### Configure Google Gemini Language Model in Ruby

Source: https://vicentereig.github.io/dspy.rb/index

This example demonstrates configuring DSPy.rb to use Google Gemini models, such as Gemini 2.5 Flash. It requires a Gemini API key and enables structured outputs.

```ruby
DSPy.configure do |c|
  c.lm = DSPy::LM.new(
    'gemini/gemini-2.5-flash',
    api_key: ENV['GEMINI_API_KEY'],
    structured_outputs: true
  )
end

```

--------------------------------

### Configure Ollama for Local Models in Ruby

Source: https://vicentereig.github.io/dspy.rb/index

This example shows how to configure DSPy.rb to use local models via Ollama, such as Llama, Mistral, or Gemma. No API key is needed as it runs locally.

```ruby
DSPy.configure do |c|
  c.lm = DSPy::LM.new('ollama/llama3.2')
  # Runs locally, completely free
end

```

--------------------------------

### Define Type-Safe Email Signatures with DSPy.rb

Source: https://vicentereig.github.io/dspy.rb/index

This snippet demonstrates how to define a type-safe signature for classifying customer support emails using DSPy.rb and Sorbet. It includes custom `T::Struct` and `T::Enum` definitions for email properties, and a `DSPy::Signature` class that specifies the input email structure and the desired output classification, priority, and summary. This approach ensures type correctness and guides the LLM effectively.

```ruby
class Email < T::Struct
  const :subject, String
  const :from, String
  const :to, String
  const :body, String
end

class EmailCategory < T::Enum
  enums do
    Technical = new('technical')
    Billing = new('billing')
    General = new('general')
  end
end

class Priority < T::Enum
  enums do
    Low = new('low')
    Medium = new('medium')
    High = new('high')
  end
end

class ClassifyEmail < DSPy::Signature
  description "Classify customer support emails by analyzing content and urgency"
  
  input do
    const :email, Email,
          description: "The email to classify with all headers and content"
  end
  
  output do
    const :category, EmailCategory,
          description: "Main topic: technical (API, bugs), billing (payment, pricing), or general"
    const :priority, Priority,
          description: "Urgency level based on keywords like 'production', 'ASAP', 'urgent'"
    const :summary, String,
          description: "One-line summary of the issue for support dashboard"
  end
end

```

--------------------------------

### Implement Email Classification with DSPy.rb Chain of Thought

Source: https://vicentereig.github.io/dspy.rb/index

This code illustrates how to use DSPy.rb's `ChainOfThought` to classify an email based on the previously defined `ClassifyEmail` signature. It creates a `ChainOfThought` instance, constructs a typed `Email` object, and calls the classifier. The output is a typed classification object, ensuring that the returned category, priority, and summary are correctly structured and validated. Examples show accessing the results and demonstrating type safety.

```ruby
classifier = DSPy::ChainOfThought.new(ClassifyEmail)

# Create a properly typed email object
email = Email.new(
  subject: "URGENT: API Key Not Working!!!",
  from: "john.doe@acmecorp.com",
  to: "support@yourcompany.com",
  body: "My API key stopped working after the update. I need this fixed ASAP for our production deployment!"
)

classification = classifier.call(email: email)  # Type-checked at runtime!

# Example outputs:
# irb> classification.reasoning
# => "Let me analyze this email step by step:\n1. The customer mentions an API key issue - this is technical\n2. They mention it stopped working after an update - suggests a system change\n3. They emphasize 'ASAP' and 'production deployment' - this is urgent\n4. Production issues always warrant high priority"
# 
# irb> classification.category
# => #<EmailCategory::Technical:0x00007f8b2c0a1b80>
# 
# irb> classification.priority.serialize  # Get the string value when needed
# => "high"
# 
# irb> classification.summary
# => "API key authentication failure post-update affecting production"

# Type safety examples:
# irb> EmailCategory.values
# => [#<EmailCategory::Technical>, #<EmailCategory::Billing>, #<EmailCategory::General>]
# irb> classification.category = "invalid"  # This would raise an error!

```

--------------------------------

### Configure OpenRouter for Multiple Providers in Ruby

Source: https://vicentereig.github.io/dspy.rb/index

This snippet demonstrates configuring DSPy.rb to access a wide range of models from multiple providers through the OpenRouter API. It requires an OpenRouter API key.

```ruby
DSPy.configure do |c|
  c.lm = DSPy::LM.new(
    'openrouter/deepseek/deepseek-chat-v3.1:free',
    api_key: ENV['OPENROUTER_API_KEY']
  )
end

```

--------------------------------

### Configure Anthropic Claude Language Model in Ruby

Source: https://vicentereig.github.io/dspy.rb/index

This snippet illustrates how to set up DSPy.rb with Anthropic Claude models, like Claude 3.5 or Claude 4. It requires an Anthropic API key and utilizes tool-based extraction for structured outputs.

```ruby
DSPy.configure do |c|
  c.lm = DSPy::LM.new(
    'anthropic/claude-sonnet-4-5-20250929',
    api_key: ENV['ANTHROPIC_API_KEY'],
    structured_outputs: true
  )
end

```

--------------------------------

### Configure OpenAI Language Model in Ruby

Source: https://vicentereig.github.io/dspy.rb/index

This snippet shows how to configure DSPy.rb to use OpenAI models like GPT-4o mini. It requires an OpenAI API key and enables structured outputs for better integration.

```ruby
DSPy.configure do |c|
  c.lm = DSPy::LM.new(
    'openai/gpt-4o-mini',
    api_key: ENV['OPENAI_API_KEY'],
    structured_outputs: true
  )
end

```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.