Add Deep Research tool — agent + rank/rerank RAG

New surface at /deep-research.php where the user pastes a question or uploads PDF/DOCX/TXT case files and a LLM-orchestrated agent researches the Do Better Norge legal corpus from 3-5 angles, with hybrid retrieval, cross-encoder rerank, and synthesis that emits an inline-[n]-cited markdown brief plus a numbered sources panel. Uploaded documents are chunked + embedded in memory only (nomic-embed-text via LiteLLM) and searched alongside the shared corpus during the same request — never persisted to disk, DB, or Qdrant. Reuses ClientRagPipeline::searchAll (hybrid + rerank), dbnV6 slice helpers, and the existing extract.php text-extraction logic via a new dbnToolsExtractUploadedFile() helper. Also adds dbnToolsCallGpuLlm() helper in bootstrap.php — fixes a latent bug where LegalTools.php was already calling that name with no definition. Search.php is unchanged.
2026-05-15 10:30:47 +02:00
parent 55e11cb649
commit 4cbe0a4ac4
10 changed files with 2119 additions and 125 deletions
@@ -0,0 +1,67 @@
+<?php
+declare(strict_types=1);
+
+require_once __DIR__ . '/../includes/bootstrap.php';
+require_once __DIR__ . '/../includes/DeepResearchAgent.php';
+
+dbnToolsRequireMethod('POST');
+dbnToolsRequireAuth();
+
+$isMultipart = stripos((string)($_SERVER['CONTENT_TYPE'] ?? ''), 'multipart/form-data') !== false;
+
+if ($isMultipart) {
+    $payloadRaw = (string)($_POST['payload'] ?? '');
+    if ($payloadRaw === '') {
+        dbnToolsError('Multipart request is missing the "payload" JSON field.', 422, 'missing_payload');
+    }
+    $input = json_decode($payloadRaw, true);
+    if (!is_array($input)) {
+        dbnToolsError('Multipart "payload" field must be valid JSON.', 422, 'invalid_payload_json');
+    }
+} else {
+    $input = dbnToolsJsonInput(120000);
+}
+
+$language = dbnToolsNormalizeLanguage($input['language'] ?? 'en');
+
+dbnToolsWithTelemetry('deep_research', $language, function () use ($input, $language) {
+    $seedQuery   = dbnToolsString($input, 'query', 4000, false);
+    $pastedText  = dbnToolsString($input, 'paste_text', 64000, false);
+    $sliceInput  = $input['slices'] ?? null;
+    $engine      = (string)($input['engine'] ?? 'azure_mini');
+    $controls    = is_array($input['controls'] ?? null) ? $input['controls'] : [];
+
+    $uploadedFiles = [];
+    if (!empty($_FILES['files']) && is_array($_FILES['files']['tmp_name'] ?? null)) {
+        $count = count($_FILES['files']['tmp_name']);
+        if ($count > 5) {
+            dbnToolsAbort('At most 5 files can be uploaded per request.', 413, 'too_many_files');
+        }
+        for ($i = 0; $i < $count; $i++) {
+            $file = [
+                'name'     => $_FILES['files']['name'][$i]     ?? '',
+                'type'     => $_FILES['files']['type'][$i]     ?? '',
+                'tmp_name' => $_FILES['files']['tmp_name'][$i] ?? '',
+                'error'    => $_FILES['files']['error'][$i]    ?? UPLOAD_ERR_NO_FILE,
+                'size'     => $_FILES['files']['size'][$i]     ?? 0,
+            ];
+            $extracted = dbnToolsExtractUploadedFile($file);
+            $uploadedFiles[] = [
+                'filename'  => $extracted['filename'],
+                'text'      => $extracted['text'],
+                'chars'     => $extracted['chars'],
+                'truncated' => $extracted['truncated'],
+            ];
+        }
+    }
+
+    return (new DbnDeepResearchAgent())->run(
+        $seedQuery,
+        $pastedText,
+        $uploadedFiles,
+        is_array($sliceInput) ? $sliceInput : [],
+        $engine,
+        $language,
+        $controls
+    );
+});