A simple implementation of Open AI assistant for study purpose. The assistant can:
- Create itself
- put user message into thread
- add file to OpenAI to vector store
- take the file as a contecst and instructions from files
- base on instructions and file(s) answer to user via console
install project and it's dependencies:
# Clone the repository
git clone https://github.com/yourusername/openai-assistant.git
# Navigate to the project directory
cd openai-assistant
# Install dependencies
npm i- Put you file into
filesfolder - Fill
assistant_instructions.mdfile with instruction for the assistant. - Get the OpenAI API key.
- Make a copy of file
.env.examlerename it to.envand fill it with correct data (tokens, vector store name, file name ... etc.); File name should be WITH EXTENSION! (examp:my_schedule.docx).
npm start
- Follow the instructions in application console.
Guidelines for contributing to the project:
- Fork the repository
- Create a new branch (git checkout -b feature-branch)
- Make your changes
- Commit your changes (git commit -m 'Add some feature')
- Push to the branch (git push origin feature-branch)
- Open a pull request