revert

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
 import time
 import pandas as pd
-import asyncio
 from uuid import uuid4
 from gradio_client import Client, handle_file
 
-# Sample questions for examples
+# Sample questions for examples 
 SAMPLE_QUESTIONS = {
     "Deforestation Analysis": [
         "What are the main deforestation hotspots in Ecuador?",
@@ -24,130 +23,145 @@ SAMPLE_QUESTIONS = {
     ]
 }
 
-# ------------------------
-# NEW: Generate readable summary from WHISP API DataFrame
-# ------------------------
-def generate_summary(df: pd.DataFrame) -> str:
-    """Generate human-readable summary from WHISP API output"""
-    try:
-        # Convert DataFrame to dict for easier access
-        data = {row[0]: row[1] for row in df.values}
-
-        country = data.get("Country", "Unknown")
-        admin = data.get("Admin_Level_1", "Unknown region")
-        area = data.get("Area", "Unknown")
-        risk_level = data.get("Risk level", "Unknown")
-        risk_pcrop = data.get("risk_pcrop", "Unknown")
-        risk_acrop = data.get("risk_acrop", "Unknown")
-        risk_timber = data.get("risk_timber", "Unknown")
-        def_after_2020 = data.get("TMF_def_after_2020", "0")
-
-        summary = f"""
-**Analysis Summary**  
-
-The uploaded GeoJSON corresponds to a region in **{admin}, {country}**, covering about **{area} hectares**.  
-
-- **Overall Deforestation Risk**: The area is classified as **{risk_level} risk**, meaning there is a likelihood that agricultural or timber activities are linked to deforestation.  
-- **Perennial Crops Risk**: The risk from crops such as cocoa, coffee, and oil palm is **{risk_pcrop}**.  
-- **Annual Crops Risk**: The risk from crops like maize or soy is **{risk_acrop}**.  
-- **Timber Risk**: The risk linked to timber extraction is **{risk_timber}**.  
-- **Recent Deforestation**: Since 2020, about **{def_after_2020} hectares** of natural forest have been cleared in this area.  
-
-This indicates that while some crops may not be a major concern, perennial crops and timber extraction could present notable risks to deforestation-free compliance.  
-"""
-        return summary
-    except Exception as e:
-        return f"⚠️ Could not generate summary: {str(e)}"
-
-# ------------------------
-# GeoJSON upload handler
-# ------------------------
 def handle_geojson_upload(file):
     """Handle GeoJSON file upload and call WHISP API"""
     if file is not None:
         try:
             # Initialize WHISP API client
             client = Client("https://giz-chatfed-whisp.hf.space/")
-
+            
             # Call the API with the uploaded file
             result = client.predict(
                 file=handle_file(file.name),
                 api_name="/get_statistics"
             )
-
+            
             # Convert result to DataFrame
             df = pd.DataFrame(result['data'], columns=result['headers'])
-
-            # Generate human-readable summary
-            summary = generate_summary(df)
-
+            
             return (
                 "✅ GeoJSON file processed successfully! Analysis results are displayed below.",
                 gr.update(visible=True),  # upload_status
-                gr.update(value=df, visible=True),  # results_table
-                summary  # NEW: summary to send into chatbot
+                gr.update(value=df, visible=True)  # results_table
             )
+            
         except Exception as e:
             error_msg = f"❌ Error processing GeoJSON file: {str(e)}"
-            return (error_msg, gr.update(visible=True), gr.update(visible=False), None)
+            return (
+                error_msg,
+                gr.update(visible=True),  # upload_status
+                gr.update(visible=False)  # results_table
+            )
     else:
-        return ("", gr.update(visible=False), gr.update(visible=False), None)
+        return (
+            "",
+            gr.update(visible=False),  # upload_status
+            gr.update(visible=False)   # results_table
+        )
+
+
+def retrieve_paragraphs(query):
+
+    """Connect to retriever and retrieve paragraphs"""
+    
+    if file is not None:
+        try:
+            # Initialize WHISP API client
+            client = Client("https://giz-eudr-retriever.hf.space/")
+            
+            # Call the API with the uploaded file
+            result = client.predict(
+                file=handle_file(file.name),
+                api_name="/retrieve"
+            )
+            
+            return (
+                "These are the most relevant findings.",
+                gr.update(visible=True),  # upload_status
+                gr.update(value=results, visible=True)  # results_table
+            )
+            
+        except Exception as e:
+            error_msg = f"❌ Error creating a response {str(e)}"
+            return (
+                error_msg,
+                gr.update(visible=True),  # upload_status
+                gr.update(visible=False)  # results_table
+            )
+    
+    else:
+        return (
+            "",
+            gr.update(visible=False),  # upload_status
+            gr.update(visible=False)   # results_table
+         )
+
 
