Crate x_ai

Expand description

§✨ 𝕏-AI

banner

✨ X-AI: A CLI, TUI, and SDK for interacting with the xAI Grok API, allowing you to chat with Grok models, create embeddings, and inspect your API key and available models.

§📖 Table of Contents

Installation
Features
Usage as CLI
Options
Subcommands
Usage as SDK
Contributing
License

§🚀 Installation

To install the xai CLI:

cargo install x-ai --all-features

§✨ Features

Interactive TUI with Settings, Chat, History, and Model Info tabs
Chat with Grok models (grok-4 by default)
Legacy text completions
Create text embeddings
List all available models
Inspect a specific model’s details
Fetch API key information
Deferred Chat Completions
Full Responses API (Create, Get, Delete)

§Environment Variables

Before using the CLI or SDK, export your API key:

export XAI_API_KEY=<your_xai_api_key>
export XAI_MODEL=grok-4   # optional, defaults to grok-4

Generate an API key from the xAI Console.

§⌨️ Usage as CLI

§Launch TUI (default, no subcommand):

xai

§Chat with Grok:

xai chat -t "What is the answer to life?"

§Legacy text completion:

xai complete -p "Once upon a time" --max-tokens 200

§Create embeddings:

xai embed -t "Hello, world!"

§List all models:

xai models

§Get details for a specific model:

xai model -m grok-4

§Show API key info:

xai apikey

§🎨 Options

Option	Description
(none)	Launch TUI mode.
`--api-key`	xAI API key (overrides `XAI_API_KEY` env var).
`--model`	Model to use (overrides `XAI_MODEL` env var).

§🛠 Subcommands

Subcommand	Description
`chat`	Chat with a Grok model.
`complete`	Legacy text completion.
`embed`	Create text embeddings.
`models`	List all available models.
`model`	Get details for a specific model.
`apikey`	Show API key information.

§✨ Usage as SDK

Add to your Cargo.toml:

[dependencies]
x-ai = "0.1.0"
tokio = { version = "1", features = ["full"] }

§Fetch API Key Information 🔑

use std::env;
use x_ai::api_key::ApiKeyRequestBuilder;
use x_ai::client::XaiClient;
use x_ai::traits::{ApiKeyFetcher, ClientConfig};

#[tokio::main]
async fn main() {
    let client = XaiClient::builder()
        .build()
        .expect("Failed to build XaiClient");

    client.set_api_key(
        env::var("XAI_API_KEY")
            .expect("XAI_API_KEY must be set!")
            .to_string(),
    );

    let builder = ApiKeyRequestBuilder::new(client.clone());
    let result = builder.fetch_api_key_info().await;
    println!("{:?}", result.unwrap());
}

§Chat Completions 💬

use std::env;
use x_ai::chat_compl::{ChatCompletionsRequestBuilder, Message};
use x_ai::client::XaiClient;
use x_ai::traits::{ChatCompletionsFetcher, ClientConfig};

#[tokio::main]
async fn main() {
    let client = XaiClient::builder()
        .build()
        .expect("Failed to build XaiClient");

    client.set_api_key(
        env::var("XAI_API_KEY")
            .expect("XAI_API_KEY must be set!")
            .to_string(),
    );

    let messages = vec![
        Message::text("system", "You are Grok, a chatbot inspired by the Hitchhiker's Guide to the Galaxy."),
        Message::text("user", "What is the answer to life and the universe?"),
    ];

    let builder = ChatCompletionsRequestBuilder::new(client.clone(), "grok-4".to_string(), messages);
    let request = builder.clone().build().unwrap();
    let completion = builder.create_chat_completion(request).await.unwrap();
    println!("Response: {}", completion.choices[0].message.content);
}

§Text Completions 📝

use std::env;
use x_ai::client::XaiClient;
use x_ai::completions::CompletionsRequestBuilder;
use x_ai::traits::{ClientConfig, CompletionsFetcher};

