https://github.com/woheller69/gpt4all-tk-chat

A TK based graphical user interface for gpt4all. It uses the python bindings. Run LLMs in a very slimmer environment and leave maximum resources for inference
https://github.com/woheller69/gpt4all-tk-chat

ai gpt gpt4all gui-application llm-inference python

Last synced: 6 days ago
JSON representation

A TK based graphical user interface for gpt4all. It uses the python bindings. Run LLMs in a very slimmer environment and leave maximum resources for inference

• Host: GitHub
• URL: https://github.com/woheller69/gpt4all-tk-chat
• Owner: woheller69
• License: mit
• Created: 2024-02-18T08:12:33.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-05-17T21:10:22.000Z (6 months ago)
• Last Synced: 2024-10-31T08:37:26.244Z (13 days ago)
• Topics: ai, gpt, gpt4all, gui-application, llm-inference, python
• Language: Python
• Homepage:
• Size: 177 KB
• Stars: 7
• Watchers: 4
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# GPT4All TK CHAT GUI

## Quickstart

The TK GUI is based on the `gpt4all` Python bindings and the `typer` and `tkinter` package.

The following shows one way to get started with the GUI.

Typically, you will want to replace `python` with `python3` on _Unix-like_ systems. 

Also, it's assumed you have all the necessary Python components already installed.

The GUI is a self-contained Python script named `appGUI.py`. As long as

its package dependencies are present, you can download and run it from wherever you like.

```shell

# pip-install the necessary packages;

python -m pip install --upgrade gpt4all typer tkinter

```

Specify the path to the model with the `-m`/`--model` argument and an optional prompt template with `-p`/`--prompt`. 

A system prompt can also be set with `-s`/`--sysprompt`.

Context length defaults to 2048, it can be set with `-c`/`--context-length`. The number of threads can be set with `-t`/`--n-threads`.

The device to use, e.g. gpu, amd, nvidia, intel, can be set with `-d`/`--device`. It defaults to CPU.

```shell

python appGUI.py --model /home/user/my-gpt4all-models/gpt4all-13b-snoozy-q4_0.gguf --prompt 'Human: {0} Assistant: '

(or --prompt $'Human:\n{0}\n Assistant:\n' with line breaks)

```

Input your request in the bottom window and click ```Generate```.

Inference can be interrupted using the ``Stop`` button.