-# ------------------------
-# Chat functions
-# ------------------------
 def start_chat(query, history):
+    """Start a new chat interaction"""
     history = history + [(query, None)]
     return gr.update(interactive=False), gr.update(selected=1), history
 
 def finish_chat():
+    """Finish chat and reset input"""
     return gr.update(interactive=True, value="")
 
-async def chat_response(query, history, method, country, uploaded_file, geojson_summary):
+async def chat_response(query, history, method, country, uploaded_file):
+    """Generate chat response based on method and inputs"""
+    
+    # Validate inputs based on method
     if method == "Upload GeoJSON":
         if uploaded_file is None:
             warning_message = "⚠️ **No GeoJSON file uploaded.** Please upload a GeoJSON file first."
             history[-1] = (query, warning_message)
             yield history, ""
             return
-        else:
-            if geojson_summary:
-                full_response = geojson_summary
-            else:
-                full_response = f"Based on your uploaded GeoJSON file, I can help you analyze the deforestation patterns and EUDR compliance aspects in your area of interest."
-    else:
+    else:  # "Talk to Reports"
         if not country:
             warning_message = "⚠️ **No country selected.** Please select a country to analyze reports."
             history[-1] = (query, warning_message)
             yield history, ""
             return
-        else:
-            full_response = f"Based on EUDR reports for {country}, I can help you understand deforestation patterns and compliance requirements."
-
+    
+    # Simulate processing time
     response = ""
+    if method == "Upload GeoJSON":
+        full_response = f"Based on your uploaded GeoJSON file, I can help you analyze the deforestation patterns and EUDR compliance aspects in your area of interest. Your question: '{query}' is being processed against the geographic data you provided."
+    else:
+        full_response = f"Based on EUDR reports for {country}, I can help you understand deforestation patterns and compliance requirements. Your question: '{query}' is being analyzed against our {country} database."
+    
+    # Simulate streaming response
     words = full_response.split()
     for word in words:
         response += word + " "
         history[-1] = (query, response)
         yield history, "**Sources:** Sample source documents would appear here..."
-        await asyncio.sleep(0.02)
+        await asyncio.sleep(0.05)
 
 def toggle_search_method(method):
+    """Toggle between GeoJSON upload and country selection"""
     if method == "Upload GeoJSON":
-        return (gr.update(visible=True), gr.update(visible=False), gr.update(value=None))
-    else:
-        return (gr.update(visible=False), gr.update(visible=True), gr.update())
+        return (
+            gr.update(visible=True),   # geojson_section
+            gr.update(visible=False),  # reports_section
+            gr.update(value=None),     # dropdown_country
+        )
+    else:  # "Talk to Reports"
+        return (
+            gr.update(visible=False),  # geojson_section 
+            gr.update(visible=True),   # reports_section
+            gr.update(),               # dropdown_country
+        )
 
 def change_sample_questions(key):
+    """Update visible examples based on selected category"""
     keys = list(SAMPLE_QUESTIONS.keys())
     index = keys.index(key)
     visible_bools = [False] * len(keys)
     visible_bools[index] = True
     return [gr.update(visible=visible_bools[i]) for i in range(len(keys))]
 
-# ------------------------
-# UI Setup
-# ------------------------
+# Set up Gradio Theme
 theme = gr.themes.Base(
     primary_hue="green",
     secondary_hue="blue",
@@ -155,14 +169,54 @@ theme = gr.themes.Base(
     text_size=gr.themes.utils.sizes.text_sm,
 )
 
