> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keywordsai.co/llms.txt
> Use this file to discover all available pages before exploring further.

# RubyLLM

> Use RubyLLM with Keywords AI gateway for logging, analytics, and access to 250+ models.

<Note> This integration is for the **Keywords AI gateway**. </Note>

## Overview

[RubyLLM](https://rubyllm.com/) is a delightful Ruby gem that provides a unified interface for interacting with AI models from OpenAI, Anthropic, Google, and more.

By pointing RubyLLM's OpenAI-compatible endpoint to Keywords AI, you get automatic logging, analytics, fallbacks, and access to 250+ models through a single API key.

## Quickstart

### Step 1: Get a Keywords AI API key

Create an API key in the [Keywords AI dashboard](https://platform.keywordsai.co/platform/api/api-keys).

<Frame className="rounded-md">
  <img src="https://keywordsai-static.s3.us-east-1.amazonaws.com/docs/documentation/admin/kai_create_api_key_v0.png" alt="Create a Keywords AI API key" />
</Frame>

### Step 2: Install RubyLLM

Add to your Gemfile:

```bash theme={"system"}
gem 'ruby_llm'
```

Then run:

```bash theme={"system"}
bundle install
```

### Step 3: Configure RubyLLM

Point RubyLLM to the Keywords AI gateway by setting the `openai_api_base` and `openai_api_key`:

```ruby {3-4} theme={"system"}
RubyLLM.configure do |config|
  config.openai_api_base = "https://api.keywordsai.co/api/"
  config.openai_api_key = ENV['KEYWORDS_AI_API_KEY']
end
```

### Step 4: Make Your First Request

```ruby theme={"system"}
chat = RubyLLM.chat(model: 'gpt-4o-mini')
response = chat.ask("Hello, world!")
puts response.content
```

### Step 5: See your log on [platform](https://platform.keywordsai.co/platform/requests?sort_by=-timestamp)

## Switch models

Since all requests go through the Keywords AI gateway, you can use any of the 250+ supported models by changing the model name:

```ruby {2-4} theme={"system"}
# OpenAI
chat = RubyLLM.chat(model: 'gpt-4o')
# Anthropic
# chat = RubyLLM.chat(model: 'claude-3-5-sonnet-20241022')
# Google
# chat = RubyLLM.chat(model: 'gemini-1.5-pro')

response = chat.ask("Your message")
```

<Note>
  See the [full model list](https://platform.keywordsai.co/platform/models) for all available models.
</Note>

## Streaming

```ruby theme={"system"}
chat = RubyLLM.chat(model: 'gpt-4o-mini')
chat.ask("Tell me a story") do |chunk|
  print chunk.content
end
```

## Rails integration

For Rails applications, configure RubyLLM in an initializer:

```ruby theme={"system"}
# config/initializers/ruby_llm.rb
RubyLLM.configure do |config|
  config.openai_api_base = "https://api.keywordsai.co/api/"
  config.openai_api_key = ENV['KEYWORDS_AI_API_KEY']
end
```

<Card title="View your analytics" href="https://platform.keywordsai.co/platform/dashboard">
  Access your Keywords AI dashboard to see detailed analytics
</Card>

## Next Steps

<CardGroup cols={2}>
  <Card title="Advanced settings" href="/documentation/products/users/customer-identifier">
    Track user behavior and patterns
  </Card>

  <Card title="Prompt Management" href="/documentation/products/prompt_management/quickstart">
    Manage and version your prompts
  </Card>
</CardGroup>