AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-05-31 17:53:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

logging updates

Browse Source
This commit is contained in:
Aaron Po
2026-05-17 02:58:47 -04:00
parent 5d80b53351
commit be3c324b38
37 changed files with 643 additions and 389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tooling/pipeline/CMakeLists.txt
View File

@@ -138,7 +138,8 @@ FetchContent_MakeAvailable(cpp-httplib)
# 5. Executable & Sources
add_executable(${PROJECT_NAME}
includes/services/enrichment/mock_enrichment.h)
includes/services/enrichment/mock_enrichment.h
includes/json_handling/pretty_print.h)
# --- Entry point ---
target_sources(${PROJECT_NAME} PRIVATE

33
tooling/pipeline/includes/biergarten_pipeline_orchestrator.h
View File

@@ -1,8 +1,8 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
/**
* @file biergarten_data_generator.h
* @file biergarten_pipeline_orchestrator.h
* @brief Orchestration for end-to-end brewery data generation pipeline.
*
* Intent: Coordinates location loading, enrichment, and generation phases
@@ -28,14 +28,14 @@
*/
class BiergartenPipelineOrchestrator {
public:
/**
* @brief Constructs the orchestrator with injected pipeline dependencies.
*
* @param context_service Provides regional context for locations.
* @param generator Implementation (Llama or Mock) for brewery/user generation.
* @param exporter Database backend for persisting generated records.
* @param application_options CLI configuration and paths.
*/
/**
* @brief Constructs the orchestrator with injected pipeline dependencies.
*
* @param context_service Provides regional context for locations.
* @param generator Implementation (Llama or Mock) for brewery/user generation.
* @param exporter Database backend for persisting generated records.
* @param application_options CLI configuration and paths.
*/
BiergartenPipelineOrchestrator(
std::shared_ptr<ILogger> logger,
std::unique_ptr<IEnrichmentService> context_service,
@@ -65,11 +65,11 @@ class BiergartenPipelineOrchestrator {
/// @brief Generator dependency selected in the composition root.
std::unique_ptr<DataGenerator> generator_;
/// @brief Storage backend for generated brewery records.
std::unique_ptr<IExportService> exporter_;
/// @brief Storage backend for generated brewery records.
std::unique_ptr<IExportService> exporter_;
/// @brief CLI configuration: paths, model settings, generation parameters.
ApplicationOptions application_options_;
/// @brief CLI configuration: paths, model settings, generation parameters.
ApplicationOptions application_options_;
/**
* @brief Load locations from JSON and sample cities.
@@ -93,4 +93,5 @@ class BiergartenPipelineOrchestrator {
/// @brief Stores generated brewery data.
std::vector<GeneratedBrewery> generated_breweries_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_

2
tooling/pipeline/includes/concurrency/bounded_channel.h
View File

@@ -8,7 +8,7 @@
#include <queue>
/**
* @file bounded_channel.h
* @file concurrency/bounded_channel.h
* @brief Thread-safe, bounded multi-producer/multi-consumer synchronous channel.
*
* Intent: Enables asynchronous inter-thread communication with backpressure.

5
tooling/pipeline/includes/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h
View File

@@ -1,6 +1,11 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
/**
* @file data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h
* @brief Prompt formatter for Google Gemma 4 model using Jinja2 template syntax.
*/
#include <string>
#include <string_view>

5
tooling/pipeline/includes/data_generation/prompt_formatting/prompt_formatter.h
View File

@@ -1,6 +1,11 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
/**
* @file data_generation/prompt_formatting/prompt_formatter.h
* @brief Abstract interface for formatting system and user prompts.
*/
#include <string>
#include <string_view>

109
tooling/pipeline/includes/json_handling/pretty_print.h Normal file
View File

@@ -0,0 +1,109 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
#define BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
/**
* @file json_handling/pretty_print.h
* @brief Pretty-printing utilities for JSON values.
*
* Provides formatting capability for boost::json::value with indentation and
* readable output. Adapted from Boost JSON library examples.
*/
#include <boost/json.hpp>
#include <ostream>
#include <string>
/**
* @brief Pretty-prints a JSON value to an output stream with indentation.
*
* Recursively formats JSON objects and arrays with consistent 4-space
* indentation. Adapted from:
* https://raw.githubusercontent.com/boostorg/json/refs/heads/develop/example/pretty.cpp
*
* @param outstream Output stream to write formatted JSON.
* @param json_val JSON value to format.
* @param indent Optional indentation string (managed internally on first call).
*/
inline void PrettyPrint(std::ostream& outstream,
boost::json::value const& json_val,
std::string* indent = nullptr) {
std::string str;
if (indent == nullptr) {
indent = &str;
}
switch (json_val.kind()) {
case boost::json::kind::object: {
outstream << "{\n";
indent->append(4, ' ');
auto const& obj = json_val.get_object();
if (!obj.empty()) {
const auto* iter = obj.begin();
for (;;) {
outstream << *indent << boost::json::serialize(iter->key()) << " : ";
PrettyPrint(outstream, iter->value(), indent);
iter = std::next(iter);
if (iter == obj.end()) {
break;
}
outstream << ",\n";
}
}
outstream << "\n";
indent->resize(indent->size() - 4);
outstream << *indent << "}";
break;
}
case boost::json::kind::array: {
outstream << "[\n";
indent->append(4, ' ');
auto const& arr = json_val.get_array();
if (!arr.empty()) {
const auto* iter = arr.begin();
for (;;) {
outstream << *indent;
PrettyPrint(outstream, *iter, indent);
iter = std::next(iter);
if (iter == arr.end()) {
break;
}
outstream << ",\n";
}
}
outstream << "\n";
indent->resize(indent->size() - 4);
outstream << *indent << "]";
break;
}
case boost::json::kind::string: {
outstream << serialize(json_val.get_string());
break;
}
case boost::json::kind::uint64:
case boost::json::kind::int64:
case boost::json::kind::double_:
outstream << json_val;
break;
case boost::json::kind::bool_:
if (json_val.get_bool()) {
outstream << "true";
} else {
outstream << "false";
}
break;
case boost::json::kind::null:
outstream << "null";
break;
}
if (indent->empty()) {
outstream << "\n";
}
}
#endif

