refactor: migrate chat and ingestion logic into dedicated services and consolidate database initialization

feat: introduce VECTOR_SIZE configuration for dynamic Qdrant collection creation

feat: implement document chunking with configurable size and overlap during ingestion

refactor: modularize data loading and ingestion logic for improved maintainability

feat: clear existing collection in Qdrant before running ingestion process

feat: implement RAG pipeline with Qdrant vector store, Groq LLM integration, and structured prompt management