)** - Vector embeddings and search\n- **[LLM Integration](./showcase/llm-integration/)** - Tool calling examples\n\n## 🛠️ Key Technical Features\n\n### 1. Custom Tool Registry Pattern\nClean separation between LLM communication and data functions:\n\n```typescript\n// Extensible tool registry\nconst TOOL_REGISTRY = {\n  'analyze_data': {\n    description: 'Comprehensive data analysis tool',\n    handler: async (params) =\u003e { /* ... */ }\n  }\n}\n```\n\n### 2. RAG System with Vector Search\nProduction-ready retrieval-augmented generation:\n\n- Vector embedding generation\n- Semantic similarity search\n- Knowledge base integration\n- Context retrieval for LLM\n\n### 3. Structured LLM Outputs\nType-safe JSON generation with validation:\n\n- Schema validation\n- Error handling\n- Data integrity measures\n- Reliable structured outputs\n\n### 4. Production-Ready Patterns\n- Comprehensive error handling\n- Logging and monitoring\n- Type safety with TypeScript\n- Scalable architecture\n\n## 💡 Technical Insights\n\n### Why MCP-Like Architecture?\n- Provides clean separation of concerns\n- Makes LLM integration maintainable\n- Allows easy addition of new tools\n- Facilitates migration to real MCP server\n\n### RAG Implementation Decisions\n- Chose pgvector over external vector DB for simplicity\n- OpenAI embeddings for reliability\n- Top-K retrieval for performance\n- Integration with existing PostgreSQL infrastructure\n\n### LLM Integration Challenges\n- Structured output reliability\n- Data integrity enforcement\n- Error handling and fallbacks\n- Token optimization\n\n## 🚀 Key Achievements\n\n- ✅ Implemented custom MCP-like architecture for LLM tool integration\n- ✅ Built production RAG system with vector embeddings\n- ✅ Designed scalable data models for multi-modal analytics\n- ✅ Created evidence-based analysis engine with citation requirements\n- ✅ Deployed production application with optimized performance\n\n## 📄 License\n\nTechnical showcase - Code examples are for demonstration and educational purposes.\n\n**Note**: This repository contains sanitized code examples and architecture documentation. The full production application remains private to protect intellectual property.\n\n---\n\n## Connect\n\n- LinkedIn: http://linkedin.com/in/david-elliott-6304555a\n- Email: ellttdave218@gmail.com\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fellttdave%2Fathlete-performance-platform-showcase","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fellttdave%2Fathlete-performance-platform-showcase","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fellttdave%2Fathlete-performance-platform-showcase/lists"}