- AI chat with SSE streaming (Microsoft Agent Framework + Qwen)
- RAG Q&A with hybrid retrieval (vector + keyword RRF fusion)
- Knowledge base CRUD with semantic text chunking
- Embedding generation via Azure.AI.OpenAI / LM Studio
- Document upload with chunked upload support
- Redis caching for chat messages
- Chunk/vector preview endpoints
- gRPC auth service improvements
- Removed demo menus, cleaned up seed data