Implement Phase 2 - Local AI Core

**Description:**
With the core backend foundation complete, the next step is to integrate the agentic AI system. This involves setting up the RAG pipeline with a local vector store and orchestrating the team of LLM agents using AutoGen.

**Acceptance Criteria:**
- [ ] Integrate ChromaDB for local vector storage.
- [ ] Implement a RAG pipeline to embed new notes into ChromaDB.
- [ ] Set up AutoGen with the defined team of local Ollama models.
- [ ] Create a `/chat` endpoint that accepts a user query and returns a response from the agentic system.
- [ ] The AI's response should be informed by the content of the user's notes via the RAG pipeline.