8000 GitHub - huyu9711/pyrag · GitHub
[go: up one dir, main page]

Skip to content
huyu9711Public

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Local RAG Knowledge Base Tool

A Python GUI application that allows you to create and query a local RAG (Retrieval-Augmented Generation) knowledge base using Ollama models.

Features

  • Create a knowledge base from local files
  • Choose different Ollama models for embeddings and question answering
  • Query the knowledge base with natural language questions
  • Simple and intuitive GUI interface
  • Local processing - no data leaves your computer

Prerequisites

  • Python 3.8 or higher
  • Ollama installed and running locally
  • Required Python packages (install using pip install -r requirements.txt)

Installation

  1. Clone this repository:
git clone <repository-url>
cd <repository-name>
  1. Install the required packages:
pip install -r requirements.txt
  1. Make sure Ollama is installed and running on your system. You can download it from Ollama's official website.

  2. Pull the required Ollama models:

ollama pull llama2
ollama pull mistral
ollama pull codellama

Usage

  1. Run the application:
python main.py
  1. Using the application:
    • Click "Select Files" to choose the files you want to include in your knowledge base
    • Select the embedding model for creating the knowledge base
    • Select the QA model for answering questions
    • Click "Create Knowledge Base" to process your files
    • Once the knowledge base is created, you can ask questions in the question input field
    • Click "Ask Question" to get answers based on your knowledge base

Supported Models

The application supports the following Ollama models:

  • llama2
  • mistral
  • codellama

Notes

  • The knowledge base is stored locally in the knowledge_base directory
  • Processing large files may take some time
  • Make sure you have enough disk space for the vector store
  • The application requires an active internet connection to download Ollama models (first time only)

License

This project is licensed under the MIT License - see the LICENSE file for details.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages

0