A community-maintained library provides a simple and convenient way to interact with the OpenAI API. No complex async and redundant dependencies.
check official API reference |API|Support| |---|---| |Models|✔️| |Completions|✔️| |Chat|✔️| |Edits|✔️| |Images|✔️| |Embeddings|✔️| |Audio|✔️| |Files|❌| |Fine-tunes|❌| |Moderations|❌| |Engines|❌|
Add the following to your Cargo.toml file:
toml
openai_api_rust = "0.1.5"
Export your API key into the environment variables
bash
export OPENAI_API_KEY=<your_api_key>
Then use the crate in your Rust code:
```rust use openaiapirust::; use openai_api_rust::chat::; use openaiapirust::completions::*;
fn main() {
// Load API key from environment OPENAIAPIKEY.
// You can also hadcode through Auth::new(<your_api_key>), but it is not recommended.
let auth = Auth::fromenv().unwrap();
let openai = OpenAI::new(auth, "https://api.openai.com/v1/");
let body = ChatBody {
model: "gpt-3.5-turbo".tostring(),
maxtokens: Some(7),
temperature: Some(0f32),
topp: Some(0f32),
n: Some(2),
stream: Some(false),
stop: None,
presencepenalty: None,
frequencypenalty: None,
logitbias: None,
user: None,
messages: vec![Message { role: Role::User, content: "Hello!".tostring() }],
};
let rs = openai.chatcompletioncreate(&body);
let choice = rs.unwrap().choices;
let message = &choice[0].message.as_ref().unwrap();
assert!(message.content.contains("Hello"));
}
```
Load proxy from env
rust
let openai = OpenAI::new(auth, "https://api.openai.com/v1/")
.use_env_proxy();
Set the proxy manually
rust
let openai = OpenAI::new(auth, "https://api.openai.com/v1/")
.set_proxy("http://127.0.0.1:1080");
This library is distributed under the terms of the MIT license. See LICENSE for details.