25 releases (12 breaking)

new 0.12.0 Apr 29, 2025
0.11.0 Mar 31, 2025
0.6.0 Dec 19, 2024
0.4.1 Nov 13, 2024
0.0.6 Jun 12, 2024

#63 in Web programming

Download history 646/week @ 2025-01-13 646/week @ 2025-01-20 607/week @ 2025-01-27 890/week @ 2025-02-03 1213/week @ 2025-02-10 1287/week @ 2025-02-17 1281/week @ 2025-02-24 1193/week @ 2025-03-03 1094/week @ 2025-03-10 1433/week @ 2025-03-17 959/week @ 2025-03-24 1042/week @ 2025-03-31 1690/week @ 2025-04-07 1639/week @ 2025-04-14 1304/week @ 2025-04-21 1440/week @ 2025-04-28

6,285 downloads per month
Used in 49 crates (27 directly)

MIT and maybe GPL-3.0

2MB
18K 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, SQLite, 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
  • Anthropic
  • Perplexity
  • Google Gemini
  • xAI
  • DeepSeek

Additionally, Rig currently has the following integration sub-libraries:

  • MongoDB vector store: rig-mongodb

Dependencies

~5–22MB
~279K SLoC