Updating app version July 15th, 2025

app.py

@@ -1,8 +1,16 @@
+# import spacy.cli
+# spacy.cli.download("ja_core_news_sm")
+# spacy.cli.download("zh_core_web_sm")
+import spacy_udpipe
+spacy_udpipe.download("ja")
+spacy_udpipe.download("zh")
+
 from ui.layout import build_ui
 from logic.data_utils import load_concepts, load_metadata
 
 from config.settings import HF_API_TOKEN, HF_DATASET_NAME
 
+
 concepts = load_concepts()
 metadata = load_metadata()
 

data/concepts.json

@@ -2639,21 +2639,77 @@
         "ጥብስ",
         "ፍርፍር",
         "ሰላጣ",
-        "ብርዝ"
+        "ብርዝ",
+        "ሽሮ",
+        "ዶሮ ወጥ",
+        "ምንቸት አብሽ",
+        "ጎረድ ጎርድ",
+        "አልጫ ",
+        "ገንፎ",
+        "ጨጨብሳ",
+        "ፈጢራ",
+        "ባቅላባ",
+        "ኽለዋ",
+        "ክክ ወጥ",
+        "ምስር ወጥ",
+        "ድንች ወጥ",
+        "በየአይነቱ ",
+        "አነባብሮሽ",
+        "እንቁላል ፍርፍር",
+        "ፉል",
+        "ህልብት",
+        "ፋታ",
+        "ጭቆ",
+        "አንባሻ",
+        "ቆሎ",
+        "ንፍሮ",
+        "ድንች ቅቅል",
+        "ሳምቡሳ",
+        "ቦምቦሊኖ",
+        "አጥሚት",
+        "ቦርዲ",
+        "ቡና",
+        "አረቄ"
       ],
       "Clothing": [
         "ሱሪ",
         "ነጠላ",
         "ጋቢ",
         "ቀሚስ",
-        "ካልሲ",
+        "ካልስ",
         "ካፖርት",
         "ኮት",
         "ጫማ",
         "ብርድ ልብስ",
         "አንሶላ",
         "ሰዓት",
-        "ሻሽ"
+        "ሻሽ",
+        "እጀ ጠባብ",
+        "መቀነት",
+        "ጉንፍ",
+        "ሹፎን",
+        "ሽብሽቦ",
+        "ሂጃብ",
+        "አባያ",
+        "ጅልባብ",
+        "ጀላብያ",
+        "ጥምጣም",
+        "ሽርጥ",
+        "ፎጣ",
+        "ጎጃም አዘነ",
+        "ቁምጣ",
+        "ጥበብ",
+        "ዉስጥ ልብስ",
+        "ባርኔጣ",
+        "ገሳ",
+        "ካባ",
+        "ቤሎ",
+        "መቅና",
+        "ኒቃብ",
+        "ማተብ",
+        "የዉስጥ ሱሪ",
+        "ሸበጥ",
+        "ነጠላ ጫማ"
       ],
       "Buildings (interior and exterior)": [
         "ቤት",
@@ -2681,7 +2737,10 @@
         "አደባባይ",
         "ቤተመንግስት",
         "መስጊድ ",
-        "ቤተ ክርስቲያን "
+        "ቤተ ክርስቲያን ",
+        "ጎጆ ቤት",
+        "ሽንት ቤት",
+        "በረንዳ"
       ],
       "Instruments, Tools and Utensils": [
         "ምጣድ",
@@ -2693,18 +2752,66 @@
         "ዶማ",
         "ቀንበር",
         "ከበሮ",
-        "ሞሰብ"
+        "ሞሰብ",
+        "ዋሽንት",
+        "ክራር",
+        "ዲቢ",
+        "ሰፌድ",
+        "ሰባጤራ",
+        "እንስራ",
+        "ቶፋ",
+        "ጎታ",
+        "ጀበና",
+        "ጥዋ",
+        "ዋንጫ",
+        "ብርሌ",
+        "ፋጋ",
+        "ሰኔል",
+        "ጭልፋ",
+        "መገበሪያ",
+        "ሙግድ",
+        "ቆጥ",
+        "መደብ",
+        "ቁና",
+        "ቀፎ",
+        "ሙቅጫ",
+        "ዘነዘና",
+        "ዘንቢል",
+        "ወንፊት"
       ],
       "Celebrations, Sports and Events": [
         "ሰርግ",
         "ቀብር",
-        "የትውልድ ስም",
+        "የልድተ ቀን",
         "አዲስ አመት",
         "ኢድ አልፈጥር",
         "ኢድ አልአድሃ",
-        "አዲስ አመት",
+        "ተስካር",
         "ገና",
-        "ጥምቀት"
+        "ጥምቀት",
+        "መዉሊደ",
+        "ቡሄ",
+        "ፋሲካ",
+        "የመስቀል በዓል",
+        "ታላቁ ሩጫ",
+        "ህዳር ጺዎን",
+        "ቁልቢ ገብርኤል",
+        "የአድዋ በዓል",
+        "የአርበኞች ቀን",
+        "የላባደሮች ቀን",
+        "የብሄር ብሄረሰቦች ቀን",
+        "ኢሬቻ",
+        "ሻደይ",
+        "ፊቸ ጨምበላላ",
+        "አሸንዳ",
+        "ህዳር ሲታጠን",
+        "የገና ጨዋታ",
+        "እግር ኳስ ጨዋታ",
+        "አገዉ ፈረሰኞች",
+        "ምርቃት",
+        "እርሻ",
+        "ትግል",
+        "ገበጣ"
       ]
     }
   },
@@ -5820,7 +5927,7 @@
         "Maji",
         "Sharubati",
         "Mayai",
-        "Ugali",
+        "Ugali/Sima",
         "Wali",
         "Maharagwe",
         "Mahindi",
@@ -5829,10 +5936,10 @@
         "Kuku",
         "Viazi",
         "Mandazi",
-        "Mahamri",
         "Chapati",
         "Pilau",
-        "Samaki"
+        "Samaki",
+        "Mkate"
       ],
       "Clothing": [
         "Kaptura",
@@ -5844,7 +5951,7 @@
         "Soksi",
         "Kofia",
         "Kitenge",
-        "Viatu",
+        "Kiatu",
         "Champali",
         "Sidiria"
       ],
@@ -5897,7 +6004,7 @@
         "Tarumbeta",
         "Kayamba",
         "Kinanda",
-        "Guitaa"
+        "Gitaa"
       ],
       "Celebrations, Sports and Events": [
         "Harusi",
@@ -5917,7 +6024,7 @@
         "Siku ya Wafanyakazi /Leba Dei",
         "Sikukuu ya Krismasi",
         "Siku ya Wanawake Duniani",
-        "Siku ya Kina Baba",
+        "Siku ya Baba",
         "Siku ya Mama"
       ]
     }
@@ -6343,7 +6450,6 @@
         "Rijtjeshuis",
         "Boerderij",
         "Villa",
-        "Molen",
         "Flat",
         "Kasteel",
         "Watertoren",
@@ -6356,7 +6462,8 @@
         "Bunker",
         "Woonboot",
         "Begijnhof",
-        "Sluis"
+        "Sluis",
+        "Fietsenstalling"
       ],
       "Instruments, Tools and Utensils": [
         "Poffertjespan",
@@ -6995,7 +7102,28 @@
         "Galocha",
         "Chapéu"
       ],
-      "Buildings (interior and exterior)": [],
+      "Buildings (interior and exterior)": [
+        "Casa",
+        "Mosteiro",
+        "Hospital",
+        "Quinta",
+        "Igreja",
+        "Escola",
+        "Cozinha",
+        "Restaurante",
+        "Estação ferroviária",
+        "Quarto",
+        "Centro comercial",
+        "Despensa",
+        "Parque",
+        "Castelo",
+        "Estádio",
+        "Museu",
+        "Padaria",
+        "Pastelaria",
+        "Bar",
+        "Posto de abastecimento"
+      ],
       "Instruments, Tools and Utensils": [
         "Guitarra portuguesa",
         "Cavaquinho",
@@ -9443,8 +9571,70 @@
   },
   "Venezuela": {
     "Spanish": {
-      "Food and Beverages": [],
-      "Clothing": [],
+      "Food and Beverages": [
+        "Cachapa",
+        "Hallaca",
+        "Cachito de Jamón",
+        "Pabellón Criollo",
+        "Chicha Criolla",
+        "Asado Negro",
+        "Pan de Jamon",
+        "Papelón con Limón",
+        "Empanada Venezolana",
+        "Tequeño",
+        "Golfeado",
+        "Patacón",
+        "Arepa",
+        "Bollo Pelón",
+        "Casabe",
+        "Frescolita",
+        "Mandoca",
+        "Ponche Crema",
+        "Malta",
+        "Ensalda de Gallina",
+        "Carne Mechada",
+        "Chicharrón",
+        "Guasacaca",
+        "Licor de Cocuy",
+        "Majarete",
+        "Mojito",
+        "Mondongo de chivo",
+        "Parilla",
+        "Pastelito",
+        "Tizana",
+        "Vuelve a la Vida",
+        "Arepa andina / Arepa de trigo",
+        "Sopa de Mondongo",
+        "Pisca andina",
+        "Sancocho",
+        "Perico",
+        "Reina Pepeada",
+        "Dulce de lechosa",
+        "Queso",
+        "Ron"
+      ],
+      "Clothing": [
+        "Alpargata",
+        "Ruana",
+        "Liqui Liqui",
+        "Manta Guajira / Manta Wayuu",
+        "Sombrero de Cogollo",
+        "Guayabera",
+        "Guayuco",
+        "Sombrero de Pelo e' Guama",
+        "Traje de Dama Antañona",
+        "Blusa",
+        "Collar de Semillas",
+        "Falda Llanera",
+        "Tocado Wayuu",
+        "Capris",
+        "Chancla / Chancleta",
+        "Franela",
+        "Gorra",
+        "Zapatos de Goma",
+        "Pantalón Tubito",
+        "Franelilla"
+      ],
       "Buildings (interior and exterior)": [
         "Casa / Quinta",
         "Apartamento",
@@ -9487,13 +9677,69 @@
         "Cuartel",
         "Centro Comercial"
       ],
-      "Instruments, Tools and Utensils": [],
+      "Instruments, Tools and Utensils": [
+        "Bandola",
+        "Arpa",
+        "Maracas",
+        "Furruco",
+        "Charrasca",
+        "Cuatro",
+        "Tambor",
+        "Tostiarepa",
+        "Pilón",
+        "Budare",
+        "Guarura",
+        "Sebucán",
+        "Anafre",
+        "Hamaca",
+        "Totuma / Tapara",
+        "Flauta",
+        "Cesta",
+        "Coleto ",
+        "Machete",
+        "Gurrufío"
+      ],
       "Celebrations, Sports and Events": [
         "Boda",
         "Funeral",
         "Bautizo",
         "Año Nuevo",
-        "Cumpleaños"
+        "Cumpleaños",
+        "Feria de la Chinita",
+        "Diablos Danzantes de Yare",
+        "Fiesta de San Juan",
+        "Día de la Divina Pastora",
+        "Semana Santa",
+        "Serie del Caribe",
+        "Beisbol",
+        "Día de la Independencia de Venezuela",
+        "Día de la Resistencia Indígena",
+        "Navidad",
+        "Paradura del Niño",
+        "Carnaval",
+        "Carnaval de El Callao",
+        "Feria Internacional de San Sebastián",
+        "Día de Nuestra Señora de Coromoto",
+        "Parranda de San Pedro",
+        "Tambores de San Benito",
+        "Día de la Virgen de la Candelaria",
+        "Día de la Virgen del Valle",
+        "Día de Reyes",
+        "Bolas Criollas",
+        "Coleo de toros",
+        "Baloncesto",
+        "Superliga Profesional de Baloncesto",
+        "Quema de Judas",
+        "Feria Internacional del Sol\n",
+        "Miss Venezuela\n",
+        "Miss Universo\n",
+        "La Cruz de Mayo",
+        "Día de la Madre",
+        "Día del Padre",
+        "Día del Maestro",
+        "Ferias de San Felipe",
+        "Día del Niño",
+        "Futbol"
       ]
     }
   },

