AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-10-15 01:54:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

Formatted includes/data_model

Browse Source
This commit is contained in:
Aaron Po
2026-07-19 04:10:32 -04:00
parent 4fae5ead08
commit ffabd85b6d
2 changed files with 181 additions and 181 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
tooling/pipeline/includes/data_model/generated_models.h
View File

@@ -17,64 +17,64 @@
* @brief Generated brewery payload. * @brief Generated brewery payload.
*/ */
struct BreweryResult { struct BreweryResult {
/** /**
* @brief Brewery display name in English. * @brief Brewery display name in English.
*/ */
std::string name_en; std::string name_en;
/** /**
* @brief Brewery description text in English. * @brief Brewery description text in English.
*/ */
std::string description_en; std::string description_en;
/** /**
* @brief Brewery display name in the local language. * @brief Brewery display name in the local language.
*/ */
std::string name_local; std::string name_local;
/** /**
* @brief Brewery description text in the local language. * @brief Brewery description text in the local language.
*/ */
std::string description_local; std::string description_local;
}; };
/** /**
* @brief Generated user profile payload. * @brief Generated user profile payload.
*/ */
struct UserResult { struct UserResult {
/** /**
* @brief First (given) name, copied from the sampled Name -- not * @brief First (given) name, copied from the sampled Name -- not
* LLM-invented. * LLM-invented.
*/ */
std::string first_name{}; std::string first_name{};
/** /**
* @brief Last (family) name, copied from the sampled Name -- not * @brief Last (family) name, copied from the sampled Name -- not
* LLM-invented. * LLM-invented.
*/ */
std::string last_name{}; std::string last_name{};
/** /**
* @brief Gender associated with the sampled first name, copied from the * @brief Gender associated with the sampled first name, copied from the
* sampled Name -- not LLM-invented. * sampled Name -- not LLM-invented.
*/ */
std::string gender{}; std::string gender{};
/** /**
* @brief Username handle. * @brief Username handle.
*/ */
std::string username{}; std::string username{};
/** /**
* @brief Short user biography. * @brief Short user biography.
*/ */
std::string bio{}; std::string bio{};
/** /**
* @brief Relative check-in/activity weight for this user, used to drive * @brief Relative check-in/activity weight for this user, used to drive
* a J-curve activity profile in later pipeline phases. * a J-curve activity profile in later pipeline phases.
*/ */
float activity_weight{}; float activity_weight{};
}; };
// Pipeline Data Models // Pipeline Data Models
@@ -83,8 +83,8 @@ struct UserResult {
* @brief Enriched city data with Wikipedia context. * @brief Enriched city data with Wikipedia context.
*/ */
struct EnrichedCity { struct EnrichedCity {
City location; City location;
std::string region_context{}; std::string region_context{};
}; };
/** /**
@@ -92,8 +92,8 @@ struct EnrichedCity {
* from that city's curated postal-code examples. * from that city's curated postal-code examples.
*/ */
struct BreweryAddress { struct BreweryAddress {
City city; City city;
std::string postal_code{}; std::string postal_code{};
}; };
/** /**
@@ -101,16 +101,16 @@ struct BreweryAddress {
* postal code selected from that city's curated postal-code examples. * postal code selected from that city's curated postal-code examples.
*/ */
struct UserAddress { struct UserAddress {
City city; City city;
std::string postal_code{}; std::string postal_code{};
}; };
/** /**
* @brief Helper struct to store generated brewery data. * @brief Helper struct to store generated brewery data.
*/ */
struct BreweryRecord { struct BreweryRecord {
BreweryAddress address; BreweryAddress address;
BreweryResult brewery; BreweryResult brewery;
}; };
/** /**
@@ -121,10 +121,10 @@ struct BreweryRecord {
* consumer can register real accounts from the pipeline's SQLite export. * consumer can register real accounts from the pipeline's SQLite export.
*/ */
struct UserRecord { struct UserRecord {
UserAddress address; UserAddress address;
UserResult user; UserResult user;
std::string email{}; std::string email{};
std::string date_of_birth{}; std::string date_of_birth{};
}; };
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_ #endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_

