Crate openai_responses

OpenAI Responses SDK

An unofficial Rust SDK for the OpenAI Responses API.

Usage

To get started, create a new Client and call the create method with a Request object. The Request object contains the parameters for the API call, such as the model, instructions, and input. The create method returns a Response object, which contains the output of the API call.

use openai_responses::{Client, Request, types::{Input, Model}};

let response = Client::from_env()?.create(Request {
    model: Model::GPT4o,
    input: Input::Text("Are semicolons optional in JavaScript?".to_string()),
    instructions: Some("You are a coding assistant that talks like a pirate".to_string()),
    ..Default::default()
}).await?;

println!("{}", response.output_text());

To stream the response as it is generated, use the stream method:

use openai_responses::{Client, Request};

// You can also build the `Request` struct with a fluent interface
let mut stream = Client::from_env()?.stream(
    Request::builder()
        .model("gpt-4o")
        .input("Are semicolons optional in JavaScript?")
        .instructions("You are a coding assistant that talks like a pirate")
        .build()
);

while let Some(event) = stream.next().await {
    dbg!(event?);
}

License

This project is licensed under the MIT License - see the LICENSE file for details.

Modules

types

Types for interacting with the Responses API.

Structs

Client

The OpenAI Responses API Client.

Enums

CreateError

Errors that can occur when creating a new Client.

StreamError