See https://github.com/AineeJames/ChatGPTerminator for more details!
Project description
GPTerminator :robot:
This terminal interface provides a convenient way to interact with OpenAI's chat completion and image generation API's using your command line interface.
Getting Started :rocket:
To use this terminal interface, follow these steps:
-
Either clone this repository to your local machine and run
pip install .
or install it from PyPi by runningpip install gpterminator
-
Set the OPENAI_API_KEY env variable (you may want this in your .rc file):
export OPENAI_API_KEY=PUT_API_KEY_HERE
-
Run the following command to start the ChatGPT terminal interface:
gpterm
-
You can now start chatting. Type a message and press Enter to get a response.
-
Type !help for a list of commands to use
Running with podman/docker :package:
Build the image and provide the APIKEY
podman build \
--build-arg APIKEY=$(echo $OPENAI_API_KEY) \
-t gpterm .
Run gpterm in the container
podman run -it --rm --name gpterm gpterm
Set an alias for easy access
echo "alias gpterm='podman run -it --rm --name gpterm gpterm'" >> ~/.bashrc
Usage :bulb:
Configuration :gear:
The config.ini directory resides in different locations dependent on your OS. In order to find the path, run GPTerminator and then type !pconf
.
GPTerminator is configurable and can support multiple configurations. Add the following to your config.ini:
[CONFIG_TEMPLATE]
ModelName =
SystemMessage =
Temperature =
PresencePenalty =
FrequencyPenalty =
CommandInitiator =
SavePath =
- ModelName: this is the model used when chatting
- Temperature = between 0 and 2
- PresencePenalty = between -2 and 2
- FrequencyPenalty = between -2 and 2
- SystemMessage: this is the starting system message sent to the API
- CommandInitiator: this can be set to change the default ! structure
- SavePath: this changes the location of the save path when loading/saving
Note: More details on some settings can be found here
After saving the config file, run: gpterm
Then, type !setconf and select which config you wish to use, you can also run the !pconf commang to view the current config details.
Note: If you change the CommandInitiator, you will now type to execute commands...
Contributing :raised_hands:
Current Contributors:
We welcome contributions to this project. If you find a bug, have a feature request, or want to contribute code, please open an issue or submit a pull request.
Disclaimer :warning:
This program uses the openai API to chat and generate images using dalle. It is a good idea to put a usage cap on your billing, just in case something goes wrong!
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for gpterminator-0.1.7-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a7ec9b846e0fc5c94ca020490bf49b9bcad4eb3b136227b184bc796f4f6c2cce |
|
MD5 | 1924ace9b11a839526ce8bad3d7dc424 |
|
BLAKE2b-256 | a6d8dda39fbb22594431cfdf156324009e3e160237538404e47e2f90faadff27 |