feat: Add API models and schemas for chat, collections, documents, vectorization, synthesis, and queries

- Implemented Pydantic models for request and response validation in `api_models.py`.
- Created models for chat messages, knowledge sources, collections, documents, vectorization requests, synthesis requests, and health checks.
- Added new Bruno collection scripts for various API endpoints including chat, collections, documents, health checks, and queries.
- Developed a comprehensive RAG service in `rag_service.py` to handle document processing, vectorization, querying, and synthesis.
- Introduced a run script to start either Streamlit UI or FastAPI server.
- Added a test script to verify the functionality of the system components.