A modern full-stack application that enables intelligent knowledge discovery using Pinecone vector database, Google Gemini AI, and role-based access control.
- π Intelligent Search: Multiple retrieval modes (Dense, Sparse, Hybrid)
- π Role-Based Access: Different access levels (Intern, Employee, Manager, Executive)
- π€ AI-Powered: Pinecone vector database + Google Gemini response generation
- π Session History: Track searches during your session
- π¨ Modern UI: Beautiful React interface with smooth animations
- β‘ Real-time: FastAPI backend with live search capabilities
- Select your role (Intern, Employee, Manager, Executive)
- Choose retrieval mode:
- Dense: Semantic similarity search
- Sparse: Keyword-based BM25 search
- Hybrid: Combined approach
- Enter your query and click "Generate Insights"
- View results with AI-generated summaries
- Check history panel for previous searches
| Mode | Description | Best For |
|---|---|---|
| Dense | Semantic embeddings | Conceptual queries, synonyms |
| Sparse | Keyword matching (BM25) | Exact terms, technical queries |
| Hybrid | Combined dense + sparse | Best overall performance |
- Intern: Learning materials and basic information
- Employee: Standard company policies and procedures
- Manager: Team management and operational data
- Executive: Strategic and high-level information
- Automatically tracks all searches during your session
- Click any history item to restore previous results
- History clears when you refresh the page
- Shows search metadata (time, mode, role, results count)