Update src/streamlit_app.py

src/streamlit_app.py

@@ -211,45 +211,142 @@ if st.button("Results"):
                 fig_treemap = px.treemap(df, path=[px.Constant("all"), 'category', 'label', 'text'], values='score', color='category')
                 fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25), paper_bgcolor='#F5FFFA', plot_bgcolor='#F5FFFA')
                 st.plotly_chart(fig_treemap)
+
+                @st.cache_resource
+                def load_gliner_model():
+                    try:
+                        return GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0", device="cpu")
+                    except Exception as e:
+                        st.error(f"Error loading the GLiNER model: {e}")
+                        st.stop()
                 
-                # Pie and Bar charts
-                grouped_counts = df['category'].value_counts().reset_index()
-                grouped_counts.columns = ['category', 'count']
-                col1, col2 = st.columns(2)
-                
-                with col1:
-                    st.subheader("Pie chart", divider = "green")
-                    fig_pie = px.pie(grouped_counts, values='count', names='category', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted categories')
-                    fig_pie.update_traces(textposition='inside', textinfo='percent+label')
-                    fig_pie.update_layout(
-                        paper_bgcolor='#F5FFFA',
-                        plot_bgcolor='#F5FFFA'
-                    )
-                    st.plotly_chart(fig_pie)
-                
-                with col2:
-                    st.subheader("Bar chart", divider = "green")
-                    fig_bar = px.bar(grouped_counts, x="count", y="category", color="category", text_auto=True, title='Occurrences of predicted categories')
-                    fig_pie.update_layout(
-                        paper_bgcolor='#F5FFFA',
-                        plot_bgcolor='#F5FFFA'
-                    )
-                    st.plotly_chart(fig_bar)
+                model = load_gliner_model()
+                st.subheader("Question-Answering", divider = "violet")
+
+
+                question_input = st.text_input("Ask wh-questions. **Wh-questions begin with what, when, where, who, whom, which, whose, why and how. We use them to ask for specific information.**")
+
+
+                if st.button("Add Question"):
+                    if question_input:
+                        if question_input not in st.session_state.user_labels:
+                            st.session_state.user_labels.append(question_input)
+                            st.success(f"Added question: {question_input}")
+                        else:
+                            st.warning("This question has already been added.")
+                    else:
+                        st.warning("Please enter a question.")
+                        st.markdown("---")
                 
-                # Most Frequent Entities
-                st.subheader("Most Frequent Entities", divider="green")
-                word_counts = df['text'].value_counts().reset_index()
-                word_counts.columns = ['Entity', 'Count']
-                repeating_entities = word_counts[word_counts['Count'] > 1]
-                if not repeating_entities.empty:
-                    st.dataframe(repeating_entities, use_container_width=True)
-                    fig_repeating_bar = px.bar(repeating_entities, x='Entity', y='Count', color='Entity')
-                    fig_repeating_bar.update_layout(xaxis={'categoryorder': 'total descending'},
-                        paper_bgcolor='#F5FFFA',
-                        plot_bgcolor='#F5FFFA')
-                    st.plotly_chart(fig_repeating_bar)
+                st.subheader("Record of Questions", divider = "violet")
+
+                if st.session_state.user_labels:
+    
+    for i, label in enumerate(st.session_state.user_labels):
+        col_list, col_delete = st.columns([0.9, 0.1])
+        with col_list:
+            st.write(f"- {label}", key=f"label_{i}")
+        with col_delete:
+            # Create a unique key for each button using the index
+            if st.button("Delete", key=f"delete_{i}"):
+                # Remove the label at the specific index
+                st.session_state.user_labels.pop(i)
+                # Rerun to update the UI
+                st.rerun()
+else:
+    st.info("No questions defined yet. Use the input above to add one.")
+
+def get_stable_color(label):
+    """Generates a consistent hexadecimal color from a given string."""
+    hash_object = hashlib.sha1(label.encode('utf-8'))
+    hex_dig = hash_object.hexdigest()
+    return '#' + hex_dig[:6]
+
+st.divider()
+
+# --- Main Processing Logic ---
+if st.button("Extract Answers"):
+    if not user_text.strip():
+        st.warning("Please enter some text to analyze.")
+    elif not st.session_state.user_labels:
+        st.warning("Please define at least one question.")
+    else:
+        if comet_initialized:
+            experiment = Experiment(
+                api_key=COMET_API_KEY,
+                workspace=COMET_WORKSPACE,
+                project_name=COMET_PROJECT_NAME
+            )
+            experiment.log_parameter("input_text_length", len(user_text))
+            experiment.log_parameter("defined_labels", st.session_state.user_labels)
+
+        start_time = time.time()
+        with st.spinner("Analyzing text...", show_time=True):
+            try:
+                entities = model.predict_entities(user_text, st.session_state.user_labels)
+                end_time = time.time()
+                elapsed_time = end_time - start_time
+                st.info(f"Processing took **{elapsed_time:.2f} seconds**.")
+
+                if entities:
+                    df1 = pd.DataFrame(entities)
+                    df2 = df1[['label', 'text', 'score']]
+                    df = df2.rename(columns={'label': 'question', 'text': 'answer'})
+                    
+                    st.subheader("Extracted Answers", divider = "violet")
+                    st.dataframe(df, use_container_width=True)
+
+                    
+
+                    
+                    csv_data = df.to_csv(index=False).encode('utf-8')
+                    with stylable_container(
+                        key="download_button",
+                        css_styles="""button { background-color: red; border: 1px solid black; padding: 5px; color: white; }""",
+                    ):
+                        st.download_button(
+                            label="Download CSV",
+                            data=csv_data,
+                            file_name="nlpblogs_results.csv",
+                            mime="text/csv",
+                        )
+
+                    if comet_initialized:
+                        experiment.log_metric("processing_time_seconds", elapsed_time)
+                        experiment.log_table("predicted_entities", df)
+                        experiment.log_figure(figure=fig_treemap, figure_name="entity_treemap")
+                        
+                        experiment.end()
                 else:
-                    st.warning("No entities were found that occur more than once.")
+                    st.info("No answers were found in the text with the defined questions.")
+                    if comet_initialized:
+                        experiment.end()
+            except Exception as e:
+                st.error(f"An error occurred during processing: {e}")
+                st.write(f"Error details: {e}")
+                if comet_initialized:
+                    experiment.log_text(f"Error: {e}")
+                    experiment.end()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
                 
                 # Download Section
                 st.divider()