Feature/semantic similarity (#36)

* fix: mixed up migrations

* feat: semantic similarity first take

* feat: semantic similarity first round of fixes

* feat: more work on making semantic similarity work properly

* feat: getPostBySlug for the AI

* feat: show similarity in post-link-insert-modal

* chore: remove done doc

---------

Co-authored-by: hugo <hugoms@me.com>

src/main/shared/i18n/locales/de.json

@@ -36,11 +36,13 @@
   "menu.item.previewPost": "Beitragsvorschau",
   "menu.item.rebuildDatabase": "Datenbank aus Dateien neu aufbauen",
   "menu.item.reindexText": "Suchtext neu indizieren",
+  "menu.item.rebuildEmbeddingIndex": "Embedding-Index neu aufbauen",
   "menu.item.metadataDiff": "Metadaten-Diff-Werkzeug",
   "menu.item.editMenu": "Blog-Menü bearbeiten",
   "menu.item.generateSitemap": "Site rendern",
   "menu.item.regenerateCalendar": "Kalender neu erzeugen",
   "menu.item.validateSite": "Website validieren",
+  "menu.item.findDuplicates": "Doppelte Beiträge finden",
   "menu.item.uploadSite": "Website hochladen",
   "menu.item.about": "Über Blogging Desktop Server",
   "menu.item.openDocumentation": "Dokumentation öffnen",
@@ -80,5 +82,12 @@
   "render.month.11": "Nov.",
   "render.month.12": "Dezember",
   "ai.imageAnalysis.system": "Du erzeugst Bild-Metadaten. Schreibe alle Werte auf Deutsch.\n\nRegeln:\n- \"title\": kurzer beschreibender Titel (3-8 Wörter)\n- \"alt\": sachliche Beschreibung des Sichtbaren (5-12 Wörter). Keine Interpretationen. Kein Präfix \"Bild von\".\n- \"caption\": ansprechende Blog-Bildunterschrift (5-20 Wörter)\n\nAntworte ausschließlich mit JSON: {\"title\": \"...\", \"alt\": \"...\", \"caption\": \"...\"}",
-  "ai.imageAnalysis.user": "Analysiere dieses Bild. Antworte mit JSON auf Deutsch."
+  "ai.imageAnalysis.user": "Analysiere dieses Bild. Antworte mit JSON auf Deutsch.",
+  "task.embeddingIndex.name": "Beiträge für semantische Ähnlichkeit indexieren",
+  "task.embeddingIndex.loading": "Modell wird geladen…",
+  "task.embeddingIndex.indexing": "Indexierung: {indexed}/{total}",
+  "task.rebuildEmbeddingIndex.name": "Embedding-Index neu aufbauen",
+  "task.rebuildEmbeddingIndex.clearing": "Index wird geleert…",
+  "task.duplicateSearch.name": "Doppelte Beiträge finden",
+  "task.duplicateSearch.searching": "Prüfe: {checked}/{total}"
 }

src/main/shared/i18n/locales/en.json

@@ -36,11 +36,13 @@
   "menu.item.previewPost": "Preview Post",
   "menu.item.rebuildDatabase": "Rebuild Database from Files",
   "menu.item.reindexText": "Reindex Search Text",
+  "menu.item.rebuildEmbeddingIndex": "Rebuild Embedding Index",
   "menu.item.metadataDiff": "Metadata Diff Tool",
   "menu.item.editMenu": "Edit Blog Menu",
   "menu.item.generateSitemap": "Render Site",
   "menu.item.regenerateCalendar": "Regenerate Calendar",
   "menu.item.validateSite": "Validate Site",
+  "menu.item.findDuplicates": "Find Duplicate Posts",
   "menu.item.uploadSite": "Upload Site",
   "menu.item.about": "About Blogging Desktop Server",
   "menu.item.openDocumentation": "Open Documentation",
@@ -80,5 +82,12 @@
   "render.month.11": "November",
   "render.month.12": "December",
   "ai.imageAnalysis.system": "You generate image metadata. Write all values in English.\n\nRules:\n- \"title\": short descriptive title (3-8 words)\n- \"alt\": factual description of what is visible (5-12 words). No interpretations. No \"Image of\" prefix.\n- \"caption\": engaging blog caption (5-20 words)\n\nRespond with JSON only: {\"title\": \"...\", \"alt\": \"...\", \"caption\": \"...\"}",
-  "ai.imageAnalysis.user": "Analyze this image. Respond with JSON in English."
+  "ai.imageAnalysis.user": "Analyze this image. Respond with JSON in English.",
+  "task.embeddingIndex.name": "Index posts for Semantic Similarity",
+  "task.embeddingIndex.loading": "Loading model…",
+  "task.embeddingIndex.indexing": "Indexing: {indexed}/{total}",
+  "task.rebuildEmbeddingIndex.name": "Rebuild Embedding Index",
+  "task.rebuildEmbeddingIndex.clearing": "Clearing index…",
+  "task.duplicateSearch.name": "Find Duplicate Posts",
+  "task.duplicateSearch.searching": "Checking: {checked}/{total}"
 }

