Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,6 +1,7 @@
 import os
 os.environ['HF_HOME'] = '/tmp'
 
+
 import time
 import streamlit as st
 import pandas as pd
@@ -13,6 +14,7 @@ from streamlit_extras.stylable_container import stylable_container
 from typing import Optional
 from gliner import GLiNER
 from comet_ml import Experiment
+import hashlib
 
 st.markdown(
     """
@@ -187,126 +189,9 @@ if st.button("Results"):
                 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)
 
-                # --- 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.
-                    """
-                    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()
-
-                # Load the model
-                model = load_gliner_model()
-                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.**")
-
-                if 'user_labels' not in st.session_state:
-                    st.session_state.user_labels = []
-
-                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("---")
-                st.subheader("Record of Questions", divider="violet")
-
-                if st.session_state.user_labels:
-                    # Use enumerate to create a unique key for each item
-                    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.")
-
-                st.divider()
-
-                # --- Main Processing Logic ---
-                if st.button("Extract Answers"):
-                    if not 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(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(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)
-                                    st.divider()
-
-                                    dfa = pd.DataFrame(
-                                        data={
-                                            'Column Name': ['text', 'label', 'score', 'start', 'end', 'category'],
-                                            'Description': [
-                                                'entity extracted from your text data',
-                                                'label (tag) assigned to a given extracted entity',
-                                                'accuracy score; how accurately a tag has been assigned to a given entity',
-                                                'index of the start of the corresponding entity',
-                                                'index of the end of the corresponding entity',
-                                                'the broader category the entity belongs to',
-                                            ]
-                                        }
-                                    )
-                                    buf = io.BytesIO()
-                                    with zipfile.ZipFile(buf, "w") as myzip:
-                                        myzip.writestr("Summary of the results.csv", df.to_csv(index=False))
-                                        myzip.writestr("Glossary of tags.csv", dfa.to_csv(index=False))
-
-                                    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 results and glossary (zip)",
-                                            data=buf.getvalue(),
-                                            file_name="nlpblogs_results.zip",
-                                            mime="application/zip",
-                                        )
-
-                                    if comet_initialized:
-                                        experiment.log_figure(figure=fig_treemap, figure_name="entity_treemap_categories")
-                                        experiment.end()
-                                else: # If df is empty
-                                    st.warning("No entities were found in the provided text.")
-                            except Exception as e:
-                                st.error(f"An error occurred during entity extraction: {e}")
+                if comet_initialized:
+                    experiment.log_figure(figure=fig_treemap, figure_name="entity_treemap_categories")
+                    experiment.end()
 
             else:  # If df is empty from the first extraction
                 st.warning("No entities were found in the provided text.")
@@ -317,3 +202,128 @@ if st.button("Results"):
         st.text("")
         st.info(f"Results processed in **{elapsed_time:.2f} seconds**.")
 
+# --- Question Answering Section (Moved outside the "Results" button) ---
+# --- 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.
+    """
+    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()
+
+# Load the model
+model = load_gliner_model()
+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.**")
+
+if 'user_labels' not in st.session_state:
+    st.session_state.user_labels = []
+
+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("---")
+st.subheader("Record of Questions", divider="violet")
+if st.session_state.user_labels:
+    # Use enumerate to create a unique key for each item
+    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.")
+
+st.divider()
+# --- Main Processing Logic ---
+if st.button("Extract Answers"):
+    if not 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(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(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)
+                    st.divider()
+
+                    dfa = pd.DataFrame(
+                        data={
+                            'Column Name': ['text', 'label', 'score', 'start', 'end', 'category'],
+                            'Description': [
+                                'entity extracted from your text data',
+                                'label (tag) assigned to a given extracted entity',
+                                'accuracy score; how accurately a tag has been assigned to a given entity',
+                                'index of the start of the corresponding entity',
+                                'index of the end of the corresponding entity',
+                                'the broader category the entity belongs to',
+                            ]
+                        }
+                    )
+                    buf = io.BytesIO()
+                    with zipfile.ZipFile(buf, "w") as myzip:
+                        myzip.writestr("Summary of the results.csv", df.to_csv(index=False))
+                        myzip.writestr("Glossary of tags.csv", dfa.to_csv(index=False))
+
+                    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 results and glossary (zip)",
+                            data=buf.getvalue(),
+                            file_name="nlpblogs_results.zip",
+                            mime="application/zip",
+                        )
+
+                    if comet_initialized:
+                        # Assuming fig_treemap is still defined from the main NER run
+                        # If not, you might need to re-generate it or handle the case where it's not available.
+                        try:
+                            experiment.log_figure(figure=fig_treemap, figure_name="entity_treemap_categories")
+                        except NameError:
+                            pass # Or handle this gracefully
+                        experiment.end()
+                else:  # If df is empty
+                    st.warning("No answers were found for the provided questions.")
+            except Exception as e:
+                st.error(f"An error occurred during answer extraction: {e}")