How selvendran-b/skillpulse-analytics works
SkillPulse Analytics combines authenticated career-source ingestion with a dashboard and an AI assistant grounded in a user’s connected data. Source-specific routes and services process Resume, LinkedIn, GitHub, and LeetCode information; synchronization builds searchable knowledge, embeddings, and project links. For questions, routing selects sources and retrieval strategies before retrieval supplies context for AI responses. The graph retains the documented comparison and dashboard capabilities. Some links come from the README or source-index references; unsampled implementation details are not assumed.
Main entry points: App.jsx Web application · models.py PostgreSQL data · ai_orchestrator.py AI data sync · main.py API application
Components 26
User experience
- Web application
frontend/src/App.jsx - Resume page
frontend/src/pages/Resume.jsx - LinkedIn page
frontend/src/pages/LinkedIn.jsx - GitHub page
frontend/src/pages/GitHub.jsx - LeetCode page
frontend/src/pages/LeetCode.jsx - Comparison page
frontend/src/pages/Comparison.jsx - AI assistant page
frontend/src/pages/AIAssistant.jsx
Career data
- API application
backend/main.py - Resume processing
backend/routes/resume.py - LinkedIn processing
backend/linkedin/linkedin_service.py - GitHub integration
backend/github/github_service.py - LeetCode integration
backend/leetcode/leetcode_service.py - Career profile
backend/career/profile_builder.py
Knowledge preparation
- AI data sync
backend/services/ai_orchestrator.py - Knowledge builder
backend/knowledge/builder.py - Project linking
backend/project_link/project_linker.py - Embedding service
backend/embeddings/embedding_service.py
AI answering
- AI API routes
backend/ai/router.py - Question routing
backend/ai/query_router.py - Context retrieval
backend/rag/retrieval_router.py - Cross-source retrieval
backend/rag/cross_source_retriever.py - LLM client
backend/ai/llm_client.py
Persistence
- PostgreSQL data
backend/models.py - Vector store
Other components
- Career user
- Groq service
Connections 35
- Career user → Web application: uses
- Web application → Resume page: routes
frontend/src/App.jsx - Web application → LinkedIn page: routes
frontend/src/App.jsx - Web application → GitHub page: routes
frontend/src/App.jsx - Web application → LeetCode page: routes
frontend/src/App.jsx - Web application → Comparison page: routes
frontend/src/App.jsx - Web application → AI assistant page: routes
frontend/src/App.jsx - Web application → API application: requests
- API application → Resume processing: registers
backend/main.py - API application → LinkedIn processing: registers
backend/main.py - API application → LeetCode integration: registers
backend/main.py - API application → GitHub integration: registers
backend/main.py - Resume processing → AI data sync: synchronizes
backend/routes/resume.py - LinkedIn processing → AI data sync: synchronizes
backend/linkedin/linkedin_service.py - GitHub integration → AI data sync: synchronizes
backend/github/github_service.py - LeetCode integration → AI data sync: synchronizes
backend/leetcode/leetcode_service.py - Resume processing → PostgreSQL data: stores profile
backend/routes/resume.py - LinkedIn processing → PostgreSQL data: stores profile
backend/linkedin/linkedin_routes.py - LeetCode integration → PostgreSQL data: stores profile
backend/leetcode/leetcode_routes.py - GitHub integration → PostgreSQL data: stores data
backend/routes/github.py - Resume processing → Career profile: builds profile
- AI data sync → Knowledge builder: builds knowledge
backend/services/ai_orchestrator.py - AI data sync → Project linking: builds links
backend/services/ai_orchestrator.py - AI data sync → Embedding service: updates vectors
backend/services/ai_orchestrator.py - Knowledge builder → PostgreSQL data: writes chunks
backend/knowledge/builder.py - Embedding service → PostgreSQL data: reads chunks
backend/embeddings/embedding_service.py - Embedding service → Vector store: writes vectors
backend/embeddings/embedding_service.py - AI API routes → Question routing: routes question
- Question routing → Context retrieval: selects retrieval
backend/rag/retrieval_router.py - Context retrieval → Cross-source retrieval: retrieves context
backend/rag/retrieval_router.py - Context retrieval → PostgreSQL data: queries records
backend/rag/retrieval_router.py - Context retrieval → Vector store: searches vectors
- AI API routes → LLM client: generates answers
- LLM client → Groq service: sends prompts
- AI API routes → PostgreSQL data: loads data
backend/ai/router.py