#[tokio::main]
async fn main() {
    let client = XaiClient::builder()
        .build()
        .expect("Failed to build XaiClient");

    client.set_api_key(
        env::var("XAI_API_KEY")
            .expect("XAI_API_KEY must be set!")
            .to_string(),
    );

    let builder = CompletionsRequestBuilder::new(
        client.clone(),
        "grok-4".to_string(),
        "What is AI?".to_string(),
    )
    .max_tokens(50);

    let request = builder.clone().build().unwrap();
    let completion = builder.create_completions(request).await.unwrap();
    println!("{}", completion.choices[0].text);
}

§Embedding Creation 📊

use std::env;
use x_ai::client::XaiClient;
use x_ai::embedding::EmbeddingRequestBuilder;
use x_ai::traits::{ClientConfig, EmbeddingFetcher};

#[tokio::main]
async fn main() {
    let client = XaiClient::builder()
        .build()
        .expect("Failed to build XaiClient");

    client.set_api_key(
        env::var("XAI_API_KEY")
            .expect("XAI_API_KEY must be set!")
            .to_string(),
    );

    let builder = EmbeddingRequestBuilder::new(
        client.clone(),
        "grok-4".to_string(),
        vec!["Hello, world!".to_string()],
        "float".to_string(),
    );

    let request = builder.clone().build().unwrap();
    let embedding = builder.create_embedding(request).await.unwrap();
    println!("{:?}", embedding.data);
}

§List Models 📜

use std::env;
use x_ai::client::XaiClient;
use x_ai::list_mod::ReducedModelListRequestBuilder;
use x_ai::traits::{ClientConfig, ListModelFetcher};

#[tokio::main]
async fn main() {
    let client = XaiClient::builder()
        .build()
        .expect("Failed to build XaiClient");

    client.set_api_key(
        env::var("XAI_API_KEY")
            .expect("XAI_API_KEY must be set!")
            .to_string(),
    );

    let builder = ReducedModelListRequestBuilder::new(client.clone());
    let models = builder.fetch_model_info().await.unwrap();
    for model in models.data {
        println!("• {} (owned by: {})", model.id, model.owned_by);
    }
}

§🤝 Contributing

Contributions and feedback are welcome! If you’d like to contribute, report an issue, or suggest an enhancement, please engage with the project on GitHub. Your contributions help improve this crate for the community.

§📄 License

This project is licensed under the MIT License.

Modules§

api_key: Reference: docs/api-reference#api-key
chat_compl: Reference: docs/api-reference#chat-completions
client
completions: Reference: docs/api-reference#completions-legacy
deferred_compl: Reference: docs/api-reference#deferred-completion
embedding: Reference: https://docs.x.ai/api/endpoints#create-embeddings
embedding_get: Reference: https://docs.x.ai/api/endpoints#get-embedding-model
embedding_mod: Reference: https://docs.x.ai/api/endpoints#list-embedding-models
error
get_mod: Reference: docs/api-reference#get-model
lang_mod: Reference: docs/api-reference#get-language-model
list_lang_mod: Reference: docs/api-reference#list-language-models
list_mod: Reference: docs/api-reference#list-models
responses: Reference: docs/api-reference#responses
traits

Constants§

XAI_V1_URL

Crate x_ai

Crate x_ai Copy item path

§✨ 𝕏-AI

§📖 Table of Contents

§🚀 Installation

§✨ Features

§Environment Variables

§⌨️ Usage as CLI

§Launch TUI (default, no subcommand):

§Chat with Grok:

§Legacy text completion:

§Create embeddings:

§List all models:

§Get details for a specific model:

§Show API key info:

§🎨 Options

§🛠 Subcommands

§✨ Usage as SDK

§Fetch API Key Information 🔑

§Chat Completions 💬

§Text Completions 📝

§Embedding Creation 📊

§List Models 📜

§🤝 Contributing

§📄 License

Modules§

Constants§

Crate x_ai