2
tooling/pipeline/includes/services/database/export_service.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
/**
* @file services/export_service.h
* @file services/database/export_service.h
* @brief Abstraction for persisting generated brewery data.
*/

2
tooling/pipeline/includes/services/database/sqlite_connection_helpers.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
/**
* @file services/sqlite_connection_helpers.h
* @file services/database/sqlite_connection_helpers.h
* @brief Declarations for connection-level SQLite helper functions.
*/

2
tooling/pipeline/includes/services/database/sqlite_export_service.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
/**
* @file services/sqlite_export_service.h
* @file services/database/sqlite_export_service.h
* @brief SQLite-backed export service for generated brewery data.
*/

2
tooling/pipeline/includes/services/database/sqlite_statement_helpers.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
/**
* @file services/sqlite_statement_helpers.h
* @file services/database/sqlite_statement_helpers.h
* @brief Declarations for statement-level SQLite helper functions and
* constants.
*/

2
tooling/pipeline/includes/services/datetime/date_time_provider.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
/**
* @file services/date_time_provider.h
* @file services/datetime/date_time_provider.h
* @brief Abstraction for UTC timestamp generation.
*/

2
tooling/pipeline/includes/services/datetime/timer.h
View File

@@ -4,7 +4,7 @@
#include <chrono>
/**
* @file services/timer.h
* @file services/datetime/timer.h
* @brief Simple timer utility for measuring elapsed time.
*/
class Timer {

2
tooling/pipeline/includes/services/enrichment/enrichment_service.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
/**
* @file services/enrichment_service.h
* @file services/enrichment/enrichment_service.h
* @brief Abstraction for resolving contextual enrichment for a location.
*/

22
tooling/pipeline/includes/services/enrichment/mock_enrichment.h
View File

@@ -1,15 +1,29 @@
//
// Created by aaronpo on 13/05/2026.
//
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
/**
* @file services/enrichment/mock_enrichment.h
* @brief Mock implementation of enrichment service for testing.
*/
#include <string>
#include "enrichment_service.h"
/**
* @brief Mock implementation of enrichment service for testing and prototyping.
*
* Returns empty context without performing actual web queries or enrichment.
* Useful for unit tests and development scenarios.
*/
class MockEnrichmentService final : public IEnrichmentService {
public:
/**
* @brief Returns empty location context.
*
* @param loc Unused location parameter.
* @return Empty string (no enrichment performed).
*/
std::string GetLocationContext(const Location& /*loc*/) override {
return {};
}

2
tooling/pipeline/includes/services/enrichment/wikipedia_service.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
/**
* @file services/wikipedia_service.h
* @file services/enrichment/wikipedia_service.h
* @brief Wikipedia summary retrieval service with in-memory caching.
*/

46
tooling/pipeline/includes/services/logging/log_dispatcher.h
View File

@@ -6,8 +6,8 @@
* them to spdlog on a dedicated thread.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
#include <spdlog/spdlog.h>
@@ -23,31 +23,31 @@
*/
class LogDispatcher {
public:
/**
* @brief Construct a log dispatcher.
*
* @param channel Reference to the bounded channel used for log retrieval.
*/
explicit LogDispatcher(BoundedChannel<LogEntry>& channel);
/**
* @brief Construct a log dispatcher.
*
* @param channel Reference to the bounded channel used for log retrieval.
*/
explicit LogDispatcher(BoundedChannel<LogEntry>& channel);
LogDispatcher(const LogDispatcher&) = delete;
LogDispatcher& operator=(const LogDispatcher&) = delete;
LogDispatcher(LogDispatcher&&) = delete;
LogDispatcher& operator=(LogDispatcher&&) = delete;
~LogDispatcher() = default;
LogDispatcher(const LogDispatcher&) = delete;
LogDispatcher& operator=(const LogDispatcher&) = delete;
LogDispatcher(LogDispatcher&&) = delete;
LogDispatcher& operator=(LogDispatcher&&) = delete;
~LogDispatcher() = default;
/**
* @brief Drain the channel and forward entries to spdlog.
*
* Intended to be called once on a dedicated thread. The loop returns after
* the channel has been closed and all queued entries have been processed.
*/
void Run();
/**
* @brief Drain the channel and forward entries to spdlog.
*
* Intended to be called once on a dedicated thread. The loop returns after
* the channel has been closed and all queued entries have been processed.
*/
void Run();
private:
BoundedChannel<LogEntry>& channel_;
BoundedChannel<LogEntry>& channel_;
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_

5
tooling/pipeline/includes/services/logging/log_entry.h
View File

@@ -1,3 +1,6 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
/**
* @file services/logging/log_entry.h
* @brief Structured log record shared by the pipeline logging infra.
@@ -6,8 +9,6 @@
* logging producer and dispatcher through BoundedChannel<LogEntry>.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#include <chrono>
#include <thread>

43
tooling/pipeline/includes/services/logging/log_producer.h
View File

@@ -6,8 +6,8 @@
* a bounded channel for later processing by the dispatcher.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
#include <string_view>
@@ -24,30 +24,29 @@
*/
class LogProducer final : public ILogger {
public:
/**
* @brief Construct a channel-backed producer.
*
* @param channel Reference to the bounded channel used for log transfer.
*/
explicit LogProducer(BoundedChannel<LogEntry>& channel);
/**
* @brief Construct a channel-backed producer.
*
* @param channel Reference to the bounded channel used for log transfer.
*/
explicit LogProducer(BoundedChannel<LogEntry>& channel);
LogProducer(const LogProducer&) = delete;
LogProducer& operator=(const LogProducer&) = delete;
LogProducer(LogProducer&&) = delete;
LogProducer& operator=(LogProducer&&) = delete;
LogProducer(const LogProducer&) = delete;
LogProducer& operator=(const LogProducer&) = delete;
LogProducer(LogProducer&&) = delete;
LogProducer& operator=(LogProducer&&) = delete;
~LogProducer() override = default;
~LogProducer() override = default;
/**
* @brief Queue a log message for asynchronous processing.
*
* Blocks while the channel applies backpressure.
*/
void Log(LogLevel level, PipelinePhase phase,
std::string_view message) override;
/**
* @brief Queue a log message for asynchronous processing.
*
* Blocks while the channel applies backpressure.
*/
void Log(LogEntry const& entry) override;
private:
BoundedChannel<LogEntry>& channel_;
BoundedChannel<LogEntry>& channel_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_

