Rig logo

stars - rig

✨ 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 official & crate (API Reference) documentations.

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, SQlite, 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. rig-core/examples) directory. More detailed use cases walkthroughs are regularly published on our Dev.to Blog and added to Rig's official documentation (docs.rig.rs).

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
• SQLite vector store: rig-sqlite
• SurrealDB vector store: rig-surrealdb

The following providers are available as separate companion-crates:

• Fastembed: rig-fastembed

Build by Playgrounds