hi

app.py

@@ -422,8 +422,23 @@ def create_ui() -> gr.Blocks:
         transform: scale(1.02);
     }
     
-    /* Remove hover effect from other cells */
-    .gr-dataframe td:nth-child(n+2) {
+    /* Make content columns (strengths, weaknesses, speciality) clickable for text expansion */
+    .gr-dataframe td:nth-child(2),
+    .gr-dataframe td:nth-child(3),
+    .gr-dataframe td:nth-child(4) {
+        cursor: pointer;
+        transition: all 0.3s ease;
+    }
+    
+    .gr-dataframe td:nth-child(2):hover,
+    .gr-dataframe td:nth-child(3):hover,
+    .gr-dataframe td:nth-child(4):hover {
+        background-color: rgba(102, 126, 234, 0.08);
+        box-shadow: inset 0 0 0 1px rgba(102, 126, 234, 0.2);
+    }
+    
+    /* Relevance column - not clickable */
+    .gr-dataframe td:nth-child(5) {
         cursor: default;
     }
     
@@ -554,6 +569,7 @@ def create_ui() -> gr.Blocks:
                 with gr.Row():
                     analyze_next_btn = gr.Button("⚡ Analyze Next Repository", variant="primary", size="lg", scale=1)
                     analyze_all_btn = gr.Button("🚀 Analyze All Repositories", variant="secondary", size="lg", scale=1)
+                    reset_all_btn = gr.Button("🔄 Reset Everything", variant="stop", size="lg", scale=1)
                     with gr.Column(scale=2):
                         status_box_analysis = gr.Textbox(label="📈 Analysis Status", interactive=False, lines=2)
                 
@@ -599,6 +615,26 @@ def create_ui() -> gr.Blocks:
                 
                 gr.Markdown("💡 **Tip:** Click on any repository name to explore it in detail!")
                 
+                # Text expansion modal for showing full content
+                with gr.Row():
+                    with gr.Column():
+                        text_expansion_modal = gr.Column(visible=False)
+                        with text_expansion_modal:
+                            gr.Markdown("### 📄 Full Content View")
+                            expanded_content_title = gr.Textbox(
+                                label="Content Type",
+                                interactive=False,
+                                info="Full text content for the selected field"
+                            )
+                            expanded_content_text = gr.Textbox(
+                                label="Full Text",
+                                lines=10,
+                                interactive=False,
+                                show_copy_button=True,
+                                info="Complete untruncated content"
+                            )
+                            close_text_modal_btn = gr.Button("❌ Close", size="lg")
+                
                 # Modal popup for repository action selection
                 with gr.Row():
                     with gr.Column():
@@ -802,14 +838,14 @@ def create_ui() -> gr.Blocks:
             status = "Status: Keywords extracted. User requirements saved for analysis."
             return final_keywords_str, status, user_requirements
 
-        def handle_dataframe_select(evt: gr.SelectData, df_data) -> Tuple[str, Any, Any]:
-            """Handle dataframe row selection - only repo ID column triggers modal."""
+        def handle_dataframe_select(evt: gr.SelectData, df_data) -> Tuple[str, Any, Any, str, str, Any]:
+            """Handle dataframe row selection - repo ID shows modal, content columns show full text."""
             print(f"DEBUG: Selection event triggered!")
             print(f"DEBUG: evt = {evt}")
             print(f"DEBUG: df_data type = {type(df_data)}")
             
             if evt is None:
-                return "", gr.update(visible=False), gr.update()
+                return "", gr.update(visible=False), gr.update(), "", "", gr.update(visible=False)
             
             try:
                 # Get the selected row and column from the event
@@ -817,23 +853,41 @@ def create_ui() -> gr.Blocks:
                 col_idx = evt.index[1]
                 print(f"DEBUG: Selected row {row_idx}, column {col_idx}")
                 
-                # Only respond to clicks on the repo ID column (column 0)
-                if col_idx != 0:
-                    print(f"DEBUG: Clicked on column {col_idx}, ignoring (only repo ID column responds)")
-                    return "", gr.update(visible=False), gr.update()
-                
                 # Handle pandas DataFrame
                 if isinstance(df_data, pd.DataFrame) and not df_data.empty and row_idx < len(df_data):
-                    # Get the repository ID from the first column
-                    repo_id = df_data.iloc[row_idx, 0]  # First column contains repo id
-                    print(f"DEBUG: Extracted repo_id = '{repo_id}'")
                     