33
tooling/pipeline/includes/services/logging/logger.h
View File

@@ -1,3 +1,6 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
/**
* @file services/logging/logger.h
* @brief Abstract logging interface used by pipeline components.
@@ -6,8 +9,6 @@
* transport, buffering, and formatting implementation.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#include <optional>
#include <string>
@@ -24,22 +25,20 @@
*/
class ILogger {
public:
ILogger() = default;
ILogger(const ILogger&) = delete;
ILogger& operator=(const ILogger&) = delete;
ILogger(ILogger&&) = delete;
ILogger& operator=(ILogger&&) = delete;
virtual ~ILogger() = default;
ILogger() = default;
ILogger(const ILogger&) = delete;
ILogger& operator=(const ILogger&) = delete;
ILogger(ILogger&&) = delete;
ILogger& operator=(ILogger&&) = delete;
virtual ~ILogger() = default;
/**
* @brief Submit a log message to the logging subsystem.
*
* @param level Severity of the message.
* @param phase Pipeline execution phase associated with the message.
* @param message Log message text.
*/
virtual void Log(LogLevel level, PipelinePhase phase,
std::string_view message) = 0;
/**
* @brief Submit a log message to the logging subsystem.
*
* @param entry Structured log record containing message and metadata.
*
*/
virtual void Log(const LogEntry& entry) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

2
tooling/pipeline/includes/services/prompting/prompt_directory.h
View File

@@ -2,7 +2,7 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
/**
* @file services/prompt_directory.h
* @file services/prompting/prompt_directory.h
* @brief Interface and filesystem-backed implementation for named prompt
* loading.
*

27
tooling/pipeline/includes/web_client/http_web_client.h
View File

@@ -1,19 +1,18 @@
/**
* @file web_client/http_web_client.h
* @brief cpp-httplib implementation of the WebClient interface.
*/
* @file web_client/http_web_client.h
* @brief cpp-httplib implementation of the WebClient interface.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
#define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
#include "web_client/web_client.h"
#include "services/logging/logger.h"
#include <memory>
#include <string>
#include <utility>
#include "services/logging/logger.h"
#include "web_client/web_client.h"
/**
* @brief WebClient implementation backed by cpp-httplib.
*
@@ -26,9 +25,18 @@
* bound to a single origin at construction time.
*/
class HttpWebClient final : public WebClient {
public:
public:
/**
* @brief Construct an HTTP web client with a logger.
*
* @param logger Logger instance for diagnostics.
*/
explicit HttpWebClient(std::shared_ptr<ILogger> logger)
: logger_(std::move(logger)) {}
/**
* @brief Destructor.
*/
~HttpWebClient() override = default;
/**
@@ -52,5 +60,4 @@ public:
std::shared_ptr<ILogger> logger_;
};
#endif
#endif // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_

52
tooling/pipeline/src/application_options/parse_arguments.cc
View File

@@ -1,14 +1,14 @@
#include "services/logging/logger.h"
#include <chrono>
#include <iostream>
#include <optional>
#include <sstream>
#include <string>
#include "data_model/models.h"
#include "services/logging/logger.h"
std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
std::shared_ptr<ILogger> logger) {
std::optional<ApplicationOptions> ParseArguments(
const int argc, char** argv, std::shared_ptr<ILogger> logger) {
prog_opts::options_description desc("Pipeline Options");
auto opt = desc.add_options();
@@ -70,8 +70,12 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
return usage_stream.str();
})();
if (logger) {
logger->Log(LogLevel::Info, PipelinePhase::Startup, title);
logger->Log(LogLevel::Info, PipelinePhase::Startup, usage);
logger->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = title});
logger->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = usage});
} else {
std::cout << title << std::endl << usage << std::endl;
}
@@ -87,7 +91,9 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
std::stringstream help_stream;
help_stream << "\n" << desc;
if (logger) {
logger->Log(LogLevel::Info, PipelinePhase::Startup, help_stream.str());
logger->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = help_stream.str()});
} else {
std::cout << help_stream.str() << std::endl;
}
@@ -99,8 +105,7 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
options.pipeline.output_path = var_map["output"].as<std::string>();
options.pipeline.log_path = var_map["log-path"].as<std::string>();
options.pipeline.prompt_dir = var_map["prompt-dir"].as<std::string>();
options.pipeline.location_count =
var_map["location-count"].as<uint32_t>();
options.pipeline.location_count = var_map["location-count"].as<uint32_t>();
const bool use_mocked = var_map["mocked"].as<bool>();
const std::string model_path = var_map["model"].as<std::string>();
@@ -111,7 +116,9 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
const std::string msg =
"Invalid arguments: --mocked and --model are mutually exclusive";
if (logger) {
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}
@@ -122,7 +129,9 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
const std::string msg =
"Invalid arguments: either --mocked or --model must be specified";
if (logger) {
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}
@@ -135,7 +144,9 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
const std::string msg =
"Invalid arguments: --prompt-dir is required when not using --mocked";
if (logger) {
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}
@@ -158,11 +169,13 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
if (user_provided_sampling) {
// Warn but do not fail — the run is still valid, the flags are just
// silently irrelevant when no model is loaded.
if (use_mocked) {
if (use_mocked) {
const std::string msg =
"Sampling parameters are ignored when using --mocked";
if (logger) {
logger->Log(LogLevel::Warn, PipelinePhase::Startup, msg);
logger->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}
@@ -186,15 +199,20 @@ std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
std::string("Failed to parse command-line arguments: ") +
exception.what();
if (logger) {
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}
return std::nullopt;
} catch (...) {
const std::string msg = "Failed to parse command-line arguments: unknown error";
const std::string msg =
"Failed to parse command-line arguments: unknown error";
if (logger) {
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
} else {
std::cerr << msg << std::endl;
}

48
tooling/pipeline/src/biergarten_pipeline_orchestrator/generate_breweries.cc
View File

