Implement Llama-based brewery and user data generation; remove mock generator and related files

This commit is contained in:
Aaron Po
2026-04-01 23:29:16 -04:00
parent 248a51b35f
commit 280c9c61bd
11 changed files with 445 additions and 128 deletions

View File

@@ -0,0 +1,25 @@
#pragma once
#include <string>
struct BreweryResult {
std::string name;
std::string description;
};
struct UserResult {
std::string username;
std::string bio;
};
class IDataGenerator {
public:
virtual ~IDataGenerator() = default;
virtual void load(const std::string &modelPath) = 0;
virtual BreweryResult generateBrewery(const std::string &cityName,
const std::string &regionContext) = 0;
virtual UserResult generateUser(const std::string &locale) = 0;
};

View File

@@ -1,36 +0,0 @@
#pragma once
#include <string>
#include <vector>
/// @brief Deterministic mock brewery text generator used in pipeline output.
class LlamaBreweryGenerator {
private:
const std::vector<std::string> breweryAdjectives = {
"Craft", "Heritage", "Local", "Artisan",
"Pioneer", "Golden", "Modern", "Classic"};
const std::vector<std::string> breweryNouns = {
"Brewing Co.", "Brewery", "Bier Haus", "Taproom",
"Works", "House", "Fermentery", "Ale Co."};
const std::vector<std::string> descriptions = {
"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."};
public:
/// @brief Generated brewery payload for one city.
struct Brewery {
std::string name;
std::string description;
};
/// @brief Loads model resources (mock implementation in this project).
void LoadModel(const std::string &modelPath);
/// @brief Generates deterministic brewery text for a city and seed.
Brewery GenerateBrewery(const std::string &cityName, int seed);
};

View File

@@ -2,7 +2,6 @@
#include "database.h"
#include "stream_parser.h"
#include "work_queue.h"
#include <string>
/// @brief Loads world-city JSON data into SQLite through streaming parsing.

View File

@@ -0,0 +1,24 @@
#pragma once
#include "data_generator.h"
#include <memory>
#include <string>
struct llama_model;
struct llama_context;
class LlamaGenerator final : public IDataGenerator {
public:
~LlamaGenerator() override;
void load(const std::string &modelPath) override;
BreweryResult generateBrewery(const std::string &cityName,
const std::string &regionContext) override;
UserResult generateUser(const std::string &locale) override;
private:
std::string infer(const std::string &prompt, int maxTokens = 256);
llama_model *model_ = nullptr;
llama_context *context_ = nullptr;
};

View File

@@ -0,0 +1,23 @@
#pragma once
#include "data_generator.h"
#include <string>
#include <vector>
class MockGenerator final : public IDataGenerator {
public:
void load(const std::string &modelPath) override;
BreweryResult generateBrewery(const std::string &cityName,
const std::string &regionContext) override;
UserResult generateUser(const std::string &locale) override;
private:
static std::size_t deterministicHash(const std::string &a,
const std::string &b);
static const std::vector<std::string> kBreweryAdjectives;
static const std::vector<std::string> kBreweryNouns;
static const std::vector<std::string> kBreweryDescriptions;
static const std::vector<std::string> kUsernames;
static const std::vector<std::string> kBios;
};

View File

@@ -1,63 +0,0 @@
#pragma once
#include <condition_variable>
#include <mutex>
#include <optional>
#include <queue>
/// @brief Bounded thread-safe queue with blocking push/pop and shutdown.
template <typename T> class WorkQueue {
private:
std::queue<T> queue;
std::mutex mutex;
std::condition_variable cv_not_empty;
std::condition_variable cv_not_full;
size_t max_size;
bool shutdown = false;
public:
/// @brief Creates a queue with fixed capacity.
explicit WorkQueue(size_t capacity) : max_size(capacity) {}
/// @brief Pushes an item, blocking while full unless shutdown is signaled.
bool push(T item) {
std::unique_lock<std::mutex> lock(mutex);
cv_not_full.wait(lock,
[this] { return queue.size() < max_size || shutdown; });
if (shutdown)
return false;
queue.push(std::move(item));
cv_not_empty.notify_one();
return true;
}
/// @brief Pops an item, blocking while empty unless shutdown is signaled.
std::optional<T> pop() {
std::unique_lock<std::mutex> lock(mutex);
cv_not_empty.wait(lock, [this] { return !queue.empty() || shutdown; });
if (queue.empty())
return std::nullopt;
T item = std::move(queue.front());
queue.pop();
cv_not_full.notify_one();
return item;
}
/// @brief Signals queue shutdown and wakes all waiting producers/consumers.
void shutdown_queue() {
std::unique_lock<std::mutex> lock(mutex);
shutdown = true;
cv_not_empty.notify_all();
cv_not_full.notify_all();
}
/// @brief Returns current queue size.
size_t size() const {
std::lock_guard<std::mutex> lock(mutex);
return queue.size();
}
};