Update src/streamlit_app.py

src/streamlit_app.py

@@ -58,45 +58,34 @@ st.markdown(
     unsafe_allow_html=True
 )
 
-
 # --- Page Configuration and UI Elements ---
 st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
 st.subheader("InfoFinder", divider="violet")
 st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
 
 expander = st.expander("**Important notes**")
-expander.write("""**How to Use:** 
-1. Type or paste your text into the text area below, then press Ctrl + Enter. 
+expander.write("""
+**How to Use:**
+1. Type or paste your text into the text area below, then press Ctrl + Enter.
 2. Click the 'Add Question' button to add your question to the Record of Questions. You can manage your questions by deleting them one by one.
-3. Click the 'Extract Answers' button to extract the answer to your question. 
-
-Results are presented in an easy-to-read table, visualized in an interactive tree map and are available for download.
+3. Click the 'Extract Answers' button to extract the answer to your question. Results are presented in an easy-to-read table, visualized in an interactive tree map and are available for download.
 
 **Usage Limits:** You can request results unlimited times for one (1) month.
-
-**Supported Languages:** English 
-
-**Technical issues:** If your connection times out, please refresh the page or reopen the app's URL. 
-
-For any errors or inquiries, please contact us at info@nlpblogs.com""")
+**Supported Languages:** English
+**Technical issues:** If your connection times out, please refresh the page or reopen the app's URL. For any errors or inquiries, please contact us at info@nlpblogs.com
+""")
 
 with st.sidebar:
     st.write("Use the following code to embed the InfoFinder web app on your website. Feel free to adjust the width and height values to fit your page.")
     code = '''
-    <iframe
-	src="https://aiecosystem-infofinder.hf.space"
-	frameborder="0"
-	width="850"
-	height="450"
-    ></iframe>
-    
+    <iframe src="https://aiecosystem-infofinder.hf.space" frameborder="0" width="850" height="450"></iframe>       
     '''
     st.code(code, language="html")
     st.text("")
     st.text("")
     st.divider()
     st.subheader("🚀 Ready to build your own AI Web App?", divider="violet")
-    st.link_button("AI Web App Builder", " https://nlpblogs.com/custom-web-app-development/", type="primary")
+    st.link_button("AI Web App Builder", "https://nlpblogs.com/custom-web-app-development/", type="primary")
 
 # --- Comet ML Setup ---
 COMET_API_KEY = os.environ.get("COMET_API_KEY")
@@ -107,58 +96,64 @@ comet_initialized = bool(COMET_API_KEY and COMET_WORKSPACE and COMET_PROJECT_NAM
 if not comet_initialized:
     st.warning("Comet ML not initialized. Check environment variables.")
 
-# --- Initialize session state for labels ---
+# --- Initialize session state for labels and inputs ---
 if 'user_labels' not in st.session_state:
     st.session_state.user_labels = []
+if 'my_text_area' not in st.session_state:
+    st.session_state['my_text_area'] = ""
+if 'question_input' not in st.session_state:
+    st.session_state['question_input'] = ""
 
 # --- Model Loading and Caching ---
 @st.cache_resource
 def load_gliner_model():
-    """
-    Initializes and caches the GLiNER model.
-    This ensures the model is only loaded once, improving performance.
-    """
+    """Initializes and caches the GLiNER model."""
     try:
         return GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5", device="cpu")
     except Exception as e:
         st.error(f"Error loading the GLiNER model: {e}")
         st.stop()
 
-# Load the model
 model = load_gliner_model()
 
-user_text = st.text_area("Type or paste your text below, and then press Ctrl + Enter", height=250, key='my_text_area')
-
-def clear_text():
+# --- Text Area and Clear Button ---
+def clear_text_area():
     """Clears the text area by resetting its value in session state."""
     st.session_state['my_text_area'] = ""
-st.button("Clear text", on_click=clear_text)
-
-st.subheader("Question-Answering", divider = "violet")
 
-# Replaced two columns with a single text input
-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.**")
+user_text = st.text_area("Type or paste your text below, and then press Ctrl + Enter", height=250, key='my_text_area')
+st.button("Clear text", on_click=clear_text_area)
 
+st.subheader("Question-Answering", divider="violet")
 
-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}")
+def add_question_callback():
+    """Callback to add the question and clear the input."""
+    if st.session_state.question_input:
+        if st.session_state.question_input not in st.session_state.user_labels:
+            st.session_state.user_labels.append(st.session_state.question_input)
+            st.success(f"Added question: {st.session_state.question_input}")
+            st.session_state.question_input = ""
         else:
             st.warning("This question has already been added.")
     else:
         st.warning("Please enter a question.")
-        st.markdown("---")
-        
-st.subheader("Record of Questions", divider = "violet")
+
+# The `st.columns` call has been removed to place widgets on separate lines
+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.**",
+    key='question_input'
+)
+st.button("Add Question", on_click=add_question_callback)
+
+st.markdown("---")
+st.subheader("Record of Questions", divider="violet")
 
 if st.session_state.user_labels:
     def delete_label(label_to_delete):
         """Removes a label from the session state list."""
         st.session_state.user_labels = [label for label in st.session_state.user_labels if label != label_to_delete]
         st.rerun()
-
+    
     for label in st.session_state.user_labels:
         col_list, col_delete = st.columns([0.9, 0.1])
         with col_list:
@@ -204,14 +199,18 @@ if st.button("Extract Answers"):
                     df1 = pd.DataFrame(entities)
                     df2 = df1[['label', 'text', 'score']]
                     df = df2.rename(columns={'label': 'question', 'text': 'answer'})
+
+                    # Drop duplicates based on 'question' and 'answer' columns
+                    df.drop_duplicates(subset=['question', 'answer'], keep='first', inplace=True)
                     
-                    st.subheader("Extracted Answers", divider = "violet")
+                    st.subheader("Extracted Answers", divider="violet")
                     st.dataframe(df, use_container_width=True)
-
+                    
                     # Create Tree map
                     st.subheader("Tree map", divider="violet")
                     all_labels = df['question'].unique()
                     label_color_map = {label: get_stable_color(label) for label in all_labels}
+                    
                     fig_treemap = px.treemap(
                         df,
                         path=[px.Constant("all"), 'question', 'answer'],
@@ -222,8 +221,6 @@ if st.button("Extract Answers"):
                     fig_treemap.update_layout(margin=dict(t=50, l=25, r=25, b=25), paper_bgcolor='#F3E5F5', plot_bgcolor='#F3E5F5')
                     st.plotly_chart(fig_treemap)
 
-                    
-                    
                     csv_data = df.to_csv(index=False).encode('utf-8')
                     with stylable_container(
                         key="download_button",
@@ -235,12 +232,10 @@ if st.button("Extract Answers"):
                             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.info("No answers were found in the text with the defined questions.")
@@ -272,16 +267,6 @@ if st.button("Extract Answers"):
 
 
 
-
-
-
-
-
-
-
-
-
-