Create biergarten brewery pipeline project (#199)

pipeline/includes/data_generation/data_generator.h

@@ -0,0 +1,41 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_DATA_GENERATOR_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_DATA_GENERATOR_H_
+
+/**
+ * @file data_generation/data_generator.h
+ * @brief Shared generator interfaces and result models.
+ */
+
+#include <string>
+
+#include "data_model/brewery_result.h"
+#include "data_model/location.h"
+#include "data_model/user_result.h"
+
+/**
+ * @brief Interface for data generator implementations.
+ */
+class DataGenerator {
+ public:
+  virtual ~DataGenerator() = default;
+
+  /**
+   * @brief Generates brewery data for a location.
+   *
+   * @param location Location data
+   * @param region_context Additional regional context text.
+   * @return Brewery generation result.
+   */
+  virtual BreweryResult GenerateBrewery(const Location& location,
+                                        const std::string& region_context) = 0;
+
+  /**
+   * @brief Generates a user profile for a locale.
+   *
+   * @param locale Locale hint used by generator.
+   * @return User generation result.
+   */
+  virtual UserResult GenerateUser(const std::string& locale) = 0;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_DATA_GENERATOR_H_

pipeline/includes/data_generation/llama_generator.h

@@ -0,0 +1,141 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
+
+#include <filesystem>
+
+/**
+ * @file data_generation/llama_generator.h
+ * @brief llama.cpp-backed implementation of DataGenerator.
+ */
+
+#include <cstdint>
+#include <memory>
+#include <random>
+#include <string>
+#include <string_view>
+
+#include "data_generation/data_generator.h"
+#include "data_generation/prompt_formatting/prompt_formatter.h"
+#include "data_model/application_options.h"
+
+struct llama_model;
+struct llama_context;
+
+/**
+ * @brief Data generator implementation backed by llama.cpp.
+ */
+class LlamaGenerator final : public DataGenerator {
+ public:
+  /**
+   * @brief Constructs a generator using parsed application options and loads
+   * the configured model immediately.
+   *
+   * @param options Parsed application options.
+   * @param model_path Filesystem path to GGUF model assets.
+  * @param prompt_formatter Formatter that produces model-specific prompts.
+   */
+  LlamaGenerator(const ApplicationOptions& options,
+                 const std::string& model_path,
+                 std::unique_ptr<IPromptFormatter> prompt_formatter);
+
+  ~LlamaGenerator() override;
+
+  // disable copy constructor
+  LlamaGenerator(const LlamaGenerator&) = delete;
+
+  // disable copy assignment operator
+  LlamaGenerator& operator=(const LlamaGenerator&) = delete;
+  // disable move constructor
+  LlamaGenerator(LlamaGenerator&&) = delete;
+  // disable move assignment operator
+  LlamaGenerator& operator=(LlamaGenerator&&) = delete;
+
+  /**
+   * @brief Generates brewery data for a specific location.
+   *
+   * @param location Location object.
+   * @param region_context Additional regional context.
+   * @return Generated brewery result.
+   */
+  BreweryResult GenerateBrewery(const Location& location,
+                                const std::string& region_context) override;
+
+  /**
+   * @brief Generates a user profile for the provided locale.
+   *
+   * @param locale Locale hint.
+   * @return Generated user profile.
+   */
+  UserResult GenerateUser(const std::string& locale) override;
+
+ private:
+  static constexpr int32_t kDefaultMaxTokens = 10000;
+  static constexpr float kDefaultSamplingTopP = 0.95F;
+  static constexpr uint32_t kDefaultSamplingTopK = 64;
+  static constexpr uint32_t kDefaultContextSize = 8192;
+
+  struct ModelDeleter {
+    void operator()(llama_model* model) const noexcept;
+  };
+  struct ContextDeleter {
+    void operator()(llama_context* context) const noexcept;
+  };
+
+  using ModelHandle = std::unique_ptr<llama_model, ModelDeleter>;
+  using ContextHandle = std::unique_ptr<llama_context, ContextDeleter>;
+
+  /**
+   * @brief Loads model and prepares inference context.
+   *
+   * @param model_path Filesystem path to GGUF model.
+   */
+  void Load(const std::string& model_path);
+
+  /**
+   * @brief Infers text from separate system and user prompts.
+   *
+   * This helps chat-capable models preserve system-role behavior instead of
+   * concatenating system text into user input.
+   *
+   * @param system_prompt System role prompt.
+   * @param prompt User prompt.
+   * @param max_tokens Maximum tokens to generate.
+  * @param grammar Optional GBNF grammar constraining generated output.
+   * @return Generated text.
+   */
+  std::string Infer(const std::string& system_prompt, const std::string& prompt,
+              int max_tokens = kDefaultMaxTokens,
+              std::string_view grammar = {});
+
+  /**
+   * @brief Runs inference on an already-formatted prompt.
+   *
+   * @param formatted_prompt Prompt preformatted for model chat template.
+   * @param max_tokens Maximum tokens to generate.
+  * @param grammar Optional GBNF grammar constraining generated output.
+   * @return Generated text.
+   */
+  std::string InferFormatted(const std::string& formatted_prompt,
+                    int max_tokens = kDefaultMaxTokens,
+                    std::string_view grammar = {});
+
+  /**
+   * @brief Loads the brewery system prompt from disk.
+   *
+   * @param prompt_file_path Prompt file path to try first.
+   * @return Loaded prompt text.
+   */
+  std::string LoadBrewerySystemPrompt(const std::filesystem::path& prompt_file_path);
+
+  ModelHandle model_;
+  ContextHandle context_;
+  float sampling_temperature_ = 1.0F;
+  float sampling_top_p_ = kDefaultSamplingTopP;
+  uint32_t sampling_top_k_ = kDefaultSamplingTopK;
+  std::mt19937 rng_;
+  uint32_t n_ctx_ = kDefaultContextSize;
+  std::string brewery_system_prompt_;
+  std::unique_ptr<IPromptFormatter> prompt_formatter_;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_

pipeline/includes/data_generation/llama_generator_helpers.h

@@ -0,0 +1,50 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_HELPERS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_HELPERS_H_
+
+/**
+ * @file data_generation/llama_generator_helpers.h
+ * @brief Shared helper APIs used by LlamaGenerator translation units.
+ */
+
+#include <cstddef>
+#include <cstdint>
+#include <optional>
+#include <string>
+#include <string_view>
+
+#include "data_model/brewery_result.h"
+
+struct llama_vocab;
+using llama_token = int32_t;
+
+/**
+ * @brief Normalizes and truncates regional context.
+ *
+ * @param region_context Input regional context text.
+ * @param max_chars Maximum output length.
+ * @return Processed region context.
+ */
+std::string PrepareRegionContext(std::string_view region_context,
+                                 size_t max_chars = 2000);
+
+/**
+ * @brief Decodes a sampled token and appends it to output text.
+ *
+ * @param vocab Model vocabulary.
+ * @param token Sampled token id.
+ * @param output Output text buffer.
+ */
+void AppendTokenPiece(const llama_vocab* vocab, llama_token token,
+                      std::string& output);
+
+/**
+ * @brief Validates and parses brewery JSON output.
+ *
+ * @param raw Raw model output.
+ * @param brewery_out Parsed brewery payload.
+ * @return Validation error message if invalid, or std::nullopt on success.
+ */
+std::optional<std::string> ValidateBreweryJson(const std::string& raw,
+                                               BreweryResult& brewery_out);
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_HELPERS_H_

pipeline/includes/data_generation/mock_generator.h

@@ -0,0 +1,123 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_MOCK_GENERATOR_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_MOCK_GENERATOR_H_
+
+/**
+ * @file data_generation/mock_generator.h
+ * @brief Deterministic mock implementation of DataGenerator.
+ */
+
+#include <array>
+#include <string>
+#include <string_view>
+
+#include "data_generation/data_generator.h"
+
+/**
+ * @brief Mock generator used for deterministic, model-free outputs.
+ */
+class MockGenerator final : public DataGenerator {
+ public:
+  /**
+   * @brief Generates deterministic brewery data for a location.
+   *
+   * @param location City and country names.
+   * @param region_context Unused for mock generation.
+   * @return Generated brewery result.
+   */
+  BreweryResult GenerateBrewery(const Location& location,
+                                const std::string& region_context) override;
+
+  /**
+   * @brief Generates deterministic user data for a locale.
+   *
+   * @param locale Locale hint.
+   * @return Generated user result.
+   */
+  UserResult GenerateUser(const std::string& locale) override;
+
+ private:
+  /**
+   * @brief Combines two strings into a stable hash value.
+   *
+   * @param location City and country names.
+   * @return Deterministic hash value.
+   */
+  static size_t DeterministicHash(const Location& location);
+
+  static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
+      "Craft",      "Heritage", "Local",  "Artisan",  "Pioneer",    "Golden",
+      "Modern",     "Classic",  "Summit", "Northern", "Riverstone", "Barrel",
+      "Hinterland", "Harbor",   "Wild",   "Granite",  "Copper",     "Maple"};
+
+  static constexpr std::array<std::string_view, 18> kBreweryNouns = {
+      "Brewing Co.", "Brewery",    "Bier Haus", "Taproom",      "Works",
+      "House",       "Fermentery", "Ale Co.",   "Cellars",      "Collective",
+      "Project",     "Foundry",    "Malthouse", "Public House", "Co-op",
+      "Lab",         "Beer Hall",  "Guild"};
+
+  static constexpr std::array<std::string_view, 18> kBreweryDescriptions = {
+      "Handcrafted pale ales and seasonal IPAs with local ingredients.",
+      "Traditional lagers and experimental sours in small batches.",
+      "Award-winning stouts and wildly hoppy blonde ales.",
+      "Craft brewery specializing in Belgian-style triples and dark "
+      "porters.",
+      "Modern brewery blending tradition with bold experimental flavors.",
+      "Neighborhood-focused taproom pouring crisp pilsners and citrusy "
+      "pale "
+      "ales.",
+      "Small-batch brewery known for barrel-aged releases and smoky "
+      "lagers.",
+      "Independent brewhouse pairing farmhouse ales with rotating food "
+      "pop-ups.",
+      "Community brewpub making balanced bitters, saisons, and hazy IPAs.",
+      "Experimental nanobrewery exploring local yeast and regional "
+      "grains.",
+      "Family-run brewery producing smooth amber ales and robust porters.",
+      "Urban brewery crafting clean lagers and bright, fruit-forward "
+      "sours.",
+      "Riverfront brewhouse featuring oak-matured ales and seasonal "
+      "blends.",
+      "Modern taproom focused on sessionable lagers and classic pub "
+      "styles.",
+      "Brewery rooted in tradition with a lineup of malty reds and crisp "
+      "lagers.",
+      "Creative brewery offering rotating collaborations and limited "
+      "draft-only "
+      "pours.",
+      "Locally inspired brewery serving approachable ales with bold hop "
+      "character.",
+      "Destination taproom known for balanced IPAs and cocoa-rich "
+      "stouts."};
+
+  static constexpr std::array<std::string_view, 18> kUsernames = {
+      "hopseeker",     "malttrail",   "yeastwhisper",  "lagerlane",
+      "barrelbound",   "foamfinder",  "taphunter",     "graingeist",
+      "brewscout",     "aleatlas",    "caskcompass",   "hopsandmaps",
+      "mashpilot",     "pintnomad",   "fermentfriend", "stoutsignal",
+      "sessionwander", "kettlekeeper"};
+
+  static constexpr std::array<std::string_view, 18> kBios = {
+      "Always chasing balanced IPAs and crisp lagers across local taprooms.",
+      "Weekend brewery explorer with a soft spot for dark, roasty stouts.",
+      "Documenting tiny brewpubs, fresh pours, and unforgettable beer "
+      "gardens.",
+      "Fan of farmhouse ales, food pairings, and long tasting flights.",
+      "Collecting favorite pilsners one city at a time.",
+      "Hops-first drinker who still saves room for classic malt-forward "
+      "styles.",
+      "Finding hidden tap lists and sharing the best seasonal releases.",
+      "Brewery road-tripper focused on local ingredients and clean "
+      "fermentation.",
+      "Always comparing house lagers and ranking patio pint vibes.",
+      "Curious about yeast strains, barrel programs, and cellar experiments.",
+      "Believes every neighborhood deserves a great community taproom.",
+      "Looking for session beers that taste great from first sip to last.",
+      "Belgian ale enthusiast who never skips a new saison.",
+      "Hazy IPA critic with deep respect for a perfectly clear pilsner.",
+      "Visits breweries for the stories, stays for the flagship pours.",
+      "Craft beer fan mapping tasting notes and favorite brew routes.",
+      "Always ready to trade recommendations for underrated local breweries.",
+      "Keeping a running list of must-try collab releases and tap takeovers."};
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_MOCK_GENERATOR_H_

pipeline/includes/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h

@@ -0,0 +1,15 @@
+#pragma once
+
+#include <string>
+#include <string_view>
+
+#include "data_generation/prompt_formatting/prompt_formatter.h"
+
+class Gemma4JinjaPromptFormatter final : public IPromptFormatter {
+ public:
+  Gemma4JinjaPromptFormatter() = default;
+  ~Gemma4JinjaPromptFormatter() override = default;
+
+  [[nodiscard]] std::string Format(std::string_view system_prompt,
+                                   std::string_view user_prompt) const override;
+};

pipeline/includes/data_generation/prompt_formatting/prompt_formatter.h

@@ -0,0 +1,18 @@
+#pragma once
+
+#include <string>
+#include <string_view>
+
+class IPromptFormatter {
+ public:
+  IPromptFormatter() = default;
+  IPromptFormatter(const IPromptFormatter&) = delete;
+  IPromptFormatter& operator=(const IPromptFormatter&) = delete;
+  IPromptFormatter(IPromptFormatter&&) = delete;
+  IPromptFormatter& operator=(IPromptFormatter&&) = delete;
+  virtual ~IPromptFormatter() = default;
+
+  [[nodiscard]] virtual std::string Format(
+      std::string_view system_prompt,
+      std::string_view user_prompt) const = 0;
+};