250
tooling/pipeline/includes/data_model/models.h
View File

@@ -28,54 +28,54 @@ namespace prog_opts = boost::program_options;
* `postal_code` object in the locations dataset. * `postal_code` object in the locations dataset.
*/ */
struct PostalCodeSpec { struct PostalCodeSpec {
/** /**
* @brief Permissive country-wide postal-code format regex, used as the * @brief Permissive country-wide postal-code format regex, used as the
* validation fallback for a selected example. * validation fallback for a selected example.
*/ */
std::string country_format_regex{}; std::string country_format_regex{};
/** /**
* @brief City-specific postal-code regexes (more precise than the country * @brief City-specific postal-code regexes (more precise than the country
* format). * format).
*/ */
std::vector<std::string> city_regexes{}; std::vector<std::string> city_regexes{};
/** /**
* @brief Concrete example postal codes for this city. The postal code * @brief Concrete example postal codes for this city. The postal code
* service selects from these rather than synthesizing codes. * service selects from these rather than synthesizing codes.
*/ */
std::vector<std::string> examples{}; std::vector<std::string> examples{};
}; };
/** /**
* @brief Canonical city record for city-level generation. * @brief Canonical city record for city-level generation.
*/ */
struct City { struct City {
std::string city{}; std::string city{};
std::string state_province{}; std::string state_province{};
/** /**
* @brief ISO 3166-2 subdivision code. * @brief ISO 3166-2 subdivision code.
*/ */
std::string iso3166_2{}; std::string iso3166_2{};
std::string country{}; std::string country{};
/** /**
* @brief ISO 3166-1 country code. * @brief ISO 3166-1 country code.
*/ */
std::string iso3166_1{}; std::string iso3166_1{};
/** /**
* @brief Local language codes in priority order. * @brief Local language codes in priority order.
*/ */
std::vector<std::string> local_languages{}; std::vector<std::string> local_languages{};
/** /**
* @brief Postal-code metadata (format regex, city regexes, and concrete * @brief Postal-code metadata (format regex, city regexes, and concrete
* examples) sourced directly from the curated locations dataset. * examples) sourced directly from the curated locations dataset.
*/ */
PostalCodeSpec postal_code{}; PostalCodeSpec postal_code{};
}; };
// Name / Persona Models // Name / Persona Models
@@ -86,44 +86,44 @@ struct City {
* Produced by the SampleName() helper in generate_users.cc. * Produced by the SampleName() helper in generate_users.cc.
*/ */
struct Name { struct Name {
std::string first_name{}; std::string first_name{};
std::string last_name{}; std::string last_name{};
/** /**
* @brief Gender associated with the sampled forename (e.g. "M", "F"), as * @brief Gender associated with the sampled forename (e.g. "M", "F"), as
* reported by the source dataset. * reported by the source dataset.
*/ */
std::string gender{}; std::string gender{};
}; };
/** /**
* @brief A single forename entry from the names-by-country fixture data. * @brief A single forename entry from the names-by-country fixture data.
*/ */
struct ForenameEntry { struct ForenameEntry {
/** /**
* @brief Romanized forename. * @brief Romanized forename.
*/ */
std::string name{}; std::string name{};
/** /**
* @brief Gender associated with this forename, as reported by the source * @brief Gender associated with this forename, as reported by the source
* dataset (e.g. "M", "F"). * dataset (e.g. "M", "F").
*/ */
std::string gender{}; std::string gender{};
bool operator==(const ForenameEntry& other) const { bool operator==(const ForenameEntry& other) const {
return name == other.name && gender == other.gender; return name == other.name && gender == other.gender;
} }
}; };
namespace std { namespace std {
template <> template <>
struct hash<ForenameEntry> { struct hash<ForenameEntry> {
size_t operator()(const ForenameEntry& entry) const noexcept { size_t operator()(const ForenameEntry& entry) const noexcept {
const size_t name_hash = std::hash<std::string>{}(entry.name); const size_t name_hash = std::hash<std::string>{}(entry.name);
const size_t gender_hash = std::hash<std::string>{}(entry.gender); const size_t gender_hash = std::hash<std::string>{}(entry.gender);
