https://github.com/deontologician/openai-api-rust
Rust client for OpenAI API
https://github.com/deontologician/openai-api-rust
gpt-3 openai wrapper-library
Last synced: 11 months ago
JSON representation
Rust client for OpenAI API
- Host: GitHub
- URL: https://github.com/deontologician/openai-api-rust
- Owner: deontologician
- License: apache-2.0
- Created: 2020-12-05T19:40:41.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2023-09-13T18:19:43.000Z (almost 3 years ago)
- Last Synced: 2025-07-05T01:46:18.073Z (12 months ago)
- Topics: gpt-3, openai, wrapper-library
- Language: Rust
- Homepage:
- Size: 43.9 KB
- Stars: 102
- Watchers: 2
- Forks: 25
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# openai-api-rust

[](https://crates.io/crates/openai-api)

A simple rust client for OpenAI API.
Has a few conveniences, but is mostly at the level of the API itself.
# Installation
```
$ cargo add openai-api
```
# Quickstart
```rust
#[tokio::main]
async fn main() -> Result<(), Box> {
let api_token = std::env::var("OPENAI_SK")?;
let client = openai_api::Client::new(&api_token);
let prompt = String::from("Once upon a time,");
println!(
"{}{}",
prompt,
client.complete(prompt.as_str()).await?
);
Ok(())
}
```
# Basic Usage
## Creating a completion
For simple demos and debugging, you can do a completion and use the `Display` instance of a `Completion` object to convert it to a string:
```rust
let response = client.complete_prompt("Once upon a time").await?;
println!("{}", response);
```
To configure the prompt more explicitly, you can use the `CompletionArgs` builder:
```rust
let args = openai_api::api::CompletionArgs::builder()
.prompt("Once upon a time,")
.engine("text-davinci-003")
.max_tokens(20)
.temperature(0.7)
.top_p(0.9)
.stop(vec!["\n".into()]);
let completion = client.complete_prompt(args).await?;
println!("Response: {}", response.choices[0].text);
println!("Model used: {}", response.model);
```
See [examples/](./examples)