feat: Add support for account abuse detection (#11001)

This PR adds service to automate account abuse detection. Currently
based on the signup name and URL, could potentially add more context
such as usage analysis, message metadata etc.

enterprise/app/services/llm/base_open_ai_service.rb

@@ -0,0 +1,20 @@
+class Llm::BaseOpenAiService
+  DEFAULT_MODEL = 'gpt-4o-mini'.freeze
+
+  def initialize
+    @client = OpenAI::Client.new(
+      access_token: InstallationConfig.find_by!(name: 'CAPTAIN_OPEN_AI_API_KEY').value,
+      log_errors: Rails.env.development?
+    )
+    setup_model
+  rescue StandardError => e
+    raise "Failed to initialize OpenAI client: #{e.message}"
+  end
+
+  private
+
+  def setup_model
+    config_value = InstallationConfig.find_by(name: 'CAPTAIN_OPEN_AI_MODEL')&.value
+    @model = (config_value.presence || DEFAULT_MODEL)
+  end
+end