@@ -3,13 +3,16 @@
* @brief BiergartenDataGenerator::GenerateBreweries() implementation.
*/
#include "services/logging/logger.h"
#include <chrono>
#include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h"
void BiergartenPipelineOrchestrator::GenerateBreweries(
std::span<const EnrichedCity> cities) {
logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration,
"=== SAMPLE BREWERY GENERATION ===");
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = "=== SAMPLE BREWERY GENERATION ==="});
generated_breweries_.clear();
size_t skipped_count = 0;
@@ -29,33 +32,38 @@ void BiergartenPipelineOrchestrator::GenerateBreweries(
} catch (const std::exception& export_exception) {
++export_failed_count;
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("[Pipeline] Generated brewery for '") +
location.city + "' (" + location.country +
") but SQLite export failed: " +
export_exception.what());
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::string("[Pipeline] Generated brewery for '") +
location.city + "' (" + location.country +
") but SQLite export failed: " + export_exception.what()});
}
} catch (const std::exception& e) {
++skipped_count;
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("[Pipeline] Skipping city '") + location.city +
" (" + location.country + "): brewery generation failed: " +
e.what());
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("[Pipeline] Skipping city '") +
location.city + " (" + location.country +
"): brewery generation failed: " + e.what()});
}
}
if (skipped_count > 0) {
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to generation errors");
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to generation errors"});
}
if (export_failed_count > 0) {
logger_->Log(LogLevel::Warn, PipelinePhase::Teardown,
std::string("[Pipeline] Failed to export ") +
std::to_string(export_failed_count) +
" generated brewery/breweries to SQLite");
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Teardown,
.message = std::string("[Pipeline] Failed to export ") +
std::to_string(export_failed_count) +
" generated brewery/breweries to SQLite"});
}
}

46
tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc
View File

@@ -3,29 +3,35 @@
* @brief BiergartenDataGenerator::LogResults() implementation.
*/
#include "services/logging/logger.h"
#include <boost/json/array.hpp>
#include <chrono>
#include <format>
#include "../../includes/json_handling/pretty_print.h"
#include "biergarten_pipeline_orchestrator.h"
#include <sstream>
#include "services/logging/logger.h"
void BiergartenPipelineOrchestrator::LogResults() const {
std::ostringstream msg;
msg << "GENERATED DATA DUMP\n";
size_t index = 1;
for (const auto& [location, brewery] : generated_breweries_) {
msg << index << ". city=\"" << location.city << "\" country=\""
<< location.country << "\" state=\"" << location.state_province
<< "\" iso3166_2=" << location.iso3166_2 << " lat="
<< location.latitude << " lon=" << location.longitude << "\n";
boost::json::array output;
msg << " brewery_name_en=\"" << brewery.name_en << "\"\n";
msg << " brewery_description_en=\"" << brewery.description_en
<< "\"\n";
msg << " brewery_name_local=\"" << brewery.name_local << "\"\n";
msg << " brewery_description_local=\"" << brewery.description_local
<< "\"\n";
++index;
for (const auto& [location, brewery] : generated_breweries_) {
output.push_back(boost::json::object{
{"name_en", brewery.name_en},
{"description_en", brewery.description_en},
{"name_local", brewery.name_local},
{"description_local", brewery.description_local},
{"location", boost::json::object{
{"city", location.city},
{"country", location.country},
{"state_province", location.state_province},
{"iso3166_2", location.iso3166_2},
{"latitude", location.latitude},
{"longitude", location.longitude},
}}});
}
logger_->Log(LogLevel::Debug, PipelinePhase::Teardown, msg.str());
}
std::ostringstream oss;
PrettyPrint(oss, output);
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown,
.message = oss.str()});
}

25
tooling/pipeline/src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc
View File

@@ -3,9 +3,8 @@
* @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation.
*/
#include "services/logging/logger.h"
#include <algorithm>
#include <chrono>
#include <filesystem>
#include <format>
#include <iterator>
@@ -13,16 +12,18 @@
#include "biergarten_pipeline_orchestrator.h"
#include "json_handling/json_loader.h"
#include "services/logging/logger.h"
std::vector<Location> BiergartenPipelineOrchestrator::QueryCitiesWithCountries() {
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
"=== GEOGRAPHIC DATA OVERVIEW ===");
std::vector<Location>
BiergartenPipelineOrchestrator::QueryCitiesWithCountries() {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "=== GEOGRAPHIC DATA OVERVIEW ==="});
const std::filesystem::path locations_path = "locations.json";
auto all_locations = JsonLoader::LoadLocations(locations_path, logger_);
const size_t sample_count = std::min(
static_cast<size_t>(application_options_.pipeline.location_count),
all_locations.size());
@@ -38,9 +39,13 @@ std::vector<Location> BiergartenPipelineOrchestrator::QueryCitiesWithCountries()
std::ranges::sample(all_locations, std::back_inserter(sampled_locations),
sample_count_signed, random_generator);
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::format(" Locations available: {}", all_locations.size()));
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::format(" Sampled locations: {}", sampled_locations.size()));
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format(" Locations available: {}",
all_locations.size())});
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format(" Sampled locations: {}",
sampled_locations.size())});
return sampled_locations;
}

31
tooling/pipeline/src/biergarten_pipeline_orchestrator/run.cc
View File

@@ -3,11 +3,11 @@
* @brief BiergartenDataGenerator::Run() implementation.
*/
#include "services/logging/logger.h"
#include <chrono>
#include <utility>
#include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h"
bool BiergartenPipelineOrchestrator::Run() {
try {
@@ -30,18 +30,21 @@ bool BiergartenPipelineOrchestrator::Run() {
.region_context = std::move(region_context)});
} catch (const std::exception& exception) {
++skipped_count;
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("[Pipeline] Skipping city '") + city.city +
" (" + city.country + "): context lookup failed: " +
exception.what());
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("[Pipeline] Skipping city '") + city.city +
" (" + city.country +
"): context lookup failed: " + exception.what()});
}
}
if (skipped_count > 0) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to context lookup errors");
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to context lookup errors"});
}
this->GenerateBreweries(enriched);
@@ -49,9 +52,11 @@ bool BiergartenPipelineOrchestrator::Run() {
this->LogResults();
return true;
} catch (const std::exception& e) {
logger_->Log(LogLevel::Error, PipelinePhase::Teardown,
std::string("Pipeline execution failed with error: ") +
e.what());
logger_->Log(
{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message =
std::string("Pipeline execution failed with error: ") + e.what()});
return false;
}
}