data/guidelines/USA/English/instructions.md

@@ -5,7 +5,7 @@
 - Images should NOT have empty backgrounds NOR watermarks.
 - The complexity of the image will contribute to the interestingness of the description.
 - You can blur all/selected faces before submitting your image. Once submitted, faces cannot be deblurred (you can still, however, re-upload the image if you want to).
-- If you don’t have personal pictures for a concept, please use public images:
+- If you don’t have personal pictures for a concept, please use public images by providing their URL (instead of downloading them):
   - [Google images](images.google.com)
 
 	- When searching on images.google.com, you can click on “Tools” → “Usage rights” → “Creative Commons licenses”

data/guidelines/USA/English/task.md

@@ -1,8 +1,6 @@
-# Wonders: Multicultural Images and Captions for Inclusive AI
 
-We want to collect images and annotations that are relevant for your culture.
 - **Main concept:** Choose the main category and concept for which you want to share data. You can type a new concept if it’s culturally relevant and missing from our list.
-- **Image:** An image where the *main concept is clearly visible*. The image needs to (1) show the concept *in typical contexts* where it can be found in your country, and (2) *include other* objects/people whenever possible. *Pictures taken by yourself* are preferred. Otherwise, please add a URL for publicly-licensed images from the Web (e.g., from pexels.com or freepik.com). For more details, see “Instructions” below. 
+- **Image:** An image where the *main concept is clearly visible*. The image needs to (1) show the concept *in typical contexts* where it can be found in your country, and (2) *include other* objects/people whenever possible. *Pictures taken by yourself* are preferred. Otherwise, do not download images from the Web. Instead, add the image URL below for publicly-licensed images (e.g., from pexels.com or freepik.com). For more details, see “Instructions” below. 
 - **Description:** A long description (around 40 words) that provides extensive and detailed visual information. Descriptions must be *objective*: focus on how you would describe the image to someone who can’t see it, without adding your own opinions/speculations. The text needs to *include the main concept* and describes the content of the image in detail by including:
   - **Who?** The visual *appearance* and observable *emotions* (e.g., “is smiling”) of persons and animals.
   - **What?** The *actions* performed in the image.

data/metadata.json

@@ -8,8 +8,8 @@
       "Password": "Password (Optional)",
       "Concept": "Main Concept",
       "Image": "Image",
-      "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Image_URL": "Image URL (optional, if no image is uploaded)",
+      "Description": "Description in English",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -34,8 +34,8 @@
       "Password": "Password (Optional)",
       "Concept": "Main Concept",
       "Image": "Image",
-      "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Image_URL": "Image URL (optional, if no image is uploaded)",
+      "Description": "Description in Italian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -61,7 +61,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in French",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -87,7 +87,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Spanish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -113,7 +113,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Arabic",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -139,7 +139,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Spanish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -165,7 +165,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in English",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -191,7 +191,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Bengali",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -217,7 +217,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in French",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -243,7 +243,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Portuguese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -269,7 +269,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Bulgarian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -295,7 +295,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Spanish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -321,7 +321,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Mandarin Chinese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -345,7 +345,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Yue Chinese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -371,7 +371,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Czech",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -397,7 +397,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Danish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -423,7 +423,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Spanish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -449,7 +449,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Egyptian Arabic",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -475,7 +475,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Oromo",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -499,7 +499,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Amharic",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -525,7 +525,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in German",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -551,7 +551,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Twi",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -575,7 +575,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Fante",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -599,7 +599,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in GA",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -625,7 +625,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Greek",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -651,7 +651,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Hungarian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -701,7 +701,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Kannada",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -725,7 +725,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Telugu",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -749,7 +749,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Tamil",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -773,7 +773,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Hindi",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -797,7 +797,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Bengali",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -821,7 +821,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Marathi",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -845,7 +845,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Urdu",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -871,7 +871,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Javanese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -895,7 +895,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Indonesian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -921,7 +921,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Hebrew",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -947,7 +947,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Japanese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -973,7 +973,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Jordanian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -999,7 +999,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Spanish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1025,7 +1025,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Moroccan Arabic",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1051,7 +1051,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Dutch",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1077,7 +1077,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Yoruba",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1101,7 +1101,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Hausa",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1127,7 +1127,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Tagalog",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1153,7 +1153,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Polish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1179,7 +1179,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Portuguese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1205,7 +1205,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Romanian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1231,7 +1231,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Russian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1257,7 +1257,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Kinyarwanda",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1283,7 +1283,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Mandarin Chinese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1309,7 +1309,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Korean",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1335,7 +1335,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Spanish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1361,7 +1361,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in German",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1387,7 +1387,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Swahili",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1413,7 +1413,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Turkish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1439,7 +1439,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Ukranian",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1465,7 +1465,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Uzbek",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1491,7 +1491,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Vietnamese",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1517,7 +1517,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Swahili",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1543,7 +1543,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Somali",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1569,7 +1569,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Thai",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1595,7 +1595,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Luganda",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1621,7 +1621,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Spanish",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1647,7 +1647,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Shona",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",
@@ -1671,7 +1671,7 @@
       "Concept": "Main Concept",
       "Image": "Image",
       "Image_URL": "Image URL (optional, if no image is loaded)",
-      "Description": "Description",
+      "Description": "Description in Ndebele",
       "Instructs_btn": "\ud83d\udcd8 Show instructions",
       "Clear_btn": "Clear",
       "Submit_btn": "Submit",

data/update_metadata_from_concepts.py

@@ -9,6 +9,9 @@ for country in concepts:
     for language in concepts[country]:
         if language not in meta[country]:
             meta[country][language] = meta["USA"]["English"]
+        # FIXME: Remove this after we ask language leads to translate
+        if not meta[country][language]["Description"].endswith(language):
+            meta[country][language]["Description"] += f"in {language}"
 
 with open("metadata.json", "w", encoding="utf-8") as f:
     json.dump(meta, f, indent=2)

logic/data_utils.py

@@ -169,7 +169,7 @@ class CustomHFDatasetSaver:
         if values_dic.get("username"):
             sample_dir = os.path.join("logged_in_users", values_dic["country"], values_dic["language"], values_dic["username"], str(current_timestamp))
         else:
-            sample_dir = os.path.join("anonymous_users", values_dic["country"], values_dic["language"], str(uuid.uuid4()))
+            sample_dir = os.path.join("anonymous_users", values_dic["country"], values_dic["language"], str(uuid.uuid4()), str(current_timestamp))
 
         os.makedirs(os.path.join(self.local_ds_folder, sample_dir), exist_ok=True)
 

logic/handlers.py

@@ -3,6 +3,8 @@ import datetime
 import io
 import PIL
 import requests
+from typing import Literal
+
 from datasets import load_dataset, concatenate_datasets, Image
 from data.lang2eng_map import lang2eng_mapping
 from data.words_map import words_mapping
@@ -19,6 +21,25 @@ import time
 import re
 import os
 import glob
+from pyuca import Collator
+from pillow_heif import register_heif_opener
+register_heif_opener()
+
+import spacy_udpipe
+# ja_nlp = spacy.load("ja_core_news_sm")
+# zh_nlp = spacy.load("zh_core_web_sm")
+# import ja_core_news_sm
+# import zh_core_web_sm
+import spacy_thai
+ja_nlp = spacy_udpipe.load("ja")
+zh_nlp = spacy_udpipe.load("zh")
+th_nlp = spacy_thai.load()
+
+
+def sort_with_pyuca(strings):
+    collator = Collator()
+    return sorted(strings, key=collator.sort_key)
+
 
 def update_image(image_url):
     try:
@@ -45,7 +66,11 @@ def update_timestamp():
     return gr.Textbox(datetime.datetime.now().timestamp(), label="Timestamp", visible=False) # FIXME visible=False)
 
 
-def clear_data():
+def clear_data(message: Literal["submit", "remove"] | None = None):
+    if message == "submit":
+        gr.Info("If you logged in, you will soon see it at the bottom of the page, where you can edit it or delete it", title="Thank you for submitting your data! 🎉", duration=5)
+    elif message == "remove":
+        gr.Info("", title="Your data has been deleted! 🗑️", duration=5)
     return (None, None, None, None, None, gr.update(value=None), 
             gr.update(value=[]), gr.update(value=[]), gr.update(value=[]),
             gr.update(value=[]), gr.update(value=[]))
@@ -59,11 +84,23 @@ def exit():
             gr.update(value=None), gr.update(value=None))
 
 
-def validate_inputs(image, ori_img): # is_blurred
+def validate_metadata(country, language):
+    # Perform your validation logic here
+    if country is None or language is None:
+        return gr.Button("Proceed", interactive=False)
+
+    return gr.Button("Proceed", interactive=True)
+
+
+def validate_inputs(image, ori_img, concept): # is_blurred
     # Perform your validation logic here
+    # import pdb; pdb.set_trace()
     if image is None:
         return gr.Button("Submit", variant="primary", interactive=False), None, None,  # False
-        
+    
+    if concept is None:
+        raise gr.Error("⚠️ Please select the main concept first. Click the ❌ on the image uploader to reset the image.", duration=10)
+        return gr.Button("Submit", variant="primary", interactive=False), None, None,  # False
     # Define maximum dimensions
     MAX_WIDTH = 1024
     MAX_HEIGHT = 1024
@@ -93,6 +130,24 @@ def validate_inputs(image, ori_img): # is_blurred
     return gr.Button("Submit", variant="primary", interactive=True), result_image, ori_img # is_blurred
 
 
+def count_words(caption, language):
+    match language:
+        case "Japanese":
+            doc = ja_nlp(caption)
+            tokens = [tok.text for tok in doc if not tok.is_punct]
+            num_words = len(tokens)
+        case "Chinese":
+            doc = zh_nlp(caption)
+            tokens = [tok.text for tok in doc if not tok.is_punct]
+            num_words = len(tokens)
+        case "Thai":
+            num_words = len(th_nlp(caption))
+        case _:
+            num_words = len(caption.split())
+    return num_words
+    # return gr.Markdown(f"Number of words: {num_words}")
+
+
 def add_prefix(example, column_name, prefix):
     example[column_name] = (f"{prefix}/" + example[column_name])
     return example
@@ -135,7 +190,10 @@ def update_user_data(username, password, country, language_choice, HF_DATASET_NA
 
     # Handle all empty
     if not datasets_list:
-        return gr.Dataset(samples=[]), gr.Markdown("<p style='color: red;'>No data available for this user. Please upload an image.</p>")
+        if username:  # User is logged in but has no data
+            return gr.Dataset(samples=[]), gr.Markdown("<p style='color: red;'>No data available for this user. Please upload an image.</p>")
+        else:  # No user logged in 
+            return gr.Dataset(samples=[]), gr.Markdown("")
 
     dataset = concatenate_datasets(datasets_list)
     # TODO: we should link username with password and language and country, otherwise there will be an error when loading with different language and clicking on the example
@@ -171,7 +229,33 @@ def update_user_data(username, password, country, language_choice, HF_DATASET_NA
                     d['image_file'], d['image_url'], d['caption'] or "", d['country'],  
                     d['language'], d['category'], d['concept'], additional_concepts_by_category, d['id']] # d['is_blurred']
             )
-        return gr.Dataset(samples=samples), None
+        # return gr.Dataset(samples=samples), None
+        # ───────────────────────────────────────────────────
+        # Clean up the “Additional Concepts” column (index 7)
+        cleaned = []
+        for row in samples:
+            # row is a list, index 7 holds the list-of-lists
+            ac = row[7]
+
+            # flatten & drop empty strings
+            vals = []
+            for sub in ac:
+                if isinstance(sub, list):
+                    for v in sub:
+                        v = v.strip()
+                        if v:
+                            vals.append(v)
+
+            # now vals contains every non-empty string from every sub-list
+            # e.g. ['Arquitectura colonial española', 'Año Nuevo', 'Bata',
+            #        'Aborrajado', 'Ajiaco', 'Abanico/ventilador']
+
+            # make a copy and replace only that field
+            row_copy = list(row)
+            row_copy[7] = ", ".join(vals)
+            cleaned.append(row_copy)
+
+        return gr.Dataset(samples=cleaned), None
     else:
         # TODO: should we show the entire dataset instead? What about "other data" tab?
         return gr.Dataset(samples=[]), None
@@ -181,13 +265,13 @@ def update_language(local_storage, metadata_dict, concepts_dict):
     country, language, email, password, = local_storage
     # my_translator = GoogleTranslator(source='english', target=metadata_dict[country][language])
     categories = concepts_dict[country][lang2eng_mapping.get(language, language)]
+    categories_list = sort_with_pyuca(list(categories.keys()))
     if language in words_mapping:
-        categories_keys_translated = [words_mapping[language].get(cat, cat) for cat in categories.keys()]
+        categories_keys_translated = [words_mapping[language].get(cat, cat) for cat in categories_list]
     else:
-        categories_keys_translated = list(categories.keys())
+        categories_keys_translated = categories_list
     
     # Get the 5 categories in alphabetical order
-    categories_list = sorted(list(categories.keys()))[:5]
     
     # Create translated labels for the 5 categories
     translated_categories = []
@@ -197,6 +281,15 @@ def update_language(local_storage, metadata_dict, concepts_dict):
         else:
             translated_cat = cat
         translated_categories.append(translated_cat)
+
+    # Load all possible concepts
+    concepts_list = []
+    # cats = []  # FIXME: Assumes concepts are unique across all categories
+    for cat in concepts_dict[country][language]:
+        for concept in concepts_dict[country][language][cat]:
+            # cats.append(cat)
+            concepts_list.append(concept)
+    concepts_list = sort_with_pyuca(concepts_list)
     
     fn = metadata_dict[country][language]["Task"]
     if os.path.exists(fn):
@@ -222,7 +315,7 @@ def update_language(local_storage, metadata_dict, concepts_dict):
         gr.update(label=metadata_dict[country][language]["Email"], value=email),
         gr.update(label=metadata_dict[country][language]["Password"], value=password),
         gr.update(choices=categories_keys_translated, interactive=True, label=metadata_dict[country][language]["Category"], allow_custom_value=False, elem_id="category_btn"),
-        gr.update(choices=[], interactive=True, label=metadata_dict[country][language]["Concept"], allow_custom_value=True, elem_id="concept_btn"),
+        gr.update(choices=concepts_list, interactive=True, label=metadata_dict[country][language]["Concept"], allow_custom_value=True, elem_id="concept_btn"),
         gr.update(label=metadata_dict[country][language]["Image"]),
         gr.update(label=metadata_dict[country][language]["Image_URL"]),
         gr.update(label=metadata_dict[country][language]["Description"]),
@@ -243,11 +336,11 @@ def update_language(local_storage, metadata_dict, concepts_dict):
         gr.update(value=metadata_dict[country][language].get("Hide_btn","👤 Hide Specific Faces")),
         gr.update(value=metadata_dict[country][language].get("Unhide_btn","👀 Unhide Faces")),
         gr.update(value=metadata_dict[country][language].get("Exclude_btn","Exclude Selected Example")),
-        gr.update(label=translated_categories[0], choices=sorted(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[0]])),
-        gr.update(label=translated_categories[1], choices=sorted(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[1]])),
-        gr.update(label=translated_categories[2], choices=sorted(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[2]])),
-        gr.update(label=translated_categories[3], choices=sorted(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[3]])),
-        gr.update(label=translated_categories[4], choices=sorted(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[4]])),
+        gr.update(label=translated_categories[0], choices=sort_with_pyuca(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[0]])),
+        gr.update(label=translated_categories[1], choices=sort_with_pyuca(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[1]])),
+        gr.update(label=translated_categories[2], choices=sort_with_pyuca(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[2]])),
+        gr.update(label=translated_categories[3], choices=sort_with_pyuca(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[3]])),
+        gr.update(label=translated_categories[4], choices=sort_with_pyuca(concepts_dict[country][lang2eng_mapping.get(language, language)][categories_list[4]])),
     )
 
 
@@ -265,20 +358,58 @@ def update_intro_language(selected_country, selected_language, intro_markdown, m
 
 
 def handle_click_example(user_examples, concepts_dict):
-    print("handle_click_example")
-    print(user_examples)
-    ex = [item for item in user_examples]
-    # print(ex)
+    # print("handle_click_example")
+    # print(user_examples)
+    # ex = [item for item in user_examples]
+    # ───────────────────────────────────────────────────────────────
+    # 1) Turn the flat string in slot 7 back into a list-of-lists
+    ex = list(user_examples)
+    raw_ac = ex[7] if len(ex) > 7 else ""
+
+    country_btn = ex[3]
+    language_btn = ex[4]
+    concepts = concepts_dict[country_btn][language_btn]
+    categories_list = sort_with_pyuca(list(concepts.keys()))
+    # NOTE: assuming concepts are unique across all categories
+    if isinstance(raw_ac, str):
+        parts = [p.strip() for p in raw_ac.split(",")]
+        if raw_ac.strip() == "":
+            additional_concepts_by_category = [[], [], [] ,[], []]
+        else:
+            additional_concepts_by_category = [[], [], [] ,[], []]
+            for p in parts:
+                if p in concepts[categories_list[0]]:
+                    additional_concepts_by_category[0].append(p)
+                    continue
+                elif p in concepts[categories_list[1]]:
+                    additional_concepts_by_category[1].append(p)
+                    continue
+                elif p in concepts[categories_list[2]]:
+                    additional_concepts_by_category[2].append(p)
+                    continue
+                elif p in concepts[categories_list[3]]:
+                    additional_concepts_by_category[3].append(p)
+                    continue
+                elif p in concepts[categories_list[4]]:
+                    additional_concepts_by_category[4].append(p)
+                    continue
+            # check if any of the lists are empty, if so, add an empty string
+            # for i in range(len(additional_concepts_by_category)):
+            #     if not additional_concepts_by_category[i]:
+            #         additional_concepts_by_category[i].append("")
+        
+    else:
+        # if it somehow already is a list, leave it
+        additional_concepts_by_category = raw_ac
+    # ───────────────────────────────────────────────────────────────
     image_inp = ex[0]
     image_url_inp = ex[1]
     long_caption_inp = ex[2]
-    country_btn = ex[3]
-    language_btn = ex[4]
     category_btn = ex[5]
     concept_btn = ex[6]
-    additional_concepts_by_category = ex[7]
+    # additional_concepts_by_category = ex[7]
     exampleid_btn = ex[8]
-    additional_concepts_by_category = [[] if (len(cat_concept)==1 and cat_concept[0]=='') else cat_concept for cat_concept in additional_concepts_by_category]
+    # additional_concepts_by_category = [[] if (len(cat_concept)==1 and cat_concept[0]=='') else cat_concept for cat_concept in additional_concepts_by_category]
     
     # import pdb; pdb.set_trace()
     # # excluded_btn = ex[10] # TODO: add functionality that if True "exclude" button changes to "excluded"
@@ -311,6 +442,16 @@ def handle_click_example(user_examples, concepts_dict):
 
     # Need to return values for each category dropdown
     return [image_inp, image_url_inp, long_caption_inp, exampleid_btn, category_btn, concept_btn] + additional_concepts_by_category + [True]
+    # return [
+    #     image_inp,
+    #     image_url_inp,
+    #     long_caption_inp,
+    #     exampleid_btn,
+    #     category_btn,
+    #     concept_btn,
+    #     *additional_concepts_by_category,
+    #     True  # loading_example flag
+    # ]
 
 
 def is_password_correct(hashed_password, entered_password):
@@ -352,16 +493,30 @@ def select_faces_to_hide(image, blur_faces_ids):
         # pdb.set_trace()
         # Draw detections with IDs
         for face_id, face_data in enumerate(faces.values(), start=1):
-            # Get face coordinates
-            facial_area = face_data['facial_area']
-            x1, y1, x2, y2 = facial_area
-            
-            # Draw rectangle around face
-            cv2.rectangle(face_images, (x1, y1), (x2, y2), (0, 0, 255), 2)
-            
-            # Add ID text
-            cv2.putText(face_images, f"ID: {face_id}", (x1, y1 - 10),
-                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
+            x1, y1, x2, y2 = face_data['facial_area']
+            box_h = y2 - y1
+
+            # 1) dynamic scale & thickness
+            scale     = max(0.5, box_h / 150)
+            thickness = max(1, int(box_h / 200))
+
+            # 2) prepare text & size
+            text       = f"ID:{face_id}"
+            font       = cv2.FONT_HERSHEY_SIMPLEX
+            (tw, th), baseline = cv2.getTextSize(text, font, scale, thickness)
+
+            # 3) background rectangle (semi‐opaque or solid)
+            bg_tl = (x1, y1 - th - baseline - 4)
+            bg_br = (x1 + tw + 4, y1)
+            cv2.rectangle(face_images, bg_tl, bg_br, (0,0,0), cv2.FILLED)
+
+            # 4) put contrasting text
+            cv2.putText(face_images, text,
+                        (x1 + 2, y1 - baseline - 2),
+                        font, scale, (255,255,255), thickness, cv2.LINE_AA)
+
+            # 5) draw the face box (optional: use same contrasting color)
+            cv2.rectangle(face_images, (x1, y1), (x2, y2), (0,255,0), thickness)
         # Update face count
         face_count = len(faces)
         blur_faces_ids = gr.update(choices=[f"Face ID: {i}" for i in range(1, face_count + 1)])

ui/layout.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import time
 
 from logic.data_utils import CustomHFDatasetSaver
 from data.lang2eng_map import lang2eng_mapping
@@ -9,6 +10,7 @@ from functools import partial
 
 from .selection_page import build_selection_page
 from .main_page import build_main_page
+from .main_page import sort_with_pyuca
 
 def get_key_by_value(dictionary, value):
     for key, val in dictionary.items():
@@ -25,22 +27,62 @@ def load_concepts(category, concept_btn, local_storage, loading_example, concept
         # I'm doing this to avoid the case where the user load a previous example and the concept 'reamins' selected even if category changed
         if loading_example:
             concept_val = concept_btn if concept_btn else None
-        return gr.update(choices=sorted(concepts[country][lang2eng_mapping.get(lang, lang)][category]), value=concept_val), False
+        if country is None or lang is None:
+            return gr.update(choices=[], value=None), False
+        else:
+            return gr.update(choices=sort_with_pyuca(concepts[country][lang2eng_mapping.get(lang, lang)][category]), value=concept_val), False
     else:
-        return gr.update(choices=[], value=None), False
+        concepts_list = []
+        # cats = []  # FIXME: Assumes concepts are unique across all categories
+        if country is None or lang is None:
+            return gr.update(choices=[], value=None), False
+        else:
+            for cat in concepts[country][lang]:
+                for concept in concepts[country][lang][cat]:
+                    # cats.append(cat)
+                    concepts_list.append(concept)
+            return gr.update(choices=sort_with_pyuca(concepts_list), value=None), False
+        # return gr.update(choices=[], value=None), False
+
+def update_category(category, concept_btn, local_storage, loading_example, concepts):
+    country, lang, _, _ = local_storage
+    if not category and concept_btn:
+        # FIXME: Assumes unique concepts across categories
+        for cat in concepts[country][lang2eng_mapping.get(lang, lang)]:
+            for concept in concepts[country][lang2eng_mapping.get(lang, lang)][cat]:
+                if concept == concept_btn:
+                    category = cat
+        return gr.update(choices=sort_with_pyuca(concepts[country][lang2eng_mapping.get(lang, lang)]), value=category), True
+    else:
+        # import pdb; pdb.set_trace()
+        if country is None or lang is None:
+            return gr.update(choices=[], value=None), False
+        else:
+            return gr.update(choices=sort_with_pyuca(concepts[country][lang2eng_mapping.get(lang, lang)]), value=category), False
+
 
 def switch_ui(country, language, username, password, flag=False, metadata_dict=None):
+    # wait for 2 seconds
     print(f"Language: {language}, Country: {country}")
 
+    if not country or not language:
+        gr.Warning(f"⚠️ Please select Country and Language first.",  duration=3)
+        return
+
     # Hide the selection page and show the main UI.
     if flag:
+        gr.Info(f"Loading the Language Selection UI",  duration=3)
+        time.sleep(2)
         local_storage = [None, None, "", ""]
+        countries = sort_with_pyuca(list(metadata_dict.keys()))
         return (local_storage, gr.update(visible=flag), gr.update(visible=not flag), 
                 gr.update(visible=not flag), 
-                gr.update(choices=list(metadata_dict.keys()), label="Country", value=None), 
+                gr.update(choices=countries, label="Country", value=None), 
                 gr.update(value=None, choices=[], label="Language", allow_custom_value=False, interactive=False))
     
     else:
+        gr.Info(f"Loading the Main UI",  duration=3)
+        time.sleep(2)
         local_storage = [country, language, username, password]
         return local_storage, gr.update(visible=flag), gr.update(visible=not flag), gr.update(visible=not flag)
 
@@ -54,7 +96,12 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
         }
         .compact-btn {
         }
+        #image_inp img {
+            object-fit: contain;        /* make sure the full image shows */
+            height: 460px;           /* set a fixed height */
+        }
     """
+    ############################################################################
     with gr.Blocks(css=custom_css) as ui:
         local_storage = gr.State([None, None, "", ""])
         loading_example = gr.State(False) # to check if the values are loaded from a user click on an example in 
@@ -71,6 +118,7 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
         image_inp = cmp_main_ui["image_inp"]
         image_url_inp = cmp_main_ui["image_url_inp"]
         long_caption_inp = cmp_main_ui["long_caption_inp"]
+        num_words_inp = cmp_main_ui["num_words_inp"]
         category_btn = cmp_main_ui["category_btn"]
         concept_btn = cmp_main_ui["concept_btn"]
         category_concept_dropdowns = cmp_main_ui["category_concept_dropdowns"]
@@ -104,6 +152,15 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
             inputs=[category_btn, concept_btn, local_storage, loading_example],
             outputs=[concept_btn, loading_example]
         )
+        concept_btn.change(
+            fn=partial(update_category, concepts=concepts_dict),
+            inputs=[category_btn, concept_btn, local_storage, loading_example],
+            outputs=[category_btn, loading_example]
+        ).then(
+            fn=partial(load_concepts, concepts=concepts_dict),
+            inputs=[category_btn, concept_btn, local_storage, gr.State(True)],
+            outputs=[concept_btn, loading_example]
+        )
         ####
 
         # is_blurred = gr.State(False)  # Initialize as False
@@ -114,6 +171,12 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
             # gr.Warning(f"⚠️ The image URL is not valid. Please provide a valid image URL.")
 
         # Event listeners
+        gr.on(
+            triggers=[country_choice.change, language_choice.change],
+            fn=validate_metadata,
+            inputs=[country_choice, language_choice],
+            outputs=[proceed_btn],
+        )
         gr.on(
             triggers=[image_url_inp.change],
             fn=update_image,
@@ -136,10 +199,17 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
         gr.on(
             triggers=[image_inp.change],
             fn=validate_inputs,
-            inputs=[image_inp, ori_img], # is_blurred
+            inputs=[image_inp, ori_img, concept_btn], # is_blurred
             outputs=[submit_btn, image_inp, ori_img], # is_blurred
         )
 
+        gr.on(
+            triggers=[long_caption_inp.change],
+            fn=count_words,
+            inputs=[long_caption_inp, language_choice],
+            outputs=[num_words_inp],
+        )
+
         # Clear Button
         clear_btn.click(
             fn=clear_data,
@@ -257,7 +327,7 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
                 category_concept_dropdowns[0], category_concept_dropdowns[1], category_concept_dropdowns[2], 
                 category_concept_dropdowns[3], category_concept_dropdowns[4]
             ],
-        ).then(
+        ).success(
             fn=partial(switch_ui, flag=True, metadata_dict=metadata_dict),
             inputs=[country_choice, language_choice, username, password],
             outputs=[local_storage, selection_page, main_ui_placeholder, browse_data_placeholder, country_choice, language_choice],
@@ -311,7 +381,7 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
             list(data_outputs.values()),
             None,
         ).success(
-            fn=clear_data,
+            fn=partial(clear_data, "submit"),
             outputs=[
                 image_inp, image_url_inp, long_caption_inp, exampleid_btn, 
                 category_btn, concept_btn,
@@ -380,7 +450,7 @@ def build_ui(concepts_dict, metadata_dict, HF_API_TOKEN, HF_DATASET_NAME):
             ],
             outputs=None
         ).success(
-            fn=clear_data,
+            fn=partial(clear_data, "remove"),
             outputs=[
                 image_inp, image_url_inp, long_caption_inp, exampleid_btn, 
                 category_btn, concept_btn, 

ui/main_page.py

@@ -4,6 +4,13 @@ from gradio_modal import Modal
 from data.lang2eng_map import lang2eng_mapping
 from data.words_map import words_mapping
 import datetime
+from pyuca import Collator
+
+
+def sort_with_pyuca(strings):
+    collator = Collator()
+    return sorted(strings, key=collator.sort_key)
+
 
 def build_main_page(concepts_dict, metadata_dict, local_storage):
     try:
@@ -19,8 +26,19 @@ def build_main_page(concepts_dict, metadata_dict, local_storage):
 
         with open(metadata_dict["USA"]["English"]["Instructions"], "r", encoding="utf-8") as f:
             INST_TEXT = f.read()
-        
-        intro_text_inp = gr.Markdown(TASK_TEXT)
+
+        gr.Markdown("# Wonders: Multicultural Images and Captions for Inclusive AI")
+        gr.Markdown("Help us collect culturally rich images and captions to improve AI for everyone!")
+        gr.Markdown("Choose a concept, upload an image showing it in a typical local situation, and write a detailed description about the image.<br> For more information, see the overviews below or click on 'Show instructions' for detailed guidelines.")
+        gr.Markdown(""" \
+            ### Notes
+            - By participating in this task, you agree to donate images and captions under [CC BY license](https://creativecommons.org/licenses/by/4.0/), which will allow us to share the data with others to improve AI.
+            - You will be able to **update or remove** any provided data at any time if you wish so.
+            - Participants that provide more data, across more concepts and of high quality (see "Instructions" button) will be **rewarded** (see TODO).
+            """
+        )
+        # with gr.Accordion("📘 Show task overview", open=False):
+        intro_text_inp = gr.Markdown(TASK_TEXT, visible=False)
 
         # gr.Markdown("## Data Collection")
         with gr.Row(equal_height=True):
@@ -33,25 +51,64 @@ def build_main_page(concepts_dict, metadata_dict, local_storage):
         with gr.Row(equal_height=True, ):
             with gr.Column():
                 # Main category and concept row - SINGLE SELECTION
-                with gr.Row():
-                    categories = concepts_dict["USA"]["English"]
-                    category_btn = gr.Dropdown(choices=categories.keys(), interactive=True, label="Main Category", 
-                                              allow_custom_value=False, elem_id="category_btn", multiselect=False, value=None)
-                    concept_btn = gr.Dropdown(choices=[], interactive=True, label="Main Concept", 
-                                             allow_custom_value=True, elem_id="concept_btn", multiselect=False)
+                with gr.Group():
+                    gr.Markdown("### Main Concept")
+                    gr.Markdown("""\
+                        Select the main concept and category for which you want to share data.<br>
+                        If you want to add a new concept, you can just type it in the same box (after selecting its category).
+                        """
+                    )
+                    with gr.Row():
+                        # Use concepts_dict to populate the dropdown
+                        categories = concepts_dict["USA"]["English"]
+                        category_btn = gr.Dropdown(choices=sort_with_pyuca(categories.keys()), interactive=True, label="Main Category", 
+                                                allow_custom_value=False, elem_id="category_btn", multiselect=False, value=None)
+                        concept_btn = gr.Dropdown(choices=[], interactive=True, label="Main Concept", 
+                                                allow_custom_value=True, elem_id="concept_btn", multiselect=False)
                 
-                image_inp = gr.Image(label="Image", elem_id="image_inp", format="png", height=512, width=768)
-                with gr.Row():
-                    hide_all_faces_btn = gr.Button("👤 Hide All Faces", elem_id="hide_all_faces_btn")
-                    hide_faces_btn = gr.Button("👤 Hide Specific Faces", elem_id="hide_faces_btn")
-                    unhide_faces_btn = gr.Button("👀 Unhide Faces", elem_id="unhide_faces_btn")
-                image_url_inp = gr.Textbox(label="Image URL (Optional, if not uploading an image)", type="text", elem_id="image_url_inp")                
+                with gr.Group():
+                    gr.Markdown("### Image")
+                    with gr.Accordion("📘 An image of the main concept in typical contexts (click to read more)", open=False):
+                        gr.Markdown("""\=
+                            An image where the *main concept is clearly visible*
+                            - in typical contexts in your country, and
+                            - with other objects/people when possible
+                            
+                            Pictures taken by yourself are preferred.
+                            If you want to use an image from the Web, directly add its URL below.
+                            - Please use publicly-licensed images (e.g., from pexels.com or freepik.com)
+                            
+                            For more details, click on “Show instructions” below.
+                            """
+                        )
+                    image_url_inp = gr.Textbox(label="Image URL (Optional, if not uploading an image)", type="text", elem_id="image_url_inp")                
+                    image_inp = gr.Image(label="Image", elem_id="image_inp", format="png", height=512, width=768)
+                    with gr.Row():
+                        hide_all_faces_btn = gr.Button("👤 Hide All Faces", elem_id="hide_all_faces_btn")
+                        hide_faces_btn = gr.Button("👤 Hide Specific Faces", elem_id="hide_faces_btn")
+                        unhide_faces_btn = gr.Button("👀 Unhide Faces", elem_id="unhide_faces_btn")
 
             with gr.Column():
                 # short_caption_inp = gr.Textbox(lines=2, label="Short Description", elem_id="short_caption_inp")
-                long_caption_inp = gr.Textbox(lines=6, label="Description", elem_id="long_caption_inp")
+                with gr.Group():
+                    gr.Markdown("### Description")
+                    with gr.Accordion("📘 A detailed description (around 40 words covering who?, what? and where?) for the image (click to read more)", open=False):
+                        gr.Markdown("""\
+                            A long image description (around 40 words) with extensive and detailed visual information.<br>
+                            Descriptions must be *objective*: focus on how you would describe the image to someone who can’t see it, without your own opinions/speculations.
+                            The text needs to *include the main concept* and describes the content of the image in detail by including:
+                            - **Who?** The visual *appearance* and observable *emotions* (e.g., “is smiling”) of persons and animals.
+                            - **What?** The *actions* performed in the image.
+                            - **Where?** The *setting* of the image, including the size, color and relationships between objects.
+                            
+                            For more details, click on “Show instructions” below.
+                            """
+                        )
+                    long_caption_inp = gr.Textbox(lines=6, label="Description", elem_id="long_caption_inp")
+                    num_words_inp = gr.Textbox(lines=1, label="Number of words", elem_id="num_words", interactive=False, value=0)
+                    # num_words_inp = gr.Markdown("Number of words", elem_id="num_words")
 
-                categories_list = sorted(list(concepts_dict["USA"]["English"].keys()))[:5]
+                categories_list = sort_with_pyuca(list(concepts_dict["USA"]["English"].keys()))
                 
                 def create_category_dropdown(category, index):
                     original_category = category
@@ -62,7 +119,7 @@ def build_main_page(concepts_dict, metadata_dict, local_storage):
                         display_category = original_category
                     
                     category_choices = concepts_dict[country][lang2eng_mapping.get(lang, lang)][original_category]
-                    sorted_choices = sorted(category_choices)
+                    sorted_choices = sort_with_pyuca(category_choices)
                     
                     dropdown = gr.Dropdown(
                         choices=sorted_choices, 
@@ -77,24 +134,27 @@ def build_main_page(concepts_dict, metadata_dict, local_storage):
                 
                 category_concept_dropdowns = []
                 
-                # First row - categories 1 and 2
-                with gr.Row():
-                    dropdown1 = create_category_dropdown(categories_list[0], 0)
-                    category_concept_dropdowns.append(dropdown1)
-                    
-                    dropdown2 = create_category_dropdown(categories_list[1], 1)
-                    category_concept_dropdowns.append(dropdown2)
+                with gr.Group():
+                    gr.Markdown("### Additional concepts (optional)")
+                    gr.Markdown("Tag any other concept that is visible in the image.")
+                    # First row - categories 1 and 2
+                    with gr.Row():
+                        dropdown1 = create_category_dropdown(categories_list[0], 0)
+                        category_concept_dropdowns.append(dropdown1)
+                        
+                        dropdown2 = create_category_dropdown(categories_list[1], 1)
+                        category_concept_dropdowns.append(dropdown2)
 
-                # Second row - categories 3 and 4
-                # with gr.Row():
-                    dropdown3 = create_category_dropdown(categories_list[2], 2)
-                    category_concept_dropdowns.append(dropdown3)
-                    
-                    dropdown4 = create_category_dropdown(categories_list[3], 3)
-                    category_concept_dropdowns.append(dropdown4)
+                    # Second row - categories 3 and 4
+                    # with gr.Row():
+                        dropdown3 = create_category_dropdown(categories_list[2], 2)
+                        category_concept_dropdowns.append(dropdown3)
+                        
+                        dropdown4 = create_category_dropdown(categories_list[3], 3)
+                        category_concept_dropdowns.append(dropdown4)
 
-                    dropdown5 = create_category_dropdown(categories_list[4], 4)
-                    category_concept_dropdowns.append(dropdown5)
+                        dropdown5 = create_category_dropdown(categories_list[4], 4)
+                        category_concept_dropdowns.append(dropdown5)
 
                 # Third row - category 5 and instructions button
                 with gr.Row(equal_height=True):
@@ -137,6 +197,7 @@ def build_main_page(concepts_dict, metadata_dict, local_storage):
         "image_inp": image_inp,
         "image_url_inp": image_url_inp,
         "long_caption_inp": long_caption_inp,
+        "num_words_inp": num_words_inp,
         "category_btn": category_btn,
         "concept_btn": concept_btn,
         "category_concept_dropdowns": category_concept_dropdowns,

ui/selection_page.py

@@ -2,12 +2,15 @@ import os.path
 import gradio as gr
 from functools import partial
 
+from .main_page import sort_with_pyuca
+
+
 def update_language_options(selected_country, metadata):
     with open(metadata["USA"]["English"]["Intro"], "r", encoding="utf-8") as f:
-            INTRO_TEXT = f.read() # default
+        INTRO_TEXT = f.read() # default
     # Retrieve the list of languages available for the selected country.
     if selected_country in metadata:
-        languages = list(metadata[selected_country].keys())
+        languages = sort_with_pyuca(list(metadata[selected_country].keys()))
         if len(languages) == 0:
             gr.Warning("No languages available for the selected country.")
             return gr.Dropdown(choices=[], interactive=False, value=None), gr.Markdown(INTRO_TEXT)
@@ -17,40 +20,43 @@ def update_language_options(selected_country, metadata):
             with open(fn, "r", encoding="utf-8") as f:
                 INTRO_TEXT = f.read()
         # Use gr.Dropdown.update to change the choices of the language dropdown.
-        return gr.Dropdown(choices=languages, interactive=True, value=None, allow_custom_value=False), gr.Markdown(INTRO_TEXT)
+        val = languages[0] if len(languages) == 1 else None
+        return gr.Dropdown(choices=languages, interactive=True, value=val, allow_custom_value=False), gr.Markdown(INTRO_TEXT)
     else:
         return gr.Dropdown(choices=[], interactive=False, value=None, allow_custom_value=False), gr.Markdown(INTRO_TEXT)
 
+
 def build_selection_page(metadata_dict):
     with gr.Column(visible=True, elem_classes=["compact-container"]) as selection_page:
-            with gr.Row():
-                with open(metadata_dict["USA"]["English"]["Intro"], "r", encoding="utf-8") as f:
-                    INTRO_TEXT = f.read()
-                intro_markdown = gr.Markdown(INTRO_TEXT)
-
-            gr.Markdown("## Please select your country")
-            
-            country_choice = gr.Dropdown(
-                choices=list(metadata_dict.keys()), label="Country", allow_custom_value=False
-            )
-
-            language_choice = gr.Dropdown(
-                choices=[], 
-                label="Language",
-                allow_custom_value=False,
-                interactive=False  # Initially disabled.
-            )
-            
-            # When the country selection changes, update the language dropdown.
-            country_choice.change(
-                fn=partial(update_language_options, metadata=metadata_dict),
-                inputs=country_choice,
-                outputs=[language_choice, intro_markdown]
-            )
-            with gr.Row():
-                username = gr.Textbox(label="Email (optional)", type="email", elem_id="username_text")
-                password = gr.Textbox(label="Password (optional)", type="password", elem_id="password_text")
-
-            proceed_btn = gr.Button("Proceed")
+        with gr.Row():
+            with open(metadata_dict["USA"]["English"]["Intro"], "r", encoding="utf-8") as f:
+                INTRO_TEXT = f.read()
+            intro_markdown = gr.Markdown(INTRO_TEXT)
+
+        gr.Markdown("## Please select your country")
+        
+        countries = sort_with_pyuca(list(metadata_dict.keys()))
+        country_choice = gr.Dropdown(
+            choices=countries, label="Country", allow_custom_value=False, value=None,
+        )
+
+        language_choice = gr.Dropdown(
+            choices=[], 
+            label="Language",
+            allow_custom_value=False,
+            interactive=False  # Initially disabled.
+        )
+        
+        # When the country selection changes, update the language dropdown.
+        country_choice.change(
+            fn=partial(update_language_options, metadata=metadata_dict),
+            inputs=country_choice,
+            outputs=[language_choice, intro_markdown]
+        )
+        with gr.Row():
+            username = gr.Textbox(label="Email (optional)", type="email", elem_id="username_text")
+            password = gr.Textbox(label="Password (optional)", type="password", elem_id="password_text")
+
+        proceed_btn = gr.Button("Proceed")
 
     return selection_page, country_choice, language_choice, proceed_btn, username, password, intro_markdown