+# Custom CSS for DataFrame styling
+custom_css = """
+/* DataFrame text sizing - Modify these values to change text size */
+.dataframe table {
+    font-size: 12px !important;  /* Change this value (e.g., 10px, 14px, 16px) */
+}
+
+.dataframe th {
+    font-size: 13px !important;  /* Header text size */
+    font-weight: 600 !important;
+}
+
+.dataframe td {
+    font-size: 12px !important;  /* Cell text size */
+    padding: 8px !important;     /* Cell padding */
+}
+
+/* Alternative size classes - change elem_classes="dataframe-small" in DataFrame component */
+.dataframe-small table { font-size: 10px !important; }
+.dataframe-small th { font-size: 11px !important; }
+.dataframe-small td { font-size: 10px !important; }
+
+.dataframe-medium table { font-size: 14px !important; }
+.dataframe-medium th { font-size: 15px !important; }
+.dataframe-medium td { font-size: 14px !important; }
+
+.dataframe-large table { font-size: 16px !important; }
+.dataframe-large th { font-size: 17px !important; }
+.dataframe-large td { font-size: 16px !important; }
+"""
+
 init_prompt = """
-Hello, I am EUDR Q&A, an AI-powered conversational assistant designed to help you understand EU Deforestation Regulation compliance and analysis.
-I will answer your questions by using **EUDR reports and uploaded GeoJSON files**.
+Hello, I am EUDR Q&A, an AI-powered conversational assistant designed to help you understand EU Deforestation Regulation compliance and analysis. I will answer your questions by using **EUDR reports and uploaded GeoJSON files**.
+
+💡 **How to use (tabs on right)**
+- **Data Sources**: Choose to either upload a GeoJSON file for analysis or talk to EUDR reports filtered by country.
+- **Examples**: Select from curated example questions across different categories.
+- **Sources**: View the content sources used to generate answers for fact-checking.
+
+⚠️ For limitations and data collection information, please check the **Disclaimer** tab.
 """
 
