Easily prototype and scale Retrieval-augmented generation apps with Ragtastic.
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
·
Table of Contents
Ragtastic is designed to simplify the development of Retrieval-augmented generation (RAG) applications, making it easy to integrate large language models and vector databases through an intuitive UI. Whether you're a developer looking to prototype AI interactions or a data professional aiming to build generative search apps, Ragtastic provides the essential tools to enhance your AI-driven solutions efficiently.
This section lists any major frameworks/libraries used to bootstrap your project:
There are several ways to get started working with Ragtastic. You can use one of our release builds listed here. To get a local copy up and running follow these simple steps.
Installation Clone the repo
git clone https://github.com/Yerrington-Consulting/Ragtastic.gitInstall Packages
From the Ragtastic/client directory, install the client packages.
yarn install| Command | Description |
|---|---|
yarn dev |
🚀 Starts the development server using Vite. |
yarn build:web |
🌐 Builds the web version of the application with specific Vite config. |
yarn build:electron |
🖥️ Builds the Electron version of the application with specific Vite config. |
yarn lint |
🔍 Runs ESLint to check for code issues in .js and .jsx files. |
yarn preview |
📦 Serves the built app for testing with Vite preview. |
Setting Up the Python Environment
For this project, we recommend using a virtual environment to isolate the package dependencies. Follow these steps to set up your environment and run the application.
Prerequisites
Python: Ensure you have Python installed on your machine. You can download it from python.org or use a package manager on your operating system.
Soon, we will add the
requirements.txt
From the Ragtastic/server directory, create a separate environment (highly recommended).
Create a Virtual Environment Navigate to the project directory where the requirements.txt is located and create a virtual environment using:
python -m venv venvpython3 -m venv venvActivate the Virtual Environment Before you install dependencies or run the application, activate the virtual environment:
.\venv\Scripts\activatesource venv/bin/activateInstall Dependencies
With the virtual environment activated, install the project dependencies:
pip install -r requirements.txtRunning the Application
With the virtual environment set up and dependencies installed, you are ready to run the application.
Start the FastAPI server To run the FastAPI application, use the following command:
uvicorn app.main:app --reloadDeactivating the Virtual Environment When you're done working with the application, you can deactivate the virtual environment by running:
deactivateThis command will return you to your system’s default Python interpreter.
Use Ragtastic to manage chat sessions, configure prompts dynamically, and integrate with vector databases for enhanced user queries. For more examples, refer to the Documentation.
- Initial Release with basic chat session management
- Integration with OpenAI API models (GPT-3.x, GPT-4.x)
- Support for Vector Database (ChromaDB)
- Cross-platform builds for Mac, Windows, and Linux
See the open issues for a full list of proposed features (and known issues) or come to our Discord #feature-requests channel.
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request