OpenAI Copilot

Your life Copilot powered by OpenAI (CLI interface for OpenAI with searching).

Features:

• Web access and Google search support without leaving the terminal.
• Automatically execute any steps predicted from prompt instructions.
• Human interactions on uncertain instructions to avoid inappropriate operations.

Install

Install the copilot with pip command below:

pip install openai-copilot

Setup

• OpenAI API key should be set to OPENAI_API_KEY environment variable to enable the ChatGPT feature.
  • OPENAI_API_BASE should be set as well for Azure OpenAI service.
• Google Search API key and CSE ID should be set to GOOGLE_API_KEY and GOOGLE_CSE_ID.

How to use

Usage: openai-copilot [OPTIONS]

  Your life Copilot powered by OpenAI

Options:
  --version          Show the version and exit.
  --verbose          Enable verbose information of copilot execution steps
  --model MODEL      OpenAI model to use for copilot execution, default is
                     gpt-3.5-turbo
  --enable-terminal  Enable Copilot to run programs within terminal. Enable
                     with caution since Copilot may execute inappropriate
                     commands
  --help             Show this message and exit.

Here is a conversation sample (user inputs are after >>>)):

# openai-copilot
>>> What is OpenAI?
OpenAI is an artificial intelligence research laboratory consisting of the for-profit corporation OpenAI LP and its parent company, the non-profit OpenAI Inc. The company is dedicated to advancing digital intelligence in a way that is safe and beneficial for humanity as a whole. OpenAI was founded in 2015 by a group of technology leaders including Elon Musk, Sam Altman, Greg Brockman, and Ilya Sutskever. Its mission is to develop and promote friendly AI for the betterment of all humans.
>>> What are the differences between GPT-4 and GPT-3.5?
According to my search results, one of the main differences between GPT-4 and GPT-3.5 is that while GPT-3.5 is a text-to-text model, GPT-4 is more of a data-to-text model. Additionally, GPT-4 has the advantage of providing more creative replies to prompts. However, it's important to note that GPT-4 is not yet released and there is limited information available about it.
>>>

Run in Kubernetes

# Run with gpt-4 (default model)
kubectl run -it --rm copilot \
  --env="OPENAI_API_KEY=$OPENAI_API_KEY" \
  --restart=Never \
  --image=ghcr.io/feiskyer/openai-copilot

# Run with a different model and enable verbose outputs
kubectl run -it --rm copilot \
  --env="OPENAI_API_KEY=$OPENAI_API_KEY" \
  --restart=Never \
  --image=ghcr.io/feiskyer/openai-copilot \
  -- --model=gpt-3.5-turbo --verbose

Contribution

The project is opensource at github feiskyer/openai-copilot with Apache License.

If you would like to contribute to the project, please follow these guidelines:

1. Fork the repository and clone it to your local machine.
2. Create a new branch for your changes.
3. Make your changes and commit them with a descriptive commit message.
4. Push your changes to your forked repository.
5. Open a pull request to the main repository.