Update src/streamlit_app.py

src/streamlit_app.py

@@ -9,15 +9,14 @@ import io
 import plotly.express as px
 import zipfile
 import json
-from cryptography.fernet import Fernet
+
 from streamlit_extras.stylable_container import stylable_container
 from typing import Optional
 from gliner import GLiNER
 from comet_ml import Experiment
 import hashlib
 
-# Set up environment variables
-os.environ['HF_HOME'] = '/tmp'
+
 
 st.markdown(
     """
@@ -45,6 +44,15 @@ st.markdown(
         background-color: #D4F4D4; /* A light, soft green */
         color: #000000; /* Black for text */
     }
+
+     /* Text input background and text color */
+    .stTextInput textinput {
+        background-color: #D4F4D4; /* A light, soft green */
+        color: #000000; /* Black for text */
+    }
+
+
+    
     /* Button background and text color */
     .stButton > button {
         background-color: #D4F4D4;
@@ -69,18 +77,31 @@ st.markdown(
 st.set_page_config(layout="wide", page_title="Named Entity Recognition App")
 st.subheader("HR.ai", divider="green")
 st.link_button("by nlpblogs", "https://nlpblogs.com", type="tertiary")
+
 expander = st.expander("**Important notes**")
-expander.write("""**Named Entities:** This HR.ai predicts thirty-six (36) labels: "Email", "Phone_number", "Street_address", "City", "Country", "Date_of_birth", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Terminated", "Retired", "Job_title", "Date", "Organization", "Role", "Performance_score", "Leave_of_absence", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Pay_rate", "Annual_salary", "Tax", "Deductions", "Interview_type", "Applicant", "Referral", "Job_board", "Recruiter", "Offer_letter", "Agreement", "Certification", "Skill"
+expander.write("""**Named Entities:** This HR.ai predicts thirty-six (35) labels: "Email", "Phone_number", "Street_address", "City", "Country", "Date_of_birth", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Terminated", "Retired", "Date", "Organization", "Role", "Performance_score", "Leave_of_absence", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Pay_rate", "Annual_salary", "Tax", "Deductions", "Interview_type", "Applicant", "Referral", "Job_board", "Recruiter", "Offer_letter", "Agreement", "Certification", "Skill"
+
 Results are presented in easy-to-read tables, visualized in an interactive tree map, pie chart and bar chart, and are available for download along with a Glossary of tags.
+
 **How to Use:** Type or paste your text into the text area below, then press Ctrl + Enter. Click the 'Results' button to extract and tag entities in your text data.
+
 **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""")
+
+**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 HR.ai web app on your website. Feel free to adjust the width and height values to fit your page.")
     code = '''
-    <iframe	src="https://aiecosystem-hr-ai.hf.space"	frameborder="0"	width="850"	height="450"    ></iframe>
+    <iframe
+	src="https://aiecosystem-hr-ai.hf.space"
+	frameborder="0"
+	width="850"
+	height="450"
+    ></iframe>
     '''
     st.code(code, language="html")
     st.text("")
@@ -99,14 +120,14 @@ if not comet_initialized:
     st.warning("Comet ML not initialized. Check environment variables.")
 
 # --- Label Definitions ---
-labels = ["Email", "Phone_number", "Street_address", "City", "Country", "Date_of_birth", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Terminated", "Retired", "Job_title", "Date", "Organization", "Role", "Performance_score", "Leave_of_absence", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Pay_rate", "Annual_salary", "Tax", "Deductions", "Interview_type", "Applicant", "Referral", "Job_board", "Recruiter", "Offer_letter", "Agreement", "Certification", "Skill"]
+labels = ["Email", "Phone_number", "Street_address", "City", "Country", "Date_of_birth", "Marital_status", "Person", "Full_time", "Part_time", "Contract", "Terminated", "Retired", "Date", "Organization", "Role", "Performance_score", "Leave_of_absence", "Retirement_plan", "Bonus", "Stock_options", "Health_insurance", "Pay_rate", "Annual_salary", "Tax", "Deductions", "Interview_type", "Applicant", "Referral", "Job_board", "Recruiter", "Offer_letter", "Agreement", "Certification", "Skill"]
 
 # Create a mapping dictionary for labels to categories
 category_mapping = {
     "Contact Information": ["Email", "Phone_number", "Street_address", "City", "Country"],
     "Personal Details": ["Date_of_birth", "Marital_status", "Person"],
     "Employment Status": ["Full_time", "Part_time", "Contract", "Terminated", "Retired"],
-    "Employment Information": ["Job_title", "Date", "Organization", "Role"],
+    "Employment Information": ["Date", "Organization", "Role"],
     "Performance": ["Performance_score"],
     "Attendance": ["Leave_of_absence"],
     "Benefits": ["Retirement_plan", "Bonus", "Stock_options", "Health_insurance"],
@@ -197,7 +218,7 @@ if st.button("Results"):
 # --- Treemap Display Section ---
 if 'df' in st.session_state and not st.session_state.df.empty:
     st.divider()
-    st.subheader("Tree map", divider="green")
+    st.subheader("Candidate Card", divider="green")
     fig_treemap = px.treemap(st.session_state.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)
@@ -213,7 +234,7 @@ def load_gliner_model():
         st.stop()
 
 qa_model = load_gliner_model()
-st.subheader("Question-Answering", divider="violet")
+st.subheader("Question-Answering", divider="green")
 
 if 'user_labels' not in st.session_state:
     st.session_state.user_labels = []
@@ -231,7 +252,7 @@ if st.button("Add Question"):
         st.warning("Please enter a question.")
 
 st.markdown("---")
-st.subheader("Record of Questions", divider="violet")
+st.subheader("Record of Questions", divider="green")
 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])
@@ -274,39 +295,56 @@ if st.button("Extract Answers"):
                     df2 = df1[['label', 'text', 'score']]
                     df = df2.rename(columns={'label': 'question', 'text': 'answer'})
 
-                    st.subheader("Extracted Answers", divider="violet")
+                    st.subheader("Extracted Answers", divider="green")
                     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",
-                        )
-                else:
-                    st.warning("No answers were found for the provided questions.")
-            except Exception as e:
-                st.error(f"An error occurred during answer extraction: {e}")
+def create_zip_file_and_get_bytes():
+    """Generates a zip file in memory with all available dataframes."""
+    
+    # Define the glossary DataFrame here to ensure it's always available
+    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',
+            ]
+        }
+    )
+
+    if 'df_ner' not in st.session_state and 'df_qa' not in st.session_state:
+        return None, None
+
+    buf = io.BytesIO()
+    with zipfile.ZipFile(buf, "w") as myzip:
+        if 'df_ner' in st.session_state and not st.session_state.df_ner.empty:
+            myzip.writestr("Extracted_Entities.csv", st.session_state.df_ner.to_csv(index=False))
+        if 'df_qa' in st.session_state and not st.session_state.df_qa.empty:
+            myzip.writestr("Extracted_Answers.csv", st.session_state.df_qa.to_csv(index=False))
+        myzip.writestr("Glossary_of_tags.csv", dfa.to_csv(index=False))
+
+    return buf.getvalue(), "nlpblogs_results.zip"
+
+st.divider()
+
+if ('df_ner' in st.session_state and not st.session_state.df_ner.empty) or \
+   ('df_qa' in st.session_state and not st.session_state.df_qa.empty):
+    zip_data, file_name = create_zip_file_and_get_bytes()
+    if zip_data:
+        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=zip_data,
+                file_name=file_name,
+                mime="application/zip",
+            )
+
+