Pipeline: Add LLM and mocked user generation to the pipeline (#230)

This commit is contained in:
2026-07-01 07:47:24 -04:00
committed by GitHub
parent 880f73e004
commit 2b8a900d12
90 changed files with 57254 additions and 800 deletions

View File

@@ -15,7 +15,6 @@
*/
class IEnrichmentService {
public:
/// @brief Virtual destructor for polymorphic cleanup.
virtual ~IEnrichmentService() = default;
/**

View File

@@ -1,13 +1,18 @@
//
// 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 No-op IEnrichmentService used when network enrichment is disabled.
*/
#include <string>
#include "enrichment_service.h"
#include "services/enrichment/enrichment_service.h"
/**
* @brief Enrichment service that returns no context for any location.
*/
class MockEnrichmentService final : public IEnrichmentService {
public:
std::string GetLocationContext(const Location& /*loc*/) override {

View File

@@ -11,25 +11,37 @@
#include <string_view>
#include <unordered_map>
#include "enrichment_service.h"
#include "services/enrichment/enrichment_service.h"
#include "services/logging/logger.h"
#include "web_client/web_client.h"
/// @brief Provides Wikipedia summary lookups backed by cached raw extracts.
/**
* @brief Provides Wikipedia summary lookups backed by cached raw extracts.
*/
class WikipediaEnrichmentService final : public IEnrichmentService {
public:
/// @brief Creates a new Wikipedia service with the provided web client.
/**
* @brief Creates a new Wikipedia service with the provided web client.
*/
explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
std::shared_ptr<ILogger> logger);
/// @brief Returns the Wikipedia-derived context for a location.
/**
* @brief Returns the Wikipedia-derived context for a location.
*/
[[nodiscard]] std::string GetLocationContext(const Location& loc) override;
private:
std::string FetchExtract(std::string_view query);
std::unique_ptr<WebClient> client_;
std::shared_ptr<ILogger> logger_;
/// @brief Canonical cache for raw Wikipedia query extracts.
/**
* @brief Cache for raw Wikipedia query extracts, keyed by query string.
*
* GetLocationContext() always queries "brewing" and reuses "beer in
* {country}" for every city in that country, so caching avoids refetching
* the same extract across locations in a run.
*/
std::unordered_map<std::string, std::string> extract_cache_;
};