39
tooling/pipeline/src/data_generation/llama/generate_brewery.cc
View File

@@ -4,6 +4,7 @@
* inference, and validates structured JSON output for brewery records.
*/
#include <chrono>
#include <format>
#include <optional>
#include <stdexcept>
@@ -99,9 +100,11 @@ BreweryResult LlamaGenerator::GenerateBrewery(
raw = this->Infer(system_prompt, user_prompt, max_tokens,
kBreweryJsonGrammar);
if (logger_) {
logger_->Log(LogLevel::Debug, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: raw output (attempt ") +
std::to_string(attempt + 1) + "): " + raw);
logger_->Log(
{.level = LogLevel::Debug,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("LlamaGenerator: raw output (attempt ") +
std::to_string(attempt + 1) + "): " + raw});
}
// Validate output: parse JSON and check required fields
@@ -114,10 +117,12 @@ BreweryResult LlamaGenerator::GenerateBrewery(
// Success: return parsed brewery data
if (logger_) {
logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration,
std::string(
"LlamaGenerator: successfully generated brewery data on attempt ") +
std::to_string(attempt + 1));
logger_->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::string("LlamaGenerator: successfully generated "
"brewery data on attempt ") +
std::to_string(attempt + 1)});
}
return brewery;
@@ -127,9 +132,12 @@ BreweryResult LlamaGenerator::GenerateBrewery(
last_error = *validation_error;
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: malformed brewery JSON (attempt ") +
std::to_string(attempt + 1) + "): " + *validation_error);
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::string("LlamaGenerator: malformed brewery JSON (attempt ") +
std::to_string(attempt + 1) + "): " + *validation_error});
}
// Update prompt with error details to guide LLM toward correct output.
@@ -148,10 +156,13 @@ BreweryResult LlamaGenerator::GenerateBrewery(
// All retry attempts exhausted: log failure and throw exception
if (logger_) {
logger_->Log(LogLevel::Error, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: malformed brewery response after ") +
std::to_string(max_attempts) + " attempts: " +
(last_error.empty() ? raw : last_error));
logger_->Log(
{.level = LogLevel::Error,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::string("LlamaGenerator: malformed brewery response after ") +
std::to_string(max_attempts) +
" attempts: " + (last_error.empty() ? raw : last_error)});
}
throw std::runtime_error("LlamaGenerator: malformed brewery response");
}

81
tooling/pipeline/src/data_generation/llama/helpers.cc
View File

@@ -16,11 +16,11 @@
#include "data_generation/llama_generator_helpers.h"
#include "llama.h"
namespace {
/**
* String trimming: removes leading and trailing whitespace
*/
static std::string Trim(std::string_view value) {
std::string Trim(std::string_view value) {
constexpr std::string_view whitespace = " \t\n\r\f\v";
const size_t first_index = value.find_first_not_of(whitespace);
if (first_index == std::string_view::npos) {
@@ -35,7 +35,7 @@ static std::string Trim(std::string_view value) {
* Normalize whitespace: collapses multiple spaces/tabs/newlines into single
* spaces
*/
static std::string CondenseWhitespace(std::string_view text) {
std::string CondenseWhitespace(std::string_view text) {
std::string out;
out.reserve(text.size());
@@ -61,7 +61,37 @@ static std::string CondenseWhitespace(std::string_view text) {
// Guard against truncating in the first half of the string.
// This preserves the critical opening content and avoids cutting critical
// context words early in the region description.
static constexpr size_t kTruncationGuardDivisor = 2;
constexpr size_t kTruncationGuardDivisor = 2;
bool ReadRequiredTrimmedStringField(const boost::json::object& obj,
std::string_view key, std::string& out,
std::string* error_out) {
const boost::json::value* field = obj.if_contains(key);
if (field == nullptr || !field->is_string()) {
return false;
}
const auto& string_value = field->as_string();
out = Trim(std::string_view(string_value.data(), string_value.size()));
return !out.empty();
}
bool HasSchemaPlaceholder(const std::array<std::string*, 4>& values) {
for (const std::string* value : values) {
std::string lowered = *value;
std::ranges::transform(lowered, lowered.begin(),
[](const unsigned char character) {
return static_cast<char>(std::tolower(character));
});
if (lowered == "string") {
return true;
}
}
return false;
}
} // namespace
/**
* Truncate region context to fit within max length while preserving word
@@ -121,47 +151,6 @@ void AppendTokenPiece(const llama_vocab* vocab, llama_token token,
"LlamaGenerator: failed to decode sampled token piece");
}
static bool ReadRequiredTrimmedStringField(const boost::json::object& obj,
std::string_view key,
std::string& out,
std::string* error_out) {
const boost::json::value* field = obj.if_contains(key);
if (field == nullptr || !field->is_string()) {
if (error_out != nullptr) {
*error_out =
"JSON field '" + std::string(key) + "' is missing or not a string";
}
return false;
}
const auto& string_value = field->as_string();
out = Trim(std::string_view(string_value.data(), string_value.size()));
if (out.empty()) {
if (error_out != nullptr) {
*error_out = "JSON field '" + std::string(key) + "' must not be empty";
}
return false;
}
return true;
}
static bool HasSchemaPlaceholder(const std::array<std::string*, 4>& values) {
for (const std::string* value : values) {
std::string lowered = *value;
std::ranges::transform(lowered, lowered.begin(),
[](unsigned char character) {
return static_cast<char>(std::tolower(character));
});
if (lowered == "string") {
return true;
}
}
return false;
}
std::optional<std::string> ValidateBreweryJson(const std::string& raw,
BreweryResult& brewery_out) {
boost::system::error_code error_code;
@@ -209,7 +198,7 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
return validation_error;
}
const std::array<std::string*, 4> schema_placeholders = {
const std::array schema_placeholders = {
&brewery_out.name_en, &brewery_out.description_en,
&brewery_out.name_local, &brewery_out.description_local};
if (HasSchemaPlaceholder(schema_placeholders)) {