return name_hash ^ (gender_hash << 1); return name_hash ^ (gender_hash << 1);
} }
}; };
} // namespace std } // namespace std
@@ -131,20 +131,20 @@ struct hash<ForenameEntry> {
* @brief A persona archetype used to ground LLM-generated user bios. * @brief A persona archetype used to ground LLM-generated user bios.
*/ */
struct UserPersona { struct UserPersona {
/** /**
* @brief Persona display name (e.g. "Hophead Explorer"). * @brief Persona display name (e.g. "Hophead Explorer").
*/ */
std::string name{}; std::string name{};
/** /**
* @brief Short description of the persona's interests and voice. * @brief Short description of the persona's interests and voice.
*/ */
std::string description{}; std::string description{};
/** /**
* @brief Beer styles this persona gravitates toward. * @brief Beer styles this persona gravitates toward.
*/ */
std::vector<std::string> style_affinities{}; std::vector<std::string> style_affinities{};
}; };
// Configuration Models // Configuration Models
@@ -153,88 +153,88 @@ struct UserPersona {
* @brief LLM sampling parameters. * @brief LLM sampling parameters.
*/ */
struct SamplingOptions { struct SamplingOptions {
/** /**
* @brief LLM sampling temperature (higher = more random). * @brief LLM sampling temperature (higher = more random).
*/ */
float temperature = 1.0F; float temperature = 1.0F;
/** /**
* @brief LLM nucleus sampling top-p parameter. * @brief LLM nucleus sampling top-p parameter.
*/ */
float top_p = 0.95F; float top_p = 0.95F;
/** /**
* @brief LLM top-k sampling parameter. * @brief LLM top-k sampling parameter.
*/ */
uint32_t top_k = 64; uint32_t top_k = 64;
/** /**
* @brief Context window size (tokens). * @brief Context window size (tokens).
*/ */
uint32_t n_ctx = 8192; uint32_t n_ctx = 8192;
/** /**
* @brief Random seed (-1 for random, otherwise non-negative). * @brief Random seed (-1 for random, otherwise non-negative).
*/ */
int seed = -1; int seed = -1;
/** /**
* @brief Number of layers to offload to GPU. * @brief Number of layers to offload to GPU.
*/ */
int n_gpu_layers = 0; int n_gpu_layers = 0;
}; };
/** /**
* @brief Configuration for the LLM generator component. * @brief Configuration for the LLM generator component.
*/ */
struct GeneratorOptions { struct GeneratorOptions {
/** /**
* @brief Path to the LLM model file (gguf format). * @brief Path to the LLM model file (gguf format).
*/ */
std::filesystem::path model_path; std::filesystem::path model_path;
/** /**
* @brief Use mocked generator instead of actual LLM inference. * @brief Use mocked generator instead of actual LLM inference.
*/ */
bool use_mocked = false; bool use_mocked = false;
/** /**
* @brief Specific sampling parameters for this generator. * @brief Specific sampling parameters for this generator.
* If nullopt, the application should use global defaults. * If nullopt, the application should use global defaults.
*/ */
std::optional<SamplingOptions> sampling; std::optional<SamplingOptions> sampling;
}; };
/** /**
* @brief Configuration for the pipeline execution and output. * @brief Configuration for the pipeline execution and output.
*/ */
struct PipelineOptions { struct PipelineOptions {
/** /**
* @brief Directory for generated artifacts. * @brief Directory for generated artifacts.
*/ */
std::filesystem::path output_path; std::filesystem::path output_path;
/** /**
* @brief Directory that contains named prompt files (e.g. * @brief Directory that contains named prompt files (e.g.
* BREWERY_GENERATION.md). * BREWERY_GENERATION.md).
*/ */
std::filesystem::path prompt_dir; std::filesystem::path prompt_dir;
std::filesystem::path log_path; std::filesystem::path log_path;
/** /**
* @brief Number of locations to sample from the dataset * @brief Number of locations to sample from the dataset
* More locations -> more users/more breweries * More locations -> more users/more breweries
*/ */
uint32_t location_count; uint32_t location_count;
}; };
/** /**
* @brief Root configuration object for the Biergarten pipeline. * @brief Root configuration object for the Biergarten pipeline.
*/ */
struct ApplicationOptions { struct ApplicationOptions {
GeneratorOptions generator; GeneratorOptions generator;
PipelineOptions pipeline; PipelineOptions pipeline;
}; };
// Function Declarations // Function Declarations