13 releases (4 breaking)

new 0.4.0 Nov 7, 2024
0.3.0 Oct 24, 2024
0.2.1 Oct 1, 2024
0.1.0 Sep 16, 2024
0.0.0 May 29, 2024

#166 in Machine learning

Download history 13/week @ 2024-07-25 4/week @ 2024-08-01 93/week @ 2024-08-29 54/week @ 2024-09-05 159/week @ 2024-09-12 54/week @ 2024-09-19 292/week @ 2024-09-26 98/week @ 2024-10-03 19/week @ 2024-10-10 7/week @ 2024-10-17 155/week @ 2024-10-24 31/week @ 2024-10-31

220 downloads per month
Used in 4 crates

MIT license

215KB
3.5K SLoC

Rig

Rig is a Rust library for building LLM-powered applications that focuses on ergonomics and modularity.

More information about this crate can be found in the crate documentation.

Table of contents

High-level features

  • Full support for LLM completion and embedding workflows
  • Simple but powerful common abstractions over LLM providers (e.g. OpenAI, Cohere) and vector stores (e.g. MongoDB, in-memory)
  • Integrate LLMs in your app with minimal boilerplate

Installation

cargo add rig-core

Simple example:

use rig::{completion::Prompt, providers::openai};

#[tokio::main]
async fn main() {
    // Create OpenAI client and model
    // This requires the `OPENAI_API_KEY` environment variable to be set.
    let openai_client = openai::Client::from_env();

    let gpt4 = openai_client.model("gpt-4").build();

    // Prompt the model and print its response
    let response = gpt4
        .prompt("Who are you?")
        .await
        .expect("Failed to prompt GPT-4");

    println!("GPT-4: {response}");
}

Note using #[tokio::main] requires you enable tokio's macros and rt-multi-thread features or just full to enable all features (cargo add tokio --features macros,rt-multi-thread).

Integrations

Rig supports the following LLM providers natively:

  • OpenAI
  • Cohere
  • Google Gemini Additionally, Rig currently has the following integration sub-libraries:
  • MongoDB vector store: rig-mongodb

Dependencies

~5–23MB
~252K SLoC