fix: llama backend lifetime, Wikipedia enrichment depth, and misc cleanup

This commit is contained in:
Aaron Po
2026-04-09 21:59:13 -04:00
parent 824f5b2b4f
commit b53f9e5582
17 changed files with 161 additions and 104 deletions

View File

@@ -5,36 +5,13 @@
#include <curl/curl.h>
#include <memory>
#include <sstream>
#include <stdexcept>
#include <string>
#include "curl_web_client_utils.h"
#include "web_client/curl_web_client.h"
// RAII wrapper for CURL handle using unique_ptr
using CurlHandle = std::unique_ptr<CURL, decltype(&curl_easy_cleanup)>;
static CurlHandle create_handle() {
CURL* handle = curl_easy_init();
if (!handle) {
throw std::runtime_error(
"[CURLWebClient] Failed to initialize libcurl handle");
}
return CurlHandle(handle, &curl_easy_cleanup);
}
static void set_common_get_options(CURL* curl, const std::string& url,
long connect_timeout, long total_timeout) {
curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
curl_easy_setopt(curl, CURLOPT_USERAGENT, "biergarten-pipeline/0.1.0");
curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
curl_easy_setopt(curl, CURLOPT_MAXREDIRS, 5L);
curl_easy_setopt(curl, CURLOPT_CONNECTTIMEOUT, connect_timeout);
curl_easy_setopt(curl, CURLOPT_TIMEOUT, total_timeout);
curl_easy_setopt(curl, CURLOPT_ACCEPT_ENCODING, "gzip");
}
// curl write callback that appends response data into a std::string
static size_t WriteCallbackString(void* contents, size_t size, size_t nmemb,
void* userp) {
@@ -48,7 +25,7 @@ std::string CURLWebClient::Get(const std::string& url) {
auto curl = create_handle();
std::string response_string;
set_common_get_options(curl.get(), url, 10L, 20L);
set_common_get_options(curl.get(), url, {10L, 20L});
curl_easy_setopt(curl.get(), CURLOPT_WRITEFUNCTION, WriteCallbackString);
curl_easy_setopt(curl.get(), CURLOPT_WRITEDATA, &response_string);