feat: implement real-time text-to-speech highlighting and document management within chat interface

feat: implement backend configuration, dynamic frontend API routing, and core React application structure with modular components

feat: implement Midnight Amethyst theme, ChatWindow UI component, and backend entry point

feat: implement RAG chat endpoint with session management and cross-document streaming response generation

clean: remove obsolete docker dependencies and empty temporary scripts

perf: swap to lightweight ms-marco-MiniLM reranker for lower cpu latency

fix: create qdrant payload indexes on startup for filtering

chore: add dynamic API base URL and improve backend error handling

feat: implement full-stack authentication, chat interface, document management, and voice service integration

feat: implement SpeechModelManager to handle STT and TTS model initialization and warmup

feat: implement voice transcription service with FFmpeg audio processing and API routing

feat: add VoiceService with audio transcription using FFmpeg and Whisper model integration

feat: add Dockerfile for backend service with system dependencies and model configurations

feat: initialize FastAPI application with database setup, CORS middleware, and background model warming

feat: implement speech-to-text and text-to-speech services using Whisper and Kokoro with a background model manager.

refactor: condense Dockerfile patching logic and add a dedicated backend Dockerfile for containerized deployment

feat: add backend-specific Dockerfile and apply automated input validation patch for Qwen modules

Initial clean commit