mag/ABSDEV
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style updates

Browse Source
This commit is contained in:
Mark Gregory
2026-07-24 14:59:44 +01:00
parent 24ab771cd3
commit dd23205d0b
482 changed files with 7173 additions and 1435 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Modules/AI/Services/KnowledgeIndexer.php
+28 -9
View File
@@ -1,20 +1,39 @@
<?php
namespace Modules\AI\Services;
use Modules\AI\Models\AIKnowledgeSource;
final class KnowledgeIndexer
{
public function index(AIKnowledgeSource $source,int $chunkSize=1800): AIKnowledgeSource
public function index(AIKnowledgeSource $source, int $chunkSize = 1800): AIKnowledgeSource
{
$content=trim((string)$source->content); $source->chunks()->delete();
$chunks=$content===''?[]:$this->split($content,max(500,$chunkSize));
foreach($chunks as $position=>$chunk) $source->chunks()->create(['position'=>$position+1,'content'=>$chunk]);
$source->update(['checksum'=>hash('sha256',$content),'status'=>'indexed','chunk_count'=>count($chunks),'indexed_at'=>now()]);
$content = trim((string) $source->content);
$source->chunks()->delete();
$chunks = $content === '' ? [] : $this->split($content, max(500, $chunkSize));
foreach ($chunks as $position => $chunk) {
$source->chunks()->create(['position' => $position + 1, 'content' => $chunk]);
}
$source->update(['checksum' => hash('sha256', $content), 'status' => 'indexed', 'chunk_count' => count($chunks), 'indexed_at' => now()]);
return $source->refresh();
}
private function split(string $content,int $size): array
private function split(string $content, int $size): array
{
$paragraphs=preg_split('/\R{2,}/',$content) ?: [$content]; $chunks=[]; $buffer='';
foreach($paragraphs as $paragraph){ if(strlen($buffer)+strlen($paragraph)+2>$size && $buffer!==''){ $chunks[]=trim($buffer); $buffer=''; } $buffer.=$paragraph."\n\n"; }
if(trim($buffer)!=='') $chunks[]=trim($buffer); return $chunks;
$paragraphs = preg_split('/\R{2,}/', $content) ?: [$content];
$chunks = [];
$buffer = '';
foreach ($paragraphs as $paragraph) {
if (strlen($buffer) + strlen($paragraph) + 2 > $size && $buffer !== '') {
$chunks[] = trim($buffer);
$buffer = '';
} $buffer .= $paragraph."\n\n";
}
if (trim($buffer) !== '') {
$chunks[] = trim($buffer);
}
return $chunks;
}
}