16
tooling/pipeline/src/data_generation/llama/infer.cc
View File

@@ -6,6 +6,8 @@
*/
#include <algorithm>
#include <chrono>
#include <format>
#include <memory>
#include <stdexcept>
#include <string>
@@ -105,7 +107,7 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
.top_p = sampling_top_p_,
.seed = static_cast<uint32_t>(rng_()),
};
auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
const auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
/**
* Clear KV cache to ensure clean inference state (no residual context)
@@ -170,12 +172,12 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
prompt_tokens.resize(static_cast<size_t>(token_count));
if (token_count > prompt_budget) {
if (logger_) {
logger_->Log(
LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: prompt too long (") +
std::to_string(token_count) + ") tokens, truncating to " +
std::to_string(prompt_budget) +
" tokens to fit n_batch/n_ctx limits");
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format(
"LlamaGenerator: prompt too long ({} tokens), "
"truncating to {} tokens to fit n_batch/n_ctx limits",
token_count, prompt_budget)});
}
prompt_tokens.resize(static_cast<size_t>(prompt_budget));
token_count = prompt_budget;

27
tooling/pipeline/src/data_generation/llama/llama_generator.cc
View File

@@ -53,45 +53,46 @@ LlamaGenerator::LlamaGenerator(
"LlamaGenerator: prompt directory dependency must not be null");
}
const auto sampling = options.generator.sampling.value_or(SamplingOptions{});
const auto [temperature, top_p, top_k, n_ctx, seed, n_gpu_layers] =
options.generator.sampling.value_or(SamplingOptions{});
if (sampling.temperature < 0.0F) {
if (temperature < 0.0F) {
throw std::runtime_error(
"LlamaGenerator: sampling temperature must be >= 0");
}
if (sampling.top_p <= 0.0F || sampling.top_p > 1.0F) {
if (top_p <= 0.0F || top_p > 1.0F) {
throw std::runtime_error(
"LlamaGenerator: sampling top-p must be in (0, 1]");
}
if (sampling.top_k == 0U) {
if (top_k == 0U) {
throw std::runtime_error("LlamaGenerator: sampling top-k must be > 0");
}
if (sampling.seed < -1) {
if (seed < -1) {
throw std::runtime_error(
"LlamaGenerator: seed must be >= 0, or -1 for random");
}
if (sampling.n_ctx == 0 || sampling.n_ctx > kMaxContextSize) {
if (n_ctx == 0 || n_ctx > kMaxContextSize) {
throw std::runtime_error(
"LlamaGenerator: context size must be in range [1, 32768]");
}
sampling_temperature_ = sampling.temperature;
sampling_top_p_ = sampling.top_p;
sampling_top_k_ = sampling.top_k;
sampling_temperature_ = temperature;
sampling_top_p_ = top_p;
sampling_top_k_ = top_k;
if (sampling.seed == -1) {
if (seed == -1) {
std::random_device random_device;
rng_.seed(random_device());
} else {
rng_.seed(static_cast<uint32_t>(sampling.seed));
rng_.seed(static_cast<uint32_t>(seed));
}
n_ctx_ = sampling.n_ctx;
n_gpu_layers_ = sampling.n_gpu_layers;
n_ctx_ = n_ctx;
n_gpu_layers_ = n_gpu_layers;
this->Load(model_path);
}

14
tooling/pipeline/src/data_generation/llama/load.cc
View File

@@ -5,6 +5,7 @@
*/
#include <algorithm>
#include <chrono>
#include <stdexcept>
#include <string>
#include <utility>
@@ -27,8 +28,10 @@ void LlamaGenerator::Load(const std::string& model_path) {
llama_model_params model_params = llama_model_default_params();
model_params.n_gpu_layers = n_gpu_layers_;
LlamaGenerator::ModelHandle loaded_model(
ModelHandle loaded_model(
llama_model_load_from_file(model_path.c_str(), model_params));
if (!loaded_model) {
throw std::runtime_error(
"LlamaGenerator: failed to load model from path: " + model_path);
@@ -38,8 +41,9 @@ void LlamaGenerator::Load(const std::string& model_path) {
context_params.n_ctx = n_ctx_;
context_params.n_batch = std::min(n_ctx_, kMaxBatchSize);
LlamaGenerator::ContextHandle loaded_context(
ContextHandle loaded_context(
llama_init_from_model(loaded_model.get(), context_params));
if (!loaded_context) {
throw std::runtime_error("LlamaGenerator: failed to create context");
}
@@ -48,7 +52,9 @@ void LlamaGenerator::Load(const std::string& model_path) {
context_ = std::move(loaded_context);
if (logger_) {
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::string("[LlamaGenerator] Loaded model: ") + model_path);
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format("[LlamaGenerator] Loaded model: {} ",
model_path)});
}
}

