Journal RAG

🚀 Journal RAG System

This repository contains the code for implementing a Journal Retrieval Augmented Generation (RAG) system. The code is used for the journal published at https://dev.to/lord_magus/supercharging-my-vs-code-ai-agent-with-local-rag-25n8.

🚀 Quick Start

Directory Structure

The project is organized around journals, with technical components hidden:

/
├── README.md                 # Project overview
├── journal/                  # Journal entries
│   ├── 2025/                 # Categorized by year
│   │   └── 04/               # Month
│   │       ├── 18.md         # Daily journal
│   │       └── 19.md
│   └── topics/               # Topic entries (for future use)
├── code/                     # Code and scripts
│   ├── mcp/                  # MCP server code
│   │   └── journal_rag_mcp.py
│   ├── scripts/              # Python scripts
│   │   └── rag_search.py
│   └── data/                 # Data storage (e.g., vector database)
│       └── chroma_db/        # Vector database (example)
└── .venv/                    # Python virtual environment

Usage Instructions

Journal Keeping

Add daily journal entries to the journal/YYYY/MM/ directory structure. Note: Currently, the .md files in the journal/ directory are AI-generated example files for testing indexing and querying functions.

RAG Search

Perform semantic searches on journals using natural language queries:

source .venv/bin/activate
python .tech/code/scripts/rag_search.py

This will recursively index all journal entries and allow you to perform semantic searches using natural language queries. For detailed installation steps, refer to install_instructions.md.

MCP Server

This repository also includes the code for an MCP server. The server allows you to connect the journal RAG system to an AI agent to enhance interactions. For detailed instructions on setting up and connecting the MCP server, refer to install_instructions.md.