Move pipeline directory

tooling/pipeline/diagrams/current/activity.puml

@@ -0,0 +1,125 @@
+@startuml
+skinparam style strictuml
+skinparam defaultFontName "DM Sans"
+skinparam defaultFontSize 14
+skinparam titleFontName "Volkhov"
+skinparam titleFontSize 20
+skinparam backgroundColor #FAFCF9
+skinparam defaultFontColor #28342A
+skinparam titleFontColor #28342A
+skinparam ArrowColor #628A5B
+skinparam NoteBackgroundColor #EAF0E8
+skinparam NoteBorderColor #547461
+skinparam ActivityBackgroundColor #FAFCF9
+skinparam ActivityBorderColor #547461
+skinparam ActivityDiamondBackgroundColor #FAFCF9
+skinparam ActivityDiamondBorderColor #628A5B
+skinparam ActivityBarColor #628A5B
+skinparam SwimlaneBorderColor #547461
+skinparam SwimlaneBorderThickness 0.3
+
+title The Biergarten Data Pipeline (Streaming Architecture)
+
+|#F2F6F0|main.cc|
+start
+:ParseArguments(argc, argv);
+if (Are arguments valid?) then (no)
+  :spdlog::error usage info;
+  stop
+else (yes)
+endif
+
+:Init CurlGlobalState & LlamaBackendState;
+:di::make_injector(...);
+:injector.create<std::unique_ptr<BiergartenDataGenerator>>();
+:BiergartenDataGenerator::Run();
+
+|#EAF0E8|BiergartenDataGenerator|
+:Initialize SQLite export;
+
+|#E0EAE0|SqliteExportService|
+:GetUtcTimestamp() from SystemDateTimeProvider;
+:Initialize();
+note right
+  Builds a fresh biergarten_seed_<UTC datetime>.sqlite filename
+  Appends a numeric suffix if the timestamp already exists
+  Opens DB Connection
+  Executes Schema DDL
+  Begins Transaction
+end note
+
+|#EAF0E8|BiergartenDataGenerator|
+:QueryCitiesWithCountries();
+
+|#E2EBDC|JsonLoader|
+:JsonLoader::LoadLocations("locations.json");
+:std::ranges::sample(all_locations, 50);
+
+|#EAF0E8|BiergartenDataGenerator|
+while (For each sampled Location?) is (Remaining cities)
+  |#DCE8D8|WikipediaService|
+  :GetLocationContext(loc);
+  :FetchExtracts(City, Country, Beer);
+  |#EAF0E8|BiergartenDataGenerator|
+  :Store EnrichedCity{Location, region_context};
+endwhile (Done)
+
+|#EAF0E8|BiergartenDataGenerator|
+:GenerateBreweries(enriched_cities);
+
+|#E5EDE1|DataGenerator|
+while (For each EnrichedCity?) is (Remaining cities)
+  if (Generator Mode) then (MockGenerator)
+    :DeterministicHash & Format;
+  else (LlamaGenerator)
+    :PrepareRegionContext;
+    :LoadBrewerySystemPrompt("prompts/system.md");
+    repeat
+      :Infer(system_prompt, user_prompt, max_tokens, kBreweryJsonGrammar);
+      :ValidateBreweryJson(raw, brewery);
+      if (Is JSON Valid?) then (yes)
+        break
+      else (no)
+        :Attempt++;
+      endif
+    repeat while (Attempt < 3?) is (yes)
+  endif
+
+  |#EAF0E8|BiergartenDataGenerator|
+  if (Generation successful?) then (yes)
+    |#E0EAE0|SqliteExportService|
+    :ProcessRecord(GeneratedBrewery);
+    if (Location in cache?) then (yes)
+      :Reuse location_id;
+    else (no)
+      :Insert Location & Cache ID;
+    endif
+    :Insert Brewery (FK: location_id);
+
+    if (Exception caught during insert?) then (yes)
+      |#EAF0E8|BiergartenDataGenerator|
+      :spdlog::warn "Failed to stream record to SQLite export";
+      note right
+        Data loss is prevented per-record.
+        The pipeline continues running.
+      end note
+    else (no)
+    endif
+  else (no)
+    :spdlog::warn "Generation failed, skipping...";
+  endif
+  |#E5EDE1|DataGenerator|
+endwhile (Done)
+
+|#E0EAE0|SqliteExportService|
+:Finalize();
+note right
+  Commits Transaction
+  Closes Database Connection
+end note
+
+|#F2F6F0|main.cc|
+:Return 0;
+stop
+
+@enduml