Files
dobetternorge-tools/api/summarize.php
T
daveadmin e768662efe Add Summarize Document tool — engine selector, file upload, optional corpus enrichment
- summarize.php: full custom inline form (replaces tool_form.php wrapper) with
  lang switcher, azure_mini/azure_full/gpu engine selector, 8 corpus-slice
  toggles (all off by default), doc picker, file upload zone, and textarea
- api/summarize.php: rewritten to streaming NDJSON (matches barnevernet pattern);
  accepts JSON payload with text, language, engine, slices[], doc_ids[]
- includes/LegalTools.php: adds corpusContextForSummarize() (keyword search via
  ClientRagPipeline) and summarizeWithContext() (engine-aware LLM call with
  optional corpus prepend); returns structured JSON matching existing summarize format
- assets/js/summarize.js: self-contained IIFE handling file upload via
  api/extract.php, slice toggles, NDJSON stream reader, result rendering,
  and trace panel update
- includes/i18n.php: adds 'summarize' to nav in all 4 languages (EN/NO/UK/PL),
  inserted after 'redact' in the tool order with icon 'SZ'

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-23 23:25:40 +02:00

83 lines
2.8 KiB
PHP

<?php
declare(strict_types=1);
require_once __DIR__ . '/../includes/LegalTools.php';
require_once __DIR__ . '/../includes/ToolModels.php';
dbnToolsRequireMethod('POST');
dbnToolsRequireAuth();
$ftUid = dbnToolsFreeTierCheck('summarize');
$input = dbnToolsJsonInput(400000);
$language = dbnToolsNormalizeLanguage($input['language'] ?? 'en');
$engine = ToolModels::engineForUser($ftUid, (string)($input['engine'] ?? 'azure_mini'));
$slices = is_array($input['slices'] ?? null) ? array_values(array_filter($input['slices'])) : [];
// Streaming headers — flush each NDJSON line as it's written
header('Content-Type: application/x-ndjson; charset=utf-8');
header('X-Accel-Buffering: no');
header('Cache-Control: no-cache, no-store');
while (ob_get_level()) {
ob_end_clean();
}
$emit = static function (string $event, array $payload): void {
echo json_encode(['event' => $event] + $payload, JSON_UNESCAPED_UNICODE) . "\n";
flush();
};
try {
$text = dbnToolsInjectDocContent($input, dbnToolsString($input, 'text', 128000));
if (mb_strlen(trim($text), 'UTF-8') < 50) {
$emit('error', [
'error' => 'Paste text, upload a file, or select a document before running.',
'code' => 'empty_text',
]);
exit;
}
$emit('progress', [
'step' => 'text_ready',
'detail' => mb_strlen($text, 'UTF-8') . ' chars ready.',
]);
$corpusContext = '';
if (!empty($slices)) {
$sliceCount = count($slices);
$emit('progress', [
'step' => 'corpus_search',
'detail' => 'Searching legal corpus (' . $sliceCount . ' slice' . ($sliceCount === 1 ? '' : 's') . ')…',
]);
$svc = new DbnLegalToolsService();
$query = mb_substr(trim($text), 0, 600, 'UTF-8');
$corpusContext = $svc->corpusContextForSummarize($query, 8);
$emit('progress', [
'step' => 'corpus_done',
'detail' => $corpusContext !== ''
? 'Legal context retrieved.'
: 'No matching passages found; summarising without corpus.',
]);
}
$emit('progress', [
'step' => 'generating',
'detail' => 'Generating summary…',
]);
$result = (new DbnLegalToolsService())->summarizeWithContext($text, $language, $engine, $corpusContext);
if ($ftUid > 0) {
$balance = dbnToolsFreeTierDeduct($ftUid, 'summarize');
$result['balance'] = $balance;
}
$emit('final', $result);
} catch (DbnToolsHttpException $e) {
$emit('error', ['error' => $e->getMessage(), 'code' => (string)$e->getCode()]);
} catch (Throwable $e) {
error_log('summarize error: ' . $e->getMessage());
$emit('error', ['error' => 'An unexpected error occurred. Please try again.', 'code' => 'server_error']);
}