GPTO (Geppetto)
An Unofficial OpenAI GPT3 Terminal Client
```bash
gpto -h
A tiny unofficial OpenAI GPT3 client
Usage: gpto [OPTIONS]
Options:
-p, --prompt ... The prompt(s) to generate completions for
-s, --suffix ... The suffix that comes after a completion of inserted text. Defaults to an empty string
-t, --temperature What sampling temperature to use.
Higher values means the model will take more risks.
Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.
Defaults to 1.0
-n, --number How many completions to generate for each prompt. Defaults to 1
-k, --topp An alternative to sampling with temperature, called nucleus sampling,
where the model considers the results of the tokens with topp probability mass.
So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature but not both.
Defaults to 1.0
-m, --model Model to use for completion. Defaults to text-davinci-003. Use --models to see complete list.
-o, --config Absolute path of configuration. Defaults to $XDGCONFIGHOME/gpto.cfg
-d, --models Returns a list of models from OpenAI
-e, --echo Echo back the prompt in addition to the completion. Defaults to false
-h, --help Print help information
-V, --version Print version information
```
Learn more about how to use text completion
Install from Crates.io
Install Rust
```bash
Linux and MacOS
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
```
Install GTPO
bash
cargo install gtpo
Install from AUR
```bash
Use yay or another AUR helper
yay gpto-bin
```
Install from GitHub
Install Rust
Clone the project
bash
git clone git@github.com:alanvardy/gpto.git
cd gpto
./test.sh # run the tests
cargo build --release
You can then find the binary in /target/release/
Usage
Get a completion with default parameters
```bash
gpto --prompt tell me a joke
Q: What did the fish say when it hit the wall?
A: Dam!
```
Get a completion with a different model (this example uses the leading code completion model). And yes, the generated code is not idiomatic!
Read more about models here
```bash
gpto -m code-davinci-002 -p language is elixir\nwrite a function that raises an error if the argument is not an integer and multiplies it by 2 if it is an integer
def multiplybytwo(x)
raise ArgumentError, "Argument is not an integer" unless x.is_a? Integer
x * 2
end
```
Give an exhaustive list of all models
```bash
gpto --models
Models:
babbage
ada
davinci
babbage-code-search-code
text-similarity-babbage-001
... and so on
```