RevivAI is an AI-powered code documentation assistant designed to help developers document their codebases more effectively. It analyses code and generates meaningful documentation, breathing new life into abandoned or poorly documented projects.
-
AI-Powered Documentation: Automatically generate documentation from codebases using advanced language models.
-
Chat With Your Code: It provides a chat interface where you can ask questions or get explanations about your code.
-
Local Files or Github Repository: Upload code files directly or link to public GitHub repositories for analysis.
-
Bring Your Own Key: Easily integrate LLM APIs like OpenAI, OpenRouter, Anthropic, Google or Ollama by providing your own API keys.
-
Customizable Settings: Configure LLM provider settings and adjust documentation parameters.
Before getting started, make sure to complete the Setup Instructions below. Once the application is running, refer to the guide in the /guide folder for detailed instructions on using all available features.
To set up RevivAI locally, follow these steps:
-
Clone the Repository:
git clone https://github.com/jrcz-data-science-lab/RevivAI.git cd RevivAI -
Install Dependencies: Ensure you have Node.js installed (v22.14 or later) , then run:
npm install
Note
If you getting an errors during npm install, try to delete package-lock.json and node_modules directory, then run npm install again.
- Environment Variables (Optional):
You can specify default AI provider (Self-hosted Ollama) by setting the following environment variables in a
.envfile at the root of the project:PUBLIC_OLLAMA_API_URL=your_llm_api_url PUBLIC_OLLAMA_API_MODEL=your_llm_model
Note
Ollama server should be accessible from the browser. If you are using a self-hosted Ollama server, ensure it is running and accessible at the specified URL. It is recommended to put Ollama server behind a reverse proxy (e.g., Nginx) to handle CORS configurations and rate limit.
-
Run the Application: Start the development server:
npm run dev
-
Access the Application: Open your browser and navigate to
http://localhost:4321. -
Build for Production (Optional): To build the application for production, specify
.envvariables, and run:npm run build
-
Start the Production Server: After building, you can start the production server with:
node dist/server/entry.mjs
-
Build the Docker image:
docker build -t revivai . -
Run the Docker container:
docker run -p 3000:3000 --name revivai-app revivai
Contributions are welcome! Please follow these steps to contribute:
- Fork the repository.
- Create a new branch (
git checkout -b feature-branch). - Make your changes and commit them (
git commit -m 'Add new feature'). - Push to the branch (
git push origin feature-branch). - Open a pull request.
This project was created by Kirills Reunovs as a bachelor thesis project during an internship at the JRCZ Data Science Labs, affiliated with HZ University of Applied Sciences.
This project is licensed under the MIT License. See the LICENSE file for details.