-                    # Only proceed if we actually have a repository ID
-                    if repo_id and str(repo_id).strip() and str(repo_id).strip() != 'nan':
-                        clean_repo_id = str(repo_id).strip()
-                        logger.info(f"Showing modal for repository: {clean_repo_id}")
-                        # Show modal and populate selected repo
-                        return clean_repo_id, gr.update(visible=True), gr.update()
+                    # Column mapping: 0=repo, 1=strength, 2=weakness, 3=speciality, 4=relevance
+                    if col_idx == 1:  # Strengths column
+                        full_text = str(df_data.iloc[row_idx, 1])
+                        repo_name = str(df_data.iloc[row_idx, 0])
+                        title = f"Strengths - {repo_name}"
+                        return "", gr.update(visible=False), gr.update(), title, full_text, gr.update(visible=True)
+                    
+                    elif col_idx == 2:  # Weaknesses column
+                        full_text = str(df_data.iloc[row_idx, 2])
+                        repo_name = str(df_data.iloc[row_idx, 0])
+                        title = f"Weaknesses - {repo_name}"
+                        return "", gr.update(visible=False), gr.update(), title, full_text, gr.update(visible=True)
+                    
+                    elif col_idx == 3:  # Speciality column
+                        full_text = str(df_data.iloc[row_idx, 3])
+                        repo_name = str(df_data.iloc[row_idx, 0])
+                        title = f"Speciality - {repo_name}"
+                        return "", gr.update(visible=False), gr.update(), title, full_text, gr.update(visible=True)
+                    
+                    elif col_idx == 0:  # Repository name column - show action modal
+                        repo_id = df_data.iloc[row_idx, 0]
+                        print(f"DEBUG: Extracted repo_id = '{repo_id}'")
+                        
+                        if repo_id and str(repo_id).strip() and str(repo_id).strip() != 'nan':
+                            clean_repo_id = str(repo_id).strip()
+                            logger.info(f"Showing modal for repository: {clean_repo_id}")
+                            return clean_repo_id, gr.update(visible=True), gr.update(), "", "", gr.update(visible=False)
+                    
+                    # For other columns (like relevance), do nothing
+                    else:
+                        print(f"DEBUG: Clicked on column {col_idx}, no action defined")
+                        return "", gr.update(visible=False), gr.update(), "", "", gr.update(visible=False)
                 else:
                     print(f"DEBUG: df_data is not a DataFrame or row_idx {row_idx} out of range")
                 
@@ -841,7 +895,7 @@ def create_ui() -> gr.Blocks:
                 print(f"DEBUG: Exception occurred: {e}")
                 logger.error(f"Error handling dataframe selection: {e}")
             
-            return "", gr.update(visible=False), gr.update()
+            return "", gr.update(visible=False), gr.update(), "", "", gr.update(visible=False)
 
         def handle_analyze_all_repos(repo_ids: List[str], user_requirements: str, progress=gr.Progress()) -> Tuple[pd.DataFrame, str, pd.DataFrame, Any]:
             """Analyzes all repositories in the CSV file with progress tracking."""
@@ -973,6 +1027,71 @@ def create_ui() -> gr.Blocks:
             """Handle closing the modal."""
             return gr.update(visible=False)
 
+        def handle_close_text_modal() -> Any:
+            """Handle closing the text expansion modal."""
+            return gr.update(visible=False)
+
+        def handle_reset_everything() -> Tuple[List[str], int, str, pd.DataFrame, pd.DataFrame, Any, Any, Any, List[Dict[str, str]], str, str, str]:
+            """Reset everything to initial state - clear all data, CSV, and UI components."""
+            try:
+                # Clear the CSV file
+                if os.path.exists(CSV_FILE):
+                    os.remove(CSV_FILE)
+                    logger.info("CSV file deleted for reset")
+                
+                # Create empty dataframe
+                empty_df = pd.DataFrame(columns=["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
+                
+                # Reset state variables
+                repo_ids_reset = []
+                current_idx_reset = 0
+                user_requirements_reset = ""
+                
+                # Reset status
+                status_reset = "Status: Everything has been reset. Ready to start fresh!"
+                
+                # Reset UI components
+                current_requirements_reset = "No requirements extracted yet."
+                extracted_keywords_reset = ""
+                
+                # Reset chatbot to initial message
+                chatbot_reset = [{"role": "assistant", "content": CHATBOT_INITIAL_MESSAGE}]
+                
+                logger.info("Complete system reset performed")
+                
+                return (
+                    repo_ids_reset,           # repo_ids_state
+                    current_idx_reset,        # current_repo_idx_state  
+                    user_requirements_reset,  # user_requirements_state
+                    empty_df,                 # df_output
+                    empty_df,                 # top_repos_df
+                    gr.update(visible=False), # top_repos_section
+                    gr.update(visible=False), # repo_action_modal
+                    gr.update(visible=False), # text_expansion_modal
+                    chatbot_reset,            # chatbot
+                    status_reset,             # status_box_analysis
+                    current_requirements_reset, # current_requirements_display
+                    extracted_keywords_reset  # extracted_keywords_output
+                )
+                
+            except Exception as e:
+                logger.error(f"Error during reset: {e}")
+                error_status = f"Reset failed: {e}"
+                return (
+                    [],                       # repo_ids_state
+                    0,                        # current_repo_idx_state
+                    "",                       # user_requirements_state
+                    pd.DataFrame(),           # df_output
+                    pd.DataFrame(),           # top_repos_df
+                    gr.update(visible=False), # top_repos_section
+                    gr.update(visible=False), # repo_action_modal
+                    gr.update(visible=False), # text_expansion_modal
+                    [{"role": "assistant", "content": CHATBOT_INITIAL_MESSAGE}], # chatbot
+                    error_status,             # status_box_analysis
+                    "No requirements extracted yet.", # current_requirements_display
+                    ""                        # extracted_keywords_output
+                )
+
         # --- Component Event Wiring ---
         
