christian/website-ai-generator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: enhance error logging and add HTTP timeout configuration in generator

Browse Source
This commit is contained in:
Chris
2026-06-09 21:33:06 +02:00
parent 56c7219bf3
commit 002628497e
2 changed files with 25 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -22,4 +22,6 @@
`llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q4_K_S --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 194 t/s `llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q4_K_S --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 194 t/s
`llama-server -hf unsloth/gemma-4-E4B-it-GGUF:Q3_K_XL --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 126 t/s `llama-server -hf unsloth/gemma-4-E4B-it-GGUF:Q3_K_XL --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 126 t/s
`llama-server -hf unsloth/gemma-4-26B-A4B-it-qat-GGUF:UD-Q4_K_XL --reasoning off -fa on -ngl 99 -b 2048 -ub 2048 -c 4096 --temp 1.0 --top-p 0.95 --top-k 64 --no-mmap -t 4` -> 20 t/s

23
web/generator.php
View File

@@ -1,9 +1,20 @@
<?php <?php
declare(strict_types=1); declare(strict_types=1);
// overwrite log behaviour so all php errors are logged into errors.log
ini_set('log_errors', '1');
ini_set('error_log', __DIR__ . '/../errors.log');
ini_set('display_errors', '0');
error_reporting(E_ALL);
require_once __DIR__ . '/../vendor/autoload.php'; require_once __DIR__ . '/../vendor/autoload.php';
use Symfony\Component\HttpClient\HttpClient;
use Symfony\Component\HttpClient\Psr18Client;
function readLocalEnvValue(string $envFilePath, string $key): string function readLocalEnvValue(string $envFilePath, string $key): string
{ {
if (! is_file($envFilePath) || ! is_readable($envFilePath)) { if (! is_file($envFilePath) || ! is_readable($envFilePath)) {
@@ -238,6 +249,12 @@ $apiKey = getenv('LLAMA_API_KEY') ?: '';
$model = getenv('LLAMA_MODEL') ?: 'local-model'; $model = getenv('LLAMA_MODEL') ?: 'local-model';
$maxTokens = (int) (getenv('LLAMA_MAX_TOKENS') ?: 4096); $maxTokens = (int) (getenv('LLAMA_MAX_TOKENS') ?: 4096);
$reasoningEffort = getenv('LLAMA_REASONING_EFFORT') ?: 'none'; $reasoningEffort = getenv('LLAMA_REASONING_EFFORT') ?: 'none';
$httpTimeoutSeconds = (float) (getenv('LLAMA_HTTP_TIMEOUT') ?: '600');
$httpMaxDurationSeconds = (float) (getenv('LLAMA_HTTP_MAX_DURATION') ?: '0');
if ($httpTimeoutSeconds <= 0) {
$httpTimeoutSeconds = 600.0;
}
$topicHint = isset($_GET['topic']) ? trim((string) $_GET['topic']) : ''; $topicHint = isset($_GET['topic']) ? trim((string) $_GET['topic']) : '';
$topicHint = mb_substr($topicHint, 0, 120); $topicHint = mb_substr($topicHint, 0, 120);
@@ -276,6 +293,10 @@ $bannedTerms = [
$bannedTermsList = implode(', ', $bannedTerms); $bannedTermsList = implode(', ', $bannedTerms);
$factory = OpenAI::factory()->withBaseUri('http://localhost:8080/v1'); $factory = OpenAI::factory()->withBaseUri('http://localhost:8080/v1');
$factory = $factory->withHttpClient(new Psr18Client(HttpClient::create([
'timeout' => $httpTimeoutSeconds,
'max_duration' => $httpMaxDurationSeconds,
])));
if ($apiKey !== '') { if ($apiKey !== '') {
$factory = $factory->withApiKey($apiKey); $factory = $factory->withApiKey($apiKey);
} }