Update app.py

app.py

@@ -40,7 +40,13 @@ available_models = [] # to be filled in later
   
 def display_chat_history(model_selections):
     eval_item = sample_an_eval_result(eval_results, model_selections)
+    session_id = eval_item["session_id"]
     task = eval_item["task"]
+    task_type = eval_item["task_type"]
+    prediction = eval_item["pred"]
+    gold_answer = eval_item["answer"]
+    correctness = eval_item["correctness"]
+    
     if eval_item["image"]:
         image_path = eval_item["image"]
     else:
@@ -53,12 +59,13 @@ def display_chat_history(model_selections):
         chats_ground += [item_user, item_asst]
     chats_plan = [(chats_plan[i], chats_plan[i+1]) for i in range(0, len(chats_plan), 2)]
     chats_ground = [(chats_ground[i], chats_ground[i+1]) for i in range(0, len(chats_ground), 2)]
+    task_metadata = f"- 🆔: `{session_id}` \n- **Task category**: {task_type}"
     
     if image_path != "":
         image = f'<div style="text-align: center;"> <img src="{image_path}" style="height: 250px;"> </div>'
-        return task, chats_plan, chats_ground, image
+        return task, chats_plan, chats_ground, task_metadata, prediction, gold_answer, correctness, image
     else:
-        return task, chats_plan, chats_ground, f'<div style="text-align: center;"> </div>'
+        return task, chats_plan, chats_ground, task_metadata, prediction, gold_answer, correctness, f'<div style="text-align: center;"> </div>'
 
 
 
@@ -118,6 +125,12 @@ def build_demo(TYPES):
                             image = gr.HTML("", elem_id="input_image")
                             image.change(lambda x: x, inputs=[], outputs=[], scroll_to_output=False, js=js_code)
 
+                with gr.Row():
+                    with gr.Column():
+                        with gr.Accordion("📝 Task Metadata", open=False, elem_classes="accordion-label"):
+                            task_metadata = gr.Markdown("", elem_classes="markdown-text-tiny")
+                            task_metadata.change(lambda x: x, inputs=[], outputs=[], scroll_to_output=False, js=js_code)
+
                 with gr.Row():
                     with gr.Column():
                         gr.Markdown("## 📢 Plan Module Process History", elem_classes="markdown-text")
@@ -127,9 +140,25 @@ def build_demo(TYPES):
                         gr.Markdown("## 📢 Ground Module Process History", elem_classes="markdown-text")
                         Chatbot_Common_Ground = gr.Chatbot(avatar_images=["human_icon.jpeg", "ai_icon.png"], height="auto", container=False, label="Common Ground History", likeable=False, show_share_button=False, show_label=True, elem_classes="chat-common", layout="bubble")
                         Chatbot_Common_Ground.change(lambda x: x, inputs=[], outputs=[], scroll_to_output=False, js=js_code)
+
+                with gr.Row():
+                    with gr.Column():
+                        with gr.Accordion("🙋 Prediction", open=True, elem_classes="accordion-label"):
+                            prediction = gr.Markdown("", elem_classes="markdown-text-tiny")
+                            prediction.change(lambda x: x, inputs=[], outputs=[], scroll_to_output=False, js=js_code)
+                    
+                    with gr.Column():
+                        with gr.Accordion("🔑 Ground-Truth Answer", open=True, elem_classes="accordion-label"):
+                            gold_answer = gr.HTML("", elem_id="ground-truth-answer")
+                            gold_answer.change(lambda x: x, inputs=[], outputs=[], scroll_to_output=False, js=js_code)
+
+                    with gr.Column():
+                        with gr.Accordion("Correctness", open=True, elem_classes="accordion-label"):
+                            correctness = gr.HTML("", elem_id="correct-or-not")
+                            correctness.change(lambda x: x, inputs=[], outputs=[], scroll_to_output=False, js=js_code)
                 
                 # Display chat history when button is clicked
-                btn_show_history.click(fn=display_chat_history, inputs=[selected_models], outputs=[task, Chatbot_Common_Plan, Chatbot_Common_Ground, image])
+                btn_show_history.click(fn=display_chat_history, inputs=[selected_models], outputs=[task, Chatbot_Common_Plan, Chatbot_Common_Ground, task_metadata, prediction, gold_answer, correctness, image])
 
             with gr.TabItem("📮 About Us", elem_id="od-benchmark-tab-table", id=3):
                 gr.Markdown(ABOUT_MD, elem_classes="markdown-text")