         # Initialize chatbot with welcome message on app load
@@ -1062,18 +1181,30 @@ def create_ui() -> gr.Blocks:
             outputs=[repo_action_modal]
         )
         
+        # Text expansion modal events
+        close_text_modal_btn.click(
+            fn=handle_close_text_modal,
+            outputs=[text_expansion_modal]
+        )
+        
         # Add dataframe selection event
         df_output.select(
             fn=handle_dataframe_select,
             inputs=[df_output],
-            outputs=[selected_repo_display, repo_action_modal, tabs]
+            outputs=[selected_repo_display, repo_action_modal, tabs, expanded_content_title, expanded_content_text, text_expansion_modal]
         )
         
         # Add selection event for top repositories dataframe too
         top_repos_df.select(
             fn=handle_dataframe_select,
             inputs=[top_repos_df],
-            outputs=[selected_repo_display, repo_action_modal, tabs]
+            outputs=[selected_repo_display, repo_action_modal, tabs, expanded_content_title, expanded_content_text, text_expansion_modal]
+        )
+        
+        # Reset button event
+        reset_all_btn.click(
+            fn=handle_reset_everything,
+            outputs=[repo_ids_state, current_repo_idx_state, user_requirements_state, df_output, top_repos_df, top_repos_section, repo_action_modal, text_expansion_modal, chatbot, status_box_analysis, current_requirements_display, extracted_keywords_output]
         )
         
     return app

chatbot_page.py

@@ -4,9 +4,11 @@ import os
 
 # System prompt for the chatbot
 CHATBOT_SYSTEM_PROMPT = (
-    "You are a helpful and friendly assistant. Your goal is to help the user discover their ideal Hugging Face repository. "
-    "Engage in a natural conversation, ask clarifying questions about their needs, such as their use case, preferred programming languages, or specific features they are looking for. "
+    "Your goal is to undertsand what the user needs in their ideal Hugging Face repository. Specifically a Hugging Face Space. "
+    "Engage in a natural conversation, ask clarifying questions about their needs, such as their use case or specific features they are looking for. "
     "Keep your responses concise and focused on helping the user."
+    "When you feel you have gathered enough detailed information about their requirements, ask the user to end chat."
+    
 )
 
 # Store the conversation
@@ -44,10 +46,12 @@ def extract_keywords_from_conversation(history):
     # Combine all user and assistant messages into a single string
     conversation = "\n".join([f"User: {msg[0]}\nAssistant: {msg[1]}" for msg in history if msg[1]])
     system_prompt = (
-        "You are an expert at helping users find open-source repos on Hugging Face. "
-        "Given a conversation, extract about 5 keywords that would be most useful for searching Hugging Face repos to find the most relevant results for the user. "
+        "You are an expert at helping find Hugging Face Spaces. You must look at the conversation carefully."
+        "Given a conversation, extract about 5 keywords that would be most useful for searching Hugging Face Spaces.. "
         "Return only the keywords as a comma-separated list."
         "Use keywords that are specific to the user's use case and features they are looking for."
+        "Dont use very generic search words like programming, language, hugging face, ML, AI, etc."
+        
     )
     user_prompt = (
         "Conversation:\n" + conversation + "\n\nExtract about 5 keywords for Hugging Face repo search."