Code Embeddings

🚀 Code Knowledge Tool

A knowledge management system for code repositories that uses vector embedding technology to maintain and query knowledge in the codebase.

🚀 Quick Start

This tool leverages advanced embedding technology to manage and query knowledge in code repositories.

📦 Installation

1. Build the Package

First, generate the distribution files:

# Clone the repository
git clone https://github.com/yourusername/code-knowledge-tool.git
cd code-knowledge-tool

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate

# Install build tools
python -m pip install --upgrade pip build

# Build the package
python -m build

This will generate two files in the dist/ directory:

• code_knowledge_tool-0.1.0-py3-none-any.whl (Wheel file for installation)
• code_knowledge_tool-0.1.0.tar.gz (Source distribution)

2. Install the Package

Prerequisites

1. Ensure Ollama is installed and running:

# Install Ollama if not already installed
curl https://ollama.ai/install.sh | sh

# Start the Ollama service
ollama serve

2. Install the package:

Option 1: Install from the wheel file (Recommended for usage)

# Navigate to the directory of the built package
cd /path/to/code-knowledge-tool

# Install using the wheel file
pip install dist/code_knowledge_tool-0.1.0-py3-none-any.whl

Option 2: Install in development mode (Recommended for development)

This option is suitable if you want to modify the tool or contribute to its development:

# Assume you are already in the code-knowledge-tool directory and the virtual environment is activated

# Install in development mode with development dependencies
pip install -e ".[dev]"

💻 Usage Examples

Integration with RooCode/Cline

1. Copy the MCP configuration to your settings:

For Cline (VSCode):

# Open the settings file
open ~/Library/Application\ Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json

Add the following configuration:

{
  "mcpServers": {
    "code_knowledge": {
      "command": "python",
      "args": ["-m", "code_knowledge_tool.mcp_tool"],
      "env": {
        "PYTHONPATH": "${workspaceFolder}"
      }
    }
  }
}

For RooCode:

# Open the settings file
open ~/Library/Application\ Support/RooCode/settings/mcp_config.json

Add the following configuration:

{
  "mcpServers": {
    "code_knowledge": {
      "command": "python",
      "args": ["-m", "code_knowledge_tool.mcp_tool"],
      "env": {
        "PYTHONPATH": "${workspaceFolder}"
      }
    }
  }
}

✨ Features

As a Memory Bank and RAG Context Provider

This tool can serve as a memory bank for code repositories, helping you store code knowledge in the form of vector embeddings and supporting queries through similarity searches. This is very useful for code completion, understanding code context, and development assistance.

🧪 Testing and Verification

1. Install Test Dependencies

If you need to conduct more in-depth testing or verify the tool's functionality, you can install the following test dependencies:

pip install -r requirements-test.txt

2. Run Tests

Run the following command to execute unit tests and integration tests:

pytest tests/

🚧 Future Development

If you want to publish this tool to PyPI (Python Package Index), you need to:

1. Register an account on PyPI.
2. Install twine: pip install twine
3. Upload the distribution using the following command:

   twine upload dist/*
   

However, currently, it is recommended to use the local build and installation method.

📄 License

MIT License