142
tooling/pipeline/src/main.cc
View File

@@ -4,12 +4,15 @@
* initializes shared infrastructure, and executes the pipeline entry flow.
*/
#include <spdlog/spdlog.h>
#include <spdlog/fmt/fmt.h>
#include <spdlog/spdlog.h>
#include <boost/di.hpp>
#include <boost/program_options.hpp>
#include <chrono>
#include <exception>
#include <format>
#include <iostream>
#include <memory>
#include <optional>
#include <string>
@@ -43,12 +46,13 @@ int main(const int argc, char** argv) {
spdlog::set_level(spdlog::level::debug);
spdlog::set_pattern("│ %Y-%m-%d %H:%M:%S.%e │ %^%-7l%$ │ %v");
BoundedChannel<LogEntry> log_channel(kLogMaxCount);
auto log_dispatcher = std::make_unique<LogDispatcher>(log_channel);
std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); });
auto log_dispatcher = //
std::make_unique<LogDispatcher>(log_channel);
std::shared_ptr<ILogger> log_producer =
std::make_shared<LogProducer>(log_channel);
std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); });
auto shutdown = [&](const int exit_code) {
log_channel.Close();
log_thread.join();
@@ -62,18 +66,21 @@ int main(const int argc, char** argv) {
const LlamaBackendState llama_backend_state;
#endif
log_producer->Log(LogLevel::Info, PipelinePhase::Startup, "STARTING PIPELINE");
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "STARTING PIPELINE"});
const std::optional<ApplicationOptions> parsed_options =
ParseArguments(argc, argv, log_producer);
if (!parsed_options.has_value()) {
return shutdown(0);
return shutdown(EXIT_FAILURE);
}
const auto options = *parsed_options;
const std::string model_path = options.generator.model_path.string();
const auto sampling = options.generator.sampling.value_or(SamplingOptions{});
const auto sampling =
options.generator.sampling.value_or(SamplingOptions{});
std::unique_ptr<IPromptDirectory> prompt_directory;
@@ -82,9 +89,12 @@ int main(const int argc, char** argv) {
prompt_directory = std::make_unique<PromptDirectory>(
options.pipeline.prompt_dir, log_producer);
} catch (const std::exception& dir_error) {
log_producer->Log(LogLevel::Error, PipelinePhase::Startup,
fmt::format("Invalid --prompt-dir: {}", dir_error.what()));
return shutdown(1);
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = std::format("Invalid --prompt-dir: {}",
dir_error.what())});
return shutdown(EXIT_FAILURE);
}
}
@@ -93,26 +103,39 @@ int main(const int argc, char** argv) {
di::bind<ApplicationOptions>().to(options),
di::bind<std::string>().to(model_path),
di::bind<IExportService>().to<SqliteExportService>(),
di::bind<IPromptFormatter>().to(
[options, log_producer] {
if (options.generator.use_mocked) {
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"Prompt formatter: none (mock mode)");
return std::unique_ptr<IPromptFormatter>(nullptr);
}
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"Prompt formatter: Gemma4JinjaPromptFormatter");
return std::unique_ptr<IPromptFormatter>(
std::make_unique<Gemma4JinjaPromptFormatter>());
}),
di::bind<IPromptFormatter>().to([options, log_producer] {
if (options.generator.use_mocked) {
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Prompt formatter: none (mock mode)"});
}
return std::unique_ptr<IPromptFormatter>(nullptr);
}
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Prompt formatter: Gemma4JinjaPromptFormatter"});
}
return std::unique_ptr<IPromptFormatter>(
std::make_unique<Gemma4JinjaPromptFormatter>());
}),
di::bind<WebClient>().to([options, log_producer] {
if (options.generator.use_mocked) {
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"Web client: none (mock mode)");
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: none (mock mode)"});
}
return std::unique_ptr<WebClient>(nullptr);
}
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"Web client: HttpWebClient");
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: HttpWebClient"});
}
return std::unique_ptr<WebClient>(
std::make_unique<HttpWebClient>(log_producer));
}),
@@ -120,12 +143,18 @@ int main(const int argc, char** argv) {
[options, &log_producer](
const auto& inj) -> std::unique_ptr<IEnrichmentService> {
if (options.generator.use_mocked) {
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"Enrichment: mock");
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: mock"});
}
return std::make_unique<MockEnrichmentService>();
}
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"Enrichment: Wikipedia");
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: Wikipedia"});
}
return std::make_unique<WikipediaEnrichmentService>(
inj.template create<std::unique_ptr<WebClient>>(),
log_producer);
@@ -134,20 +163,23 @@ int main(const int argc, char** argv) {
[&options, &model_path, &sampling, &prompt_directory,
&log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> {
if (options.generator.use_mocked) {
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"Generator: mock");
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Generator: mock"});
}
return std::make_unique<MockGenerator>();
}
log_producer->Log(
LogLevel::Info, PipelinePhase::Startup,
fmt::format(
"Generator: LlamaGenerator | model={} | temp={:.2f} top_p={:.2f} top_k={} n_ctx={} seed={}",
model_path,
sampling.temperature,
sampling.top_p,
sampling.top_k,
sampling.n_ctx,
sampling.seed));
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format(
"Generator: LlamaGenerator | model={} | temp={:.2f} "
"top_p={:.2f} top_k={} n_ctx={} seed={}",
model_path, sampling.temperature, sampling.top_p,
sampling.top_k, sampling.n_ctx, sampling.seed)});
}
return std::make_unique<LlamaGenerator>(
options, model_path, log_producer,
inj.template create<std::unique_ptr<IPromptFormatter>>(),
@@ -158,21 +190,29 @@ int main(const int argc, char** argv) {
injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
if (!orchestrator->Run()) {
log_producer->Log(LogLevel::Error, PipelinePhase::Teardown,
"Pipeline execution failed");
return shutdown(1);
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = "Pipeline execution failed"});
return shutdown(EXIT_FAILURE);
}
log_producer->Log(LogLevel::Info, PipelinePhase::Teardown,
fmt::format("Pipeline complete in {} ms", timer.Elapsed()));
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown,
.message = std::format("Pipeline complete in {} ms",
timer.Elapsed())});
return shutdown(0);
return shutdown(EXIT_SUCCESS);
} catch (const std::exception& exception) {
const LogEntry log_entry{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = exception.what()};
if (log_producer) {
log_producer->Log(LogLevel::Error, PipelinePhase::Teardown,
fmt::format("Unhandled fatal error: {}", exception.what()));
log_producer->Log(log_entry);
} else {
std::cerr << log_entry.message << std::endl;
}
return shutdown(1);
return shutdown(EXIT_FAILURE);
}
}
}

78
tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc
View File

@@ -14,15 +14,16 @@
using namespace boost;
std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
const std::string cache_key(query);
// 1. Cache Lookup
if (const auto cache_it = this->extract_cache_.find(cache_key);
cache_it != this->extract_cache_.end()) {
if (logger_) {
logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
std::string("Wikipedia: Cache hit for ") + cache_key + "!");
logger_->Log({.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.message = std::string("Wikipedia: Cache hit for ") +
cache_key + "!"});
}
return cache_it->second;
}
@@ -33,7 +34,6 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
"api.php?action=query&titles={}&prop=extracts&explaintext=1&format=json",
encoded);
const std::string body = this->client_->Get(url);
{
using namespace std::literals::chrono_literals;
@@ -46,9 +46,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (ec) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: JSON parse error for '") +
std::string(query) + "': " + ec.message());
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: JSON parse error for '") +
std::string(query) + "': " + ec.message()});
}
return {};
}
@@ -57,9 +59,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
const json::object* obj = doc.if_object();
if (obj == nullptr) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Expected root object for '") +
std::string(query) + "'");
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: Expected root object for '") +
std::string(query) + "'"});
}
return {};
}
@@ -72,9 +77,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Missing query.pages for '") +
std::string(query) + "'");
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: Missing query.pages for '") +
std::string(query) + "'"});
}
return {};
}
@@ -83,9 +91,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (pages.empty()) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: No pages returned for '") +
std::string(query) + "'");
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: No pages returned for '") +
std::string(query) + "'"});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -97,9 +107,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (!page_val.is_object()) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Unexpected page format for '") +
std::string(query) + "'");
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: Unexpected page format for '") +
std::string(query) + "'"});
}
return {};
}
@@ -109,9 +122,10 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
// Handle 404/Missing status
if (page.contains("missing")) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Page '") + std::string(query) +
"' does not exist");
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: Page '") +
std::string(query) + "' does not exist"});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -121,9 +135,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: No extract string found for '") +
std::string(query) + "'");
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("WikipediaService: No extract string found for '") +
std::string(query) + "'"});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -132,13 +149,14 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
// 4. Success
std::string extract(extract_ptr->as_string());
if (logger_) {
logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration,
std::string("WikipediaService: Fetched ") +
std::to_string(extract.size()) + " chars for '" +
std::string(query) + "'");
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService: Fetched ") +
std::to_string(extract.size()) + " chars for '" +
std::string(query) + "'"});
}
this->extract_cache_.insert_or_assign(cache_key, extract);
return extract;
}
}

