mirror of
https://github.com/aaronpo97/the-biergarten-app.git
synced 2026-07-16 09:37:23 +00:00
Pipeline: Add LLM and mocked user generation to the pipeline (#230)
This commit is contained in:
GitHub
@@ -67,11 +67,50 @@ package "Domain: Models" {
|
||||
}
|
||||
|
||||
class UserResult {
|
||||
+ first_name : std::string
|
||||
+ last_name : std::string
|
||||
+ gender : std::string
|
||||
+ username : std::string
|
||||
+ bio : std::string
|
||||
+ activity_weight : float
|
||||
}
|
||||
|
||||
class Name {
|
||||
+ first_name : std::string
|
||||
+ last_name : std::string
|
||||
+ gender : std::string
|
||||
}
|
||||
|
||||
class ForenameEntry {
|
||||
+ name : std::string
|
||||
+ gender : std::string
|
||||
}
|
||||
|
||||
note right of ForenameEntry
|
||||
forename_list = std::unordered_set<ForenameEntry>
|
||||
surname_list = std::unordered_set<std::string>
|
||||
(aliases declared in curated_data_service.h).
|
||||
ICuratedDataService::LoadForenamesByCountry() /
|
||||
LoadSurnamesByCountry() each return a flat
|
||||
std::unordered_map<std::string, forename_list>
|
||||
or <std::string, surname_list> keyed by ISO
|
||||
3166-1 country code -- no NamesByCountry
|
||||
wrapper class. SampleName(forenames_by_country,
|
||||
surnames_by_country, iso3166_1, rng) is a free
|
||||
function, not a method, so it can be called by
|
||||
any per-city worker without owning the maps.
|
||||
Sourced from popular-names-by-country-dataset
|
||||
(CC0) -- see ETHICS-AND-KNOWN-ISSUES.md. Gender
|
||||
is preserved per forename so it can be threaded
|
||||
through to persona/bio generation later; surnames
|
||||
carry no gender in the source data. Pairing
|
||||
happens at sample time, not at fixture-authoring
|
||||
time, so no information from the source dataset
|
||||
is discarded up front.
|
||||
end note
|
||||
|
||||
ForenameEntry ..> Name : SampleName() produces
|
||||
|
||||
class CheckinResult {
|
||||
+ checked_in_at : std::string
|
||||
+ note : std::string
|
||||
@@ -110,9 +149,20 @@ package "Domain: Models" {
|
||||
+ user_id : uint64_t
|
||||
+ location : Location
|
||||
+ user : UserResult
|
||||
+ email : std::string
|
||||
+ date_of_birth : std::string
|
||||
+ password : std::string
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
note right of GeneratedUser
|
||||
email, date_of_birth, and password are
|
||||
programmatically generated by the orchestrator
|
||||
(not LLM-authored) so a downstream auth-account
|
||||
seeding consumer can register real accounts from
|
||||
this export. See ROADMAP.md §1.
|
||||
end note
|
||||
|
||||
class GeneratedCheckin {
|
||||
+ checkin_id : uint64_t
|
||||
+ user_id : uint64_t
|
||||
@@ -318,20 +368,43 @@ package "Infrastructure: Pipeline Channel" {
|
||||
|
||||
package "Infrastructure: Data Preloading" {
|
||||
|
||||
interface DataPreloader <<interface>> {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : std::vector<Persona>
|
||||
+ LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
|
||||
interface ICuratedDataService <<interface>> {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : const std::vector<BeerStyle>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(forenames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(surnames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
class JsonLoader {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : std::vector<Persona>
|
||||
+ LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : const std::vector<BeerStyle>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(forenames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(surnames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
note right of JsonLoader
|
||||
Each Load* call is memoized after its first
|
||||
parse -- implemented today, ahead of the rest
|
||||
of this package (LoadBeerStyles is still planned).
|
||||
end note
|
||||
|
||||
class MockCuratedDataService {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : const std::vector<BeerStyle>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(forenames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(surnames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
note right of MockCuratedDataService
|
||||
Fixed in-memory dataset used in --mocked mode,
|
||||
implemented today for Locations/Personas/
|
||||
Forenames/Surnames; would need a LoadBeerStyles
|
||||
fixture too once that method is implemented.
|
||||
end note
|
||||
|
||||
}
|
||||
|
||||
package "Infrastructure: Enrichment" {
|
||||
@@ -380,7 +453,7 @@ package "Infrastructure: Data Generation" {
|
||||
interface DataGenerator <<interface>> {
|
||||
+ GenerateBrewery(location : const Location&,\n context : const LocationContext&) : BreweryResult
|
||||
+ GenerateBeer(brewery_id : uint64_t,\n location : const Location&,\n context : const LocationContext&,\n style : const BeerStyle&) : BeerResult
|
||||
+ GenerateUser(location : const Location&) : UserResult
|
||||
+ GenerateUser(city : const EnrichedCity&,\n persona : const UserPersona&,\n name : const Name&) : UserResult
|
||||
+ GenerateCheckin(user : const GeneratedUser&,\n brewery : const GeneratedBrewery&,\n timestamp : const std::string&) : CheckinResult
|
||||
+ GenerateRating(user : const GeneratedUser&,\n beer : const GeneratedBeer&,\n checkin_id : uint64_t) : RatingResult
|
||||
}
|
||||
@@ -473,7 +546,7 @@ package "Infrastructure: Data Export" {
|
||||
}
|
||||
|
||||
class BiergartenPipelineOrchestrator {
|
||||
- preloader_ : std::unique_ptr<DataPreloader>
|
||||
- curated_data_service_ : std::unique_ptr<ICuratedDataService>
|
||||
- enrichment_service_ : std::unique_ptr<EnrichmentService>
|
||||
- generator_ : std::unique_ptr<DataGenerator>
|
||||
- logger_ : std::unique_ptr<Logger>
|
||||
@@ -501,7 +574,7 @@ class BiergartenPipelineOrchestrator {
|
||||
}
|
||||
|
||||
' --- Orchestration Aggregations (Services & Strategies) ---
|
||||
BiergartenPipelineOrchestrator *-- DataPreloader
|
||||
BiergartenPipelineOrchestrator *-- ICuratedDataService
|
||||
BiergartenPipelineOrchestrator *-- EnrichmentService
|
||||
BiergartenPipelineOrchestrator *-- DataGenerator
|
||||
BiergartenPipelineOrchestrator *-- ExportService
|
||||
@@ -520,7 +593,8 @@ BiergartenPipelineOrchestrator *-- "0..*" GeneratedCheckin : checkin_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedFollow : follow_pool_
|
||||
|
||||
' --- Interfaces & Implementations ---
|
||||
DataPreloader <|.. JsonLoader
|
||||
ICuratedDataService <|.. JsonLoader
|
||||
ICuratedDataService <|.. MockCuratedDataService
|
||||
Logger <|.. PipelineLogger
|
||||
ContextStrategy <|.. BreweryContextStrategy
|
||||
ContextStrategy <|.. BeerContextStrategy
|
||||
|
||||
Reference in New Issue
Block a user