* Add gpt4all-bindings/cli/README.md * Unify version information - Was previously split; base one on the other - Add VERSION_INFO as the "source of truth": - Modelled after sys.version_info. - Implemented as a tuple, because it's much easier for (partial) programmatic comparison. - Previous API is kept intact. * Add gpt4all-bindings/cli/developer_notes.md - A few notes on what's what, especially regarding docs * Add gpt4all-bindings/python/docs/gpt4all_cli.md - The CLI user documentation * Bump CLI version to 0.3.5 * Finalise docs & add to index.md - Amend where necessary - Fix typo in gpt4all_cli.md - Mention and add link to CLI doc in index.md * Add docstings to gpt4all-bindings/cli/app.py * Better 'groovy' link & fix typo - Documentation: point to the Hugging Face model card for 'groovy' - Correct typo in app.py
1.7 KiB
GPT4All Command-Line Interface (CLI)
GPT4All on the command-line.
Documentation
https://docs.gpt4all.io/gpt4all_cli.html
Quickstart
The CLI is based on the gpt4all
Python bindings and the typer
package.
The following shows one way to get started with the CLI, the documentation has more information.
Typically, you will want to replace python
with python3
on Unix-like systems and py -3
on
Windows. Also, it's assumed you have all the necessary Python components already installed.
The CLI is a self-contained Python script named app.py (download). As long as its package dependencies are present, you can download and run it from wherever you like.
# optional but recommended: create and use a virtual environment
python -m venv gpt4all-cli
Windows and Unix-like systems differ slightly in how you activate a virtual environment:
- Unix-like, typically:
. gpt4all-cli/bin/activate
- Windows:
gpt4all-cli\Scripts\activate
Then:
# pip-install the necessary packages; omit '--user' if using a virtual environment
python -m pip install --user --upgrade gpt4all typer
# run the CLI
python app.py repl
By default, it will automatically download the groovy
model to .cache/gpt4all/
in your user
directory, if necessary.
If you have already saved a model beforehand, specify its path with the -m
/--model
argument,
for example:
python app.py repl --model /home/user/my-gpt4all-models/GPT4All-13B-snoozy.ggmlv3.q4_0.bin