-with gr.Blocks(title="EUDR Q&A", theme=theme) as demo:
+with gr.Blocks(title="EUDR Q&A", theme=theme, css=custom_css) as demo:
+    
+    # Main Chat Interface
     with gr.Tab("EUDR Q&A"):
         with gr.Row():
+            # Left column - Chat interface (2/3 width)
             with gr.Column(scale=2):
                 chatbot = gr.Chatbot(
                     value=[(None, init_prompt)],
@@ -172,53 +226,194 @@ with gr.Blocks(title="EUDR Q&A", theme=theme) as demo:
                     avatar_images=(None, "🌳"),
                     height=500
                 )
-                textbox = gr.Textbox(
-                    placeholder="Ask me anything about EUDR compliance or upload your GeoJSON for analysis!",
-                    show_label=False,
-                    scale=7,
-                    lines=1,
-                    interactive=True
-                )
-
+                
+                # Feedback UI
+                with gr.Column():
+                    with gr.Row(visible=False) as feedback_row:
+                        gr.Markdown("Was this response helpful?")
+                        with gr.Row():
+                            okay_btn = gr.Button("👍 Okay", size="sm")
+                            not_okay_btn = gr.Button("👎 Not to expectations", size="sm")
+                    feedback_thanks = gr.Markdown("Thanks for the feedback!", visible=False)
+                
+                # Input textbox
+                with gr.Row():
+                    textbox = gr.Textbox(
+                        placeholder="Ask me anything about EUDR compliance or upload your GeoJSON for analysis!",
+                        show_label=False,
+                        scale=7,
+                        lines=1,
+                        interactive=True
+                    )
+            
+            # Right column - Controls and tabs (1/3 width)
             with gr.Column(scale=1, variant="panel"):
                 with gr.Tabs() as tabs:
+                    
+                    # Data Sources Tab
                     with gr.Tab("Data Sources", id=2):
                         search_method = gr.Radio(
                             choices=["Upload GeoJSON", "Talk to Reports"],
                             label="Choose data source",
-                            value="Upload GeoJSON"
+                            info="Upload a GeoJSON file for analysis or select country-specific EUDR reports",
+                            value="Upload GeoJSON",
                         )
+                        
+                        # GeoJSON Upload Section
                         with gr.Group(visible=True) as geojson_section:
-                            uploaded_file = gr.File(label="Upload GeoJSON File", file_types=[".geojson", ".json"], file_count="single")
+                            uploaded_file = gr.File(
+                                label="Upload GeoJSON File",
+                                file_types=[".geojson", ".json"],
+                                file_count="single"
+                            )
                             upload_status = gr.Markdown("", visible=False)
-                            results_table = gr.DataFrame(label="Analysis Results", visible=False, interactive=False, wrap=True)
+                            
+                            # Results table for WHISP API response
+                            results_table = gr.DataFrame(
+                                label="Analysis Results",
+                                visible=False,
+                                interactive=False,
+                                wrap=True,
+                                elem_classes="dataframe"
+                            )
+                        
+                        # Talk to Reports Section
                         with gr.Group(visible=False) as reports_section:
-                            dropdown_country = gr.Dropdown(["Ecuador", "Guatemala"], label="Select Country", value=None, interactive=True)
+                            dropdown_country = gr.Dropdown(
+                                ["Ecuador", "Guatemala"],
+                                label="Select Country",
+                                value=None,
+                                interactive=True,
+                            )
+                    
+                    # Examples Tab
                     with gr.Tab("Examples", id=0):
                         examples_hidden = gr.Textbox(visible=False)
+                        
                         first_key = list(SAMPLE_QUESTIONS.keys())[0]
-                        dropdown_samples = gr.Dropdown(SAMPLE_QUESTIONS.keys(), value=first_key, interactive=True, show_label=True, label="Select a category of sample questions")
+                        dropdown_samples = gr.Dropdown(
+                            SAMPLE_QUESTIONS.keys(),
+                            value=first_key,
+                            interactive=True,
+                            show_label=True,
+                            label="Select a category of sample questions"
+                        )
+                        
+                        # Create example sections
                         sample_groups = []
                         for i, (key, questions) in enumerate(SAMPLE_QUESTIONS.items()):
                             examples_visible = True if i == 0 else False
                             with gr.Row(visible=examples_visible) as group_examples:
-                                gr.Examples(questions, [examples_hidden], examples_per_page=8, run_on_click=False)
+                                gr.Examples(
+                                    questions,
+                                    [examples_hidden],
+                                    examples_per_page=8,
+                                    run_on_click=False,
+                                )
                             sample_groups.append(group_examples)
+                    
+                    # Sources Tab
                     with gr.Tab("Sources", id=1):
-                        sources_textbox = gr.HTML(show_label=False, value="Source documents will appear here after you ask a question...")
-
-    # Hidden state to store summary from WHISP API
-    geojson_summary = gr.State()
-
-    # Event handlers
