MCPcopy Index your code
hub / github.com/deontologician/openai-api-rust

github.com/deontologician/openai-api-rust @v0.1.2

Chat with this repo
repository ↗ · DeepWiki ↗ · release v0.1.2 ↗ · + Follow
38 symbols 63 edges 3 files 9 documented · 24% updated 2y agov0.1.1-beta.1 · 2020-12-09★ 1006 open issues
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

openai-api-rust

docs Crates.io build

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

use openai_api::OpenAIClient;

#[tokio::main]
async fn main() {
    let api_token = std::env::var("OPENAI_SK").unwrap();
    let client = OpenAIClient::new(&api_token);
    let prompt = String::from("Once upon a time,");
    println!(
        "{}{}",
        prompt,
        client.complete(prompt.as_str()).await.unwrap()
    );
}

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:

let response = client.complete("Once upon a time").await?;
println!("{}", response);

To configure the prompt more explicitly, you can use the CompletionArgs builder:

let args = openai_api::api::CompletionArgs::builder()
        .prompt("Once upon a time,")
        .engine(Engine::Davinci)
        .max_tokens(20)
        .temperature(0.7)
        .top_p(0.9)
        .stop(vec!["\n".into()]);
let response = args.complete(&client).await?;
println!("Response: {}", response.choices[0].text);
println!("Model used: {}", response.model);

See examples/

Core symbols most depended-on inside this repo

complete
called by 5
src/lib.rs
get_client
called by 5
src/lib.rs
engine
called by 4
src/lib.rs
mocked_client
called by 4
src/lib.rs
get
called by 2
src/lib.rs
engines
called by 2
src/lib.rs
set_api_root
called by 1
src/lib.rs
post
called by 1
src/lib.rs

Shape

Function 14
Method 11
Class 10
Enum 3

Languages

Rust100%

Modules by API surface

src/lib.rs36 symbols
examples/story.rs1 symbols
examples/chatloop.rs1 symbols

For agents

$ claude mcp add openai-api-rust \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact