Refactor Llama generator, helpers, and build assets

make Gemma 4 the default model, enable thinking mode
style updates

pipeline/src/data_generation/mock/data.cpp

@@ -1,71 +0,0 @@
-/**
- * @file data_generation/mock/data.cpp
- * @brief Defines static lookup tables used by MockGenerator for deterministic
- * brewery names, descriptions, usernames, and bios.
- */
-
-#include <string>
-#include <vector>
-
-#include "data_generation/mock_generator.h"
-
-const std::vector<std::string> MockGenerator::kBreweryAdjectives = {
-    "Craft",      "Heritage", "Local",  "Artisan",  "Pioneer",    "Golden",
-    "Modern",     "Classic",  "Summit", "Northern", "Riverstone", "Barrel",
-    "Hinterland", "Harbor",   "Wild",   "Granite",  "Copper",     "Maple"};
-
-const std::vector<std::string> MockGenerator::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"};
-
-const std::vector<std::string> MockGenerator::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."};
-
-const std::vector<std::string> MockGenerator::kUsernames = {
-    "hopseeker",     "malttrail",   "yeastwhisper",  "lagerlane",
-    "barrelbound",   "foamfinder",  "taphunter",     "graingeist",
-    "brewscout",     "aleatlas",    "caskcompass",   "hopsandmaps",
-    "mashpilot",     "pintnomad",   "fermentfriend", "stoutsignal",
-    "sessionwander", "kettlekeeper"};
-
-const std::vector<std::string> MockGenerator::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."};

pipeline/src/data_generation/mock/deterministic_hash.cpp

@@ -5,14 +5,12 @@
  */
 
 #include <boost/container_hash/hash.hpp>
-#include <string>
 
 #include "data_generation/mock_generator.h"
 
-std::size_t MockGenerator::DeterministicHash(const std::string& a,
-                                             const std::string& b) {
-   std::size_t seed = 0;
-   boost::hash_combine(seed, a);
-   boost::hash_combine(seed, b);
+size_t MockGenerator::DeterministicHash(const Location& location) {
+   size_t seed = 0;
+   boost::hash_combine(seed, location.city);
+   boost::hash_combine(seed, location.country);
    return seed;
 }

pipeline/src/data_generation/mock/generate_brewery.cpp

@@ -4,28 +4,39 @@
  * and country into fixed mock phrase catalogs.
  */
 
+#include <format>
 #include <string>
+#include <string_view>
 
 #include "data_generation/mock_generator.h"
 
-auto MockGenerator::GenerateBrewery(const std::string& city_name,
-                                    const std::string& country_name,
-                                    const std::string& /*region_context*/)
-    -> BreweryResult {
-   const std::size_t hash = DeterministicHash(city_name, country_name);
+BreweryResult MockGenerator::GenerateBrewery(
+    const Location& location, const std::string& /*region_context*/) {
+   const std::size_t hash = DeterministicHash(location);
 
-   const std::string& adjective =
+   const std::string_view adjective =
        kBreweryAdjectives.at(hash % kBreweryAdjectives.size());
-   const std::string& noun =
-       kBreweryNouns.at((hash / 7) % kBreweryNouns.size());
-   const std::string& base_description =
+   const std::string_view noun =
+       kBreweryNouns.at(hash / 7 % kBreweryNouns.size());
+   const std::string_view base_description =
        kBreweryDescriptions.at((hash / 13) % kBreweryDescriptions.size());
 
-   const std::string name = city_name + " " + adjective + " " + noun;
-   const std::string description =
-       base_description + " Based in " + city_name +
-       (country_name.empty() ? std::string(".")
-                             : std::string(", ") + country_name + ".");
+   const std::string name =
+       std::format("{} {} {}", location.city, adjective, noun);
 
-   return {name, description};
+   const std::string state_suffix =
+       location.state_province.empty()
+           ? std::string{}
+           : std::format(", {}", location.state_province);
+   const std::string country_suffix =
+       location.country.empty() ? std::string{}
+                                : std::format(", {}", location.country);
+   const std::string description = std::format(
+       "{} Located in {}{}{}.", base_description, location.city,
+       state_suffix, country_suffix);
+
+   return {
+       .name = name,
+       .description = description,
+   };
 }

pipeline/src/data_generation/mock/generate_user.cpp

@@ -6,6 +6,7 @@
 
 #include <functional>
 #include <string>
+#include <string_view>
 
 #include "data_generation/mock_generator.h"
 
@@ -13,7 +14,9 @@ UserResult MockGenerator::GenerateUser(const std::string& locale) {
    const std::size_t hash = std::hash<std::string>{}(locale);
 
    UserResult result;
-   result.username = kUsernames[hash % kUsernames.size()];
-   result.bio = kBios[(hash / 11) % kBios.size()];
+   const std::string_view username = kUsernames[hash % kUsernames.size()];
+   const std::string_view bio = kBios[hash / 11 % kBios.size()];
+   result.username = username;
+   result.bio = bio;
    return result;
 }