Skip to content
Glitch

Ruby SDK

Use the Ruby OpenAI gem with Glitch by configuring the base URL and adding your Glitch API key.

Basic Setup

Section titled “Basic Setup”
require "openai"


client = OpenAI::Client.new(
  access_token: ENV["GLITCH_API_KEY"],  # Your Glitch API key
  uri_base: "https://api.golabrat.ai/v1",  # Glitch sensor URL
)


response = client.chat(
  parameters: {
    model: "gpt-4",
    messages: [{ role: "user", content: "Hello!" }]
  }
)


puts response.dig("choices", 0, "message", "content")

Error Handling

Section titled “Error Handling”

Handle Glitch security blocks gracefully:

require "openai"


client = OpenAI::Client.new(
  access_token: ENV["GLITCH_API_KEY"],
  uri_base: "https://api.golabrat.ai/v1",
)


begin
  response = client.chat(
    parameters: {
      model: "gpt-4",
      messages: [{ role: "user", content: user_input }]
    }
  )
  return response.dig("choices", 0, "message", "content")
rescue OpenAI::Error => e
  if e.status == 403
    # Security block - handle gracefully
    return "I can't process that request."
  end
  raise
end

Accessing Security Headers

Section titled “Accessing Security Headers”

To access security headers, use a direct HTTP client:

require "net/http"
require "json"
require "uri"


uri = URI("https://api.golabrat.ai/v1/chat/completions")
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true


request = Net::HTTP::Post.new(uri)
request["Authorization"] = "Bearer #{ENV['GLITCH_API_KEY']}"
request["Content-Type"] = "application/json"
request.body = {
  model: "gpt-4",
  messages: [{ role: "user", content: "Hello" }]
}.to_json


response = http.request(request)


# Access security headers
blocked = response["X-Risk-Blocked"] == "true"
categories = response["X-Risk-Categories"]
confidence = response["X-Risk-Confidence"].to_f


if categories
  puts "Flagged: #{categories} (confidence: #{confidence})"
end

Next Steps

Section titled “Next Steps”