Update generate pipeline to add OpenAI api as an additional backend (for comparison testing), add brewery coordinates (#244)

* add brewery coordinates

* Add openai mode

* Add coordinates to schema

* Fix C++ review findings in pipeline: k-prefixed enum values, include ordering, populated validation error messages, conventional const notation, and endl replaced with newline

tooling/pipeline/includes/data_model/models.h

@@ -66,6 +66,9 @@ struct City {
     */
    std::string iso3166_1{};
 
+   double longitude{};
+   double latitude{};
+
    /**
     * @brief Local language codes in priority order.
     */
@@ -184,25 +187,47 @@ struct SamplingOptions {
    int n_gpu_layers = 0;
 };
 
+/**
+ * @brief Selects which DataGenerator backend the pipeline uses.
+ */
+enum class GeneratorMode {
+   kMock,
+   kLlama,
+   kOpenAI,
+};
+
 /**
  * @brief Configuration for the LLM generator component.
  */
 struct GeneratorOptions {
    /**
-    * @brief Path to the LLM model file (gguf format).
+    * @brief Path to the LLM model file (gguf format). Only meaningful for
+    * GeneratorMode::kLlama.
     */
    std::filesystem::path model_path;
 
    /**
-    * @brief Use mocked generator instead of actual LLM inference.
+    * @brief Which generator backend to use.
     */
-   bool use_mocked = false;
+   GeneratorMode mode = GeneratorMode::kMock;
 
    /**
-    * @brief Specific sampling parameters for this generator.
-    * If nullopt, the application should use global defaults.
+    * @brief Specific sampling parameters for this generator. Only
+    * meaningful for GeneratorMode::kLlama; if nullopt, LlamaGenerator uses
+    * its own defaults.
     */
    std::optional<SamplingOptions> sampling;
+
+   /**
+    * @brief OpenAI API key, read from the OPENAI_API_KEY environment
+    * variable. Only populated for GeneratorMode::kOpenAI.
+    */
+   std::string openai_api_key;
+
+   /**
+    * @brief OpenAI model ID used by OpenAIGenerator.
+    */
+   std::string openai_model = "gpt-4o-mini";
 };
 
 /**