23
tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc
View File

@@ -10,12 +10,14 @@
#include "services/enrichment/wikipedia_service.h"
std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) {
std::string WikipediaEnrichmentService::GetLocationContext(
const Location& loc) {
using namespace std::literals::chrono_literals;
if (!this->client_) {
if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
"Wikipedia client is nullptr.");
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = "Wikipedia client is nullptr."});
}
return {};
}
@@ -48,17 +50,20 @@ std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc)
append_extract(FetchExtract(brewing_query));
append_extract(FetchExtract(beer_query));
if (logger_) {
logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration,
std::string("Done fetching for ") + location_query +
". Sleeping for 10 seconds.");
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::string("Done fetching for ") +
location_query + ". Sleeping for 10 seconds."});
}
std::this_thread::sleep_for(10s);
} catch (const std::runtime_error& e) {
if (logger_) {
logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
std::string("WikipediaService lookup failed for '") +
location_query + "': " + e.what());
logger_->Log(
{.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.message = std::string("WikipediaService lookup failed for '") +
location_query + "': " + e.what()});
}
}
return result;

8
tooling/pipeline/src/services/logging/log_producer.cc
View File

@@ -16,10 +16,4 @@
LogProducer::LogProducer(BoundedChannel<LogEntry>& channel)
: channel_(channel) {}
void LogProducer::Log(LogLevel level, PipelinePhase phase,
const std::string_view message) {
channel_.Send(LogEntry{.timestamp = std::chrono::system_clock::now(),
.level = level,
.phase = phase,
.message = std::string(message)});
}
void LogProducer::Log(const LogEntry& entry) { channel_.Send(entry); }

19
tooling/pipeline/src/services/prompt_directory.cc
View File

@@ -6,6 +6,7 @@
#include "services/prompting/prompt_directory.h"
#include <chrono>
#include <filesystem>
#include <fstream>
#include <stdexcept>
@@ -48,9 +49,12 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir,
}
if (logger_) {
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::string("[PromptDirectory] Resolved prompt directory: ") +
prompt_dir_.string());
logger_->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message =
std::string("[PromptDirectory] Resolved prompt directory: ") +
prompt_dir_.string()});
}
}
@@ -84,10 +88,11 @@ std::string PromptDirectory::Load(std::string_view key) {
}
if (logger_) {
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::string("[PromptDirectory] Loaded prompt '") + key_str +
"' from '" + file_path.string() + "' (" +
std::to_string(content.size()) + " chars)");
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::string("[PromptDirectory] Loaded prompt '") +
key_str + "' from '" + file_path.string() + "' (" +
std::to_string(content.size()) + " chars)"});
}
cache_.emplace(key_str, content);

32
tooling/pipeline/src/web_client/http_web_client.cc
View File

@@ -1,5 +1,5 @@
/**
* @file web_client/http_web_client.cc
* @file web_client/http_web_client.cc
* @brief cpp-httplib implementation of WebClient.
*/
@@ -7,6 +7,7 @@
#include <httplib.h>
#include <chrono>
#include <regex>
#include <stdexcept>
#include <string>
@@ -31,7 +32,7 @@ std::pair<std::string, std::string> SplitUrl(const std::string& url) {
return {match[1].str(), match[2].matched ? match[2].str() : "/"};
}
} // namespace
} // namespace
std::string HttpWebClient::Get(const std::string& url) {
const auto [origin, path] = SplitUrl(url);
@@ -40,28 +41,27 @@ std::string HttpWebClient::Get(const std::string& url) {
client.set_follow_location(true);
client.set_connection_timeout(kConnectionTimeoutSeconds);
client.set_read_timeout(kReadTimeoutSeconds);
client.set_default_headers({
{"Accept", "application/json"},
{"User-Agent", "biergarten-pipeline/1.0"}
});
client.set_default_headers({{"Accept", "application/json"},
{"User-Agent", "biergarten-pipeline/1.0"}});
const httplib::Result result = client.Get(path);
if (!result) {
throw std::runtime_error(
"[HttpWebClient] Request failed for URL: " + url +
" — " + httplib::to_string(result.error()));
throw std::runtime_error("[HttpWebClient] Request failed for URL: " + url +
" — " + httplib::to_string(result.error()));
}
if (result->status < kSuccessMin || result->status >= kSuccessMax) {
if (logger_) {
logger_->Log(LogLevel::Error, PipelinePhase::UserGeneration,
std::string("[HttpWebClient] Request failed for URL: ") +
url);
logger_->Log(
{.level = LogLevel::Error,
.phase = PipelinePhase::UserGeneration,
.message =
std::string("[HttpWebClient] Request failed for URL: ") + url});
}
throw std::runtime_error(
"[HttpWebClient] HTTP " + std::to_string(result->status) +
" for URL: " + url);
throw std::runtime_error("[HttpWebClient] HTTP " +
std::to_string(result->status) +
" for URL: " + url);
}
return result->body;
@@ -69,4 +69,4 @@ std::string HttpWebClient::Get(const std::string& url) {
std::string HttpWebClient::EncodeURL(const std::string& value) {
return httplib::encode_uri_component(value);
}
}