⚙️🦀 Build portable, modular & lightweight Fullstack Agents

✨ If you would like to help spread the word about Rig, please consider starring the repo!

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.

Help us improve Rig by contributing to our Feedback form.

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

• 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

cargo add rig-core

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.agent("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).

You can find more examples each crate's examples (ie. src/examples) directory. More detailed use cases walkthroughs are regularly published on our Dev.to Blog.

Model Providers	Vector Stores

Vector stores are available as separate companion-crates:

• MongoDB vector store: rig-mongodb
• LanceDB vector store: rig-lancedb
• Neo4j vector store: rig-neo4j
• Qdrant vector store: rig-qdrant