Add timeout to wikipedia enrichment to avoid breaking rate limits, add mock enrichment (#224)

* Add timeout for enrichment, refactor json deserialization

* Add location count to application options and as a cli arg

* Add mock enrichment process

tooling/pipeline/includes/biergarten_data_generator.h

@@ -12,8 +12,8 @@
 
 #include "data_generation/data_generator.h"
 #include "data_model/generated_models.h"
-#include "services/enrichment/enrichment_service.h"
 #include "services/database/export_service.h"
+#include "services/enrichment/enrichment_service.h"
 
 /**
  * @brief Main data generator class for the Biergarten pipeline.
@@ -32,7 +32,8 @@ class BiergartenDataGenerator {
    */
   BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
                           std::unique_ptr<DataGenerator> generator,
-                          std::unique_ptr<IExportService> exporter);
+                          std::unique_ptr<IExportService> exporter,
+                          const ApplicationOptions& application_options);
 
   /**
    * @brief Run the data generation pipeline.
@@ -56,12 +57,14 @@ class BiergartenDataGenerator {
   /// @brief Storage backend for generated brewery records.
   std::unique_ptr<IExportService> exporter_;
 
+  const ApplicationOptions application_options_;
+
   /**
    * @brief Load locations from JSON and sample cities.
    *
    * @return Vector of sampled locations capped at 50 entries.
    */
-  static std::vector<Location> QueryCitiesWithCountries();
+  std::vector<Location> QueryCitiesWithCountries();
 
   /**
    * @brief Generate breweries for enriched cities.

tooling/pipeline/includes/data_model/models.h

@@ -83,6 +83,9 @@ struct SamplingOptions {
 
   /// @brief Random seed (-1 for random, otherwise non-negative).
   int seed = -1;
+
+  /// @brief Number of layers to offload to GPU.
+  int n_gpu_layers = 0;
 };
 
 /**
@@ -95,8 +98,7 @@ struct GeneratorOptions {
   /// @brief Use mocked generator instead of actual LLM inference.
   bool use_mocked = false;
 
-  /// @brief Number of layers to offload to GPU.
-  int n_gpu_layers = 0;
+
 
   /// @brief Specific sampling parameters for this generator.
   /// If nullopt, the application should use global defaults.
@@ -116,6 +118,10 @@ struct PipelineOptions {
 
   /// @brief Path for application logs.
   std::filesystem::path log_path;
+
+  /// @brief Number of locations to sample from the dataset
+  /// More locations -> more users/more breweries
+  uint32_t location_count;
 };
 
 /**

tooling/pipeline/includes/services/enrichment/mock_enrichment.h

@@ -0,0 +1,17 @@
+//
+// Created by aaronpo on 13/05/2026.
+//
+
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
+#include <string>
+
+#include "enrichment_service.h"
+
+class MockEnrichmentService final : public IEnrichmentService {
+ public:
+  std::string GetLocationContext(const Location& /*loc*/) override {
+    return {};
+  }
+};
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_

tooling/pipeline/includes/services/enrichment/wikipedia_service.h

@@ -15,10 +15,10 @@
 #include "web_client/web_client.h"
 
 /// @brief Provides Wikipedia summary lookups backed by cached raw extracts.
-class WikipediaService final : public IEnrichmentService {
+class WikipediaEnrichmentService final : public IEnrichmentService {
  public:
   /// @brief Creates a new Wikipedia service with the provided web client.
-  explicit WikipediaService(std::unique_ptr<WebClient> client);
+  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client);
 
   /// @brief Returns the Wikipedia-derived context for a location.
   [[nodiscard]] std::string GetLocationContext(const Location& loc) override;

tooling/pipeline/includes/web_client/http_web_client.h

@@ -42,7 +42,7 @@ public:
    * @param value Raw string to encode.
    * @return Percent-encoded string safe for use in a URL.
    */
-  std::string UrlEncode(const std::string& value) override;
+  std::string EncodeURL(const std::string& value) override;
 };
 
 

tooling/pipeline/includes/web_client/web_client.h

@@ -30,7 +30,7 @@ class WebClient {
    * @param value Raw string value.
    * @return Encoded value safe for URL usage.
    */
-  virtual std::string UrlEncode(const std::string& value) = 0;
+  virtual std::string EncodeURL(const std::string& value) = 0;
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_WEB_CLIENT_H_