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:

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