Warning

Here be dragons! Rig is alpha software and will contain breaking changes as it evolves. We'll annotate them and highlight migration paths as we encounter them.

What is Rig?

Rig is a Rust library for building scalable, modular, and ergonomic LLM-powered applications.

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

We'd love your feedback. Please take a moment to let us know what you think using this Feedback form.

Table of contents

• What is Rig?
• Table of contents
• High-level features
• Installation
• Simple example:
• Integrations

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
• Anthropic
• Perplexity
• Google Gemini

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

• MongoDB vector store: rig-mongodb
• LanceDB vector store: rig-lancedb