Skip to main content

Command-line interface using GPT4ALL bindings

Project description

A simple GNU Readline-based application for interaction with chat-oriented AI models using GPT4All Python bindings.

Contents

Install

The following installation options are available:

Pip

$ pip install git+https://github.com/sergei-mironov/gpt4all-cli.git

Note: pip install gpt4all-cli might also work, but the git+https method would bring the most recent version.

Nix

$ git clone --depth=1 https://github.com/sergei-mironov/gpt4all-cli && cd gpt4all-cli
# Optionally, change the 'nixpkgs' input of the flake.nix to a more suitable
$ nix profile install ".#python-gpt4all-cli"

Usage

usage: gpt4all-cli [-h] [--model-dir MODEL_DIR] [--model MODEL]
                   [--num-threads NUM_THREADS]
                   [--model-temperature MODEL_TEMPERATURE] [--device DEVICE]
                   [--readline-key-send READLINE_KEY_SEND]
                   [--readline-prompt READLINE_PROMPT] [--revision]

Command-line arguments

options:
  -h, --help            show this help message and exit
  --model-dir MODEL_DIR
                        Model directory to prepend to model file names
  --model MODEL, -m MODEL
                        Model to use for chatbot
  --num-threads NUM_THREADS, -t NUM_THREADS
                        Number of threads to use for chatbot
  --model-temperature MODEL_TEMPERATURE
                        Temperature parameter of the model
  --device DEVICE, -d DEVICE
                        Device to use for chatbot, e.g. gpu, amd, nvidia,
                        intel. Defaults to CPU.
  --readline-key-send READLINE_KEY_SEND
                        Terminal code to treat as Ctrl+Enter (default: \C-k)
  --readline-prompt READLINE_PROMPT
                        Input prompt (default: >>>)
  --revision            Print the revision

The console accepts language defined by the following grammar:

start: (command | escape | text)? (command | escape | text)*
escape.3: /\\./
command.2: /\/reset|\/help|\/ask|\/exit/ | \
           /\/model/ / +/ string | \
           /\/nthreads/ / +/ (number | def) | \
           /\/temp/ / +/ (float | def ) | \
           /\/echo/ | /\/echo/ / /
string: /"[^\"]+"/ | /""/
number: /[0-9]+/
float: /[0-9]+\.[0-9]*/
def: "default"
text: /(.(?!\/|\\))*./s

Example session

$ gpt4all-cli
Type /help or a question followed by the /ask command (or by pressing `C-k` key).
>>> /model "~/.local/share/nomic.ai/GPT4All/Meta-Llama-3-8B-Instruct.Q4_0.gguf"
>>> Hi!
>>> /ask
Hello! I'm happy to help you. What's on your mind?^C
>>> What's your name?
>>> /ask
I don't really have a personal name, but you can call me "Assistant"

Vim integration

Gpt4all-cli is supported by the Litrepl text processor.

Peek 2024-07-19 00-11

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gpt4all_cli-1.2.0.tar.gz (7.4 kB view details)

Uploaded Source

Built Distribution

gpt4all_cli-1.2.0-py3-none-any.whl (7.4 kB view details)

Uploaded Python 3

File details

Details for the file gpt4all_cli-1.2.0.tar.gz.

File metadata

  • Download URL: gpt4all_cli-1.2.0.tar.gz
  • Upload date:
  • Size: 7.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.11.9

File hashes

Hashes for gpt4all_cli-1.2.0.tar.gz
Algorithm Hash digest
SHA256 c8c7642f18b9532c3dd0e455aa6aa55637d67a686bf76a237485c09dd4eacf29
MD5 cc6e3f52fca186a14e5a4790bbf210ea
BLAKE2b-256 1584c504cadea419fa208c796a9371a8fd6efd927ac0378d24abfaa5541f133a

See more details on using hashes here.

File details

Details for the file gpt4all_cli-1.2.0-py3-none-any.whl.

File metadata

  • Download URL: gpt4all_cli-1.2.0-py3-none-any.whl
  • Upload date:
  • Size: 7.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.11.9

File hashes

Hashes for gpt4all_cli-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f10d9f92e3b5853ff8424951cb3ec89ecf286449e6016524606c39f2f20c6d60
MD5 7e7a583e7db3a36d506ac34f8ff616b5
BLAKE2b-256 cc6b49672789994079f972201cadff875ce001a7882a7d41ed1061c24f234cc9

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page