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

@@ -1,5 +1,6 @@
/**
* @file wikipedia/fetch_extract.cc
* @brief WikipediaEnrichmentService::FetchExtract() implementation.
*/
#include <boost/json.hpp>
@@ -20,9 +21,10 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (const auto cache_it = this->extract_cache_.find(cache_key);
cache_it != this->extract_cache_.end()) {
if (logger_) {
logger_->Log({.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.message = std::format("Wikipedia: Cache hit for {}!", cache_key)});
logger_->Log(
{.level = LogLevel::Debug,
.phase = PipelinePhase::Enrichment,
.message = std::format("Wikipedia: Cache hit for {}!", cache_key)});
}
return cache_it->second;
}
@@ -30,7 +32,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
const std::string encoded = this->client_->EncodeURL(cache_key);
const std::string url = std::format(
"https://en.wikipedia.org/w/"
"api.php?action=query&titles={}&prop=extracts&explaintext=1&format=json",
"api.php?action=query&titles={}&prop=extracts&explaintext=1&format="
"json",
encoded);
const std::string body = this->client_->Get(url);
@@ -45,11 +48,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (ec) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: JSON parse error for '{}': {}",
std::string(query), ec.message())});
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: JSON parse error for '{}': {}",
std::string(query), ec.message())});
}
return {};
}
@@ -58,12 +61,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
const json::object* obj = doc.if_object();
if (obj == nullptr) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: Expected root object for '{}'",
std::string(query))});
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Expected root object for '{}'",
std::string(query))});
}
return {};
}
@@ -76,12 +78,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: Missing query.pages for '{}'",
std::string(query))});
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Missing query.pages for '{}'",
std::string(query))});
}
return {};
}
@@ -90,11 +91,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (pages.empty()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: No pages returned for '{}'",
std::string(query))});
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: No pages returned for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -106,12 +107,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (!page_val.is_object()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: Unexpected page format for '{}'",
std::string(query))});
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: Unexpected page format for '{}'",
std::string(query))});
}
return {};
}
@@ -121,10 +121,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
// Handle 404/Missing status
if (page.contains("missing")) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: Page '{}' does not exist",
std::string(query))});
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format("WikipediaService: Page '{}' does not exist",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -134,12 +135,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: No extract string found for '{}'",
std::string(query))});
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Enrichment,
.message = std::format(
"WikipediaService: No extract string found for '{}'",
std::string(query))});
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -148,10 +148,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
// 4. Success
std::string extract(extract_ptr->as_string());
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: Fetched {} chars for '{}'",
extract.size(), std::string(query))});
logger_->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Enrichment,
.message = std::format("WikipediaService: Fetched {} chars for '{}'",
extract.size(), std::string(query))});
}
this->extract_cache_.insert_or_assign(cache_key, extract);

View File

@@ -1,6 +1,6 @@
/**
* @file wikipedia/get_summary.cc
* @brief WikipediaService::GetLocationContext() implementation.
* @brief WikipediaEnrichmentService::GetLocationContext() implementation.
*/
#include <chrono>
@@ -16,7 +16,7 @@ std::string WikipediaEnrichmentService::GetLocationContext(
if (!this->client_) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.phase = PipelinePhase::Enrichment,
.message = "Wikipedia client is nullptr."});
}
return {};
@@ -24,13 +24,6 @@ std::string WikipediaEnrichmentService::GetLocationContext(
std::string result;
// std::string region_query(loc.city);
// if (!loc.country.empty()) {
// region_query += loc.state_province,
// region_query += ", ";
// region_query += loc.country;
// }
constexpr std::string_view brewing_query = "brewing";
const std::string location_query =
std::format("{}, {}", loc.city, loc.iso3166_2);
@@ -51,9 +44,10 @@ std::string WikipediaEnrichmentService::GetLocationContext(
append_extract(FetchExtract(beer_query));
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::format("Done fetching for {}. Sleeping for 10 seconds.",
location_query)});
.phase = PipelinePhase::Enrichment,
.message = std::format(
"Done fetching for {}. Sleeping for 10 seconds.",
location_query)});
}
std::this_thread::sleep_for(10s);
@@ -61,9 +55,9 @@ std::string WikipediaEnrichmentService::GetLocationContext(
if (logger_) {
logger_->Log(
{.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.phase = PipelinePhase::Enrichment,
.message = std::format("WikipediaService lookup failed for '{}': {}",
location_query, e.what())});
location_query, e.what())});
}
}
return result;

View File

@@ -1,6 +1,6 @@
/**
* @file services/wikipedia/wikipedia_service.cc
* @brief WikipediaService constructor implementation.
* @brief WikipediaEnrichmentService constructor implementation.
*/
#include "services/enrichment/wikipedia_service.h"