src/main/shared/i18n/locales/es.json

@@ -36,11 +36,13 @@
   "menu.item.previewPost": "Vista previa de entrada",
   "menu.item.rebuildDatabase": "Reconstruir Database from Files",
   "menu.item.reindexText": "Reindex Buscar Text",
+  "menu.item.rebuildEmbeddingIndex": "Reconstruir índice de embeddings",
   "menu.item.metadataDiff": "Herramienta diff de metadatos",
   "menu.item.editMenu": "Editar menú del blog",
   "menu.item.generateSitemap": "Renderizar sitio",
   "menu.item.regenerateCalendar": "Regenerar calendario",
   "menu.item.validateSite": "Validar sitio",
+  "menu.item.findDuplicates": "Buscar entradas duplicadas",
   "menu.item.uploadSite": "Subir sitio",
   "menu.item.about": "Acerca de Blogging Desktop Server",
   "menu.item.openDocumentation": "Abrir documentación",
@@ -80,5 +82,12 @@
   "render.month.11": "noviembre",
   "render.month.12": "diciembre",
   "ai.imageAnalysis.system": "Generas metadatos de imagen. Escribe todos los valores en español.\n\nReglas:\n- \"title\": título descriptivo corto (3-8 palabras)\n- \"alt\": descripción factual de lo visible (5-12 palabras). Sin interpretaciones. Sin prefijo \"Imagen de\".\n- \"caption\": pie de foto atractivo para blog (5-20 palabras)\n\nResponde solo con JSON: {\"title\": \"...\", \"alt\": \"...\", \"caption\": \"...\"}",
-  "ai.imageAnalysis.user": "Analiza esta imagen. Responde con JSON en español."
+  "ai.imageAnalysis.user": "Analiza esta imagen. Responde con JSON en español.",
+  "task.embeddingIndex.name": "Indexar entradas para similitud semántica",
+  "task.embeddingIndex.loading": "Cargando modelo…",
+  "task.embeddingIndex.indexing": "Indexando: {indexed}/{total}",
+  "task.rebuildEmbeddingIndex.name": "Reconstruir índice de embeddings",
+  "task.rebuildEmbeddingIndex.clearing": "Vaciando índice…",
+  "task.duplicateSearch.name": "Buscar entradas duplicadas",
+  "task.duplicateSearch.searching": "Comprobando: {checked}/{total}"
 }

src/main/shared/i18n/locales/fr.json

@@ -36,11 +36,13 @@
   "menu.item.previewPost": "Aperçu de l’article",
   "menu.item.rebuildDatabase": "Reconstruire Database from Files",
   "menu.item.reindexText": "Reindex Recherche Text",
+  "menu.item.rebuildEmbeddingIndex": "Reconstruire l'index d'embeddings",
   "menu.item.metadataDiff": "Outil de diff des métadonnées",
   "menu.item.editMenu": "Modifier le menu du blog",
   "menu.item.generateSitemap": "Rendre le site",
   "menu.item.regenerateCalendar": "Régénérer le calendrier",
   "menu.item.validateSite": "Valider le site",
+  "menu.item.findDuplicates": "Trouver les articles en double",
   "menu.item.uploadSite": "Publier le site",
   "menu.item.about": "À propos de Blogging Desktop Server",
   "menu.item.openDocumentation": "Ouvrir la documentation",
@@ -80,5 +82,12 @@
   "render.month.11": "novembre",
   "render.month.12": "décembre",
   "ai.imageAnalysis.system": "Tu génères des métadonnées d'image. Écris toutes les valeurs en français.\n\nRègles :\n- \"title\" : titre descriptif court (3-8 mots)\n- \"alt\" : description factuelle de ce qui est visible (5-12 mots). Pas d'interprétations. Pas de préfixe \"Image de\".\n- \"caption\" : légende de blog engageante (5-20 mots)\n\nRéponds uniquement en JSON : {\"title\": \"...\", \"alt\": \"...\", \"caption\": \"...\"}",
-  "ai.imageAnalysis.user": "Analyse cette image. Réponds en JSON en français."
+  "ai.imageAnalysis.user": "Analyse cette image. Réponds en JSON en français.",
+  "task.embeddingIndex.name": "Indexer les articles pour la similarité sémantique",
+  "task.embeddingIndex.loading": "Chargement du modèle…",
+  "task.embeddingIndex.indexing": "Indexation : {indexed}/{total}",
+  "task.rebuildEmbeddingIndex.name": "Reconstruire l'index d'embeddings",
+  "task.rebuildEmbeddingIndex.clearing": "Vidage de l'index…",
+  "task.duplicateSearch.name": "Trouver les articles en double",
+  "task.duplicateSearch.searching": "Vérification : {checked}/{total}"
 }

src/main/shared/i18n/locales/it.json

@@ -36,11 +36,13 @@
   "menu.item.previewPost": "Anteprima post",
   "menu.item.rebuildDatabase": "Ricostruisci Database from Files",
   "menu.item.reindexText": "Reindex Ricerca Text",
+  "menu.item.rebuildEmbeddingIndex": "Ricostruisci indice embeddings",
   "menu.item.metadataDiff": "Strumento diff metadati",
   "menu.item.editMenu": "Modifica menu blog",
   "menu.item.generateSitemap": "Renderizza sito",
   "menu.item.regenerateCalendar": "Rigenera calendario",
   "menu.item.validateSite": "Valida sito",
+  "menu.item.findDuplicates": "Trova post duplicati",
   "menu.item.uploadSite": "Carica sito",
   "menu.item.about": "Informazioni su Blogging Desktop Server",
   "menu.item.openDocumentation": "Apri documentazione",
@@ -80,5 +82,12 @@
   "render.month.11": "novembre",
   "render.month.12": "dicembre",
   "ai.imageAnalysis.system": "Generi metadati per immagini. Scrivi tutti i valori in italiano.\n\nRegole:\n- \"title\": titolo descrittivo breve (3-8 parole)\n- \"alt\": descrizione fattuale di ciò che è visibile (5-12 parole). Nessuna interpretazione. Nessun prefisso \"Immagine di\".\n- \"caption\": didascalia blog coinvolgente (5-20 parole)\n\nRispondi solo con JSON: {\"title\": \"...\", \"alt\": \"...\", \"caption\": \"...\"}",
-  "ai.imageAnalysis.user": "Analizza questa immagine. Rispondi con JSON in italiano."
+  "ai.imageAnalysis.user": "Analizza questa immagine. Rispondi con JSON in italiano.",
+  "task.embeddingIndex.name": "Indicizza i post per la similarità semantica",
+  "task.embeddingIndex.loading": "Caricamento modello…",
+  "task.embeddingIndex.indexing": "Indicizzazione: {indexed}/{total}",
+  "task.rebuildEmbeddingIndex.name": "Ricostruisci indice embeddings",
+  "task.rebuildEmbeddingIndex.clearing": "Svuotamento indice…",
+  "task.duplicateSearch.name": "Trova post duplicati",
+  "task.duplicateSearch.searching": "Controllo: {checked}/{total}"
 }