-    search_method.change(fn=toggle_search_method, inputs=[search_method], outputs=[geojson_section, reports_section, dropdown_country])
-
+                        sources_textbox = gr.HTML(
+                            show_label=False,
+                            value="Source documents will appear here after you ask a question..."
+                        )
+    
+    # Guidelines Tab
+    with gr.Tab("Guidelines"):
+        gr.Markdown("""
+        #### Welcome to EUDR Q&A! 
+        
+        This AI-powered assistant helps you understand EU Deforestation Regulation compliance and analyze geographic data.
+        
+        ## 💬 How to Ask Effective Questions
+        
+        | ❌ Less Effective | ✅ More Effective |
+        |------------------|-------------------|
+        | "What is deforestation?" | "What are the main deforestation hotspots in Ecuador?" |
+        | "Tell me about compliance" | "What EUDR requirements apply to coffee imports from Guatemala?" |
+        | "Show me data" | "What is the deforestation rate in the uploaded region?" |
+        
+        ## 🔍 Using Data Sources
+        
+        **Upload GeoJSON:** Upload your geographic data files for automatic analysis via WHISP API  
+        **Talk to Reports:** Select Ecuador or Guatemala for country-specific EUDR analysis
+        
+        ## ⭐ Best Practices
+        
+        - Be specific about regions, commodities, or time periods
+        - Ask one question at a time for clearer answers
+        - Use follow-up questions to explore topics deeper
+        - Provide context when possible
+        """)
+    
+    # About Tab
+    with gr.Tab("About"):
+        gr.Markdown("""
+        ## About EUDR Q&A
+        
+        The **EU Deforestation Regulation (EUDR)** requires companies to ensure that specific commodities 
+        placed on the EU market are deforestation-free and legally produced.
+        
+        This AI-powered tool helps stakeholders:
+        - Understand EUDR compliance requirements
+        - Analyze geographic deforestation data using WHISP API
+        - Assess supply chain risks
+        - Navigate complex regulatory landscapes
+        
+        **Developed by GIZ** to enhance accessibility and understanding of EUDR requirements 
+        through advanced AI and geographic data processing capabilities.
+        
+        ### Key Features:
+        - Automatic analysis of uploaded GeoJSON files via WHISP API
+        - Country-specific EUDR compliance guidance
+        - Real-time question answering with source citations
+        - User-friendly interface for complex regulatory information
+        """)
+    
+    # Disclaimer Tab
+    with gr.Tab("Disclaimer"):
+        gr.Markdown("""
+        ## Important Disclaimers
+        
+        ⚠️ **Scope & Limitations:**
+        - This tool is designed for EUDR compliance assistance and geographic data analysis
+        - Responses should not be considered official legal or compliance advice
+        - Always consult qualified professionals for official compliance decisions
+        
+        ⚠️ **Data & Privacy:**
+        - Uploaded GeoJSON files are processed via external WHISP API for analysis
+        - We collect usage statistics to improve the tool
+        - Files are processed temporarily and not permanently stored
+        
+        ⚠️ **AI Limitations:**
+        - Responses are AI-generated and may contain inaccuracies
+        - The tool is a prototype under continuous development
+        - Always verify important information with authoritative sources
+        
+        **Data Collection:** We collect questions, answers, feedback, and anonymized usage statistics 
+        to improve tool performance based on legitimate interest in service enhancement.
+        
+        By using this tool, you acknowledge these limitations and agree to use responses responsibly.
+        """)
+    
+    # Event Handlers
+    
+    # Toggle search method
+    search_method.change(
+        fn=toggle_search_method,
+        inputs=[search_method],
+        outputs=[geojson_section, reports_section, dropdown_country]
+    )
+    
+    # File upload - automatically process when file is uploaded
     uploaded_file.change(
         fn=handle_geojson_upload,
         inputs=[uploaded_file],
-        outputs=[upload_status, upload_status, results_table, geojson_summary]
+        outputs=[upload_status, upload_status, results_table]
     )
-
+    
+    # Chat functionality
     textbox.submit(
         start_chat,
         [textbox, chatbot],
@@ -226,12 +421,17 @@ with gr.Blocks(title="EUDR Q&A", theme=theme) as demo:
         queue=False
     ).then(
         chat_response,
-        [textbox, chatbot, search_method, dropdown_country, uploaded_file, geojson_summary],
+        [textbox, chatbot, search_method, dropdown_country, uploaded_file],
         [chatbot, sources_textbox]
     ).then(
-        finish_chat, outputs=[textbox]
+        lambda: gr.update(visible=True),
+        outputs=[feedback_row]
+    ).then(
+        finish_chat,
+        outputs=[textbox]
     )
-
+    
+    # Examples functionality
     examples_hidden.change(
         start_chat,
         [examples_hidden, chatbot],
@@ -239,13 +439,34 @@ with gr.Blocks(title="EUDR Q&A", theme=theme) as demo:
         queue=False
     ).then(
         chat_response,
-        [examples_hidden, chatbot, search_method, dropdown_country, uploaded_file, geojson_summary],
+        [examples_hidden, chatbot, search_method, dropdown_country, uploaded_file],
         [chatbot, sources_textbox]
     ).then(
-        finish_chat, outputs=[textbox]
+        lambda: gr.update(visible=True),
+        outputs=[feedback_row]
+    ).then(
+        finish_chat,
+        outputs=[textbox]
+    )
+    
+    # Sample questions dropdown
+    dropdown_samples.change(
+        change_sample_questions,
+        [dropdown_samples],
+        sample_groups
+    )
+    
+    # Feedback buttons
+    okay_btn.click(
+        lambda: (gr.update(visible=False), gr.update(visible=True)),
+        outputs=[feedback_row, feedback_thanks]
+    )
+    
+    not_okay_btn.click(
+        lambda: (gr.update(visible=False), gr.update(visible=True)),
+        outputs=[feedback_row, feedback_thanks]
     )
 
-    dropdown_samples.change(change_sample_questions, [dropdown_samples], sample_groups)
-
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()