AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-06-01 10:04:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

27
pipeline/src/web_client/curl_web_client_download_to_file.cpp
View File

@@ -7,35 +7,12 @@
#include <cstdio>
#include <fstream>
#include <memory>
#include <sstream>
#include <stdexcept>
#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 writes to a file stream
static size_t WriteCallbackFile(void* contents, size_t size, size_t nmemb,
void* userp) {
@@ -55,7 +32,7 @@ void CURLWebClient::DownloadToFile(const std::string& url,
"[CURLWebClient] Cannot open file for writing: " + file_path);
}
set_common_get_options(curl.get(), url, 30L, 300L);
set_common_get_options(curl.get(), url, {30L, 300L});
curl_easy_setopt(curl.get(), CURLOPT_WRITEFUNCTION, WriteCallbackFile);
curl_easy_setopt(curl.get(), CURLOPT_WRITEDATA,
static_cast<void*>(&outFile));

27
pipeline/src/web_client/curl_web_client_get.cpp
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);

28
pipeline/src/web_client/curl_web_client_utils.cpp Normal file
View File

@@ -0,0 +1,28 @@
/**
* @file web_client/curl_web_client_utils.cpp
* @brief Shared CURLWebClient helper implementations.
*/
#include "curl_web_client_utils.h"
#include <stdexcept>
auto create_handle() -> CurlHandle {
CURL* handle = curl_easy_init();
if (handle == nullptr) {
throw std::runtime_error(
"[CURLWebClient] Failed to initialize libcurl handle");
}
return CurlHandle(handle, &curl_easy_cleanup);
}
auto set_common_get_options(CURL* curl, const std::string& url,
CurlTimeouts timeouts) -> void {
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, timeouts.connect_timeout);
curl_easy_setopt(curl, CURLOPT_TIMEOUT, timeouts.total_timeout);
curl_easy_setopt(curl, CURLOPT_ACCEPT_ENCODING, "gzip");
}

26
pipeline/src/web_client/curl_web_client_utils.h Normal file
View File

@@ -0,0 +1,26 @@
#ifndef BIERGARTEN_PIPELINE_WEB_CLIENT_CURL_WEB_CLIENT_UTILS_H_
#define BIERGARTEN_PIPELINE_WEB_CLIENT_CURL_WEB_CLIENT_UTILS_H_
/**
* @file web_client/curl_web_client_utils.h
* @brief Shared helpers for CURLWebClient request setup.
*/
#include <curl/curl.h>
#include <memory>
#include <string>
using CurlHandle = std::unique_ptr<CURL, decltype(&curl_easy_cleanup)>;
struct CurlTimeouts {
long connect_timeout;
long total_timeout;
};
CurlHandle create_handle();
void set_common_get_options(CURL* curl, const std::string& url,
CurlTimeouts timeouts);
#endif // BIERGARTEN_PIPELINE_WEB_CLIENT_CURL_WEB_CLIENT_UTILS_H_