Title: Converting RecallOS into a Terminal-Based Local AI Document Assistant

1. RecallOS is a Python-based AI document memory and search assistant built using Streamlit, Ollama, and ChromaDB.
2. I want to convert it into a terminal-only application that runs directly inside VS Code without opening a browser.
3. The application should support PDF, DOCX, TXT, and Markdown documents.
4. It should extract text from documents and generate embeddings using Sentence Transformers.
5. ChromaDB should store document embeddings and support semantic search.
6. Ollama with Gemma 3 (4B) should generate answers locally using Retrieval-Augmented Generation (RAG).
7. The application should display relevant source documents and passages alongside answers.
8. It should preserve local chat history and allow users to search previous conversations.
9. I want to reuse my existing main.py, model.py, and tools.py functionality wherever possible.
10. Please suggest a reliable architecture and provide step-by-step implementation guidance with complete code while preserving privacy and existing features.